Merge branch 'dev' into feature-pw-removal-workflow-action

.codecov.yml

@@ -9,6 +9,15 @@ component_management:
     - component_id: frontend
       paths:
         - src-ui/**
+flags:
+  backend:
+    paths:
+      - src/**
+    carryforward: true
+  frontend:
+    paths:
+      - src-ui/**
+    carryforward: true
 # https://docs.codecov.com/docs/pull-request-comments
 comment:
   layout: "header, diff, components, flags, files"

.devcontainer/Dockerfile

@@ -1,6 +1,6 @@
 # syntax=docker/dockerfile:1
 
-FROM --platform=$BUILDPLATFORM docker.io/node:20-trixie-slim as main-app
+FROM --platform=$BUILDPLATFORM docker.io/node:24-trixie-slim as main-app
 
 ARG DEBIAN_FRONTEND=noninteractive
 

.github/workflows/ci-backend.yml

@@ -0,0 +1,104 @@
+name: Backend Tests
+on:
+  push:
+    branches-ignore:
+      - 'translations**'
+    paths:
+      - 'src/**'
+      - 'pyproject.toml'
+      - 'uv.lock'
+      - 'docker/compose/docker-compose.ci-test.yml'
+      - '.github/workflows/ci-backend.yml'
+  pull_request:
+    branches-ignore:
+      - 'translations**'
+    paths:
+      - 'src/**'
+      - 'pyproject.toml'
+      - 'uv.lock'
+      - 'docker/compose/docker-compose.ci-test.yml'
+      - '.github/workflows/ci-backend.yml'
+  workflow_dispatch:
+concurrency:
+  group: backend-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+env:
+  DEFAULT_UV_VERSION: "0.9.x"
+  NLTK_DATA: "/usr/share/nltk_data"
+jobs:
+  test:
+    name: "Python ${{ matrix.python-version }}"
+    runs-on: ubuntu-24.04
+    strategy:
+      matrix:
+        python-version: ['3.10', '3.11', '3.12']
+      fail-fast: false
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Start containers
+        run: |
+          docker compose --file docker/compose/docker-compose.ci-test.yml pull --quiet
+          docker compose --file docker/compose/docker-compose.ci-test.yml up --detach
+      - name: Set up Python
+        id: setup-python
+        uses: actions/setup-python@v6
+        with:
+          python-version: "${{ matrix.python-version }}"
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          version: ${{ env.DEFAULT_UV_VERSION }}
+          enable-cache: true
+          python-version: ${{ steps.setup-python.outputs.python-version }}
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -qq --no-install-recommends \
+            unpaper tesseract-ocr imagemagick ghostscript libzbar0 poppler-utils
+      - name: Configure ImageMagick
+        run: |
+          sudo cp docker/rootfs/etc/ImageMagick-6/paperless-policy.xml /etc/ImageMagick-6/policy.xml
+      - name: Install Python dependencies
+        run: |
+          uv sync \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            --group testing \
+            --frozen
+      - name: List installed Python dependencies
+        run: |
+          uv pip list
+      - name: Install NLTK data
+        run: |
+          uv run python -m nltk.downloader punkt punkt_tab snowball_data stopwords -d ${{ env.NLTK_DATA }}
+      - name: Run tests
+        env:
+          NLTK_DATA: ${{ env.NLTK_DATA }}
+          PAPERLESS_CI_TEST: 1
+          PAPERLESS_MAIL_TEST_HOST: ${{ secrets.TEST_MAIL_HOST }}
+          PAPERLESS_MAIL_TEST_USER: ${{ secrets.TEST_MAIL_USER }}
+          PAPERLESS_MAIL_TEST_PASSWD: ${{ secrets.TEST_MAIL_PASSWD }}
+        run: |
+          uv run \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            --dev \
+            --frozen \
+            pytest
+      - name: Upload test results to Codecov
+        if: always()
+        uses: codecov/codecov-action@v5
+        with:
+          flags: backend,backend-python-${{ matrix.python-version }}
+          files: junit.xml
+          report_type: test_results
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
+        with:
+          flags: backend,backend-python-${{ matrix.python-version }}
+          files: coverage.xml
+          report_type: coverage
+      - name: Stop containers
+        if: always()
+        run: |
+          docker compose --file docker/compose/docker-compose.ci-test.yml logs
+          docker compose --file docker/compose/docker-compose.ci-test.yml down

.github/workflows/ci-docker.yml

@@ -0,0 +1,233 @@
+name: Docker Build
+on:
+  push:
+    tags:
+      - 'v[0-9]+.[0-9]+.[0-9]+'
+      - 'v[0-9]+.[0-9]+.[0-9]+-beta.rc[0-9]+'
+    branches:
+      - dev
+      - beta
+  pull_request:
+    branches:
+      - dev
+      - main
+  workflow_dispatch:
+concurrency:
+  group: docker-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+env:
+  REGISTRY: ghcr.io
+jobs:
+  build-arch:
+    name: Build ${{ matrix.arch }}
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - runner: ubuntu-24.04
+            arch: amd64
+            platform: linux/amd64
+          - runner: ubuntu-24.04-arm
+            arch: arm64
+            platform: linux/arm64
+    runs-on: ${{ matrix.runner }}
+    permissions:
+      contents: read
+      packages: write
+    outputs:
+      can-push: ${{ steps.check-push.outputs.can-push }}
+      push-external: ${{ steps.check-push.outputs.push-external }}
+      repository: ${{ steps.repo.outputs.name }}
+      ref-name: ${{ steps.ref.outputs.name }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.1
+      - name: Determine ref name
+        id: ref
+        run: |
+          ref_name="${GITHUB_HEAD_REF:-$GITHUB_REF_NAME}"
+          # Sanitize by replacing / with - for cache keys
+          cache_ref="${ref_name//\//-}"
+
+          echo "ref_name=${ref_name}"
+          echo "cache_ref=${cache_ref}"
+
+          echo "name=${ref_name}" >> $GITHUB_OUTPUT
+          echo "cache-ref=${cache_ref}" >> $GITHUB_OUTPUT
+      - name: Check push permissions
+        id: check-push
+        env:
+          REF_NAME: ${{ steps.ref.outputs.name }}
+        run: |
+          # can-push: Can we push to GHCR?
+          # True for: pushes, or PRs from the same repo (not forks)
+          can_push=${{ github.event_name == 'push' || github.event.pull_request.head.repo.full_name == github.repository }}
+          echo "can-push=${can_push}"
+          echo "can-push=${can_push}" >> $GITHUB_OUTPUT
+
+          # push-external: Should we also push to Docker Hub and Quay.io?
+          # Only for main repo on dev/beta branches or version tags
+          push_external="false"
+          if [[ "${can_push}" == "true" && "${{ github.repository_owner }}" == "paperless-ngx" ]]; then
+            case "${REF_NAME}" in
+              dev|beta)
+                push_external="true"
+                ;;
+            esac
+            case "${{ github.ref }}" in
+              refs/tags/v*|*beta.rc*)
+                push_external="true"
+                ;;
+            esac
+          fi
+          echo "push-external=${push_external}"
+          echo "push-external=${push_external}" >> $GITHUB_OUTPUT
+      - name: Set repository name
+        id: repo
+        run: |
+          repo_name="${{ github.repository }}"
+          repo_name="${repo_name,,}"
+
+          echo "repository=${repo_name}"
+          echo "name=${repo_name}" >> $GITHUB_OUTPUT
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3.12.0
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3.6.0
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Docker metadata
+        id: docker-meta
+        uses: docker/metadata-action@v5.10.0
+        with:
+          images: |
+            ${{ env.REGISTRY }}/${{ steps.repo.outputs.name }}
+          tags: |
+            type=ref,event=branch
+            type=raw,value=${{ steps.ref.outputs.name }},enable=${{ github.event_name == 'pull_request' }}
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+      - name: Build and push by digest
+        id: build
+        uses: docker/build-push-action@v6.18.0
+        with:
+          context: .
+          file: ./Dockerfile
+          platforms: ${{ matrix.platform }}
+          labels: ${{ steps.docker-meta.outputs.labels }}
+          build-args: |
+            PNGX_TAG_VERSION=${{ steps.docker-meta.outputs.version }}
+          outputs: type=image,name=${{ env.REGISTRY }}/${{ steps.repo.outputs.name }},push-by-digest=true,name-canonical=true,push=${{ steps.check-push.outputs.can-push }}
+          cache-from: |
+            type=registry,ref=${{ env.REGISTRY }}/${{ steps.repo.outputs.name }}/cache/app:${{ steps.ref.outputs.cache-ref }}-${{ matrix.arch }}
+            type=registry,ref=${{ env.REGISTRY }}/${{ steps.repo.outputs.name }}/cache/app:dev-${{ matrix.arch }}
+          cache-to: ${{ steps.check-push.outputs.can-push == 'true' && format('type=registry,mode=max,ref={0}/{1}/cache/app:{2}-{3}', env.REGISTRY, steps.repo.outputs.name, steps.ref.outputs.cache-ref, matrix.arch) || '' }}
+      - name: Export digest
+        if: steps.check-push.outputs.can-push == 'true'
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          echo "digest=${digest}"
+          touch "/tmp/digests/${digest#sha256:}"
+      - name: Upload digest
+        if: steps.check-push.outputs.can-push == 'true'
+        uses: actions/upload-artifact@v6.0.0
+        with:
+          name: digests-${{ matrix.arch }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1
+  merge-and-push:
+    name: Merge and Push Manifest
+    runs-on: ubuntu-24.04
+    needs: build-arch
+    if: needs.build-arch.outputs.can-push == 'true'
+    permissions:
+      contents: read
+      packages: write
+    steps:
+      - name: Download digests
+        uses: actions/download-artifact@v7.0.0
+        with:
+          path: /tmp/digests
+          pattern: digests-*
+          merge-multiple: true
+      - name: List digests
+        run: |
+          echo "Downloaded digests:"
+          ls -la /tmp/digests/
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3.12.0
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3.6.0
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Login to Docker Hub
+        if: needs.build-arch.outputs.push-external == 'true'
+        uses: docker/login-action@v3.6.0
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Login to Quay.io
+        if: needs.build-arch.outputs.push-external == 'true'
+        uses: docker/login-action@v3.6.0
+        with:
+          registry: quay.io
+          username: ${{ secrets.QUAY_USERNAME }}
+          password: ${{ secrets.QUAY_ROBOT_TOKEN }}
+      - name: Docker metadata
+        id: docker-meta
+        uses: docker/metadata-action@v5.10.0
+        with:
+          images: |
+            ${{ env.REGISTRY }}/${{ needs.build-arch.outputs.repository }}
+          tags: |
+            type=ref,event=branch
+            type=raw,value=${{ needs.build-arch.outputs.ref-name }},enable=${{ github.event_name == 'pull_request' }}
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+      - name: Create manifest list and push
+        working-directory: /tmp/digests
+        env:
+          REPOSITORY: ${{ needs.build-arch.outputs.repository }}
+        run: |
+          tags=$(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "${DOCKER_METADATA_OUTPUT_JSON}")
+
+          digests=""
+          for digest in *; do
+            digests+="${{ env.REGISTRY }}/${REPOSITORY}@sha256:${digest} "
+          done
+
+          echo "Creating manifest with tags: ${tags}"
+          echo "From digests: ${digests}"
+
+          docker buildx imagetools create ${tags} ${digests}
+      - name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ fromJSON(steps.docker-meta.outputs.json).tags[0] }}
+      - name: Copy to Docker Hub
+        if: needs.build-arch.outputs.push-external == 'true'
+        env:
+          TAGS: ${{ steps.docker-meta.outputs.tags }}
+          GHCR_REPO: ${{ env.REGISTRY }}/${{ needs.build-arch.outputs.repository }}
+        run: |
+          for tag in ${TAGS}; do
+            dockerhub_tag="${tag/${GHCR_REPO}/docker.io/paperlessngx/paperless-ngx}"
+            echo "Copying ${tag} to ${dockerhub_tag}"
+            skopeo copy --all "docker://${tag}" "docker://${dockerhub_tag}"
+          done
+      - name: Copy to Quay.io
+        if: needs.build-arch.outputs.push-external == 'true'
+        env:
+          TAGS: ${{ steps.docker-meta.outputs.tags }}
+          GHCR_REPO: ${{ env.REGISTRY }}/${{ needs.build-arch.outputs.repository }}
+        run: |
+          for tag in ${TAGS}; do
+            quay_tag="${tag/${GHCR_REPO}/quay.io/paperlessngx/paperless-ngx}"
+            echo "Copying ${tag} to ${quay_tag}"
+            skopeo copy --all "docker://${tag}" "docker://${quay_tag}"
+          done

.github/workflows/ci-docs.yml

@@ -0,0 +1,88 @@
+name: Documentation
+on:
+  push:
+    branches:
+      - main
+      - dev
+    paths:
+      - 'docs/**'
+      - 'mkdocs.yml'
+      - '.github/workflows/ci-docs.yml'
+  pull_request:
+    paths:
+      - 'docs/**'
+      - 'mkdocs.yml'
+      - '.github/workflows/ci-docs.yml'
+  workflow_dispatch:
+concurrency:
+  group: docs-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+env:
+  DEFAULT_UV_VERSION: "0.9.x"
+  DEFAULT_PYTHON_VERSION: "3.11"
+jobs:
+  build:
+    name: Build Documentation
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Set up Python
+        id: setup-python
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          version: ${{ env.DEFAULT_UV_VERSION }}
+          enable-cache: true
+          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
+      - name: Install Python dependencies
+        run: |
+          uv sync --python ${{ steps.setup-python.outputs.python-version }} --dev --frozen
+      - name: Build documentation
+        run: |
+          uv run \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            --dev \
+            --frozen \
+            mkdocs build --config-file ./mkdocs.yml
+      - name: Upload artifact
+        uses: actions/upload-artifact@v6
+        with:
+          name: documentation
+          path: site/
+          retention-days: 7
+  deploy:
+    name: Deploy Documentation
+    needs: build
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Set up Python
+        id: setup-python
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          version: ${{ env.DEFAULT_UV_VERSION }}
+          enable-cache: true
+          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
+      - name: Install Python dependencies
+        run: |
+          uv sync --python ${{ steps.setup-python.outputs.python-version }} --dev --frozen
+      - name: Deploy documentation
+        run: |
+          echo "docs.paperless-ngx.com" > "${{ github.workspace }}/docs/CNAME"
+          git config --global user.name "${{ github.actor }}"
+          git config --global user.email "${{ github.actor }}@users.noreply.github.com"
+          uv run \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            --dev \
+            --frozen \
+            mkdocs gh-deploy --force --no-history

.github/workflows/ci-frontend.yml

@@ -0,0 +1,189 @@
+name: Frontend Tests
+on:
+  push:
+    branches-ignore:
+      - 'translations**'
+    paths:
+      - 'src-ui/**'
+      - '.github/workflows/ci-frontend.yml'
+  pull_request:
+    branches-ignore:
+      - 'translations**'
+    paths:
+      - 'src-ui/**'
+      - '.github/workflows/ci-frontend.yml'
+  workflow_dispatch:
+concurrency:
+  group: frontend-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+jobs:
+  install-dependencies:
+    name: Install Dependencies
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10
+      - name: Use Node.js 24
+        uses: actions/setup-node@v6
+        with:
+          node-version: 24.x
+          cache: 'pnpm'
+          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
+      - name: Cache frontend dependencies
+        id: cache-frontend-deps
+        uses: actions/cache@v5
+        with:
+          path: |
+            ~/.pnpm-store
+            ~/.cache
+          key: ${{ runner.os }}-frontend-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
+      - name: Install dependencies
+        run: cd src-ui && pnpm install
+  lint:
+    name: Lint
+    needs: install-dependencies
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10
+      - name: Use Node.js 24
+        uses: actions/setup-node@v6
+        with:
+          node-version: 24.x
+          cache: 'pnpm'
+          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
+      - name: Cache frontend dependencies
+        uses: actions/cache@v5
+        with:
+          path: |
+            ~/.pnpm-store
+            ~/.cache
+          key: ${{ runner.os }}-frontend-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
+      - name: Re-link Angular CLI
+        run: cd src-ui && pnpm link @angular/cli
+      - name: Run lint
+        run: cd src-ui && pnpm run lint
+  unit-tests:
+    name: "Unit Tests (${{ matrix.shard-index }}/${{ matrix.shard-count }})"
+    needs: install-dependencies
+    runs-on: ubuntu-24.04
+    strategy:
+      fail-fast: false
+      matrix:
+        node-version: [24.x]
+        shard-index: [1, 2, 3, 4]
+        shard-count: [4]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10
+      - name: Use Node.js 24
+        uses: actions/setup-node@v6
+        with:
+          node-version: 24.x
+          cache: 'pnpm'
+          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
+      - name: Cache frontend dependencies
+        uses: actions/cache@v5
+        with:
+          path: |
+            ~/.pnpm-store
+            ~/.cache
+          key: ${{ runner.os }}-frontend-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
+      - name: Re-link Angular CLI
+        run: cd src-ui && pnpm link @angular/cli
+      - name: Run Jest unit tests
+        run: cd src-ui && pnpm run test --max-workers=2 --shard=${{ matrix.shard-index }}/${{ matrix.shard-count }}
+      - name: Upload test results to Codecov
+        if: always()
+        uses: codecov/codecov-action@v5
+        with:
+          flags: frontend,frontend-node-${{ matrix.node-version }}
+          directory: src-ui/
+          report_type: test_results
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
+        with:
+          flags: frontend,frontend-node-${{ matrix.node-version }}
+          directory: src-ui/coverage/
+  e2e-tests:
+    name: "E2E Tests (${{ matrix.shard-index }}/${{ matrix.shard-count }})"
+    needs: install-dependencies
+    runs-on: ubuntu-24.04
+    container: mcr.microsoft.com/playwright:v1.57.0-noble
+    env:
+      PLAYWRIGHT_BROWSERS_PATH: /ms-playwright
+      PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD: 1
+    strategy:
+      fail-fast: false
+      matrix:
+        node-version: [24.x]
+        shard-index: [1, 2]
+        shard-count: [2]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10
+      - name: Use Node.js 24
+        uses: actions/setup-node@v6
+        with:
+          node-version: 24.x
+          cache: 'pnpm'
+          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
+      - name: Cache frontend dependencies
+        uses: actions/cache@v5
+        with:
+          path: |
+            ~/.pnpm-store
+            ~/.cache
+          key: ${{ runner.os }}-frontend-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
+      - name: Re-link Angular CLI
+        run: cd src-ui && pnpm link @angular/cli
+      - name: Install dependencies
+        run: cd src-ui && pnpm install --no-frozen-lockfile
+      - name: Run Playwright E2E tests
+        run: cd src-ui && pnpm exec playwright test --shard ${{ matrix.shard-index }}/${{ matrix.shard-count }}
+  bundle-analysis:
+    name: Bundle Analysis
+    needs: [unit-tests, e2e-tests]
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10
+      - name: Use Node.js 24
+        uses: actions/setup-node@v6
+        with:
+          node-version: 24.x
+          cache: 'pnpm'
+          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
+      - name: Cache frontend dependencies
+        uses: actions/cache@v5
+        with:
+          path: |
+            ~/.pnpm-store
+            ~/.cache
+          key: ${{ runner.os }}-frontend-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
+      - name: Re-link Angular CLI
+        run: cd src-ui && pnpm link @angular/cli
+      - name: Build and analyze
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+        run: cd src-ui && pnpm run build --configuration=production

.github/workflows/ci-lint.yml

@@ -0,0 +1,24 @@
+name: Lint
+on:
+  push:
+    branches-ignore:
+      - 'translations**'
+  pull_request:
+    branches-ignore:
+      - 'translations**'
+concurrency:
+  group: lint-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+jobs:
+  pre-commit:
+    name: Pre-commit Checks
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Install Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: "3.11"
+      - name: Run pre-commit
+        uses: pre-commit/action@v3.0.1

.github/workflows/ci-release.yml

@@ -0,0 +1,237 @@
+name: Release
+on:
+  push:
+    tags:
+      - 'v[0-9]+.[0-9]+.[0-9]+'
+      - 'v[0-9]+.[0-9]+.[0-9]+-beta.rc[0-9]+'
+concurrency:
+  group: release-${{ github.ref }}
+  cancel-in-progress: false
+env:
+  DEFAULT_UV_VERSION: "0.9.x"
+  DEFAULT_PYTHON_VERSION: "3.11"
+jobs:
+  wait-for-docker:
+    name: Wait for Docker Build
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Wait for Docker build
+        uses: lewagon/wait-on-check-action@v1.4.1
+        with:
+          ref: ${{ github.sha }}
+          check-name: 'Build Docker Image'
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
+          wait-interval: 60
+  build-release:
+    name: Build Release
+    needs: wait-for-docker
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      # ---- Frontend Build ----
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10
+      - name: Use Node.js 24
+        uses: actions/setup-node@v6
+        with:
+          node-version: 24.x
+          cache: 'pnpm'
+          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
+      - name: Install frontend dependencies
+        run: cd src-ui && pnpm install
+      - name: Build frontend
+        run: cd src-ui && pnpm run build --configuration production
+      # ---- Backend Setup ----
+      - name: Set up Python
+        id: setup-python
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          version: ${{ env.DEFAULT_UV_VERSION }}
+          enable-cache: true
+          python-version: ${{ steps.setup-python.outputs.python-version }}
+      - name: Install Python dependencies
+        run: |
+          uv sync --python ${{ steps.setup-python.outputs.python-version }} --dev --frozen
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update -qq
+          sudo apt-get install -qq --no-install-recommends gettext liblept5
+      # ---- Build Documentation ----
+      - name: Build documentation
+        run: |
+          uv run \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            --dev \
+            --frozen \
+            mkdocs build --config-file ./mkdocs.yml
+      # ---- Prepare Release ----
+      - name: Generate requirements file
+        run: |
+          uv export --quiet --no-dev --all-extras --format requirements-txt --output-file requirements.txt
+      - name: Compile messages
+        run: |
+          cd src/
+          uv run \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            manage.py compilemessages
+      - name: Collect static files
+        run: |
+          cd src/
+          uv run \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            manage.py collectstatic --no-input --clear
+      - name: Assemble release package
+        run: |
+          mkdir -p dist/paperless-ngx/scripts
+
+          for file_name in .dockerignore \
+                          .env \
+                          Dockerfile \
+                          pyproject.toml \
+                          uv.lock \
+                          requirements.txt \
+                          LICENSE \
+                          README.md \
+                          paperless.conf.example
+          do
+            cp --verbose ${file_name} dist/paperless-ngx/
+          done
+          mv dist/paperless-ngx/paperless.conf.example dist/paperless-ngx/paperless.conf
+
+          cp --recursive docker/ dist/paperless-ngx/docker
+          cp scripts/*.service scripts/*.sh scripts/*.socket dist/paperless-ngx/scripts/
+          cp --recursive src/ dist/paperless-ngx/src
+          cp --recursive site/ dist/paperless-ngx/docs
+          mv static dist/paperless-ngx/
+
+          find dist/paperless-ngx -name "__pycache__" -type d -exec rm -rf {} +
+      - name: Create release archive
+        run: |
+          cd dist
+          sudo chown -R 1000:1000 paperless-ngx/
+          tar -cJf paperless-ngx.tar.xz paperless-ngx/
+      - name: Upload release artifact
+        uses: actions/upload-artifact@v6
+        with:
+          name: release
+          path: dist/paperless-ngx.tar.xz
+          retention-days: 7
+  publish-release:
+    name: Publish Release
+    needs: build-release
+    runs-on: ubuntu-24.04
+    outputs:
+      prerelease: ${{ steps.get-version.outputs.prerelease }}
+      changelog: ${{ steps.create-release.outputs.body }}
+      version: ${{ steps.get-version.outputs.version }}
+    steps:
+      - name: Download release artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: release
+          path: ./
+      - name: Get version info
+        id: get-version
+        run: |
+          echo "version=${{ github.ref_name }}" >> $GITHUB_OUTPUT
+          if [[ "${{ github.ref_name }}" == *"-beta.rc"* ]]; then
+            echo "prerelease=true" >> $GITHUB_OUTPUT
+          else
+            echo "prerelease=false" >> $GITHUB_OUTPUT
+          fi
+      - name: Create release and changelog
+        id: create-release
+        uses: release-drafter/release-drafter@v6
+        with:
+          name: Paperless-ngx ${{ steps.get-version.outputs.version }}
+          tag: ${{ steps.get-version.outputs.version }}
+          version: ${{ steps.get-version.outputs.version }}
+          prerelease: ${{ steps.get-version.outputs.prerelease }}
+          publish: true
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      - name: Upload release archive
+        uses: shogo82148/actions-upload-release-asset@v1
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          upload_url: ${{ steps.create-release.outputs.upload_url }}
+          asset_path: ./paperless-ngx.tar.xz
+          asset_name: paperless-ngx-${{ steps.get-version.outputs.version }}.tar.xz
+          asset_content_type: application/x-xz
+  # ---------------------------------------------------------------------------
+  # Append changelog to docs (only on non-prerelease)
+  # ---------------------------------------------------------------------------
+  append-changelog:
+    name: Append Changelog
+    needs: publish-release
+    if: needs.publish-release.outputs.prerelease == 'false'
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+        with:
+          ref: main
+      - name: Set up Python
+        id: setup-python
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          version: ${{ env.DEFAULT_UV_VERSION }}
+          enable-cache: true
+          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
+      - name: Update changelog
+        working-directory: docs
+        run: |
+          git branch ${{ needs.publish-release.outputs.version }}-changelog
+          git checkout ${{ needs.publish-release.outputs.version }}-changelog
+
+          echo -e "# Changelog\n\n${{ needs.publish-release.outputs.changelog }}\n" > changelog-new.md
+
+          echo "Manually linking usernames"
+          sed -i -r 's|@([a-zA-Z0-9_]+) \(\[#|[@\1](https://github.com/\1) ([#|g' changelog-new.md
+
+          echo "Removing unneeded comment tags"
+          sed -i -r 's|@<!---->|@|g' changelog-new.md
+
+          CURRENT_CHANGELOG=$(tail --lines +2 changelog.md)
+          echo -e "$CURRENT_CHANGELOG" >> changelog-new.md
+          mv changelog-new.md changelog.md
+
+          uv run \
+            --python ${{ steps.setup-python.outputs.python-version }} \
+            --dev \
+            pre-commit run --files changelog.md || true
+
+          git config --global user.name "github-actions"
+          git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
+          git commit -am "Changelog ${{ needs.publish-release.outputs.version }} - GHA"
+          git push origin ${{ needs.publish-release.outputs.version }}-changelog
+      - name: Create pull request
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const { repo, owner } = context.repo;
+            const result = await github.rest.pulls.create({
+              title: 'Documentation: Add ${{ needs.publish-release.outputs.version }} changelog',
+              owner,
+              repo,
+              head: '${{ needs.publish-release.outputs.version }}-changelog',
+              base: 'main',
+              body: 'This PR is auto-generated by CI.'
+            });
+            github.rest.issues.addLabels({
+              owner,
+              repo,
+              issue_number: result.data.number,
+              labels: ['documentation', 'skip-changelog']
+            });

.github/workflows/ci.yml

@@ -1,693 +0,0 @@
-name: ci
-on:
-  push:
-    tags:
-      # https://semver.org/#spec-item-2
-      - 'v[0-9]+.[0-9]+.[0-9]+'
-      # https://semver.org/#spec-item-9
-      - 'v[0-9]+.[0-9]+.[0-9]+-beta.rc[0-9]+'
-    branches-ignore:
-      - 'translations**'
-  pull_request:
-    branches-ignore:
-      - 'translations**'
-env:
-  DEFAULT_UV_VERSION: "0.9.x"
-  # This is the default version of Python to use in most steps which aren't specific
-  DEFAULT_PYTHON_VERSION: "3.11"
-  NLTK_DATA: "/usr/share/nltk_data"
-jobs:
-  detect-duplicate:
-    name: Detect Duplicate Run
-    runs-on: ubuntu-24.04
-    outputs:
-      should_run: ${{ steps.check.outputs.should_run }}
-    steps:
-      - name: Check if workflow should run
-        id: check
-        uses: actions/github-script@v8
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            if (context.eventName !== 'push') {
-              core.info('Not a push event; running workflow.');
-              core.setOutput('should_run', 'true');
-              return;
-            }
-
-            const ref = context.ref || '';
-            if (!ref.startsWith('refs/heads/')) {
-              core.info('Push is not to a branch; running workflow.');
-              core.setOutput('should_run', 'true');
-              return;
-            }
-
-            const branch = ref.substring('refs/heads/'.length);
-            const { owner, repo } = context.repo;
-            const prs = await github.paginate(github.rest.pulls.list, {
-              owner,
-              repo,
-              state: 'open',
-              head: `${owner}:${branch}`,
-              per_page: 100,
-            });
-
-            if (prs.length === 0) {
-              core.info(`No open PR found for ${branch}; running workflow.`);
-              core.setOutput('should_run', 'true');
-            } else {
-              core.info(`Found ${prs.length} open PR(s) for ${branch}; skipping duplicate push run.`);
-              core.setOutput('should_run', 'false');
-            }
-  pre-commit:
-    needs:
-      - detect-duplicate
-    if: needs.detect-duplicate.outputs.should_run == 'true'
-    name: Linting Checks
-    runs-on: ubuntu-24.04
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v6
-      - name: Install python
-        uses: actions/setup-python@v6
-        with:
-          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
-      - name: Check files
-        uses: pre-commit/action@v3.0.1
-  documentation:
-    name: "Build & Deploy Documentation"
-    runs-on: ubuntu-24.04
-    needs:
-      - pre-commit
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-      - name: Set up Python
-        id: setup-python
-        uses: actions/setup-python@v6
-        with:
-          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
-      - name: Install uv
-        uses: astral-sh/setup-uv@v7
-        with:
-          version: ${{ env.DEFAULT_UV_VERSION }}
-          enable-cache: true
-          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
-      - name: Install Python dependencies
-        run: |
-          uv sync --python ${{ steps.setup-python.outputs.python-version }} --dev --frozen
-      - name: Make documentation
-        run: |
-          uv run \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            --dev \
-            --frozen \
-            mkdocs build --config-file ./mkdocs.yml
-      - name: Deploy documentation
-        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
-        run: |
-          echo "docs.paperless-ngx.com" > "${{ github.workspace }}/docs/CNAME"
-          git config --global user.name "${{ github.actor }}"
-          git config --global user.email "${{ github.actor }}@users.noreply.github.com"
-          uv run \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            --dev \
-            --frozen \
-            mkdocs gh-deploy --force --no-history
-      - name: Upload artifact
-        uses: actions/upload-artifact@v5
-        with:
-          name: documentation
-          path: site/
-          retention-days: 7
-  tests-backend:
-    name: "Backend Tests (Python ${{ matrix.python-version }})"
-    runs-on: ubuntu-24.04
-    needs:
-      - pre-commit
-    strategy:
-      matrix:
-        python-version: ['3.10', '3.11', '3.12']
-      fail-fast: false
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-      - name: Start containers
-        run: |
-          docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml pull --quiet
-          docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml up --detach
-      - name: Set up Python
-        id: setup-python
-        uses: actions/setup-python@v6
-        with:
-          python-version: "${{ matrix.python-version }}"
-      - name: Install uv
-        uses: astral-sh/setup-uv@v7
-        with:
-          version: ${{ env.DEFAULT_UV_VERSION }}
-          enable-cache: true
-          python-version: ${{ steps.setup-python.outputs.python-version }}
-      - name: Install system dependencies
-        run: |
-          sudo apt-get update -qq
-          sudo apt-get install -qq --no-install-recommends unpaper tesseract-ocr imagemagick ghostscript libzbar0 poppler-utils
-      - name: Configure ImageMagick
-        run: |
-          sudo cp docker/rootfs/etc/ImageMagick-6/paperless-policy.xml /etc/ImageMagick-6/policy.xml
-      - name: Install Python dependencies
-        run: |
-          uv sync \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            --group testing \
-            --frozen
-      - name: List installed Python dependencies
-        run: |
-          uv pip list
-      - name: Install or update NLTK dependencies
-        run: uv run python -m nltk.downloader punkt punkt_tab snowball_data stopwords -d ${{ env.NLTK_DATA }}
-      - name: Tests
-        env:
-          NLTK_DATA: ${{ env.NLTK_DATA }}
-          PAPERLESS_CI_TEST: 1
-          # Enable paperless_mail testing against real server
-          PAPERLESS_MAIL_TEST_HOST: ${{ secrets.TEST_MAIL_HOST }}
-          PAPERLESS_MAIL_TEST_USER: ${{ secrets.TEST_MAIL_USER }}
-          PAPERLESS_MAIL_TEST_PASSWD: ${{ secrets.TEST_MAIL_PASSWD }}
-        run: |
-          uv run \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            --dev \
-            --frozen \
-            pytest
-      - name: Upload backend test results to Codecov
-        if: always()
-        uses: codecov/codecov-action@v5
-        with:
-          flags: backend-python-${{ matrix.python-version }}
-          files: junit.xml
-          report_type: test_results
-      - name: Upload backend coverage to Codecov
-        uses: codecov/codecov-action@v5
-        with:
-          flags: backend-python-${{ matrix.python-version }}
-          files: coverage.xml
-      - name: Stop containers
-        if: always()
-        run: |
-          docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml logs
-          docker compose --file ${{ github.workspace }}/docker/compose/docker-compose.ci-test.yml down
-  install-frontend-dependencies:
-    name: "Install Frontend Dependencies"
-    runs-on: ubuntu-24.04
-    needs:
-      - pre-commit
-    steps:
-      - uses: actions/checkout@v6
-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          version: 10
-      - name: Use Node.js 20
-        uses: actions/setup-node@v6
-        with:
-          node-version: 20.x
-          cache: 'pnpm'
-          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
-      - name: Cache frontend dependencies
-        id: cache-frontend-deps
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.pnpm-store
-            ~/.cache
-          key: ${{ runner.os }}-frontenddeps-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
-      - name: Install dependencies
-        run: cd src-ui && pnpm install
-  tests-frontend:
-    name: "Frontend Unit Tests (Node ${{ matrix.node-version }} - ${{ matrix.shard-index }}/${{ matrix.shard-count }})"
-    runs-on: ubuntu-24.04
-    needs:
-      - install-frontend-dependencies
-    strategy:
-      fail-fast: false
-      matrix:
-        node-version: [20.x]
-        shard-index: [1, 2, 3, 4]
-        shard-count: [4]
-    steps:
-      - uses: actions/checkout@v6
-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          version: 10
-      - name: Use Node.js 20
-        uses: actions/setup-node@v6
-        with:
-          node-version: 20.x
-          cache: 'pnpm'
-          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
-      - name: Cache frontend dependencies
-        id: cache-frontend-deps
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.pnpm-store
-            ~/.cache
-          key: ${{ runner.os }}-frontenddeps-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
-      - name: Re-link Angular cli
-        run: cd src-ui && pnpm link @angular/cli
-      - name: Linting checks
-        run: cd src-ui && pnpm run lint
-      - name: Run Jest unit tests
-        run: cd src-ui && pnpm run test --max-workers=2 --shard=${{ matrix.shard-index }}/${{ matrix.shard-count }}
-      - name: Upload frontend test results to Codecov
-        if: always()
-        uses: codecov/codecov-action@v5
-        with:
-          flags: frontend-node-${{ matrix.node-version }}
-          directory: src-ui/
-          report_type: test_results
-      - name: Upload frontend coverage to Codecov
-        uses: codecov/codecov-action@v5
-        with:
-          flags: frontend-node-${{ matrix.node-version }}
-          directory: src-ui/coverage/
-  tests-frontend-e2e:
-    name: "Frontend E2E Tests (Node ${{ matrix.node-version }} - ${{ matrix.shard-index }}/${{ matrix.shard-count }})"
-    runs-on: ubuntu-24.04
-    container: mcr.microsoft.com/playwright:v1.57.0-noble
-    needs:
-      - install-frontend-dependencies
-    env:
-      PLAYWRIGHT_BROWSERS_PATH: /ms-playwright
-      PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD: 1
-    strategy:
-      fail-fast: false
-      matrix:
-        node-version: [20.x]
-        shard-index: [1, 2]
-        shard-count: [2]
-    steps:
-      - uses: actions/checkout@v6
-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          version: 10
-      - name: Use Node.js 20
-        uses: actions/setup-node@v6
-        with:
-          node-version: 20.x
-          cache: 'pnpm'
-          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
-      - name: Cache frontend dependencies
-        id: cache-frontend-deps
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.pnpm-store
-            ~/.cache
-          key: ${{ runner.os }}-frontenddeps-${{ hashFiles('src-ui/pnpm-lock.yaml') }}
-      - name: Re-link Angular cli
-        run: cd src-ui && pnpm link @angular/cli
-      - name: Install dependencies
-        run: cd src-ui && pnpm install --no-frozen-lockfile
-      - name: Run Playwright e2e tests
-        run: cd src-ui && pnpm exec playwright test --shard ${{ matrix.shard-index }}/${{ matrix.shard-count }}
-  frontend-bundle-analysis:
-    name: "Frontend Bundle Analysis"
-    runs-on: ubuntu-24.04
-    needs:
-      - tests-frontend
-      - tests-frontend-e2e
-    steps:
-      - uses: actions/checkout@v6
-      - name: Install pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          version: 10
-      - name: Use Node.js 20
-        uses: actions/setup-node@v6
-        with:
-          node-version: 20.x
-          cache: 'pnpm'
-          cache-dependency-path: 'src-ui/pnpm-lock.yaml'
-      - name: Cache frontend dependencies
-        id: cache-frontend-deps
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.pnpm-store
-            ~/.cache
-          key: ${{ runner.os }}-frontenddeps-${{ hashFiles('src-ui/package-lock.json') }}
-      - name: Re-link Angular cli
-        run: cd src-ui && pnpm link @angular/cli
-      - name: Build frontend and upload analysis
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
-        run: cd src-ui && pnpm run build --configuration=production
-  build-docker-image:
-    name: Build Docker image for ${{ github.event_name == 'pull_request' && github.head_ref || github.ref_name }}
-    runs-on: ubuntu-24.04
-    if: (github.event_name == 'push' && (startsWith(github.ref, 'refs/heads/feature-') || startsWith(github.ref, 'refs/heads/fix-') || github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/beta' || contains(github.ref, 'beta.rc') || startsWith(github.ref, 'refs/tags/v') || startsWith(github.ref, 'refs/heads/l10n_'))) || (github.event_name == 'pull_request' && (startsWith(github.head_ref, 'feature-') || startsWith(github.head_ref, 'fix-') || github.head_ref == 'dev' || github.head_ref == 'beta' || contains(github.head_ref, 'beta.rc') || startsWith(github.head_ref, 'l10n_')))
-    concurrency:
-      group: ${{ github.workflow }}-build-docker-image-${{ github.ref_name }}
-      cancel-in-progress: true
-    needs:
-      - tests-backend
-      - tests-frontend
-      - tests-frontend-e2e
-    steps:
-      - name: Prepare build variables
-        id: build-vars
-        uses: actions/github-script@v8
-        with:
-          result-encoding: string
-          script: |
-            const isPR = context.eventName === 'pull_request';
-            const defaultRefName = context.ref.replace('refs/heads/', '');
-            const headRef = isPR ? context.payload.pull_request.head.ref : defaultRefName;
-            const buildRef = isPR ? `refs/heads/${headRef}` : context.ref;
-            const buildCacheKey = headRef.split('/').join('-');
-            const canPush = context.eventName === 'push' || (isPR && context.payload.pull_request.head.repo.full_name === `${context.repo.owner}/${context.repo.repo}`);
-
-            core.setOutput('build-ref', buildRef);
-            core.setOutput('build-ref-name', headRef);
-            core.setOutput('build-cache-key', buildCacheKey);
-            core.setOutput('can-push', canPush ? 'true' : 'false');
-      - name: Check pushing to Docker Hub
-        id: push-other-places
-        # Only push to Dockerhub from the main repo AND the ref is either:
-        #  main
-        #  dev
-        #  beta
-        #  a tag
-        # Otherwise forks would require a Docker Hub account and secrets setup
-        env:
-          BUILD_REF: ${{ steps.build-vars.outputs.build-ref }}
-          BUILD_REF_NAME: ${{ steps.build-vars.outputs.build-ref-name }}
-        run: |
-          if [[ ${{ github.repository_owner }} == "paperless-ngx" && ( "$BUILD_REF_NAME" == "dev" || "$BUILD_REF_NAME" == "beta" || $BUILD_REF == refs/tags/v* || $BUILD_REF == *beta.rc* ) ]] ; then
-            echo "Enabling DockerHub image push"
-            echo "enable=true" >> $GITHUB_OUTPUT
-          else
-            echo "Not pushing to DockerHub"
-            echo "enable=false" >> $GITHUB_OUTPUT
-          fi
-      - name: Set ghcr repository name
-        id: set-ghcr-repository
-        run: |
-          ghcr_name=$(echo "${{ github.repository }}" | awk '{ print tolower($0) }')
-          echo "Name is ${ghcr_name}"
-          echo "ghcr-repository=${ghcr_name}" >> $GITHUB_OUTPUT
-      - name: Gather Docker metadata
-        id: docker-meta
-        uses: docker/metadata-action@v5
-        with:
-          images: |
-            ghcr.io/${{ steps.set-ghcr-repository.outputs.ghcr-repository }}
-            name=paperlessngx/paperless-ngx,enable=${{ steps.push-other-places.outputs.enable }}
-            name=quay.io/paperlessngx/paperless-ngx,enable=${{ steps.push-other-places.outputs.enable }}
-          tags: |
-            # Tag branches with branch name
-            type=ref,event=branch
-            # Pull requests need a sanitized branch tag for pushing images
-            type=raw,value=${{ steps.build-vars.outputs.build-cache-key }},enable=${{ github.event_name == 'pull_request' }}
-            # Process semver tags
-            # For a tag x.y.z or vX.Y.Z, output an x.y.z and x.y image tag
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-      - name: Checkout
-        uses: actions/checkout@v6
-      # If https://github.com/docker/buildx/issues/1044 is resolved,
-      # the append input with a native arm64 arch could be used to
-      # significantly speed up building
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-        with:
-          platforms: arm64
-      - name: Login to GitHub Container Registry
-        uses: docker/login-action@v3
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        # Don't attempt to login if not pushing to Docker Hub
-        if: steps.push-other-places.outputs.enable == 'true'
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-      - name: Login to Quay.io
-        uses: docker/login-action@v3
-        # Don't attempt to login if not pushing to Quay.io
-        if: steps.push-other-places.outputs.enable == 'true'
-        with:
-          registry: quay.io
-          username: ${{ secrets.QUAY_USERNAME }}
-          password: ${{ secrets.QUAY_ROBOT_TOKEN }}
-      - name: Build and push
-        uses: docker/build-push-action@v6
-        with:
-          context: .
-          file: ./Dockerfile
-          platforms: linux/amd64,linux/arm64
-          push: ${{ steps.build-vars.outputs.can-push == 'true' }}
-          tags: ${{ steps.docker-meta.outputs.tags }}
-          labels: ${{ steps.docker-meta.outputs.labels }}
-          build-args: |
-            PNGX_TAG_VERSION=${{ steps.docker-meta.outputs.version }}
-          # Get cache layers from this branch, then dev
-          # This allows new branches to get at least some cache benefits, generally from dev
-          cache-from: |
-            type=registry,ref=ghcr.io/${{ steps.set-ghcr-repository.outputs.ghcr-repository }}/builder/cache/app:${{ steps.build-vars.outputs.build-cache-key }}
-            type=registry,ref=ghcr.io/${{ steps.set-ghcr-repository.outputs.ghcr-repository }}/builder/cache/app:dev
-          cache-to: ${{ steps.build-vars.outputs.can-push == 'true' && format('type=registry,mode=max,ref=ghcr.io/{0}/builder/cache/app:{1}', steps.set-ghcr-repository.outputs.ghcr-repository, steps.build-vars.outputs.build-cache-key) || '' }}
-      - name: Inspect image
-        if: steps.build-vars.outputs.can-push == 'true'
-        run: |
-          docker buildx imagetools inspect ${{ fromJSON(steps.docker-meta.outputs.json).tags[0] }}
-      - name: Export frontend artifact from docker
-        if: steps.build-vars.outputs.can-push == 'true'
-        run: |
-          docker create --name frontend-extract ${{ fromJSON(steps.docker-meta.outputs.json).tags[0] }}
-          docker cp frontend-extract:/usr/src/paperless/src/documents/static/frontend src/documents/static/frontend/
-      - name: Upload frontend artifact
-        if: steps.build-vars.outputs.can-push == 'true'
-        uses: actions/upload-artifact@v5
-        with:
-          name: frontend-compiled
-          path: src/documents/static/frontend/
-          retention-days: 7
-  build-release:
-    name: "Build Release"
-    needs:
-      - build-docker-image
-      - documentation
-    if: github.event_name == 'push'
-    runs-on: ubuntu-24.04
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-      - name: Set up Python
-        id: setup-python
-        uses: actions/setup-python@v6
-        with:
-          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
-      - name: Install uv
-        uses: astral-sh/setup-uv@v7
-        with:
-          version: ${{ env.DEFAULT_UV_VERSION }}
-          enable-cache: true
-          python-version: ${{ steps.setup-python.outputs.python-version }}
-      - name: Install Python dependencies
-        run: |
-          uv sync --python ${{ steps.setup-python.outputs.python-version }} --dev --frozen
-      - name: Install system dependencies
-        run: |
-          sudo apt-get update -qq
-          sudo apt-get install -qq --no-install-recommends gettext liblept5
-      - name: Download frontend artifact
-        uses: actions/download-artifact@v6
-        with:
-          name: frontend-compiled
-          path: src/documents/static/frontend/
-      - name: Download documentation artifact
-        uses: actions/download-artifact@v6
-        with:
-          name: documentation
-          path: docs/_build/html/
-      - name: Generate requirements file
-        run: |
-          uv export --quiet --no-dev --all-extras --format requirements-txt --output-file requirements.txt
-      - name: Compile messages
-        run: |
-          cd src/
-          uv run \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            manage.py compilemessages
-      - name: Collect static files
-        run: |
-          cd src/
-          uv run \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            manage.py collectstatic --no-input
-      - name: Move files
-        run: |
-          echo "Making dist folders"
-          for directory in dist \
-                          dist/paperless-ngx \
-                          dist/paperless-ngx/scripts;
-          do
-            mkdir --verbose --parents ${directory}
-          done
-
-          echo "Copying basic files"
-          for file_name in .dockerignore \
-                          .env \
-                          Dockerfile \
-                          pyproject.toml \
-                          uv.lock \
-                          requirements.txt \
-                          LICENSE \
-                          README.md \
-                          paperless.conf.example
-          do
-            cp --verbose ${file_name} dist/paperless-ngx/
-          done
-          mv --verbose dist/paperless-ngx/paperless.conf.example dist/paperless-ngx/paperless.conf
-
-          echo "Copying Docker related files"
-          cp --recursive docker/ dist/paperless-ngx/docker
-
-          echo "Copying startup scripts"
-          cp --verbose scripts/*.service scripts/*.sh scripts/*.socket dist/paperless-ngx/scripts/
-
-          echo "Copying source files"
-          cp --recursive src/ dist/paperless-ngx/src
-          echo "Copying documentation"
-          cp --recursive docs/_build/html/ dist/paperless-ngx/docs
-
-          mv --verbose static dist/paperless-ngx
-      - name: Make release package
-        run: |
-          echo "Creating release archive"
-          cd dist
-          sudo chown -R 1000:1000 paperless-ngx/
-          tar -cJf paperless-ngx.tar.xz paperless-ngx/
-      - name: Upload release artifact
-        uses: actions/upload-artifact@v5
-        with:
-          name: release
-          path: dist/paperless-ngx.tar.xz
-          retention-days: 7
-  publish-release:
-    name: "Publish Release"
-    runs-on: ubuntu-24.04
-    outputs:
-      prerelease: ${{ steps.get_version.outputs.prerelease }}
-      changelog: ${{ steps.create-release.outputs.body }}
-      version: ${{ steps.get_version.outputs.version }}
-    needs:
-      - build-release
-    if: github.ref_type == 'tag' && (startsWith(github.ref_name, 'v') || contains(github.ref_name, '-beta.rc'))
-    steps:
-      - name: Download release artifact
-        uses: actions/download-artifact@v6
-        with:
-          name: release
-          path: ./
-      - name: Get version
-        id: get_version
-        run: |
-          echo "version=${{ github.ref_name }}" >> $GITHUB_OUTPUT
-          if [[ ${{ contains(github.ref_name, '-beta.rc') }} == 'true' ]]; then
-            echo "prerelease=true" >> $GITHUB_OUTPUT
-          else
-            echo "prerelease=false" >> $GITHUB_OUTPUT
-          fi
-      - name: Create Release and Changelog
-        id: create-release
-        uses: release-drafter/release-drafter@v6
-        with:
-          name: Paperless-ngx ${{ steps.get_version.outputs.version }}
-          tag: ${{ steps.get_version.outputs.version }}
-          version: ${{ steps.get_version.outputs.version }}
-          prerelease: ${{ steps.get_version.outputs.prerelease }}
-          publish: true # ensures release is not marked as draft
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      - name: Upload release archive
-        id: upload-release-asset
-        uses: shogo82148/actions-upload-release-asset@v1
-        with:
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-          upload_url: ${{ steps.create-release.outputs.upload_url }}
-          asset_path: ./paperless-ngx.tar.xz
-          asset_name: paperless-ngx-${{ steps.get_version.outputs.version }}.tar.xz
-          asset_content_type: application/x-xz
-  append-changelog:
-    name: "Append Changelog"
-    runs-on: ubuntu-24.04
-    needs:
-      - publish-release
-    if: needs.publish-release.outputs.prerelease == 'false'
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-        with:
-          ref: main
-      - name: Set up Python
-        id: setup-python
-        uses: actions/setup-python@v6
-        with:
-          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
-      - name: Install uv
-        uses: astral-sh/setup-uv@v7
-        with:
-          version: ${{ env.DEFAULT_UV_VERSION }}
-          enable-cache: true
-          python-version: ${{ env.DEFAULT_PYTHON_VERSION }}
-      - name: Append Changelog to docs
-        id: append-Changelog
-        working-directory: docs
-        run: |
-          git branch ${{ needs.publish-release.outputs.version }}-changelog
-          git checkout ${{ needs.publish-release.outputs.version }}-changelog
-          echo -e "# Changelog\n\n${{ needs.publish-release.outputs.changelog }}\n" > changelog-new.md
-          echo "Manually linking usernames"
-          sed -i -r 's|@([a-zA-Z0-9_]+) \(\[#|[@\1](https://github.com/\1) ([#|g' changelog-new.md
-          echo "Removing unneeded comment tags"
-          sed -i -r 's|@<!---->|@|g' changelog-new.md
-          CURRENT_CHANGELOG=`tail --lines +2 changelog.md`
-          echo -e "$CURRENT_CHANGELOG" >> changelog-new.md
-          mv changelog-new.md changelog.md
-          uv run \
-            --python ${{ steps.setup-python.outputs.python-version }} \
-            --dev \
-            pre-commit run --files changelog.md || true
-          git config --global user.name "github-actions"
-          git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
-          git commit -am "Changelog ${{ needs.publish-release.outputs.version }} - GHA"
-          git push origin ${{ needs.publish-release.outputs.version }}-changelog
-      - name: Create Pull Request
-        uses: actions/github-script@v8
-        with:
-          script: |
-            const { repo, owner } = context.repo;
-            const result = await github.rest.pulls.create({
-              title: 'Documentation: Add ${{ needs.publish-release.outputs.version }} changelog',
-              owner,
-              repo,
-              head: '${{ needs.publish-release.outputs.version }}-changelog',
-              base: 'main',
-              body: 'This PR is auto-generated by CI.'
-            });
-            github.rest.issues.addLabels({
-              owner,
-              repo,
-              issue_number: result.data.number,
-              labels: ['documentation', 'skip-changelog']
-            });

.github/workflows/repo-maintenance.yml

@@ -37,7 +37,7 @@ jobs:
     if: github.repository_owner == 'paperless-ngx'
     runs-on: ubuntu-24.04
     steps:
-      - uses: dessant/lock-threads@v5
+      - uses: dessant/lock-threads@v6
         with:
           issue-inactive-days: '30'
           pr-inactive-days: '30'

.github/workflows/translate-strings.yml

@@ -12,9 +12,11 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v6
+        env:
+          GH_REF: ${{ github.ref }} # sonar rule:githubactions:S7630 - avoid injection
         with:
           token: ${{ secrets.PNGX_BOT_PAT }}
-          ref: ${{ github.head_ref }}
+          ref: ${{ env.GH_REF }}
       - name: Set up Python
         id: setup-python
         uses: actions/setup-python@v6
@@ -37,15 +39,15 @@ jobs:
         uses: pnpm/action-setup@v4
         with:
           version: 10
-      - name: Use Node.js 20
+      - name: Use Node.js 24
         uses: actions/setup-node@v6
         with:
-          node-version: 20.x
+          node-version: 24.x
           cache: 'pnpm'
           cache-dependency-path: 'src-ui/pnpm-lock.yaml'
       - name: Cache frontend dependencies
         id: cache-frontend-deps
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: |
             ~/.pnpm-store

Dockerfile

@@ -5,14 +5,12 @@
 # Purpose: Compiles the frontend
 # Notes:
 #  - Does PNPM stuff with Typescript and such
-FROM --platform=$BUILDPLATFORM docker.io/node:20-trixie-slim AS compile-frontend
+FROM --platform=$BUILDPLATFORM docker.io/node:24-trixie-slim AS compile-frontend
 
 COPY ./src-ui /src/src-ui
 
 WORKDIR /src/src-ui
 RUN set -eux \
-  && npm update -g pnpm \
-  && npm install -g corepack@latest \
   && corepack enable \
   && pnpm install
 
@@ -110,8 +108,7 @@ ENV PYTHONDONTWRITEBYTECODE=1 \
     PYTHONWARNINGS="ignore:::django.http.response:517" \
     PNGX_CONTAINERIZED=1 \
     # https://docs.astral.sh/uv/reference/settings/#link-mode
-    UV_LINK_MODE=copy \
-    UV_CACHE_DIR=/cache/uv/
+    UV_LINK_MODE=copy
 
 #
 # Begin installation and configuration
@@ -193,14 +190,13 @@ ARG BUILD_PACKAGES="\
   pkg-config"
 
 # hadolint ignore=DL3042
-RUN --mount=type=cache,target=${UV_CACHE_DIR},id=python-cache \
-  set -eux \
+RUN set -eux \
   && echo "Installing build system packages" \
     && apt-get update \
     && apt-get install --yes --quiet --no-install-recommends ${BUILD_PACKAGES} \
   && echo "Installing Python requirements" \
     && uv export --quiet --no-dev --all-extras --format requirements-txt --output-file requirements.txt \
-    && uv pip install --system --no-python-downloads --python-preference system --requirements requirements.txt \
+    && uv pip install --no-cache --system --no-python-downloads --python-preference system --requirements requirements.txt \
   && echo "Installing NLTK data" \
     && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" snowball_data \
     && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" stopwords \

docs/configuration.md

@@ -1804,3 +1804,23 @@ password. All of these options come from their similarly-named [Django settings]
 #### [`PAPERLESS_EMAIL_USE_SSL=<bool>`](#PAPERLESS_EMAIL_USE_SSL) {#PAPERLESS_EMAIL_USE_SSL}
 
 : Defaults to false.
+
+## Remote OCR
+
+#### [`PAPERLESS_REMOTE_OCR_ENGINE=<str>`](#PAPERLESS_REMOTE_OCR_ENGINE) {#PAPERLESS_REMOTE_OCR_ENGINE}
+
+: The remote OCR engine to use. Currently only Azure AI is supported as "azureai".
+
+    Defaults to None, which disables remote OCR.
+
+#### [`PAPERLESS_REMOTE_OCR_API_KEY=<str>`](#PAPERLESS_REMOTE_OCR_API_KEY) {#PAPERLESS_REMOTE_OCR_API_KEY}
+
+: The API key to use for the remote OCR engine.
+
+    Defaults to None.
+
+#### [`PAPERLESS_REMOTE_OCR_ENDPOINT=<str>`](#PAPERLESS_REMOTE_OCR_ENDPOINT) {#PAPERLESS_REMOTE_OCR_ENDPOINT}
+
+: The endpoint to use for the remote OCR engine. This is required for Azure AI.
+
+    Defaults to None.

docs/development.md

@@ -175,7 +175,7 @@ To add a new development package `uv add --dev <package>`
 
 ## Front end development
 
-The front end is built using AngularJS. In order to get started, you need Node.js (version 14.15+) and
+The front end is built using AngularJS. In order to get started, you need Node.js (version 24+) and
 `pnpm`.
 
 !!! note

docs/index.md

@@ -25,9 +25,10 @@ physical documents into a searchable online archive so you can keep, well, _less
 ## Features
 
 -   **Organize and index** your scanned documents with tags, correspondents, types, and more.
--   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way.
+-   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way, unless you explicitly choose to do so.
 -   Performs **OCR** on your documents, adding searchable and selectable text, even to documents scanned with only images.
--   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+    -   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+    -   _New!_ Supports remote OCR with Azure AI (opt-in).
 -   Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
 -   Uses machine-learning to automatically add tags, correspondents and document types to your documents.
 -   Supports PDF documents, images, plain text files, Office documents (Word, Excel, PowerPoint, and LibreOffice equivalents)[^1] and more.

docs/usage.md

@@ -901,6 +901,21 @@ how regularly you intend to scan documents and use paperless.
     performed the task associated with the document, move it to the
     inbox.
 
+## Remote OCR
+
+!!! important
+
+    This feature is disabled by default and will always remain strictly "opt-in".
+
+Paperless-ngx supports performing OCR on documents using remote services. At the moment, this is limited to
+[Microsoft's Azure "Document Intelligence" service](https://azure.microsoft.com/en-us/products/ai-services/ai-document-intelligence).
+This is of course a paid service (with a free tier) which requires an Azure account and subscription. Azure AI is not affiliated with
+Paperless-ngx in any way. When enabled, Paperless-ngx will automatically send appropriate documents to Azure for OCR processing, bypassing
+the local OCR engine. See the [configuration](configuration.md#PAPERLESS_REMOTE_OCR_ENGINE) options for more details.
+
+Additionally, when using a commercial service with this feature, consider both potential costs as well as any associated file size
+or page limitations (e.g. with a free tier).
+
 ## Architecture
 
 Paperless-ngx consists of the following components:

pyproject.toml

@@ -16,6 +16,7 @@ classifiers = [
 # This will allow testing to not install a webserver, mysql, etc
 
 dependencies = [
+  "azure-ai-documentintelligence>=1.0.2",
   "babel>=2.17",
   "bleach~=6.3.0",
   "celery[redis]~=5.5.1",
@@ -253,6 +254,7 @@ testpaths = [
   "src/paperless_tesseract/tests/",
   "src/paperless_tika/tests",
   "src/paperless_text/tests/",
+  "src/paperless_remote/tests/",
 ]
 addopts = [
   "--pythonwarnings=all",

src-ui/angular.json

@@ -156,16 +156,7 @@
           "builder": "@angular-builders/jest:run",
           "options": {
             "tsConfig": "tsconfig.spec.json",
-            "assets": [
-              "src/favicon.ico",
-              "src/apple-touch-icon.png",
-              "src/assets",
-              "src/manifest.webmanifest"
-            ],
-            "styles": [
-              "src/styles.scss"
-            ],
-            "scripts": []
+            "zoneless": false
           }
         },
         "lint": {

src-ui/jest.config.js

@@ -1,5 +1,23 @@
+const { createEsmPreset } = require('jest-preset-angular/presets')
+
+const esmPreset = createEsmPreset({
+  tsconfig: '<rootDir>/tsconfig.spec.json',
+  stringifyContentPathRegex: '\\.(html|svg)$',
+})
+
 module.exports = {
-  preset: 'jest-preset-angular',
+  ...esmPreset,
+  transform: {
+    ...esmPreset.transform,
+    '^.+\\.(ts|js|mjs|html|svg)$': [
+      'jest-preset-angular',
+      {
+        tsconfig: '<rootDir>/tsconfig.spec.json',
+        stringifyContentPathRegex: '\\.(html|svg)$',
+        useESM: true,
+      },
+    ],
+  },
   setupFilesAfterEnv: ['<rootDir>/setup-jest.ts'],
   testPathIgnorePatterns: [
     '/node_modules/',
@@ -8,9 +26,10 @@ module.exports = {
     'abstract-paperless-service',
   ],
   transformIgnorePatterns: [
-    `<rootDir>/node_modules/.pnpm/(?!.*\\.mjs$|lodash-es|@angular\\+common.*locales)`,
+    'node_modules/(?!.*(\\.mjs$|tslib|lodash-es|@angular/common/locales/.*\\.js$))',
   ],
   moduleNameMapper: {
+    ...esmPreset.moduleNameMapper,
     '^src/(.*)': '<rootDir>/src/$1',
   },
   workerIdleMemoryLimit: '512MB',

src-ui/package.json

@@ -11,17 +11,17 @@
   },
   "private": true,
   "dependencies": {
-    "@angular/cdk": "^20.2.13",
-    "@angular/common": "~20.3.15",
-    "@angular/compiler": "~20.3.15",
-    "@angular/core": "~20.3.15",
-    "@angular/forms": "~20.3.15",
-    "@angular/localize": "~20.3.15",
-    "@angular/platform-browser": "~20.3.15",
-    "@angular/platform-browser-dynamic": "~20.3.15",
-    "@angular/router": "~20.3.15",
-    "@ng-bootstrap/ng-bootstrap": "^19.0.1",
-    "@ng-select/ng-select": "^20.7.0",
+    "@angular/cdk": "^21.0.6",
+    "@angular/common": "~21.0.8",
+    "@angular/compiler": "~21.0.8",
+    "@angular/core": "~21.0.8",
+    "@angular/forms": "~21.0.8",
+    "@angular/localize": "~21.0.8",
+    "@angular/platform-browser": "~21.0.8",
+    "@angular/platform-browser-dynamic": "~21.0.8",
+    "@angular/router": "~21.0.8",
+    "@ng-bootstrap/ng-bootstrap": "^20.0.0",
+    "@ng-select/ng-select": "^21.1.4",
     "@ngneat/dirty-check-forms": "^3.0.3",
     "@popperjs/core": "^2.11.8",
     "bootstrap": "^5.3.8",
@@ -30,8 +30,8 @@
     "ng2-pdf-viewer": "^10.4.0",
     "ngx-bootstrap-icons": "^1.9.3",
     "ngx-color": "^10.1.0",
-    "ngx-cookie-service": "^20.1.1",
-    "ngx-device-detector": "^10.1.0",
+    "ngx-cookie-service": "^21.1.0",
+    "ngx-device-detector": "^11.0.0",
     "ngx-ui-tour-ng-bootstrap": "^17.0.1",
     "rxjs": "^7.8.2",
     "tslib": "^2.8.1",
@@ -40,18 +40,18 @@
     "zone.js": "^0.15.1"
   },
   "devDependencies": {
-    "@angular-builders/custom-webpack": "^20.0.0",
-    "@angular-builders/jest": "^20.0.0",
-    "@angular-devkit/core": "^20.3.13",
-    "@angular-devkit/schematics": "^20.3.13",
-    "@angular-eslint/builder": "20.6.0",
-    "@angular-eslint/eslint-plugin": "20.6.0",
-    "@angular-eslint/eslint-plugin-template": "20.6.0",
-    "@angular-eslint/schematics": "20.6.0",
-    "@angular-eslint/template-parser": "20.6.0",
-    "@angular/build": "^20.3.13",
-    "@angular/cli": "~20.3.13",
-    "@angular/compiler-cli": "~20.3.15",
+    "@angular-builders/custom-webpack": "^21.0.0-beta.1",
+    "@angular-builders/jest": "^21.0.0-beta.1",
+    "@angular-devkit/core": "^21.0.5",
+    "@angular-devkit/schematics": "^21.0.5",
+    "@angular-eslint/builder": "21.1.0",
+    "@angular-eslint/eslint-plugin": "21.1.0",
+    "@angular-eslint/eslint-plugin-template": "21.1.0",
+    "@angular-eslint/schematics": "21.1.0",
+    "@angular-eslint/template-parser": "21.1.0",
+    "@angular/build": "^21.0.5",
+    "@angular/cli": "~21.0.5",
+    "@angular/compiler-cli": "~21.0.8",
     "@codecov/webpack-plugin": "^1.9.1",
     "@playwright/test": "^1.57.0",
     "@types/jest": "^30.0.0",
@@ -63,11 +63,11 @@
     "jest": "30.2.0",
     "jest-environment-jsdom": "^30.2.0",
     "jest-junit": "^16.0.0",
-    "jest-preset-angular": "^15.0.3",
+    "jest-preset-angular": "^16.0.0",
     "jest-websocket-mock": "^2.5.0",
     "prettier-plugin-organize-imports": "^4.3.0",
     "ts-node": "~10.9.1",
-    "typescript": "^5.8.3",
+    "typescript": "^5.9.3",
     "webpack": "^5.103.0"
   },
   "packageManager": "pnpm@10.17.1",

src-ui/src/app/components/file-drop/file-drop.component.ts

@@ -150,12 +150,11 @@ export class FileDropComponent {
     this.onDragLeave(event, true)
   }
 
-  @HostListener('window:blur', ['$event']) public onWindowBlur() {
+  @HostListener('window:blur') public onWindowBlur() {
     if (this.fileIsOver) this.onDragLeave(null)
   }
 
-  @HostListener('document:visibilitychange', ['$event'])
-  public onVisibilityChange() {
+  @HostListener('document:visibilitychange') public onVisibilityChange() {
     if (document.hidden && this.fileIsOver) this.onDragLeave(null)
   }
 }

src-ui/src/app/components/manage/correspondent-list/correspondent-list.component.ts

@@ -1,6 +1,7 @@
 import { NgClass, NgTemplateOutlet, TitleCasePipe } from '@angular/common'
 import { Component, inject } from '@angular/core'
 import { FormsModule, ReactiveFormsModule } from '@angular/forms'
+import { RouterModule } from '@angular/router'
 import {
   NgbDropdownModule,
   NgbPaginationModule,
@@ -29,6 +30,7 @@ import { ManagementListComponent } from '../management-list/management-list.comp
     TitleCasePipe,
     FormsModule,
     ReactiveFormsModule,
+    RouterModule,
     NgClass,
     NgTemplateOutlet,
     NgbDropdownModule,

src-ui/src/app/components/manage/custom-fields/custom-fields.component.html

@@ -42,7 +42,13 @@
                 <button (click)="editField(field)" *pngxIfPermissions="{ action: PermissionAction.Change, type: PermissionType.CustomField }" ngbDropdownItem i18n>Edit</button>
                 <button class="text-danger" (click)="deleteField(field)" *pngxIfPermissions="{ action: PermissionAction.Delete, type: PermissionType.CustomField }" ngbDropdownItem i18n>Delete</button>
                 @if (field.document_count > 0) {
-                  <button (click)="filterDocuments(field)" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Document }" ngbDropdownItem i18n>Filter Documents ({{ field.document_count }})</button>
+                  <a
+                    *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Document }"
+                    ngbDropdownItem
+                    [routerLink]="getDocumentFilterUrl(field)"
+                    i18n
+                    >Filter Documents ({{ field.document_count }})</a
+                  >
                 }
               </div>
             </div>
@@ -57,9 +63,13 @@
           </div>
           @if (field.document_count > 0) {
             <div class="btn-group d-none d-sm-inline-block ms-2">
-              <button class="btn btn-sm btn-outline-secondary" type="button" (click)="filterDocuments(field)">
-                <i-bs width="1em" height="1em" name="filter"></i-bs>&nbsp;<ng-container i18n>Documents</ng-container><span class="badge bg-light text-secondary ms-2">{{ field.document_count }}</span>
-              </button>
+              <a
+                class="btn btn-sm btn-outline-secondary"
+                [routerLink]="getDocumentFilterUrl(field)"
+              >
+                <i-bs width="1em" height="1em" name="filter"></i-bs>&nbsp;<ng-container i18n>Documents</ng-container
+                ><span class="badge bg-light text-secondary ms-2">{{ field.document_count }}</span>
+              </a>
             </div>
           }
         </div>

src-ui/src/app/components/manage/custom-fields/custom-fields.component.spec.ts

@@ -4,6 +4,7 @@ import { provideHttpClient, withInterceptorsFromDi } from '@angular/common/http'
 import { provideHttpClientTesting } from '@angular/common/http/testing'
 import { FormsModule, ReactiveFormsModule } from '@angular/forms'
 import { By } from '@angular/platform-browser'
+import { RouterTestingModule } from '@angular/router/testing'
 import {
   NgbModal,
   NgbModalModule,
@@ -61,6 +62,7 @@ describe('CustomFieldsComponent', () => {
         NgbModalModule,
         NgbPopoverModule,
         NgxBootstrapIconsModule.pick(allIcons),
+        RouterTestingModule,
         CustomFieldsComponent,
         IfPermissionsDirective,
         PageHeaderComponent,
@@ -108,7 +110,9 @@ describe('CustomFieldsComponent', () => {
     const toastInfoSpy = jest.spyOn(toastService, 'showInfo')
     const reloadSpy = jest.spyOn(component, 'reload')
 
-    const createButton = fixture.debugElement.queryAll(By.css('button'))[1]
+    const createButton = fixture.debugElement
+      .queryAll(By.css('button'))
+      .find((btn) => btn.nativeElement.textContent.trim().includes('Add Field'))
     createButton.triggerEventHandler('click')
 
     expect(modal).not.toBeUndefined()
@@ -133,7 +137,11 @@ describe('CustomFieldsComponent', () => {
     const toastInfoSpy = jest.spyOn(toastService, 'showInfo')
     const reloadSpy = jest.spyOn(component, 'reload')
 
-    const editButton = fixture.debugElement.queryAll(By.css('button'))[2]
+    const editButton = fixture.debugElement
+      .queryAll(By.css('button'))
+      .find((btn) =>
+        btn.nativeElement.textContent.trim().includes(fields[0].name)
+      )
     editButton.triggerEventHandler('click')
 
     expect(modal).not.toBeUndefined()
@@ -158,7 +166,9 @@ describe('CustomFieldsComponent', () => {
     const deleteSpy = jest.spyOn(customFieldsService, 'delete')
     const reloadSpy = jest.spyOn(component, 'reload')
 
-    const deleteButton = fixture.debugElement.queryAll(By.css('button'))[5]
+    const deleteButton = fixture.debugElement
+      .queryAll(By.css('button'))
+      .find((btn) => btn.nativeElement.textContent.trim().includes('Delete'))
     deleteButton.triggerEventHandler('click')
 
     expect(modal).not.toBeUndefined()
@@ -176,10 +186,10 @@ describe('CustomFieldsComponent', () => {
     expect(reloadSpy).toHaveBeenCalled()
   })
 
-  it('should support filter documents', () => {
-    const filterSpy = jest.spyOn(listViewService, 'quickFilter')
-    component.filterDocuments(fields[0])
-    expect(filterSpy).toHaveBeenCalledWith([
+  it('should provide document filter url', () => {
+    const urlSpy = jest.spyOn(listViewService, 'getQuickFilterUrl')
+    component.getDocumentFilterUrl(fields[0])
+    expect(urlSpy).toHaveBeenCalledWith([
       {
         rule_type: FILTER_CUSTOM_FIELDS_QUERY,
         value: JSON.stringify([

src-ui/src/app/components/manage/custom-fields/custom-fields.component.ts

@@ -1,4 +1,5 @@
 import { Component, OnInit, inject } from '@angular/core'
+import { RouterModule } from '@angular/router'
 import {
   NgbDropdownModule,
   NgbModal,
@@ -36,6 +37,7 @@ import { LoadingComponentWithPermissions } from '../../loading-component/loading
     NgbDropdownModule,
     NgbPaginationModule,
     NgxBootstrapIconsModule,
+    RouterModule,
   ],
 })
 export class CustomFieldsComponent
@@ -130,8 +132,8 @@ export class CustomFieldsComponent
     return DATA_TYPE_LABELS.find((l) => l.id === field.data_type).name
   }
 
-  filterDocuments(field: CustomField) {
-    this.documentListViewService.quickFilter([
+  getDocumentFilterUrl(field: CustomField) {
+    return this.documentListViewService.getQuickFilterUrl([
       {
         rule_type: FILTER_CUSTOM_FIELDS_QUERY,
         value: JSON.stringify([

src-ui/src/app/components/manage/document-type-list/document-type-list.component.ts

@@ -1,6 +1,7 @@
 import { NgClass, NgTemplateOutlet, TitleCasePipe } from '@angular/common'
 import { Component, inject } from '@angular/core'
 import { FormsModule, ReactiveFormsModule } from '@angular/forms'
+import { RouterModule } from '@angular/router'
 import {
   NgbDropdownModule,
   NgbPaginationModule,
@@ -27,6 +28,7 @@ import { ManagementListComponent } from '../management-list/management-list.comp
     IfPermissionsDirective,
     FormsModule,
     ReactiveFormsModule,
+    RouterModule,
     NgClass,
     NgTemplateOutlet,
     NgbDropdownModule,

src-ui/src/app/components/manage/management-list/management-list.component.html

@@ -120,7 +120,14 @@
               <button (click)="openEditDialog(object)" *pngxIfPermissions="{ action: PermissionAction.Change, type: permissionType }" ngbDropdownItem i18n>Edit</button>
               <button class="text-danger" (click)="openDeleteDialog(object)" *pngxIfPermissions="{ action: PermissionAction.Delete, type: permissionType }" ngbDropdownItem i18n>Delete</button>
               @if (getDocumentCount(object) > 0) {
-                <button (click)="filterDocuments(object)" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Document }" ngbDropdownItem i18n>Filter Documents ({{ getDocumentCount(object) }})</button>
+                  <a
+                    *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Document }"
+                    ngbDropdownItem
+                    [routerLink]="getDocumentFilterUrl(object)"
+                    (click)="$event?.stopPropagation()"
+                    i18n
+                    >Filter Documents ({{ getDocumentCount(object) }})</a
+                  >
               }
             </div>
           </div>
@@ -135,9 +142,15 @@
         </div>
         @if (getDocumentCount(object) > 0) {
           <div class="btn-group d-none d-sm-inline-block">
-            <button class="btn btn-sm btn-outline-secondary" (click)="filterDocuments(object); $event.stopPropagation();" *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Document }">
-              <i-bs width="1em" height="1em" name="filter"></i-bs>&nbsp;<ng-container i18n>Documents</ng-container><span class="badge bg-light text-secondary ms-2">{{ getDocumentCount(object) }}</span>
-            </button>
+            <a
+              class="btn btn-sm btn-outline-secondary"
+              *pngxIfPermissions="{ action: PermissionAction.View, type: PermissionType.Document }"
+              [routerLink]="getDocumentFilterUrl(object)"
+              (click)="$event?.stopPropagation()"
+            >
+              <i-bs width="1em" height="1em" name="filter"></i-bs>&nbsp;<ng-container i18n>Documents</ng-container
+              ><span class="badge bg-light text-secondary ms-2">{{ getDocumentCount(object) }}</span>
+            </a>
           </div>
         }
       </div>

src-ui/src/app/components/manage/management-list/management-list.component.spec.ts

@@ -13,6 +13,7 @@ import {
 } from '@angular/core/testing'
 import { FormsModule, ReactiveFormsModule } from '@angular/forms'
 import { By } from '@angular/platform-browser'
+import { RouterLinkWithHref } from '@angular/router'
 import { RouterTestingModule } from '@angular/router/testing'
 import {
   NgbModal,
@@ -230,12 +231,15 @@ describe('ManagementListComponent', () => {
   })
 
   it('should support quick filter for objects', () => {
-    const qfSpy = jest.spyOn(documentListViewService, 'quickFilter')
-    const filterButton = fixture.debugElement.queryAll(By.css('button'))[9]
-    filterButton.triggerEventHandler('click')
-    expect(qfSpy).toHaveBeenCalledWith([
+    const expectedUrl = documentListViewService.getQuickFilterUrl([
       { rule_type: FILTER_HAS_TAGS_ALL, value: tags[0].id.toString() },
-    ]) // subclasses set the filter rule type
+    ])
+    const filterLink = fixture.debugElement.query(
+      By.css('a.btn-outline-secondary')
+    )
+    expect(filterLink).toBeTruthy()
+    const routerLink = filterLink.injector.get(RouterLinkWithHref)
+    expect(routerLink.urlTree).toEqual(expectedUrl)
   })
 
   it('should reload on sort', () => {

src-ui/src/app/components/manage/management-list/management-list.component.ts

@@ -230,8 +230,8 @@ export abstract class ManagementListComponent<T extends MatchingModel>
 
   abstract getDeleteMessage(object: T)
 
-  filterDocuments(object: MatchingModel) {
-    this.documentListViewService.quickFilter([
+  getDocumentFilterUrl(object: MatchingModel) {
+    return this.documentListViewService.getQuickFilterUrl([
       { rule_type: this.filterRuleType, value: object.id.toString() },
     ])
   }

src-ui/src/app/components/manage/storage-path-list/storage-path-list.component.ts

@@ -1,6 +1,7 @@
 import { NgClass, NgTemplateOutlet, TitleCasePipe } from '@angular/common'
 import { Component, inject } from '@angular/core'
 import { FormsModule, ReactiveFormsModule } from '@angular/forms'
+import { RouterModule } from '@angular/router'
 import {
   NgbDropdownModule,
   NgbPaginationModule,
@@ -27,6 +28,7 @@ import { ManagementListComponent } from '../management-list/management-list.comp
     IfPermissionsDirective,
     FormsModule,
     ReactiveFormsModule,
+    RouterModule,
     NgClass,
     NgTemplateOutlet,
     NgbDropdownModule,

src-ui/src/app/components/manage/tag-list/tag-list.component.ts

@@ -1,6 +1,7 @@
 import { NgClass, NgTemplateOutlet, TitleCasePipe } from '@angular/common'
 import { Component, inject } from '@angular/core'
 import { FormsModule, ReactiveFormsModule } from '@angular/forms'
+import { RouterModule } from '@angular/router'
 import {
   NgbDropdownModule,
   NgbPaginationModule,
@@ -27,6 +28,7 @@ import { ManagementListComponent } from '../management-list/management-list.comp
     IfPermissionsDirective,
     FormsModule,
     ReactiveFormsModule,
+    RouterModule,
     NgClass,
     NgTemplateOutlet,
     NgbDropdownModule,

src-ui/src/app/services/document-list-view.service.spec.ts

@@ -651,4 +651,25 @@ describe('DocumentListViewService', () => {
     documentListViewService.displayFields = customFields as any
     expect(documentListViewService.displayFields).toEqual(['custom_field_1'])
   })
+
+  it('should generate quick filter URL with filter rules', () => {
+    const routerSpy = jest.spyOn(router, 'createUrlTree')
+    const urlTree = documentListViewService.getQuickFilterUrl(filterRules)
+    expect(routerSpy).toHaveBeenCalledWith(['/documents'], {
+      queryParams: expect.objectContaining({
+        tags__id__all: tags__id__all,
+      }),
+    })
+    expect(urlTree).toBeDefined()
+  })
+
+  it('should generate quick filter URL preserving default state', () => {
+    documentListViewService.reload()
+    httpTestingController.expectOne(
+      `${environment.apiBaseUrl}documents/?page=1&page_size=50&ordering=-created&truncate_content=true`
+    )
+    const urlTree = documentListViewService.getQuickFilterUrl(filterRules)
+    expect(urlTree).toBeDefined()
+    expect(router.createUrlTree).toBeDefined()
+  })
 })

src-ui/src/app/services/document-list-view.service.ts

@@ -1,5 +1,5 @@
 import { Injectable, inject } from '@angular/core'
-import { ParamMap, Router } from '@angular/router'
+import { ParamMap, Router, UrlTree } from '@angular/router'
 import { Observable, Subject, first, takeUntil } from 'rxjs'
 import {
   DEFAULT_DISPLAY_FIELDS,
@@ -483,6 +483,18 @@ export class DocumentListViewService {
     this.router.navigate(['documents'])
   }
 
+  getQuickFilterUrl(filterRules: FilterRule[]): UrlTree {
+    const defaultState = {
+      ...this.defaultListViewState(),
+      ...this.listViewStates.get(null),
+      filterRules,
+    }
+    const params = paramsFromViewState(defaultState)
+    return this.router.createUrlTree(['/documents'], {
+      queryParams: params,
+    })
+  }
+
   getLastPage(): number {
     return Math.ceil(this.collectionSize / this.pageSize)
   }

src-ui/src/main.ts

@@ -2,6 +2,7 @@ import {
   APP_INITIALIZER,
   enableProdMode,
   importProvidersFrom,
+  provideZoneChangeDetection,
 } from '@angular/core'
 
 import { DragDropModule } from '@angular/cdk/drag-drop'
@@ -363,6 +364,7 @@ if (environment.production) {
 
 bootstrapApplication(AppComponent, {
   providers: [
+    provideZoneChangeDetection(),
     importProvidersFrom(
       BrowserModule,
       AppRoutingModule,

src-ui/tsconfig.spec.json

@@ -6,9 +6,11 @@
       "jest",
       "node",
     ],
-    "module": "commonjs",
-    "emitDecoratorMetadata": true,
-    "allowJs": true
+    "module": "NodeNext",
+    "moduleResolution": "NodeNext",
+    "emitDecoratorMetadata": false,
+    "allowJs": true,
+    "isolatedModules": true
   },
   "files": [
     "src/polyfills.ts"

src/documents/index.py

@@ -10,6 +10,7 @@ from datetime import time
 from datetime import timedelta
 from datetime import timezone
 from shutil import rmtree
+from time import sleep
 from typing import TYPE_CHECKING
 from typing import Literal
 
@@ -32,6 +33,7 @@ from whoosh.highlight import HtmlFormatter
 from whoosh.idsets import BitSet
 from whoosh.idsets import DocIdSet
 from whoosh.index import FileIndex
+from whoosh.index import LockError
 from whoosh.index import create_in
 from whoosh.index import exists_in
 from whoosh.index import open_dir
@@ -97,11 +99,33 @@ def get_schema() -> Schema:
 
 
 def open_index(*, recreate=False) -> FileIndex:
-    try:
-        if exists_in(settings.INDEX_DIR) and not recreate:
-            return open_dir(settings.INDEX_DIR, schema=get_schema())
-    except Exception:
-        logger.exception("Error while opening the index, recreating.")
+    transient_exceptions = (FileNotFoundError, LockError)
+    max_retries = 3
+    retry_delay = 0.1
+
+    for attempt in range(max_retries + 1):
+        try:
+            if exists_in(settings.INDEX_DIR) and not recreate:
+                return open_dir(settings.INDEX_DIR, schema=get_schema())
+            break
+        except transient_exceptions as exc:
+            is_last_attempt = attempt == max_retries or recreate
+            if is_last_attempt:
+                logger.exception(
+                    "Error while opening the index after retries, recreating.",
+                )
+                break
+
+            logger.warning(
+                "Transient error while opening the index (attempt %s/%s): %s. Retrying.",
+                attempt + 1,
+                max_retries + 1,
+                exc,
+            )
+            sleep(retry_delay)
+        except Exception:
+            logger.exception("Error while opening the index, recreating.")
+            break
 
     # create_in doesn't handle corrupted indexes very well, remove the directory entirely first
     if settings.INDEX_DIR.is_dir():

src/documents/serialisers.py

@@ -18,6 +18,8 @@ from django.core.exceptions import ValidationError
 from django.core.validators import DecimalValidator
 from django.core.validators import EmailValidator
 from django.core.validators import MaxLengthValidator
+from django.core.validators import MaxValueValidator
+from django.core.validators import MinValueValidator
 from django.core.validators import RegexValidator
 from django.core.validators import integer_validator
 from django.db.models import Count
@@ -875,6 +877,13 @@ class CustomFieldInstanceSerializer(serializers.ModelSerializer):
                 uri_validator(data["value"])
             elif field.data_type == CustomField.FieldDataType.INT:
                 integer_validator(data["value"])
+                try:
+                    value_int = int(data["value"])
+                except (TypeError, ValueError):
+                    raise serializers.ValidationError("Enter a valid integer.")
+                # Keep values within the PostgreSQL integer range
+                MinValueValidator(-2147483648)(value_int)
+                MaxValueValidator(2147483647)(value_int)
             elif (
                 field.data_type == CustomField.FieldDataType.MONETARY
                 and data["value"] != ""

src/documents/tasks.py

@@ -493,7 +493,7 @@ def check_scheduled_workflows():
                             trigger.schedule_is_recurring
                             and workflow_runs.exists()
                             and (
-                                workflow_runs.last().run_at
+                                workflow_runs.first().run_at
                                 > now
                                 - datetime.timedelta(
                                     days=trigger.schedule_recurring_interval_days,

src/documents/tests/test_api_documents.py

@@ -1664,6 +1664,44 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
 
         self.consume_file_mock.assert_not_called()
 
+    def test_patch_document_integer_custom_field_out_of_range(self):
+        """
+        GIVEN:
+            - An integer custom field
+            - A document
+        WHEN:
+            - Patching the document with an integer value exceeding PostgreSQL's range
+        THEN:
+            - HTTP 400 is returned (validation catches the overflow)
+            - No custom field instance is created
+        """
+        cf_int = CustomField.objects.create(
+            name="intfield",
+            data_type=CustomField.FieldDataType.INT,
+        )
+        doc = Document.objects.create(
+            title="Doc",
+            checksum="123",
+            mime_type="application/pdf",
+        )
+
+        response = self.client.patch(
+            f"/api/documents/{doc.pk}/",
+            {
+                "custom_fields": [
+                    {
+                        "field": cf_int.pk,
+                        "value": 2**31,  # overflow for PostgreSQL integer fields
+                    },
+                ],
+            },
+            format="json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn("custom_fields", response.data)
+        self.assertEqual(CustomFieldInstance.objects.count(), 0)
+
     def test_upload_with_webui_source(self):
         """
         GIVEN: A document with a source file

src/documents/tests/test_index.py

@@ -1,6 +1,7 @@
 from datetime import datetime
 from unittest import mock
 
+from django.conf import settings
 from django.contrib.auth.models import User
 from django.test import SimpleTestCase
 from django.test import TestCase
@@ -251,3 +252,120 @@ class TestRewriteNaturalDateKeywords(SimpleTestCase):
         result = self._rewrite_with_now("added:today", fixed_now)
         # Should convert to UTC properly
         self.assertIn("added:[20250719", result)
+
+
+class TestIndexResilience(DirectoriesMixin, SimpleTestCase):
+    def _assert_recreate_called(self, mock_create_in):
+        mock_create_in.assert_called_once()
+        path_arg, schema_arg = mock_create_in.call_args.args
+        self.assertEqual(path_arg, settings.INDEX_DIR)
+        self.assertEqual(schema_arg.__class__.__name__, "Schema")
+
+    def test_transient_missing_segment_does_not_force_recreate(self):
+        """
+        GIVEN:
+            - Index directory exists
+        WHEN:
+            - open_index is called
+            - Opening the index raises FileNotFoundError once due to a
+              transient missing segment
+        THEN:
+            - Index is opened successfully on retry
+            - Index is not recreated
+        """
+        file_marker = settings.INDEX_DIR / "file_marker.txt"
+        file_marker.write_text("keep")
+        expected_index = object()
+
+        with (
+            mock.patch("documents.index.exists_in", return_value=True),
+            mock.patch(
+                "documents.index.open_dir",
+                side_effect=[FileNotFoundError("missing"), expected_index],
+            ) as mock_open_dir,
+            mock.patch(
+                "documents.index.create_in",
+            ) as mock_create_in,
+            mock.patch(
+                "documents.index.rmtree",
+            ) as mock_rmtree,
+        ):
+            ix = index.open_index()
+
+        self.assertIs(ix, expected_index)
+        self.assertGreaterEqual(mock_open_dir.call_count, 2)
+        mock_rmtree.assert_not_called()
+        mock_create_in.assert_not_called()
+        self.assertEqual(file_marker.read_text(), "keep")
+
+    def test_transient_errors_exhaust_retries_and_recreate(self):
+        """
+        GIVEN:
+            - Index directory exists
+        WHEN:
+            - open_index is called
+            - Opening the index raises FileNotFoundError multiple times due to
+              transient missing segments
+        THEN:
+            - Index is recreated after retries are exhausted
+        """
+        recreated_index = object()
+
+        with (
+            self.assertLogs("paperless.index", level="ERROR") as cm,
+            mock.patch("documents.index.exists_in", return_value=True),
+            mock.patch(
+                "documents.index.open_dir",
+                side_effect=FileNotFoundError("missing"),
+            ) as mock_open_dir,
+            mock.patch("documents.index.rmtree") as mock_rmtree,
+            mock.patch(
+                "documents.index.create_in",
+                return_value=recreated_index,
+            ) as mock_create_in,
+        ):
+            ix = index.open_index()
+
+        self.assertIs(ix, recreated_index)
+        self.assertEqual(mock_open_dir.call_count, 4)
+        mock_rmtree.assert_called_once_with(settings.INDEX_DIR)
+        self._assert_recreate_called(mock_create_in)
+        self.assertIn(
+            "Error while opening the index after retries, recreating.",
+            cm.output[0],
+        )
+
+    def test_non_transient_error_recreates_index(self):
+        """
+        GIVEN:
+            - Index directory exists
+        WHEN:
+            - open_index is called
+            - Opening the index raises a "non-transient" error
+        THEN:
+            - Index is recreated
+        """
+        recreated_index = object()
+
+        with (
+            self.assertLogs("paperless.index", level="ERROR") as cm,
+            mock.patch("documents.index.exists_in", return_value=True),
+            mock.patch(
+                "documents.index.open_dir",
+                side_effect=RuntimeError("boom"),
+            ),
+            mock.patch("documents.index.rmtree") as mock_rmtree,
+            mock.patch(
+                "documents.index.create_in",
+                return_value=recreated_index,
+            ) as mock_create_in,
+        ):
+            ix = index.open_index()
+
+        self.assertIs(ix, recreated_index)
+        mock_rmtree.assert_called_once_with(settings.INDEX_DIR)
+        self._assert_recreate_called(mock_create_in)
+        self.assertIn(
+            "Error while opening the index, recreating.",
+            cm.output[0],
+        )

src/documents/tests/test_workflows.py

@@ -2096,6 +2096,68 @@ class TestWorkflows(
             doc.refresh_from_db()
             self.assertIsNone(doc.owner)
 
+    def test_workflow_scheduled_recurring_respects_latest_run(self):
+        """
+        GIVEN:
+            - Scheduled workflow marked as recurring with a 1-day interval
+            - Document that matches the trigger
+            - Two prior runs exist: one 2 days ago and one 1 hour ago
+        WHEN:
+            - Scheduled workflows are checked again
+        THEN:
+            - Workflow does not run because the most recent run is inside the interval
+        """
+        trigger = WorkflowTrigger.objects.create(
+            type=WorkflowTrigger.WorkflowTriggerType.SCHEDULED,
+            schedule_date_field=WorkflowTrigger.ScheduleDateField.CREATED,
+            schedule_is_recurring=True,
+            schedule_recurring_interval_days=1,
+        )
+        action = WorkflowAction.objects.create(
+            assign_title="Doc assign owner",
+            assign_owner=self.user2,
+        )
+        w = Workflow.objects.create(
+            name="Workflow 1",
+            order=0,
+        )
+        w.triggers.add(trigger)
+        w.actions.add(action)
+        w.save()
+
+        doc = Document.objects.create(
+            title="sample test",
+            correspondent=self.c,
+            original_filename="sample.pdf",
+            created=timezone.now().date() - timedelta(days=3),
+        )
+
+        WorkflowRun.objects.create(
+            workflow=w,
+            document=doc,
+            type=WorkflowTrigger.WorkflowTriggerType.SCHEDULED,
+            run_at=timezone.now() - timedelta(days=2),
+        )
+        WorkflowRun.objects.create(
+            workflow=w,
+            document=doc,
+            type=WorkflowTrigger.WorkflowTriggerType.SCHEDULED,
+            run_at=timezone.now() - timedelta(hours=1),
+        )
+
+        tasks.check_scheduled_workflows()
+
+        doc.refresh_from_db()
+        self.assertIsNone(doc.owner)
+        self.assertEqual(
+            WorkflowRun.objects.filter(
+                workflow=w,
+                document=doc,
+                type=WorkflowTrigger.WorkflowTriggerType.SCHEDULED,
+            ).count(),
+            2,
+        )
+
     def test_workflow_scheduled_trigger_negative_offset_customfield(self):
         """
         GIVEN:

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: 2025-12-24 05:27+0000\n"
+"POT-Creation-Date: 2026-01-08 21:50+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1219,35 +1219,35 @@ msgstr ""
 msgid "workflow runs"
 msgstr ""
 
-#: documents/serialisers.py:640
+#: documents/serialisers.py:642
 msgid "Invalid color."
 msgstr ""
 
-#: documents/serialisers.py:1826
+#: documents/serialisers.py:1846
 #, python-format
 msgid "File type %(type)s not supported"
 msgstr ""
 
-#: documents/serialisers.py:1870
+#: documents/serialisers.py:1890
 #, python-format
 msgid "Custom field id must be an integer: %(id)s"
 msgstr ""
 
-#: documents/serialisers.py:1877
+#: documents/serialisers.py:1897
 #, python-format
 msgid "Custom field with id %(id)s does not exist"
 msgstr ""
 
-#: documents/serialisers.py:1894 documents/serialisers.py:1904
+#: documents/serialisers.py:1914 documents/serialisers.py:1924
 msgid ""
 "Custom fields must be a list of integers or an object mapping ids to values."
 msgstr ""
 
-#: documents/serialisers.py:1899
+#: documents/serialisers.py:1919
 msgid "Some custom fields don't exist or were specified twice."
 msgstr ""
 
-#: documents/serialisers.py:2014
+#: documents/serialisers.py:2034
 msgid "Invalid variable detected."
 msgstr ""
 
@@ -1702,151 +1702,151 @@ msgstr ""
 msgid "paperless application settings"
 msgstr ""
 
-#: paperless/settings.py:773
+#: paperless/settings.py:768
 msgid "English (US)"
 msgstr ""
 
-#: paperless/settings.py:774
+#: paperless/settings.py:769
 msgid "Arabic"
 msgstr ""
 
-#: paperless/settings.py:775
+#: paperless/settings.py:770
 msgid "Afrikaans"
 msgstr ""
 
-#: paperless/settings.py:776
+#: paperless/settings.py:771
 msgid "Belarusian"
 msgstr ""
 
-#: paperless/settings.py:777
+#: paperless/settings.py:772
 msgid "Bulgarian"
 msgstr ""
 
-#: paperless/settings.py:778
+#: paperless/settings.py:773
 msgid "Catalan"
 msgstr ""
 
-#: paperless/settings.py:779
+#: paperless/settings.py:774
 msgid "Czech"
 msgstr ""
 
-#: paperless/settings.py:780
+#: paperless/settings.py:775
 msgid "Danish"
 msgstr ""
 
-#: paperless/settings.py:781
+#: paperless/settings.py:776
 msgid "German"
 msgstr ""
 
-#: paperless/settings.py:782
+#: paperless/settings.py:777
 msgid "Greek"
 msgstr ""
 
-#: paperless/settings.py:783
+#: paperless/settings.py:778
 msgid "English (GB)"
 msgstr ""
 
-#: paperless/settings.py:784
+#: paperless/settings.py:779
 msgid "Spanish"
 msgstr ""
 
-#: paperless/settings.py:785
+#: paperless/settings.py:780
 msgid "Persian"
 msgstr ""
 
-#: paperless/settings.py:786
+#: paperless/settings.py:781
 msgid "Finnish"
 msgstr ""
 
-#: paperless/settings.py:787
+#: paperless/settings.py:782
 msgid "French"
 msgstr ""
 
-#: paperless/settings.py:788
+#: paperless/settings.py:783
 msgid "Hungarian"
 msgstr ""
 
-#: paperless/settings.py:789
+#: paperless/settings.py:784
 msgid "Indonesian"
 msgstr ""
 
-#: paperless/settings.py:790
+#: paperless/settings.py:785
 msgid "Italian"
 msgstr ""
 
-#: paperless/settings.py:791
+#: paperless/settings.py:786
 msgid "Japanese"
 msgstr ""
 
-#: paperless/settings.py:792
+#: paperless/settings.py:787
 msgid "Korean"
 msgstr ""
 
-#: paperless/settings.py:793
+#: paperless/settings.py:788
 msgid "Luxembourgish"
 msgstr ""
 
-#: paperless/settings.py:794
+#: paperless/settings.py:789
 msgid "Norwegian"
 msgstr ""
 
-#: paperless/settings.py:795
+#: paperless/settings.py:790
 msgid "Dutch"
 msgstr ""
 
-#: paperless/settings.py:796
+#: paperless/settings.py:791
 msgid "Polish"
 msgstr ""
 
-#: paperless/settings.py:797
+#: paperless/settings.py:792
 msgid "Portuguese (Brazil)"
 msgstr ""
 
-#: paperless/settings.py:798
+#: paperless/settings.py:793
 msgid "Portuguese"
 msgstr ""
 
-#: paperless/settings.py:799
+#: paperless/settings.py:794
 msgid "Romanian"
 msgstr ""
 
-#: paperless/settings.py:800
+#: paperless/settings.py:795
 msgid "Russian"
 msgstr ""
 
-#: paperless/settings.py:801
+#: paperless/settings.py:796
 msgid "Slovak"
 msgstr ""
 
-#: paperless/settings.py:802
+#: paperless/settings.py:797
 msgid "Slovenian"
 msgstr ""
 
-#: paperless/settings.py:803
+#: paperless/settings.py:798
 msgid "Serbian"
 msgstr ""
 
-#: paperless/settings.py:804
+#: paperless/settings.py:799
 msgid "Swedish"
 msgstr ""
 
-#: paperless/settings.py:805
+#: paperless/settings.py:800
 msgid "Turkish"
 msgstr ""
 
-#: paperless/settings.py:806
+#: paperless/settings.py:801
 msgid "Ukrainian"
 msgstr ""
 
-#: paperless/settings.py:807
+#: paperless/settings.py:802
 msgid "Vietnamese"
 msgstr ""
 
-#: paperless/settings.py:808
+#: paperless/settings.py:803
 msgid "Chinese Simplified"
 msgstr ""
 
-#: paperless/settings.py:809
+#: paperless/settings.py:804
 msgid "Chinese Traditional"
 msgstr ""
 

src/paperless/settings.py

@@ -8,7 +8,6 @@ import os
 import tempfile
 from os import PathLike
 from pathlib import Path
-from platform import machine
 from typing import Final
 from urllib.parse import urlparse
 
@@ -322,6 +321,7 @@ INSTALLED_APPS = [
     "paperless_tesseract.apps.PaperlessTesseractConfig",
     "paperless_text.apps.PaperlessTextConfig",
     "paperless_mail.apps.PaperlessMailConfig",
+    "paperless_remote.apps.PaperlessRemoteParserConfig",
     "django.contrib.admin",
     "rest_framework",
     "rest_framework.authtoken",
@@ -423,14 +423,9 @@ ASGI_APPLICATION = "paperless.asgi.application"
 STATIC_URL = os.getenv("PAPERLESS_STATIC_URL", BASE_URL + "static/")
 WHITENOISE_STATIC_PREFIX = "/static/"
 
-if machine().lower() == "aarch64":  # pragma: no cover
-    _static_backend = "django.contrib.staticfiles.storage.StaticFilesStorage"
-else:
-    _static_backend = "whitenoise.storage.CompressedStaticFilesStorage"
-
 STORAGES = {
     "staticfiles": {
-        "BACKEND": _static_backend,
+        "BACKEND": "whitenoise.storage.CompressedStaticFilesStorage",
     },
     "default": {"BACKEND": "django.core.files.storage.FileSystemStorage"},
 }
@@ -1402,3 +1397,10 @@ WEBHOOKS_ALLOW_INTERNAL_REQUESTS = __get_boolean(
     "PAPERLESS_WEBHOOKS_ALLOW_INTERNAL_REQUESTS",
     "true",
 )
+
+###############################################################################
+# Remote Parser                                                               #
+###############################################################################
+REMOTE_OCR_ENGINE = os.getenv("PAPERLESS_REMOTE_OCR_ENGINE")
+REMOTE_OCR_API_KEY = os.getenv("PAPERLESS_REMOTE_OCR_API_KEY")
+REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT")

src/paperless_remote/__init__.py

@@ -0,0 +1,4 @@
+# this is here so that django finds the checks.
+from paperless_remote.checks import check_remote_parser_configured
+
+__all__ = ["check_remote_parser_configured"]

src/paperless_remote/apps.py

@@ -0,0 +1,14 @@
+from django.apps import AppConfig
+
+from paperless_remote.signals import remote_consumer_declaration
+
+
+class PaperlessRemoteParserConfig(AppConfig):
+    name = "paperless_remote"
+
+    def ready(self):
+        from documents.signals import document_consumer_declaration
+
+        document_consumer_declaration.connect(remote_consumer_declaration)
+
+        AppConfig.ready(self)

src/paperless_remote/checks.py

@@ -0,0 +1,17 @@
+from django.conf import settings
+from django.core.checks import Error
+from django.core.checks import register
+
+
+@register()
+def check_remote_parser_configured(app_configs, **kwargs):
+    if settings.REMOTE_OCR_ENGINE == "azureai" and not (
+        settings.REMOTE_OCR_ENDPOINT and settings.REMOTE_OCR_API_KEY
+    ):
+        return [
+            Error(
+                "Azure AI remote parser requires endpoint and API key to be configured.",
+            ),
+        ]
+
+    return []

src/paperless_remote/parsers.py

@@ -0,0 +1,118 @@
+from pathlib import Path
+
+from django.conf import settings
+
+from paperless_tesseract.parsers import RasterisedDocumentParser
+
+
+class RemoteEngineConfig:
+    def __init__(
+        self,
+        engine: str,
+        api_key: str | None = None,
+        endpoint: str | None = None,
+    ):
+        self.engine = engine
+        self.api_key = api_key
+        self.endpoint = endpoint
+
+    def engine_is_valid(self):
+        valid = self.engine in ["azureai"] and self.api_key is not None
+        if self.engine == "azureai":
+            valid = valid and self.endpoint is not None
+        return valid
+
+
+class RemoteDocumentParser(RasterisedDocumentParser):
+    """
+    This parser uses a remote OCR engine to parse documents. Currently, it supports Azure AI Vision
+    as this is the only service that provides a remote OCR API with text-embedded PDF output.
+    """
+
+    logging_name = "paperless.parsing.remote"
+
+    def get_settings(self) -> RemoteEngineConfig:
+        """
+        Returns the configuration for the remote OCR engine, loaded from Django settings.
+        """
+        return RemoteEngineConfig(
+            engine=settings.REMOTE_OCR_ENGINE,
+            api_key=settings.REMOTE_OCR_API_KEY,
+            endpoint=settings.REMOTE_OCR_ENDPOINT,
+        )
+
+    def supported_mime_types(self):
+        if self.settings.engine_is_valid():
+            return {
+                "application/pdf": ".pdf",
+                "image/png": ".png",
+                "image/jpeg": ".jpg",
+                "image/tiff": ".tiff",
+                "image/bmp": ".bmp",
+                "image/gif": ".gif",
+                "image/webp": ".webp",
+            }
+        else:
+            return {}
+
+    def azure_ai_vision_parse(
+        self,
+        file: Path,
+    ) -> str | None:
+        """
+        Uses Azure AI Vision to parse the document and return the text content.
+        It requests a searchable PDF output with embedded text.
+        The PDF is saved to the archive_path attribute.
+        Returns the text content extracted from the document.
+        If the parsing fails, it returns None.
+        """
+        from azure.ai.documentintelligence import DocumentIntelligenceClient
+        from azure.ai.documentintelligence.models import AnalyzeDocumentRequest
+        from azure.ai.documentintelligence.models import AnalyzeOutputOption
+        from azure.ai.documentintelligence.models import DocumentContentFormat
+        from azure.core.credentials import AzureKeyCredential
+
+        client = DocumentIntelligenceClient(
+            endpoint=self.settings.endpoint,
+            credential=AzureKeyCredential(self.settings.api_key),
+        )
+
+        try:
+            with file.open("rb") as f:
+                analyze_request = AnalyzeDocumentRequest(bytes_source=f.read())
+                poller = client.begin_analyze_document(
+                    model_id="prebuilt-read",
+                    body=analyze_request,
+                    output_content_format=DocumentContentFormat.TEXT,
+                    output=[AnalyzeOutputOption.PDF],  # request searchable PDF output
+                    content_type="application/json",
+                )
+
+            poller.wait()
+            result_id = poller.details["operation_id"]
+            result = poller.result()
+
+            # Download the PDF with embedded text
+            self.archive_path = self.tempdir / "archive.pdf"
+            with self.archive_path.open("wb") as f:
+                for chunk in client.get_analyze_result_pdf(
+                    model_id="prebuilt-read",
+                    result_id=result_id,
+                ):
+                    f.write(chunk)
+            return result.content
+        except Exception as e:
+            self.log.error(f"Azure AI Vision parsing failed: {e}")
+        finally:
+            client.close()
+
+        return None
+
+    def parse(self, document_path: Path, mime_type, file_name=None):
+        if not self.settings.engine_is_valid():
+            self.log.warning(
+                "No valid remote parser engine is configured, content will be empty.",
+            )
+            self.text = ""
+        elif self.settings.engine == "azureai":
+            self.text = self.azure_ai_vision_parse(document_path)

src/paperless_remote/signals.py

@@ -0,0 +1,18 @@
+def get_parser(*args, **kwargs):
+    from paperless_remote.parsers import RemoteDocumentParser
+
+    return RemoteDocumentParser(*args, **kwargs)
+
+
+def get_supported_mime_types():
+    from paperless_remote.parsers import RemoteDocumentParser
+
+    return RemoteDocumentParser(None).supported_mime_types()
+
+
+def remote_consumer_declaration(sender, **kwargs):
+    return {
+        "parser": get_parser,
+        "weight": 5,
+        "mime_types": get_supported_mime_types(),
+    }

src/paperless_remote/tests/test_checks.py

@@ -0,0 +1,24 @@
+from unittest import TestCase
+
+from django.test import override_settings
+
+from paperless_remote import check_remote_parser_configured
+
+
+class TestChecks(TestCase):
+    @override_settings(REMOTE_OCR_ENGINE=None)
+    def test_no_engine(self):
+        msgs = check_remote_parser_configured(None)
+        self.assertEqual(len(msgs), 0)
+
+    @override_settings(REMOTE_OCR_ENGINE="azureai")
+    @override_settings(REMOTE_OCR_API_KEY="somekey")
+    @override_settings(REMOTE_OCR_ENDPOINT=None)
+    def test_azure_no_endpoint(self):
+        msgs = check_remote_parser_configured(None)
+        self.assertEqual(len(msgs), 1)
+        self.assertTrue(
+            msgs[0].msg.startswith(
+                "Azure AI remote parser requires endpoint and API key to be configured.",
+            ),
+        )

src/paperless_remote/tests/test_parser.py

@@ -0,0 +1,128 @@
+import uuid
+from pathlib import Path
+from unittest import mock
+
+from django.test import TestCase
+from django.test import override_settings
+
+from documents.tests.utils import DirectoriesMixin
+from documents.tests.utils import FileSystemAssertsMixin
+from paperless_remote.parsers import RemoteDocumentParser
+from paperless_remote.signals import get_parser
+
+
+class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
+    SAMPLE_FILES = Path(__file__).resolve().parent / "samples"
+
+    def assertContainsStrings(self, content: str, strings: list[str]):
+        # Asserts that all strings appear in content, in the given order.
+        indices = []
+        for s in strings:
+            if s in content:
+                indices.append(content.index(s))
+            else:
+                self.fail(f"'{s}' is not in '{content}'")
+        self.assertListEqual(indices, sorted(indices))
+
+    @mock.patch("paperless_tesseract.parsers.run_subprocess")
+    @mock.patch("azure.ai.documentintelligence.DocumentIntelligenceClient")
+    def test_get_text_with_azure(self, mock_client_cls, mock_subprocess):
+        # Arrange mock Azure client
+        mock_client = mock.Mock()
+        mock_client_cls.return_value = mock_client
+
+        # Simulate poller result and its `.details`
+        mock_poller = mock.Mock()
+        mock_poller.wait.return_value = None
+        mock_poller.details = {"operation_id": "fake-op-id"}
+        mock_client.begin_analyze_document.return_value = mock_poller
+        mock_poller.result.return_value.content = "This is a test document."
+
+        # Return dummy PDF bytes
+        mock_client.get_analyze_result_pdf.return_value = [
+            b"%PDF-",
+            b"1.7 ",
+            b"FAKEPDF",
+        ]
+
+        # Simulate pdftotext by writing dummy text to sidecar file
+        def fake_run(cmd, *args, **kwargs):
+            with Path(cmd[-1]).open("w", encoding="utf-8") as f:
+                f.write("This is a test document.")
+
+        mock_subprocess.side_effect = fake_run
+
+        with override_settings(
+            REMOTE_OCR_ENGINE="azureai",
+            REMOTE_OCR_API_KEY="somekey",
+            REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
+        ):
+            parser = get_parser(uuid.uuid4())
+            parser.parse(
+                self.SAMPLE_FILES / "simple-digital.pdf",
+                "application/pdf",
+            )
+
+            self.assertContainsStrings(
+                parser.text.strip(),
+                ["This is a test document."],
+            )
+
+    @mock.patch("azure.ai.documentintelligence.DocumentIntelligenceClient")
+    def test_get_text_with_azure_error_logged_and_returns_none(self, mock_client_cls):
+        mock_client = mock.Mock()
+        mock_client.begin_analyze_document.side_effect = RuntimeError("fail")
+        mock_client_cls.return_value = mock_client
+
+        with override_settings(
+            REMOTE_OCR_ENGINE="azureai",
+            REMOTE_OCR_API_KEY="somekey",
+            REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
+        ):
+            parser = get_parser(uuid.uuid4())
+            with mock.patch.object(parser.log, "error") as mock_log_error:
+                parser.parse(
+                    self.SAMPLE_FILES / "simple-digital.pdf",
+                    "application/pdf",
+                )
+
+        self.assertIsNone(parser.text)
+        mock_client.begin_analyze_document.assert_called_once()
+        mock_client.close.assert_called_once()
+        mock_log_error.assert_called_once()
+        self.assertIn(
+            "Azure AI Vision parsing failed",
+            mock_log_error.call_args[0][0],
+        )
+
+    @override_settings(
+        REMOTE_OCR_ENGINE="azureai",
+        REMOTE_OCR_API_KEY="key",
+        REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
+    )
+    def test_supported_mime_types_valid_config(self):
+        parser = RemoteDocumentParser(uuid.uuid4())
+        expected_types = {
+            "application/pdf": ".pdf",
+            "image/png": ".png",
+            "image/jpeg": ".jpg",
+            "image/tiff": ".tiff",
+            "image/bmp": ".bmp",
+            "image/gif": ".gif",
+            "image/webp": ".webp",
+        }
+        self.assertEqual(parser.supported_mime_types(), expected_types)
+
+    def test_supported_mime_types_invalid_config(self):
+        parser = get_parser(uuid.uuid4())
+        self.assertEqual(parser.supported_mime_types(), {})
+
+    @override_settings(
+        REMOTE_OCR_ENGINE=None,
+        REMOTE_OCR_API_KEY=None,
+        REMOTE_OCR_ENDPOINT=None,
+    )
+    def test_parse_with_invalid_config(self):
+        parser = get_parser(uuid.uuid4())
+        parser.parse(self.SAMPLE_FILES / "simple-digital.pdf", "application/pdf")
+        self.assertEqual(parser.text, "")

uv.lock

@@ -95,6 +95,34 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/02/ff/1175b0b7371e46244032d43a56862d0af455823b5280a50c63d99cc50f18/automat-25.4.16-py3-none-any.whl", hash = "sha256:04e9bce696a8d5671ee698005af6e5a9fa15354140a87f4870744604dcdd3ba1", size = 42842, upload-time = "2025-04-16T20:12:14.447Z" },
 ]
 
+[[package]]
+name = "azure-ai-documentintelligence"
+version = "1.0.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "azure-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "isodate", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/44/7b/8115cd713e2caa5e44def85f2b7ebd02a74ae74d7113ba20bdd41fd6dd80/azure_ai_documentintelligence-1.0.2.tar.gz", hash = "sha256:4d75a2513f2839365ebabc0e0e1772f5601b3a8c9a71e75da12440da13b63484", size = 170940 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d9/75/c9ec040f23082f54ffb1977ff8f364c2d21c79a640a13d1c1809e7fd6b1a/azure_ai_documentintelligence-1.0.2-py3-none-any.whl", hash = "sha256:e1fb446abbdeccc9759d897898a0fe13141ed29f9ad11fc705f951925822ed59", size = 106005 },
+]
+
+[[package]]
+name = "azure-core"
+version = "1.33.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "requests", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "six", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/75/aa/7c9db8edd626f1a7d99d09ef7926f6f4fb34d5f9fa00dc394afdfe8e2a80/azure_core-1.33.0.tar.gz", hash = "sha256:f367aa07b5e3005fec2c1e184b882b0b039910733907d001c20fb08ebb8c0eb9", size = 295633 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/07/b7/76b7e144aa53bd206bf1ce34fa75350472c3f69bf30e5c8c18bc9881035d/azure_core-1.33.0-py3-none-any.whl", hash = "sha256:9b5b6d0223a1d38c37500e6971118c1e0f13f54951e6893968b38910bc9cda8f", size = 207071 },
+]
+
 [[package]]
 name = "babel"
 version = "2.17.0"
@@ -1451,6 +1479,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c7/fc/4e5a141c3f7c7bed550ac1f69e599e92b6be449dd4677ec09f325cad0955/inotifyrecursive-0.3.5-py3-none-any.whl", hash = "sha256:7e5f4a2e1dc2bef0efa3b5f6b339c41fb4599055a2b54909d020e9e932cc8d2f", size = 8009, upload-time = "2020-11-20T12:38:46.981Z" },
 ]
 
+[[package]]
+name = "isodate"
+version = "0.7.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/54/4d/e940025e2ce31a8ce1202635910747e5a87cc3a6a6bb2d00973375014749/isodate-0.7.2.tar.gz", hash = "sha256:4cd1aa0f43ca76f4a6c6c0292a85f40b35ec2e43e315b59f06e6d32171a953e6", size = 29705 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/15/aa/0aca39a37d3c7eb941ba736ede56d689e7be91cab5d9ca846bde3999eba6/isodate-0.7.2-py3-none-any.whl", hash = "sha256:28009937d8031054830160fce6d409ed342816b543597cece116d966c6d99e15", size = 22320 },
+]
+
 [[package]]
 name = "jinja2"
 version = "3.1.6"
@@ -2118,6 +2155,7 @@ name = "paperless-ngx"
 version = "2.20.3"
 source = { virtual = "." }
 dependencies = [
+    { name = "azure-ai-documentintelligence", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "babel", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "bleach", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "celery", extra = ["redis"], marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2255,6 +2293,7 @@ typing = [
 
 [package.metadata]
 requires-dist = [
+    { name = "azure-ai-documentintelligence", specifier = ">=1.0.2" },
     { name = "babel", specifier = ">=2.17" },
     { name = "bleach", specifier = "~=6.3.0" },
     { name = "celery", extras = ["redis"], specifier = "~=5.5.1" },