Login message - move to login render, dont duplicate

.github/nginx-reverse-proxy-test.conf

@@ -1,33 +0,0 @@
-server {
-    listen 80;
-    server_name localhost;
-
-    # Test basic reverse proxy to changedetection.io
-    location / {
-        proxy_pass http://changedet-app:5000;
-        proxy_set_header Host $host;
-        proxy_set_header X-Real-IP $remote_addr;
-        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        proxy_set_header X-Forwarded-Proto $scheme;
-
-        # WebSocket support
-        proxy_http_version 1.1;
-        proxy_set_header Upgrade $http_upgrade;
-        proxy_set_header Connection "upgrade";
-    }
-
-    # Test subpath deployment with X-Forwarded-Prefix
-    location /changedet-sub/ {
-        proxy_pass http://changedet-app:5000/;
-        proxy_set_header X-Forwarded-Prefix /changedet-sub;
-        proxy_set_header Host $host;
-        proxy_set_header X-Real-IP $remote_addr;
-        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        proxy_set_header X-Forwarded-Proto $scheme;
-
-        # WebSocket support
-        proxy_http_version 1.1;
-        proxy_set_header Upgrade $http_upgrade;
-        proxy_set_header Connection "upgrade";
-    }
-}

.github/workflows/containers.yml

@@ -15,6 +15,7 @@ on:
   push:
     branches:
       - master
+      - dev
 
 jobs:
   metadata:
@@ -66,62 +67,43 @@ jobs:
           echo ${{ github.ref }} > changedetectionio/tag.txt
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v4
+        uses: docker/setup-qemu-action@v3
         with:
           image: tonistiigi/binfmt:latest
           platforms: all
 
       - name: Login to GitHub Container Registry
-        uses: docker/login-action@v4
+        uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Login to Docker Hub Container Registry
-        uses: docker/login-action@v4
+        uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_HUB_USERNAME }}
           password: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }}
 
       - name: Set up Docker Buildx
         id: buildx
-        uses: docker/setup-buildx-action@v4
+        uses: docker/setup-buildx-action@v3
         with:
           install: true
           version: latest
           driver-opts: image=moby/buildkit:master
 
-      # master branch -> :dev container tag
-      - name: Docker meta :dev
-        if: ${{ github.ref == 'refs/heads/master' && github.event_name != 'release' }}
-        uses: docker/metadata-action@v6
-        id: meta_dev
-        with:
-          images: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io
-            ghcr.io/${{ github.repository }}
-          tags: |
-            type=raw,value=dev
-          labels: |
-            org.opencontainers.image.created=${{ github.event.release.published_at }}
-            org.opencontainers.image.description=Website, webpage change detection, monitoring and notifications.
-            org.opencontainers.image.documentation=https://changedetection.io
-            org.opencontainers.image.revision=${{ github.sha }}
-            org.opencontainers.image.source=https://github.com/dgtlmoon/changedetection.io
-            org.opencontainers.image.title=changedetection.io
-            org.opencontainers.image.url=https://changedetection.io
-
+      # dev branch -> :dev container tag
       - name: Build and push :dev
         id: docker_build
-        if: ${{ github.ref == 'refs/heads/master' && github.event_name != 'release' }}
-        uses: docker/build-push-action@v7
+        if: ${{ github.ref == 'refs/heads/dev' }}
+        uses: docker/build-push-action@v6
         with:
           context: ./
           file: ./Dockerfile
           push: true
-          tags: ${{ steps.meta_dev.outputs.tags }}
-          labels: ${{ steps.meta_dev.outputs.labels }}
+          tags: |
+            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:dev,ghcr.io/${{ github.repository }}:dev
           platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8
           cache-from: type=gha
           cache-to: type=gha,mode=max
@@ -136,10 +118,10 @@ jobs:
           echo "Release tag: ${{ github.event.release.tag_name }}"
           echo "Github ref: ${{ github.ref }}"
           echo "Github ref name: ${{ github.ref_name }}"
-
+          
       - name: Docker meta :tag
         if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
-        uses: docker/metadata-action@v6
+        uses: docker/metadata-action@v5
         id: meta
         with:
             images: |
@@ -150,26 +132,16 @@ jobs:
                 type=semver,pattern={{major}}.{{minor}},value=${{ github.event.release.tag_name }}
                 type=semver,pattern={{major}},value=${{ github.event.release.tag_name }}
                 type=raw,value=latest
-            labels: |
-              org.opencontainers.image.created=${{ github.event.release.published_at }}
-              org.opencontainers.image.description=Website, webpage change detection, monitoring and notifications.
-              org.opencontainers.image.documentation=https://changedetection.io
-              org.opencontainers.image.revision=${{ github.sha }}
-              org.opencontainers.image.source=https://github.com/dgtlmoon/changedetection.io
-              org.opencontainers.image.title=changedetection.io
-              org.opencontainers.image.url=https://changedetection.io
-              org.opencontainers.image.version=${{ github.event.release.tag_name }}
 
       - name: Build and push :tag
         id: docker_build_tag_release
         if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
-        uses: docker/build-push-action@v7
+        uses: docker/build-push-action@v6
         with:
           context: ./
           file: ./Dockerfile
           push: true
           tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
           platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8
           cache-from: type=gha
           cache-to: type=gha,mode=max

.github/workflows/pypi-release.yml

@@ -21,7 +21,7 @@ jobs:
     - name: Build a binary wheel and a source tarball
       run: python3 -m build
     - name: Store the distribution packages
-      uses: actions/upload-artifact@v7
+      uses: actions/upload-artifact@v6
       with:
         name: python-package-distributions
         path: dist/
@@ -34,7 +34,7 @@ jobs:
     - build
     steps:
     - name: Download all the dists
-      uses: actions/download-artifact@v8
+      uses: actions/download-artifact@v7
       with:
         name: python-package-distributions
         path: dist/
@@ -61,8 +61,8 @@ jobs:
         
         # --- API test ---
         # This also means that the docs/api-spec.yml was shipped and could be read
-        test -f /tmp/changedetection.json
-        API_KEY=$(jq -r '.. | .api_access_token? // empty' /tmp/changedetection.json)
+        test -f /tmp/url-watches.json
+        API_KEY=$(jq -r '.. | .api_access_token? // empty' /tmp/url-watches.json)
         echo Test API KEY is $API_KEY
         curl -X POST "http://127.0.0.1:10000/api/v1/watch" \
           -H "x-api-key: ${API_KEY}" \
@@ -93,7 +93,7 @@ jobs:
 
     steps:
     - name: Download all the dists
-      uses: actions/download-artifact@v8
+      uses: actions/download-artifact@v7
       with:
         name: python-package-distributions
         path: dist/

.github/workflows/test-container-build.yml

@@ -60,14 +60,14 @@ jobs:
 
         # Just test that the build works, some libraries won't compile on ARM/rPi etc
         - name: Set up QEMU
-          uses: docker/setup-qemu-action@v4
+          uses: docker/setup-qemu-action@v3
           with:
             image: tonistiigi/binfmt:latest
             platforms: all
 
         - name: Set up Docker Buildx
           id: buildx
-          uses: docker/setup-buildx-action@v4
+          uses: docker/setup-buildx-action@v3
           with:
             install: true
             version: latest
@@ -75,7 +75,7 @@ jobs:
 
         - name: Test that the docker containers can build (${{ matrix.platform }} - ${{ matrix.dockerfile }})
           id: docker_build
-          uses: docker/build-push-action@v7
+          uses: docker/build-push-action@v6
           # https://github.com/docker/build-push-action#customizing
           with:
             context: ./

.github/workflows/test-only.yml

@@ -52,13 +52,4 @@ jobs:
     uses: ./.github/workflows/test-stack-reusable-workflow.yml
     with:
       python-version: '3.13'
-      skip-pypuppeteer: true
-
-
-  test-application-3-14:
-    #if: github.event_name == 'push' && github.ref == 'refs/heads/master'
-    needs: lint-code
-    uses: ./.github/workflows/test-stack-reusable-workflow.yml
-    with:
-      python-version: '3.14'
-      skip-pypuppeteer: false
+      skip-pypuppeteer: true

.github/workflows/test-stack-reusable-workflow.yml

@@ -37,29 +37,10 @@ jobs:
             ${{ runner.os }}-pip-py${{ env.PYTHON_VERSION }}-
             ${{ runner.os }}-pip-
 
-      - name: Get current date for cache key
-        id: date
-        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v4
-
       - name: Build changedetection.io container for testing under Python ${{ env.PYTHON_VERSION }}
-        uses: docker/build-push-action@v7
-        with:
-          context: ./
-          file: ./Dockerfile
-          build-args: |
-            PYTHON_VERSION=${{ env.PYTHON_VERSION }}
-            LOGGER_LEVEL=TRACE
-          tags: test-changedetectionio
-          load: true
-          cache-from: type=gha,scope=build-${{ github.ref_name }}-py${{ env.PYTHON_VERSION }}-${{ hashFiles('requirements.txt', 'Dockerfile') }}-${{ steps.date.outputs.date }}
-          cache-to: type=gha,mode=max,scope=build-${{ github.ref_name }}-py${{ env.PYTHON_VERSION }}-${{ hashFiles('requirements.txt', 'Dockerfile') }}-${{ steps.date.outputs.date }}
-
-      - name: Verify build
         run: |
-          echo "---- Built for Python ${{ env.PYTHON_VERSION }} -----"
+          echo "---- Building for Python ${{ env.PYTHON_VERSION }} -----"
+          docker build --build-arg PYTHON_VERSION=${{ env.PYTHON_VERSION }} --build-arg LOGGER_LEVEL=TRACE -t test-changedetectionio .
           docker run test-changedetectionio bash -c 'pip list'
 
       - name: We should be Python ${{ env.PYTHON_VERSION }} ...
@@ -71,7 +52,7 @@ jobs:
           docker save test-changedetectionio -o /tmp/test-changedetectionio.tar
 
       - name: Upload Docker image artifact
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v6
         with:
           name: test-changedetectionio-${{ env.PYTHON_VERSION }}
           path: /tmp/test-changedetectionio.tar
@@ -88,7 +69,7 @@ jobs:
       - uses: actions/checkout@v6
 
       - name: Download Docker image artifact
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: test-changedetectionio-${{ env.PYTHON_VERSION }}
           path: /tmp
@@ -103,7 +84,6 @@ jobs:
           docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_watch_model'
           docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_jinja2_security'
           docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_semver'
-          docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_html_to_text'         
 
   # Basic pytest tests with ancillary services
   basic-tests:
@@ -116,7 +96,7 @@ jobs:
       - uses: actions/checkout@v6
 
       - name: Download Docker image artifact
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: test-changedetectionio-${{ env.PYTHON_VERSION }}
           path: /tmp
@@ -130,32 +110,6 @@ jobs:
           docker network inspect changedet-network >/dev/null 2>&1 || docker network create changedet-network
           docker run --name test-cdio-basic-tests --network changedet-network test-changedetectionio bash -c 'cd changedetectionio && ./run_basic_tests.sh'
 
-      - name: Test CLI options
-        run: |
-          docker network inspect changedet-network >/dev/null 2>&1 || docker network create changedet-network
-          docker run --name test-cdio-cli-opts --network changedet-network test-changedetectionio bash -c 'changedetectionio/test_cli_opts.sh' &> cli-opts-output.txt
-          echo "=== CLI Options Test Output ==="
-          cat cli-opts-output.txt
-
-      - name: CLI Memory Test
-        run: |
-          echo "=== Checking CLI batch mode memory usage ==="
-          # Extract RSS memory value from output
-          RSS_MB=$(grep -oP "Memory consumption before worker shutdown: RSS=\K[\d.]+" cli-opts-output.txt | head -1 || echo "0")
-          echo "RSS Memory: ${RSS_MB} MB"
-
-          # Check if RSS is less than 100MB
-          if [ -n "$RSS_MB" ]; then
-            if (( $(echo "$RSS_MB < 100" | bc -l) )); then
-              echo "✓ Memory usage is acceptable: ${RSS_MB} MB < 100 MB"
-            else
-              echo "✗ Memory usage too high: ${RSS_MB} MB >= 100 MB"
-              exit 1
-            fi
-          else
-            echo "⚠ Could not extract memory usage, skipping check"
-          fi
-
       - name: Extract memory report and logs
         if: always()
         uses: ./.github/actions/extract-memory-report
@@ -165,18 +119,11 @@ jobs:
 
       - name: Store test artifacts
         if: always()
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@v6
         with:
           name: test-cdio-basic-tests-output-py${{ env.PYTHON_VERSION }}
           path: output-logs
 
-      - name: Store CLI test output
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: test-cdio-cli-opts-output-py${{ env.PYTHON_VERSION }}
-          path: cli-opts-output.txt
-
   # Playwright tests
   playwright-tests:
     runs-on: ubuntu-latest
@@ -188,7 +135,7 @@ jobs:
       - uses: actions/checkout@v6
 
       - name: Download Docker image artifact
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: test-changedetectionio-${{ env.PYTHON_VERSION }}
           path: /tmp
@@ -230,7 +177,7 @@ jobs:
       - uses: actions/checkout@v6
 
       - name: Download Docker image artifact
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: test-changedetectionio-${{ env.PYTHON_VERSION }}
           path: /tmp
@@ -270,7 +217,7 @@ jobs:
       - uses: actions/checkout@v6
 
       - name: Download Docker image artifact
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: test-changedetectionio-${{ env.PYTHON_VERSION }}
           path: /tmp
@@ -306,7 +253,7 @@ jobs:
       - uses: actions/checkout@v6
 
       - name: Download Docker image artifact
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: test-changedetectionio-${{ env.PYTHON_VERSION }}
           path: /tmp
@@ -324,175 +271,6 @@ jobs:
         run: |
           docker run --rm --network changedet-network test-changedetectionio bash -c 'cd changedetectionio;pytest tests/smtp/test_notification_smtp.py'
 
-  nginx-reverse-proxy:
-    runs-on: ubuntu-latest
-    needs: build
-    timeout-minutes: 10
-    env:
-      PYTHON_VERSION: ${{ inputs.python-version }}
-    steps:
-      - uses: actions/checkout@v6
-
-      - name: Download Docker image artifact
-        uses: actions/download-artifact@v8
-        with:
-          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
-          path: /tmp
-
-      - name: Load Docker image
-        run: |
-          docker load -i /tmp/test-changedetectionio.tar
-
-      - name: Spin up services
-        run: |
-          docker network create changedet-network
-
-          # Start changedetection.io container with X-Forwarded headers support
-          docker run --name changedet-app --hostname changedet-app --network changedet-network \
-            -e USE_X_SETTINGS=true \
-            -d test-changedetectionio
-          sleep 3
-
-      - name: Start nginx reverse proxy
-        run: |
-          # Start nginx with our test configuration
-          docker run --name nginx-proxy --network changedet-network -d -p 8080:80 --rm \
-            -v ${{ github.workspace }}/.github/nginx-reverse-proxy-test.conf:/etc/nginx/conf.d/default.conf:ro \
-            nginx:alpine
-          sleep 2
-
-      - name: Test reverse proxy - root path
-        run: |
-          echo "=== Testing nginx reverse proxy at root path ==="
-          curl --retry-connrefused --retry 6 -s http://localhost:8080/ > /tmp/nginx-test-root.html
-
-          # Check for changedetection.io UI elements
-          if grep -q "checkbox-uuid" /tmp/nginx-test-root.html; then
-            echo "✓ Found checkbox-uuid in response"
-          else
-            echo "ERROR: checkbox-uuid not found in response"
-            cat /tmp/nginx-test-root.html
-            exit 1
-          fi
-
-          # Check for watchlist content
-          if grep -q -i "watch" /tmp/nginx-test-root.html; then
-            echo "✓ Found watch/watchlist content in response"
-          else
-            echo "ERROR: watchlist content not found"
-            cat /tmp/nginx-test-root.html
-            exit 1
-          fi
-
-          echo "✓ Root path reverse proxy working correctly"
-
-      - name: Test reverse proxy - subpath with X-Forwarded-Prefix
-        run: |
-          echo "=== Testing nginx reverse proxy at subpath /changedet-sub/ ==="
-          curl --retry-connrefused --retry 6 -s http://localhost:8080/changedet-sub/ > /tmp/nginx-test-subpath.html
-
-          # Check for changedetection.io UI elements
-          if grep -q "checkbox-uuid" /tmp/nginx-test-subpath.html; then
-            echo "✓ Found checkbox-uuid in subpath response"
-          else
-            echo "ERROR: checkbox-uuid not found in subpath response"
-            cat /tmp/nginx-test-subpath.html
-            exit 1
-          fi
-
-          echo "✓ Subpath reverse proxy working correctly"
-
-      - name: Test API through reverse proxy subpath
-        run: |
-          echo "=== Testing API endpoints through nginx subpath /changedet-sub/ ==="
-
-          # Extract API key from the changedetection.io datastore
-          API_KEY=$(docker exec changedet-app cat /datastore/changedetection.json | grep -o '"api_access_token": *"[^"]*"' | cut -d'"' -f4)
-
-          if [ -z "$API_KEY" ]; then
-            echo "ERROR: Could not extract API key from datastore"
-            docker exec changedet-app cat /datastore/changedetection.json
-            exit 1
-          fi
-
-          echo "✓ Extracted API key: ${API_KEY:0:8}..."
-
-          # Create a watch via API through nginx proxy subpath
-          echo "Creating watch via POST to /changedet-sub/api/v1/watch"
-          RESPONSE=$(curl -s -w "\n%{http_code}" -X POST "http://localhost:8080/changedet-sub/api/v1/watch" \
-            -H "x-api-key: ${API_KEY}" \
-            -H "Content-Type: application/json" \
-            -d '{
-              "url": "https://example.com/test-nginx-proxy",
-              "tag": "nginx-test"
-            }')
-
-          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
-          BODY=$(echo "$RESPONSE" | head -n-1)
-
-          if [ "$HTTP_CODE" != "201" ]; then
-            echo "ERROR: Expected HTTP 201, got $HTTP_CODE"
-            echo "Response: $BODY"
-            exit 1
-          fi
-
-          echo "✓ Watch created successfully (HTTP 201)"
-
-          # Extract the watch UUID from response
-          WATCH_UUID=$(echo "$BODY" | grep -o '"uuid": *"[^"]*"' | cut -d'"' -f4)
-          echo "✓ Watch UUID: $WATCH_UUID"
-
-          # Update the watch via PUT through nginx proxy subpath
-          echo "Updating watch via PUT to /changedet-sub/api/v1/watch/${WATCH_UUID}"
-          RESPONSE=$(curl -s -w "\n%{http_code}" -X PUT "http://localhost:8080/changedet-sub/api/v1/watch/${WATCH_UUID}" \
-            -H "x-api-key: ${API_KEY}" \
-            -H "Content-Type: application/json" \
-            -d '{
-              "paused": true
-            }')
-
-          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
-          BODY=$(echo "$RESPONSE" | head -n-1)
-
-          if [ "$HTTP_CODE" != "200" ]; then
-            echo "ERROR: Expected HTTP 200, got $HTTP_CODE"
-            echo "Response: $BODY"
-            exit 1
-          fi
-
-          if echo "$BODY" | grep -q 'OK'; then
-            echo "✓ Watch updated successfully (HTTP 200, response: OK)"
-          else
-            echo "ERROR: Expected response 'OK', got: $BODY"
-            echo "Response: $BODY"
-            exit 1
-          fi
-
-          # Verify the watch is paused via GET
-          echo "Verifying watch is paused via GET"
-          RESPONSE=$(curl -s "http://localhost:8080/changedet-sub/api/v1/watch/${WATCH_UUID}" \
-            -H "x-api-key: ${API_KEY}")
-
-          if echo "$RESPONSE" | grep -q '"paused": *true'; then
-            echo "✓ Watch is paused as expected"
-          else
-            echo "ERROR: Watch paused state not confirmed"
-            echo "Response: $RESPONSE"
-            exit 1
-          fi
-
-          echo "✓ API tests through nginx subpath completed successfully"
-
-      - name: Cleanup nginx test
-        if: always()
-        run: |
-          docker logs nginx-proxy || true
-          docker logs changedet-app || true
-          docker stop nginx-proxy changedet-app || true
-          docker rm nginx-proxy changedet-app || true
-
-
-
   # Proxy tests
   proxy-tests:
     runs-on: ubuntu-latest
@@ -504,7 +282,7 @@ jobs:
       - uses: actions/checkout@v6
 
       - name: Download Docker image artifact
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: test-changedetectionio-${{ env.PYTHON_VERSION }}
           path: /tmp
@@ -544,7 +322,7 @@ jobs:
       - uses: actions/checkout@v6
 
       - name: Download Docker image artifact
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: test-changedetectionio-${{ env.PYTHON_VERSION }}
           path: /tmp
@@ -564,29 +342,6 @@ jobs:
           cd changedetectionio
           ./run_custom_browser_url_tests.sh
 
-  processor-plugin-tests:
-    runs-on: ubuntu-latest
-    needs: build
-    timeout-minutes: 20
-    env:
-      PYTHON_VERSION: ${{ inputs.python-version }}
-    steps:
-      - uses: actions/checkout@v6
-
-      - name: Download Docker image artifact
-        uses: actions/download-artifact@v8
-        with:
-          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
-          path: /tmp
-
-      - name: Load Docker image
-        run: |
-          docker load -i /tmp/test-changedetectionio.tar
-
-      - name: Basic processor plugin registration and checks
-        run: |
-          docker run  -e EXTRA_PACKAGES=changedetection.io-osint-processor test-changedetectionio bash -c 'cd changedetectionio;pytest -vvv -s  tests/plugins/test_processor.py::test_check_plugin_processor'
-
   # Container startup tests
   container-tests:
     runs-on: ubuntu-latest
@@ -598,7 +353,7 @@ jobs:
       - uses: actions/checkout@v6
 
       - name: Download Docker image artifact
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: test-changedetectionio-${{ env.PYTHON_VERSION }}
           path: /tmp
@@ -643,7 +398,7 @@ jobs:
       - uses: actions/checkout@v6
 
       - name: Download Docker image artifact
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@v7
         with:
           name: test-changedetectionio-${{ env.PYTHON_VERSION }}
           path: /tmp
@@ -685,154 +440,3 @@ jobs:
             exit 1
           fi
           docker rm sig-test
-
-  # Upgrade path test
-  upgrade-path-test:
-    runs-on: ubuntu-latest
-    needs: build
-    timeout-minutes: 25
-    env:
-      PYTHON_VERSION: ${{ inputs.python-version }}
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          fetch-depth: 0  # Fetch all history and tags for upgrade testing
-
-      - name: Set up Python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@v6
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      - name: Check upgrade works without error
-        run: |
-          echo "=== Testing upgrade path from 0.49.1 to ${{ github.ref_name }} (${{ github.sha }}) ==="
-          sudo apt-get update && sudo apt-get install -y --no-install-recommends \
-              g++ \
-              gcc \
-              libc-dev \
-              libffi-dev \
-              libjpeg-dev \
-              libssl-dev \
-              libxslt-dev \
-              make \
-              patch \
-              pkg-config \
-              zlib1g-dev
-          
-          # Checkout old version and create datastore
-          git checkout 0.49.1
-          python3 -m venv .venv
-          source .venv/bin/activate
-          pip install -r requirements.txt
-          pip install 'pyOpenSSL>=23.2.0'
-
-          echo "=== Running version 0.49.1 to create datastore ==="
-          ALLOW_IANA_RESTRICTED_ADDRESSES=true python3 ./changedetection.py -C -d /tmp/data &
-          APP_PID=$!
-
-          # Wait for app to be ready
-          echo "Waiting for 0.49.1 to be ready..."
-          sleep 6
-
-          # Extract API key from datastore (0.49.1 uses url-watches.json)
-          API_KEY=$(jq -r '.settings.application.api_access_token // empty' /tmp/data/url-watches.json)
-          echo "API Key: ${API_KEY:0:8}..."
-
-          # Create a watch with tag "github-group-test" via API
-          echo "Creating test watch with tag via API..."
-          curl -X POST "http://127.0.0.1:5000/api/v1/watch" \
-            -H "x-api-key: ${API_KEY}" \
-            -H "Content-Type: application/json" \
-            --show-error --fail \
-            --retry 6 --retry-delay 1 --retry-connrefused \
-            -d '{
-              "url": "https://example.com/upgrade-test",
-              "tag": "github-group-test"
-            }'
-
-          echo "✓ Created watch with tag 'github-group-test'"
-
-          # Create a specific test URL watch
-          echo "Creating test URL watch via API..."
-          curl -X POST "http://127.0.0.1:5000/api/v1/watch" \
-            -H "x-api-key: ${API_KEY}" \
-            -H "Content-Type: application/json" \
-            --show-error --fail \
-            -d '{
-              "url": "http://localhost/test.txt"
-            }'
-
-          echo "✓ Created watch for 'http://localhost/test.txt' in version 0.49.1"
-
-          # Stop the old version gracefully
-          kill $APP_PID
-          wait $APP_PID || true
-          echo "✓ Version 0.49.1 stopped"
-
-          # Upgrade to current version (use commit SHA since we're in detached HEAD)
-          echo "Upgrading to commit ${{ github.sha }}"
-          git checkout ${{ github.sha }}
-          pip install -r requirements.txt
-
-          echo "=== Running current version (commit ${{ github.sha }}) with old datastore (testing mode) ==="
-          ALLOW_IANA_RESTRICTED_ADDRESSES=true TESTING_SHUTDOWN_AFTER_DATASTORE_LOAD=1 python3 ./changedetection.py -d /tmp/data > /tmp/upgrade-test.log 2>&1
-
-          echo "=== Upgrade test output ==="
-          cat /tmp/upgrade-test.log
-          echo "✓ Datastore upgraded successfully"
-
-          # Now start the current version normally to verify the tag survived
-          echo "=== Starting current version to verify tag exists after upgrade ==="
-          ALLOW_IANA_RESTRICTED_ADDRESSES=true timeout 20 python3 ./changedetection.py -d /tmp/data > /tmp/ui-test.log 2>&1 &
-          APP_PID=$!
-
-          # Wait for app to be ready and fetch UI
-          echo "Waiting for current version to be ready..."
-          sleep 5
-          curl --retry 6 --retry-delay 1 --retry-connrefused --silent http://127.0.0.1:5000 > /tmp/ui-output.html
-
-          # Verify tag exists in UI
-          if grep -q "github-group-test" /tmp/ui-output.html; then
-            echo "✓ Tag 'github-group-test' found in UI after upgrade"
-          else
-            echo "ERROR: Tag 'github-group-test' not found in UI after upgrade"
-            echo "=== UI Output ==="
-            cat /tmp/ui-output.html
-            echo "=== App Log ==="
-            cat /tmp/ui-test.log
-            kill $APP_PID || true
-            exit 1
-          fi
-
-          # Verify test URL exists in UI
-          if grep -q "http://localhost/test.txt" /tmp/ui-output.html; then
-            echo "✓ Watch URL 'http://localhost/test.txt' found in UI after upgrade"
-          else
-            echo "ERROR: Watch URL 'http://localhost/test.txt' not found in UI after upgrade"
-            echo "=== UI Output ==="
-            cat /tmp/ui-output.html
-            echo "=== App Log ==="
-            cat /tmp/ui-test.log
-            kill $APP_PID || true
-            exit 1
-          fi
-
-          # Cleanup
-          kill $APP_PID || true
-          wait $APP_PID || true
-
-          echo ""
-          echo "✓✓✓ Upgrade test passed: 0.49.1 → ${{ github.ref_name }} ✓✓✓"
-          echo "    - Commit: ${{ github.sha }}"
-          echo "    - Datastore migrated successfully"
-          echo "    - Tag 'github-group-test' survived upgrade"
-          echo "    - Watch URL 'http://localhost/test.txt' survived upgrade"
-
-          echo "✓ Upgrade test passed: 0.49.1 → ${{ github.ref_name }}"
-
-      - name: Upload upgrade test logs
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: upgrade-test-logs-py${{ env.PYTHON_VERSION }}
-          path: /tmp/upgrade-test.log

.gitignore

@@ -29,4 +29,3 @@ test-datastore/
 
 # Memory consumption log
 test-memory.log
-tests/logs/

Dockerfile

@@ -78,12 +78,6 @@ RUN --mount=type=cache,id=pip,sharing=locked,target=/tmp/pip-cache \
 # Final image stage
 FROM python:${PYTHON_VERSION}-slim-bookworm
 LABEL org.opencontainers.image.source="https://github.com/dgtlmoon/changedetection.io"
-LABEL org.opencontainers.image.url="https://changedetection.io"
-LABEL org.opencontainers.image.documentation="https://changedetection.io/tutorials"
-LABEL org.opencontainers.image.title="changedetection.io"
-LABEL org.opencontainers.image.description="Self-hosted web page change monitoring and notification service"
-LABEL org.opencontainers.image.licenses="Apache-2.0"
-LABEL org.opencontainers.image.vendor="changedetection.io"
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libxslt1.1 \
@@ -138,15 +132,6 @@ ENV LOGGER_LEVEL="$LOGGER_LEVEL"
 ENV LC_ALL=en_US.UTF-8
 
 WORKDIR /app
-
-# Copy and set up entrypoint script for installing extra packages
-COPY docker-entrypoint.sh /docker-entrypoint.sh
-RUN chmod +x /docker-entrypoint.sh
-
-# Set entrypoint to handle EXTRA_PACKAGES env var
-ENTRYPOINT ["/docker-entrypoint.sh"]
-
-# Default command (can be overridden in docker-compose.yml)
 CMD ["python", "./changedetection.py", "-d", "/datastore"]
 
 

MANIFEST.in

@@ -9,15 +9,12 @@ recursive-include changedetectionio/notification *
 recursive-include changedetectionio/processors *
 recursive-include changedetectionio/realtime *
 recursive-include changedetectionio/static *
-recursive-include changedetectionio/store *
 recursive-include changedetectionio/templates *
 recursive-include changedetectionio/tests *
-recursive-include changedetectionio/translations *
 recursive-include changedetectionio/widgets *
 prune changedetectionio/static/package-lock.json
 prune changedetectionio/static/styles/node_modules
 prune changedetectionio/static/styles/package-lock.json
-include changedetectionio/favicon_utils.py
 include changedetection.py
 include requirements.txt
 include README-pip.md

README.md

@@ -183,9 +183,6 @@ docker compose pull && docker compose up -d
 
 See the wiki for more information https://github.com/dgtlmoon/changedetection.io/wiki
 
-## Different browser viewport sizes (mobile, desktop etc)
-
-If you are using the recommended `sockpuppetbrowser` (which is in the docker-compose.yml as a setting to be uncommented) you can easily set different viewport sizes for your web page change detection, [see more information here about setting up different viewport sizes](https://github.com/dgtlmoon/sockpuppetbrowser?tab=readme-ov-file#setting-viewport-size).
 
 ## Filters
 

babel.cfg

@@ -1,5 +0,0 @@
-[python: **.py]
-keywords = _:1,_l:1,gettext:1
-
-[jinja2: **/templates/**.html]
-encoding = utf-8

changedetectionio/__init__.py

@@ -2,24 +2,23 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 # Semver means never use .01, or 00. Should be .1.
-__version__ = '0.54.6'
+__version__ = '0.51.4'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError
-
-from loguru import logger
-import getopt
 import logging
 import os
+import getopt
 import platform
 import signal
-import threading
-import time
+
+import sys
 
 # Eventlet completely removed - using threading mode for SocketIO
 # This provides better Python 3.12+ compatibility and eliminates eventlet/asyncio conflicts
-# Note: store and changedetection_app are imported inside main() to avoid
-# initialization before argument parsing (allows --help to work without loading everything)
+from changedetectionio import store
+from changedetectionio.flask_app import changedetection_app
+from loguru import logger
 
 # ==============================================================================
 # Multiprocessing Configuration - CRITICAL for Thread Safety
@@ -42,10 +41,9 @@ import time
 #
 # IMPLEMENTATION:
 #   1. Explicit contexts everywhere (primary protection):
+#      - Watch.py: ctx = multiprocessing.get_context('spawn')
 #      - playwright.py: ctx = multiprocessing.get_context('spawn')
 #      - puppeteer.py: ctx = multiprocessing.get_context('spawn')
-#      - isolated_opencv.py: ctx = multiprocessing.get_context('spawn')
-#      - isolated_libvips.py: ctx = multiprocessing.get_context('spawn')
 #
 #   2. Global default (defense-in-depth, below):
 #      - Safety net if future code forgets explicit context
@@ -61,22 +59,8 @@ import time
 # ==============================================================================
 
 import multiprocessing
-import os
 import sys
 
-# Limit glibc malloc arena count to prevent RSS growth from concurrent requests.
-# Default: glibc creates up to 8×CPU_cores arenas. Each concurrent thread/connection
-# can trigger a new arena, and freed memory stays mapped in those arenas as RSS forever.
-# With MALLOC_ARENA_MAX=2, at most 2 arenas are used; freed pages return to the OS faster.
-# Must be set before worker threads start; env var is read lazily by glibc on first arena creation.
-if 'MALLOC_ARENA_MAX' not in os.environ:
-    os.environ['MALLOC_ARENA_MAX'] = '2'
-    try:
-        import ctypes as _ctypes
-        _ctypes.CDLL('libc.so.6').mallopt(-8, 2)  # M_ARENA_MAX = -8
-    except Exception:
-        pass
-
 # Set spawn as global default (safety net - all our code uses explicit contexts anyway)
 # Skip in tests to avoid breaking pytest-flask's LiveServer fixture (uses unpicklable local functions)
 if 'pytest' not in sys.modules:
@@ -98,26 +82,15 @@ def get_version():
 def sigshutdown_handler(_signo, _stack_frame):
     name = signal.Signals(_signo).name
     logger.critical(f'Shutdown: Got Signal - {name} ({_signo}), Fast shutdown initiated')
-
+    
     # Set exit flag immediately to stop all loops
     app.config.exit.set()
     datastore.stop_thread = True
-
-    # Log memory consumption before shutting down workers (cross-platform)
-    try:
-        import psutil
-        process = psutil.Process()
-        mem_info = process.memory_info()
-        rss_mb = mem_info.rss / 1024 / 1024
-        vms_mb = mem_info.vms / 1024 / 1024
-        logger.info(f"Memory consumption before worker shutdown: RSS={rss_mb:,.2f} MB, VMS={vms_mb:,.2f} MB")
-    except Exception as e:
-        logger.warning(f"Could not retrieve memory stats: {str(e)}")
-
+    
     # Shutdown workers and queues immediately
     try:
-        from changedetectionio import worker_pool
-        worker_pool.shutdown_workers()
+        from changedetectionio import worker_handler
+        worker_handler.shutdown_workers()
     except Exception as e:
         logger.error(f"Error shutting down workers: {str(e)}")
     
@@ -126,9 +99,9 @@ def sigshutdown_handler(_signo, _stack_frame):
         from changedetectionio.flask_app import update_q, notification_q
         update_q.close()
         notification_q.close()
-        logger.debug("Queues closed successfully")
+        logger.debug("Janus queues closed successfully")
     except Exception as e:
-        logger.critical(f"CRITICAL: Failed to close queues: {e}")
+        logger.critical(f"CRITICAL: Failed to close janus queues: {e}")
     
     # Shutdown socketio server fast
     from changedetectionio.flask_app import socketio_server
@@ -138,80 +111,31 @@ def sigshutdown_handler(_signo, _stack_frame):
         except Exception as e:
             logger.error(f"Error shutting down Socket.IO server: {str(e)}")
     
-    # With immediate persistence, all data is already saved
-    logger.success('All data already persisted (immediate commits enabled).')
-
+    # Save data quickly
+    try:
+        datastore.sync_to_json()
+        logger.success('Fast sync to disk complete.')
+    except Exception as e:
+        logger.error(f"Error syncing to disk: {str(e)}")
+    
     sys.exit()
 
-def print_help():
-    """Print help text for command line options"""
-    print('Usage: changedetection.py [options]')
-    print('')
-    print('Standard options:')
-    print('  -s                SSL enable')
-    print('  -h HOST           Listen host (default: 0.0.0.0)')
-    print('  -p PORT           Listen port (default: 5000)')
-    print('  -d PATH           Datastore path')
-    print('  -l LEVEL          Log level (TRACE, DEBUG, INFO, SUCCESS, WARNING, ERROR, CRITICAL)')
-    print('  -c                Cleanup unused snapshots')
-    print('  -C                Create datastore directory if it doesn\'t exist')
-    print('  -P true/false     Set all watches paused (true) or active (false)')
-    print('')
-    print('Add URLs on startup:')
-    print('  -u URL            Add URL to watch (can be used multiple times)')
-    print('  -u0 \'JSON\'        Set options for first -u URL (e.g. \'{"processor":"text_json_diff"}\')')
-    print('  -u1 \'JSON\'        Set options for second -u URL (0-indexed)')
-    print('  -u2 \'JSON\'        Set options for third -u URL, etc.')
-    print('                    Available options: processor, fetch_backend, headers, method, etc.')
-    print('                    See model/Watch.py for all available options')
-    print('')
-    print('Recheck on startup:')
-    print('  -r all            Queue all watches for recheck on startup')
-    print('  -r UUID,...       Queue specific watches (comma-separated UUIDs)')
-    print('  -r all N          Queue all watches, wait for completion, repeat N times')
-    print('  -r UUID,... N     Queue specific watches, wait for completion, repeat N times')
-    print('')
-    print('Batch mode:')
-    print('  -b                Run in batch mode (process queue then exit)')
-    print('                    Useful for CI/CD, cron jobs, or one-time checks')
-    print('                    NOTE: Batch mode checks if Flask is running and aborts if port is in use')
-    print('                    Use -p PORT to specify a different port if needed')
-    print('')
-
 def main():
     global datastore
     global app
 
-    # Early help/version check before any initialization
-    if '--help' in sys.argv or '-help' in sys.argv:
-        print_help()
-        sys.exit(0)
-
-    if '--version' in sys.argv or '-v' in sys.argv:
-        print(f'changedetection.io {__version__}')
-        sys.exit(0)
-
-    # Import heavy modules after help/version checks to keep startup fast for those flags
-    from changedetectionio import store
-    from changedetectionio.flask_app import changedetection_app
-
     datastore_path = None
+    do_cleanup = False
+    # Optional URL to watch since start
+    default_url = None
     # Set a default logger level
     logger_level = 'DEBUG'
     include_default_watches = True
-    all_paused = None  # None means don't change, True/False to set
 
     host = os.environ.get("LISTEN_HOST", "0.0.0.0").strip()
     port = int(os.environ.get('PORT', 5000))
     ssl_mode = False
 
-    # Lists for multiple URLs and their options
-    urls_to_add = []
-    url_options = {}  # Key: index (0-based), Value: dict of options
-    recheck_watches = None  # None, 'all', or list of UUIDs
-    recheck_repeat_count = 1  # Number of times to repeat recheck cycle
-    batch_mode = False  # Run once then exit when queue is empty
-
     # On Windows, create and use a default path.
     if os.name == 'nt':
         datastore_path = os.path.expandvars(r'%APPDATA%\changedetection.io')
@@ -220,68 +144,10 @@ def main():
         # Must be absolute so that send_from_directory doesnt try to make it relative to backend/
         datastore_path = os.path.join(os.getcwd(), "../datastore")
 
-    # Pre-process arguments to extract -u, -u<N>, and -r options before getopt
-    # This allows unlimited -u0, -u1, -u2, ... options without predefining them
-    cleaned_argv = ['changedetection.py']  # Start with program name
-    i = 1
-    while i < len(sys.argv):
-        arg = sys.argv[i]
-
-        # Handle -u (add URL)
-        if arg == '-u' and i + 1 < len(sys.argv):
-            urls_to_add.append(sys.argv[i + 1])
-            i += 2
-            continue
-
-        # Handle -u<N> (set options for URL at index N)
-        if arg.startswith('-u') and len(arg) > 2 and arg[2:].isdigit():
-            idx = int(arg[2:])
-            if i + 1 < len(sys.argv):
-                try:
-                    import json
-                    url_options[idx] = json.loads(sys.argv[i + 1])
-                except json.JSONDecodeError as e:
-                    print(f'Error: Invalid JSON for {arg}: {sys.argv[i + 1]}')
-                    print(f'JSON decode error: {e}')
-                    sys.exit(2)
-                i += 2
-                continue
-
-        # Handle -r (recheck watches)
-        if arg == '-r' and i + 1 < len(sys.argv):
-            recheck_arg = sys.argv[i + 1]
-            if recheck_arg.lower() == 'all':
-                recheck_watches = 'all'
-            else:
-                # Parse comma-separated list of UUIDs
-                recheck_watches = [uuid.strip() for uuid in recheck_arg.split(',') if uuid.strip()]
-
-            # Check for optional repeat count as third argument
-            if i + 2 < len(sys.argv) and sys.argv[i + 2].isdigit():
-                recheck_repeat_count = int(sys.argv[i + 2])
-                if recheck_repeat_count < 1:
-                    print(f'Error: Repeat count must be at least 1, got {recheck_repeat_count}')
-                    sys.exit(2)
-                i += 3
-            else:
-                i += 2
-            continue
-
-        # Handle -b (batch mode - run once and exit)
-        if arg == '-b':
-            batch_mode = True
-            i += 1
-            continue
-
-        # Keep other arguments for getopt
-        cleaned_argv.append(arg)
-        i += 1
-
     try:
-        opts, args = getopt.getopt(cleaned_argv[1:], "6Csd:h:p:l:P:", "port")
-    except getopt.GetoptError as e:
-        print_help()
-        print(f'Error: {e}')
+        opts, args = getopt.getopt(sys.argv[1:], "6Ccsd:h:p:l:u:", "port")
+    except getopt.GetoptError:
+        print('backend.py -s SSL enable -h [host] -p [port] -d [datastore path] -u [default URL to watch] -l [debug level - TRACE, DEBUG(default), INFO, SUCCESS, WARNING, ERROR, CRITICAL]')
         sys.exit(2)
 
     create_datastore_dir = False
@@ -306,6 +172,14 @@ def main():
         if opt == '-d':
             datastore_path = arg
 
+        if opt == '-u':
+            default_url = arg
+            include_default_watches = False
+
+        # Cleanup (remove text files that arent in the index)
+        if opt == '-c':
+            do_cleanup = True
+
         # Create the datadir if it doesnt exist
         if opt == '-C':
             create_datastore_dir = True
@@ -313,18 +187,6 @@ def main():
         if opt == '-l':
             logger_level = int(arg) if arg.isdigit() else arg.upper()
 
-        if opt == '-P':
-            try:
-                all_paused = bool(strtobool(arg))
-            except ValueError:
-                print(f'Error: Invalid value for -P option: {arg}')
-                print('Expected: true, false, yes, no, 1, or 0')
-                sys.exit(2)
-
-    # If URLs are provided, don't include default watches
-    if urls_to_add:
-        include_default_watches = False
-
 
     logger.success(f"changedetection.io version {get_version()} starting.")
     # Launch using SocketIO run method for proper integration (if enabled)
@@ -361,16 +223,11 @@ def main():
     logging.getLogger('pyppeteer.connection.Connection').setLevel(logging.WARNING)
 
     # isnt there some @thingy to attach to each route to tell it, that this route needs a datastore
-    app_config = {
-        'datastore_path': datastore_path,
-        'batch_mode': batch_mode,
-        'recheck_watches': recheck_watches,
-        'recheck_repeat_count': recheck_repeat_count
-    }
+    app_config = {'datastore_path': datastore_path}
 
     if not os.path.isdir(app_config['datastore_path']):
         if create_datastore_dir:
-            os.makedirs(app_config['datastore_path'], exist_ok=True)
+            os.mkdir(app_config['datastore_path'])
         else:
             logger.critical(
                 f"ERROR: Directory path for the datastore '{app_config['datastore_path']}'"
@@ -385,219 +242,17 @@ def main():
         # Dont' start if the JSON DB looks corrupt
         logger.critical(f"ERROR: JSON DB or Proxy List JSON at '{app_config['datastore_path']}' appears to be corrupt, aborting.")
         logger.critical(str(e))
-        sys.exit(1)
-
-    # Testing mode: Exit cleanly after datastore initialization (for CI/CD upgrade tests)
-    if os.environ.get('TESTING_SHUTDOWN_AFTER_DATASTORE_LOAD'):
-        logger.success(f"TESTING MODE: Datastore loaded successfully from {app_config['datastore_path']}")
-        logger.success(f"TESTING MODE: Schema version: {datastore.data['settings']['application'].get('schema_version', 'unknown')}")
-        logger.success(f"TESTING MODE: Loaded {len(datastore.data['watching'])} watches")
-        logger.success("TESTING MODE: Exiting cleanly (TESTING_SHUTDOWN_AFTER_DATASTORE_LOAD is set)")
-        sys.exit(0)
-
-    # Apply all_paused setting if specified via CLI
-    if all_paused is not None:
-        datastore.data['settings']['application']['all_paused'] = all_paused
-        logger.info(f"Setting all watches paused: {all_paused}")
+        return
 
     # Inject datastore into plugins that need access to settings
     from changedetectionio.pluggy_interface import inject_datastore_into_plugins
     inject_datastore_into_plugins(datastore)
 
-    # Step 1: Add URLs with their options (if provided via -u flags)
-    added_watch_uuids = []
-    if urls_to_add:
-        logger.info(f"Adding {len(urls_to_add)} URL(s) from command line")
-        for idx, url in enumerate(urls_to_add):
-            extras = url_options.get(idx, {})
-            if extras:
-                logger.debug(f"Adding watch {idx}: {url} with options: {extras}")
-            else:
-                logger.debug(f"Adding watch {idx}: {url}")
-
-            new_uuid = datastore.add_watch(url=url, extras=extras)
-            if new_uuid:
-                added_watch_uuids.append(new_uuid)
-                logger.success(f"Added watch: {url} (UUID: {new_uuid})")
-            else:
-                logger.error(f"Failed to add watch: {url}")
+    if default_url:
+        datastore.add_watch(url = default_url)
 
     app = changedetection_app(app_config, datastore)
 
-    # Step 2: Queue newly added watches (if -u was provided in batch mode)
-    # This must happen AFTER app initialization so update_q is available
-    if batch_mode and added_watch_uuids:
-        from changedetectionio.flask_app import update_q
-        from changedetectionio import queuedWatchMetaData, worker_pool
-
-        logger.info(f"Batch mode: Queuing {len(added_watch_uuids)} newly added watches")
-        for watch_uuid in added_watch_uuids:
-            try:
-                worker_pool.queue_item_async_safe(
-                    update_q,
-                    queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid})
-                )
-                logger.debug(f"Queued newly added watch: {watch_uuid}")
-            except Exception as e:
-                logger.error(f"Failed to queue watch {watch_uuid}: {e}")
-
-    # Step 3: Queue watches for recheck (if -r was provided)
-    # This must happen AFTER app initialization so update_q is available
-    if recheck_watches is not None:
-        from changedetectionio.flask_app import update_q
-        from changedetectionio import queuedWatchMetaData, worker_pool
-
-        watches_to_queue = []
-        if recheck_watches == 'all':
-            # Queue all watches, excluding those already queued in batch mode
-            all_watches = list(datastore.data['watching'].keys())
-            if batch_mode and added_watch_uuids:
-                # Exclude newly added watches that were already queued in batch mode
-                watches_to_queue = [uuid for uuid in all_watches if uuid not in added_watch_uuids]
-                logger.info(f"Queuing {len(watches_to_queue)} existing watches for recheck ({len(added_watch_uuids)} newly added watches already queued)")
-            else:
-                watches_to_queue = all_watches
-                logger.info(f"Queuing all {len(watches_to_queue)} watches for recheck")
-        else:
-            # Queue specific UUIDs
-            watches_to_queue = recheck_watches
-            logger.info(f"Queuing {len(watches_to_queue)} specific watches for recheck")
-
-        queued_count = 0
-        for watch_uuid in watches_to_queue:
-            if watch_uuid in datastore.data['watching']:
-                try:
-                    worker_pool.queue_item_async_safe(
-                        update_q,
-                        queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid})
-                    )
-                    queued_count += 1
-                    logger.debug(f"Queued watch for recheck: {watch_uuid}")
-                except Exception as e:
-                    logger.error(f"Failed to queue watch {watch_uuid}: {e}")
-            else:
-                logger.warning(f"Watch UUID not found in datastore: {watch_uuid}")
-
-        logger.success(f"Successfully queued {queued_count} watches for recheck")
-
-    # Step 4: Setup batch mode monitor (if -b was provided)
-    if batch_mode:
-        from changedetectionio.flask_app import update_q
-
-        # Safety check: Ensure Flask app is not already running on this port
-        # Batch mode should never run alongside the web server
-        import socket
-        test_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
-
-        try:
-            # Try to bind to the configured host:port (no SO_REUSEADDR - strict check)
-            test_socket.bind((host, port))
-            test_socket.close()
-            logger.debug(f"Batch mode: Port {port} is available (Flask app not running)")
-        except OSError as e:
-            test_socket.close()
-            # errno 98 = EADDRINUSE (Linux)
-            # errno 48 = EADDRINUSE (macOS)
-            # errno 10048 = WSAEADDRINUSE (Windows)
-            if e.errno in (48, 98, 10048) or "Address already in use" in str(e) or "already in use" in str(e).lower():
-                logger.critical(f"ERROR: Batch mode cannot run - port {port} is already in use")
-                logger.critical(f"The Flask web server appears to be running on {host}:{port}")
-                logger.critical(f"Batch mode is designed for standalone operation (CI/CD, cron jobs, etc.)")
-                logger.critical(f"Please either stop the Flask web server, or use a different port with -p PORT")
-                sys.exit(1)
-            else:
-                # Some other socket error - log but continue (might be network configuration issue)
-                logger.warning(f"Port availability check failed with unexpected error: {e}")
-                logger.warning(f"Continuing with batch mode anyway - be aware of potential conflicts")
-
-        def queue_watches_for_recheck(datastore, iteration):
-            """Helper function to queue watches for recheck"""
-            watches_to_queue = []
-            if recheck_watches == 'all':
-                all_watches = list(datastore.data['watching'].keys())
-                if batch_mode and added_watch_uuids and iteration == 1:
-                    # Only exclude newly added watches on first iteration
-                    watches_to_queue = [uuid for uuid in all_watches if uuid not in added_watch_uuids]
-                else:
-                    watches_to_queue = all_watches
-                logger.info(f"Batch mode (iteration {iteration}): Queuing all {len(watches_to_queue)} watches")
-            elif recheck_watches:
-                watches_to_queue = recheck_watches
-                logger.info(f"Batch mode (iteration {iteration}): Queuing {len(watches_to_queue)} specific watches")
-
-            queued_count = 0
-            for watch_uuid in watches_to_queue:
-                if watch_uuid in datastore.data['watching']:
-                    try:
-                        worker_pool.queue_item_async_safe(
-                            update_q,
-                            queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid})
-                        )
-                        queued_count += 1
-                    except Exception as e:
-                        logger.error(f"Failed to queue watch {watch_uuid}: {e}")
-                else:
-                    logger.warning(f"Watch UUID not found in datastore: {watch_uuid}")
-            logger.success(f"Batch mode (iteration {iteration}): Successfully queued {queued_count} watches")
-            return queued_count
-
-        def batch_mode_monitor():
-            """Monitor queue and workers, shutdown or repeat when work is complete"""
-            import time
-
-            # Track iterations if repeat mode is enabled
-            current_iteration = 1
-            total_iterations = recheck_repeat_count if recheck_watches and recheck_repeat_count > 1 else 1
-
-            if total_iterations > 1:
-                logger.info(f"Batch mode: Will repeat recheck {total_iterations} times")
-            else:
-                logger.info("Batch mode: Waiting for all queued items to complete...")
-
-            # Wait a bit for workers to start processing
-            time.sleep(3)
-
-            try:
-                while current_iteration <= total_iterations:
-                    logger.info(f"Batch mode: Waiting for iteration {current_iteration}/{total_iterations} to complete...")
-
-                    # Use the shared wait_for_all_checks function
-                    completed = worker_pool.wait_for_all_checks(update_q, timeout=300)
-
-                    if not completed:
-                        logger.warning(f"Batch mode: Iteration {current_iteration} timed out after 300 seconds")
-
-                    logger.success(f"Batch mode: Iteration {current_iteration}/{total_iterations} completed")
-
-                    # Check if we need to repeat
-                    if current_iteration < total_iterations:
-                        logger.info(f"Batch mode: Starting iteration {current_iteration + 1}...")
-                        current_iteration += 1
-
-                        # Re-queue watches for next iteration
-                        queue_watches_for_recheck(datastore, current_iteration)
-
-                        # Brief pause before continuing
-                        time.sleep(2)
-                    else:
-                        # All iterations complete
-                        logger.success(f"Batch mode: All {total_iterations} iterations completed, initiating shutdown")
-                        # Trigger shutdown
-                        import os, signal
-                        os.kill(os.getpid(), signal.SIGTERM)
-                        return
-
-            except Exception as e:
-                logger.error(f"Batch mode monitor error: {e}")
-                logger.error(f"Initiating emergency shutdown")
-                import os, signal
-                os.kill(os.getpid(), signal.SIGTERM)
-
-        # Start monitor in background thread
-        monitor_thread = threading.Thread(target=batch_mode_monitor, daemon=True, name="BatchModeMonitor")
-        monitor_thread.start()
-        logger.info("Batch mode enabled: Will exit after all queued items are processed")
-
     # Get the SocketIO instance from the Flask app (created in flask_app.py)
     from changedetectionio.flask_app import socketio_server
     global socketio
@@ -619,17 +274,19 @@ def main():
     else:
         logger.info("SIGUSR1 handler only registered on Linux, skipped.")
 
+    # Go into cleanup mode
+    if do_cleanup:
+        datastore.remove_unused_snapshots()
+
     app.config['datastore_path'] = datastore_path
 
 
     @app.context_processor
     def inject_template_globals():
-        return dict(right_sticky="v"+__version__,
+        return dict(right_sticky="v{}".format(datastore.data['version_tag']),
                     new_version_available=app.config['NEW_VERSION_AVAILABLE'],
                     has_password=datastore.data['settings']['application']['password'] != False,
-                    socket_io_enabled=datastore.data['settings']['application'].get('ui', {}).get('socket_io_enabled', True),
-                    all_paused=datastore.data['settings']['application'].get('all_paused', False),
-                    all_muted=datastore.data['settings']['application'].get('all_muted', False)
+                    socket_io_enabled=datastore.data['settings']['application']['ui'].get('socket_io_enabled', True)
                     )
 
     # Monitored websites will not receive a Referer header when a user clicks on an outgoing link.
@@ -651,43 +308,23 @@ def main():
     if os.getenv('USE_X_SETTINGS'):
         logger.info("USE_X_SETTINGS is ENABLED")
         from werkzeug.middleware.proxy_fix import ProxyFix
-        app.wsgi_app = ProxyFix(
-            app.wsgi_app,
-            x_for=1,      # X-Forwarded-For (client IP)
-            x_proto=1,    # X-Forwarded-Proto (http/https)
-            x_host=1,     # X-Forwarded-Host (original host)
-            x_port=1,     # X-Forwarded-Port (original port)
-            x_prefix=1    # X-Forwarded-Prefix (URL prefix)
-        )
+        app.wsgi_app = ProxyFix(app.wsgi_app, x_prefix=1, x_host=1)
 
 
-    # In batch mode, skip starting the HTTP server - just keep workers running
-    if batch_mode:
-        logger.info("Batch mode: Skipping HTTP server startup, workers will process queue")
-        logger.info("Batch mode: Main thread will wait for shutdown signal")
-        # Keep main thread alive until batch monitor triggers shutdown
-        try:
-            while True:
-                time.sleep(1)
-        except KeyboardInterrupt:
-            logger.info("Batch mode: Keyboard interrupt received")
-            pass
-    else:
-        # Normal mode: Start HTTP server
-        # SocketIO instance is already initialized in flask_app.py
-        if socketio_server:
-            if ssl_mode:
-                logger.success(f"SSL mode enabled, attempting to start with '{ssl_cert_file}' and '{ssl_privkey_file}' in {os.getcwd()}")
-                socketio.run(app, host=host, port=int(port), debug=False,
-                             ssl_context=(ssl_cert_file, ssl_privkey_file), allow_unsafe_werkzeug=True)
-            else:
-                socketio.run(app, host=host, port=int(port), debug=False, allow_unsafe_werkzeug=True)
+    # SocketIO instance is already initialized in flask_app.py
+    if socketio_server:
+        if ssl_mode:
+            logger.success(f"SSL mode enabled, attempting to start with '{ssl_cert_file}' and '{ssl_privkey_file}' in {os.getcwd()}")
+            socketio.run(app, host=host, port=int(port), debug=False,
+                         ssl_context=(ssl_cert_file, ssl_privkey_file), allow_unsafe_werkzeug=True)
         else:
-            # Run Flask app without Socket.IO if disabled
-            logger.info("Starting Flask app without Socket.IO server")
-            if ssl_mode:
-                logger.success(f"SSL mode enabled, attempting to start with '{ssl_cert_file}' and '{ssl_privkey_file}' in {os.getcwd()}")
-                app.run(host=host, port=int(port), debug=False,
-                        ssl_context=(ssl_cert_file, ssl_privkey_file))
-            else:
-                app.run(host=host, port=int(port), debug=False)
+            socketio.run(app, host=host, port=int(port), debug=False, allow_unsafe_werkzeug=True)
+    else:
+        # Run Flask app without Socket.IO if disabled
+        logger.info("Starting Flask app without Socket.IO server")
+        if ssl_mode:
+            logger.success(f"SSL mode enabled, attempting to start with '{ssl_cert_file}' and '{ssl_privkey_file}' in {os.getcwd()}")
+            app.run(host=host, port=int(port), debug=False,
+                    ssl_context=(ssl_cert_file, ssl_privkey_file))
+        else:
+            app.run(host=host, port=int(port), debug=False)

changedetectionio/api/Import.py

@@ -4,10 +4,6 @@ from flask import request
 from functools import wraps
 from . import auth, validate_openapi_request
 from ..validate_url import is_safe_valid_url
-import json
-
-# Number of URLs above which import switches to background processing
-IMPORT_SWITCH_TO_BACKGROUND_THRESHOLD = 20
 
 
 def default_content_type(content_type='text/plain'):
@@ -23,76 +19,6 @@ def default_content_type(content_type='text/plain'):
     return decorator
 
 
-def convert_query_param_to_type(value, schema_property):
-    """
-    Convert a query parameter string to the appropriate type based on schema definition.
-
-    Args:
-        value: String value from query parameter
-        schema_property: Schema property definition with 'type' or 'anyOf' field
-
-    Returns:
-        Converted value in the appropriate type
-
-    Supports both OpenAPI 3.1 formats:
-    - type: [string, 'null']  (array format)
-    - anyOf: [{type: string}, {type: null}]  (anyOf format)
-    """
-    prop_type = schema_property.get('type')
-
-    # Handle OpenAPI 3.1 type arrays: type: [string, 'null']
-    if isinstance(prop_type, list):
-        # Use the first non-null type from the array
-        for t in prop_type:
-            if t != 'null':
-                prop_type = t
-                break
-        else:
-            prop_type = None
-
-    # Handle anyOf schemas (older format)
-    elif 'anyOf' in schema_property:
-        # Use the first non-null type from anyOf
-        for option in schema_property['anyOf']:
-            if option.get('type') and option.get('type') != 'null':
-                prop_type = option.get('type')
-                break
-        else:
-            prop_type = None
-
-    # Handle array type (e.g., notification_urls)
-    if prop_type == 'array':
-        # Support both comma-separated and JSON array format
-        if value.startswith('['):
-            try:
-                return json.loads(value)
-            except json.JSONDecodeError:
-                return [v.strip() for v in value.split(',')]
-        return [v.strip() for v in value.split(',')]
-
-    # Handle object type (e.g., time_between_check, headers)
-    elif prop_type == 'object':
-        try:
-            return json.loads(value)
-        except json.JSONDecodeError:
-            raise ValueError(f"Invalid JSON object for field: {value}")
-
-    # Handle boolean type
-    elif prop_type == 'boolean':
-        return strtobool(value)
-
-    # Handle integer type
-    elif prop_type == 'integer':
-        return int(value)
-
-    # Handle number type (float)
-    elif prop_type == 'number':
-        return float(value)
-
-    # Default: return as string
-    return value
-
-
 class Import(Resource):
     def __init__(self, **kwargs):
         # datastore is a black box dependency
@@ -102,135 +28,40 @@ class Import(Resource):
     @default_content_type('text/plain') #3547 #3542
     @validate_openapi_request('importWatches')
     def post(self):
-        """Import a list of watched URLs with optional watch configuration."""
-        from . import get_watch_schema_properties
-        # Special parameters that are NOT watch configuration
-        special_params = {'tag', 'tag_uuids', 'dedupe', 'proxy'}
+        """Import a list of watched URLs."""
 
         extras = {}
 
-        # Handle special 'proxy' parameter
         if request.args.get('proxy'):
             plist = self.datastore.proxy_list
             if not request.args.get('proxy') in plist:
-                proxy_list_str = ', '.join(plist) if plist else 'none configured'
-                return f"Invalid proxy choice, currently supported proxies are '{proxy_list_str}'", 400
+                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
             else:
                 extras['proxy'] = request.args.get('proxy')
 
-        # Handle special 'dedupe' parameter
         dedupe = strtobool(request.args.get('dedupe', 'true'))
 
-        # Handle special 'tag' and 'tag_uuids' parameters
         tags = request.args.get('tag')
         tag_uuids = request.args.get('tag_uuids')
 
         if tag_uuids:
             tag_uuids = tag_uuids.split(',')
 
-        # Extract ALL other query parameters as watch configuration
-        # Get schema from OpenAPI spec (replaces old schema_create_watch)
-        schema_properties = get_watch_schema_properties()
-        for param_name, param_value in request.args.items():
-            # Skip special parameters
-            if param_name in special_params:
-                continue
-
-            # Skip if not in schema (unknown parameter)
-            if param_name not in schema_properties:
-                return f"Unknown watch configuration parameter: {param_name}", 400
-
-            # Convert to appropriate type based on schema
-            try:
-                converted_value = convert_query_param_to_type(param_value, schema_properties[param_name])
-                extras[param_name] = converted_value
-            except (ValueError, json.JSONDecodeError) as e:
-                return f"Invalid value for parameter '{param_name}': {str(e)}", 400
-
-        # Validate processor if provided
-        if 'processor' in extras:
-            from changedetectionio.processors import available_processors
-            available = [p[0] for p in available_processors()]
-            if extras['processor'] not in available:
-                return f"Invalid processor '{extras['processor']}'. Available processors: {', '.join(available)}", 400
-
-        # Validate fetch_backend if provided (legacy API compat — still accepted, stored as-is)
-        if 'fetch_backend' in extras:
-            from changedetectionio.content_fetchers import available_fetchers
-            available = [f[0] for f in available_fetchers()]
-            is_valid = (
-                extras['fetch_backend'] == 'system' or
-                extras['fetch_backend'] in available or
-                extras['fetch_backend'].startswith('extra_browser_')
-            )
-            if not is_valid:
-                return f"Invalid fetch_backend '{extras['fetch_backend']}'. Available: system, {', '.join(available)}", 400
-
-        # Validate browser_profile if provided
-        if 'browser_profile' in extras:
-            from changedetectionio.model.browser_profile import get_builtin_profiles, RESERVED_MACHINE_NAMES
-            store_profiles = self.datastore.data['settings']['application'].get('browser_profiles', {})
-            known = set(get_builtin_profiles().keys()) | set(store_profiles.keys()) | {'system', None}
-            if extras['browser_profile'] not in known:
-                return f"Invalid browser_profile '{extras['browser_profile']}'. Available: {', '.join(str(k) for k in known)}", 400
-
-        # Validate notification_urls if provided
-        if 'notification_urls' in extras:
-            from wtforms import ValidationError
-            from changedetectionio.api.Notifications import validate_notification_urls
-            try:
-                validate_notification_urls(extras['notification_urls'])
-            except ValidationError as e:
-                return f"Invalid notification_urls: {str(e)}", 400
-
         urls = request.get_data().decode('utf8').splitlines()
-        # Clean and validate URLs upfront
-        urls_to_import = []
+        added = []
         for url in urls:
             url = url.strip()
             if not len(url):
                 continue
 
-            # Validate URL
+            # If hosts that only contain alphanumerics are allowed ("localhost" for example)
             if not is_safe_valid_url(url):
                 return f"Invalid or unsupported URL - {url}", 400
 
-            # Check for duplicates if dedupe is enabled
             if dedupe and self.datastore.url_exists(url):
                 continue
 
-            urls_to_import.append(url)
+            new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags, tag_uuids=tag_uuids)
+            added.append(new_uuid)
 
-        # For small imports, process synchronously for immediate feedback
-        if len(urls_to_import) < IMPORT_SWITCH_TO_BACKGROUND_THRESHOLD:
-            added = []
-            for url in urls_to_import:
-                new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags, tag_uuids=tag_uuids)
-                added.append(new_uuid)
-            return added, 200
-
-        # For large imports (>= 20), process in background thread
-        else:
-            import threading
-            from loguru import logger
-
-            def import_watches_background():
-                """Background thread to import watches - discarded after completion."""
-                try:
-                    added_count = 0
-                    for url in urls_to_import:
-                        try:
-                            self.datastore.add_watch(url=url, extras=extras, tag=tags, tag_uuids=tag_uuids)
-                            added_count += 1
-                        except Exception as e:
-                            logger.error(f"Error importing URL {url}: {e}")
-
-                    logger.info(f"Background import complete: {added_count} watches created")
-                except Exception as e:
-                    logger.error(f"Error in background import: {e}")
-
-            # Start background thread and return immediately
-            thread = threading.Thread(target=import_watches_background, daemon=True, name="ImportWatches-Background")
-            thread.start()
-
-            return {'status': f'Importing {len(urls_to_import)} URLs in background', 'count': len(urls_to_import)}, 202
+        return added

changedetectionio/api/Notifications.py

@@ -1,6 +1,8 @@
+from flask_expects_json import expects_json
 from flask_restful import Resource, abort
 from flask import request
 from . import auth, validate_openapi_request
+from . import schema_create_notification_urls, schema_delete_notification_urls
 
 class Notifications(Resource):
     def __init__(self, **kwargs):
@@ -20,6 +22,7 @@ class Notifications(Resource):
     
     @auth.check_token
     @validate_openapi_request('addNotifications')
+    @expects_json(schema_create_notification_urls)
     def post(self):
         """Create Notification URLs."""
 
@@ -47,6 +50,7 @@ class Notifications(Resource):
     
     @auth.check_token
     @validate_openapi_request('replaceNotifications')
+    @expects_json(schema_create_notification_urls)
     def put(self):
         """Replace Notification URLs."""
         json_data = request.get_json()
@@ -63,12 +67,13 @@ class Notifications(Resource):
 
         clean_urls = [url.strip() for url in notification_urls if isinstance(url, str)]
         self.datastore.data['settings']['application']['notification_urls'] = clean_urls
-        self.datastore.commit()
+        self.datastore.needs_write = True
 
         return {'notification_urls': clean_urls}, 200
         
     @auth.check_token
     @validate_openapi_request('deleteNotifications')
+    @expects_json(schema_delete_notification_urls)
     def delete(self):
         """Delete Notification URLs."""
 
@@ -90,7 +95,7 @@ class Notifications(Resource):
             abort(400, message="No matching notification URLs found.")
 
         self.datastore.data['settings']['application']['notification_urls'] = notification_urls
-        self.datastore.commit()
+        self.datastore.needs_write = True
 
         return 'OK', 204
     

changedetectionio/api/Spec.py

@@ -1,21 +0,0 @@
-import functools
-from flask import make_response
-from flask_restful import Resource
-
-
-@functools.cache
-def _get_spec_yaml():
-    """Build and cache the merged spec as a YAML string (only serialized once per process)."""
-    import yaml
-    from changedetectionio.api import build_merged_spec_dict
-    return yaml.dump(build_merged_spec_dict(), default_flow_style=False, allow_unicode=True)
-
-
-class Spec(Resource):
-    def get(self):
-        """Return the merged OpenAPI spec including all registered processor extensions."""
-        return make_response(
-            _get_spec_yaml(),
-            200,
-            {'Content-Type': 'application/yaml'}
-        )

changedetectionio/api/Tags.py

@@ -1,13 +1,13 @@
 from changedetectionio import queuedWatchMetaData
-from changedetectionio import worker_pool
+from changedetectionio import worker_handler
+from flask_expects_json import expects_json
 from flask_restful import abort, Resource
-from loguru import logger
 
-import threading
 from flask import request
 from . import auth
 
-from . import validate_openapi_request
+# Import schemas from __init__.py
+from . import schema_tag, schema_create_tag, schema_update_tag, validate_openapi_request
 
 
 class Tag(Resource):
@@ -17,78 +17,38 @@ class Tag(Resource):
         self.update_q = kwargs['update_q']
 
     # Get information about a single tag
-    # curl http://localhost:5000/api/v1/tag/<uuid_str:uuid>
+    # curl http://localhost:5000/api/v1/tag/<string:uuid>
     @auth.check_token
     @validate_openapi_request('getTag')
     def get(self, uuid):
         """Get data for a single tag/group, toggle notification muting, or recheck all."""
-        tag = self.datastore.data['settings']['application']['tags'].get(uuid)
+        from copy import deepcopy
+        tag = deepcopy(self.datastore.data['settings']['application']['tags'].get(uuid))
         if not tag:
             abort(404, message=f'No tag exists with the UUID of {uuid}')
 
         if request.args.get('recheck'):
-            # Recheck all watches with this tag, including muted
-            # First collect watches to queue
-            watches_to_queue = []
+            # Recheck all, including muted
+            # Get most overdue first
+            i=0
             for k in sorted(self.datastore.data['watching'].items(), key=lambda item: item[1].get('last_checked', 0)):
                 watch_uuid = k[0]
                 watch = k[1]
-                if not watch['paused'] and tag['uuid'] in watch['tags']:
-                    watches_to_queue.append(watch_uuid)
+                if not watch['paused'] and tag['uuid'] not in watch['tags']:
+                    continue
+                worker_handler.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
+                i+=1
 
-            # If less than 20 watches, queue synchronously for immediate feedback
-            if len(watches_to_queue) < 20:
-                for watch_uuid in watches_to_queue:
-                    worker_pool.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
-                return {'status': f'OK, queued {len(watches_to_queue)} watches for rechecking'}, 200
-            else:
-                # 20+ watches - queue in background thread to avoid blocking API response
-                def queue_watches_background():
-                    """Background thread to queue watches - discarded after completion."""
-                    try:
-                        for watch_uuid in watches_to_queue:
-                            worker_pool.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
-                        logger.info(f"Background queueing complete for tag {tag['uuid']}: {len(watches_to_queue)} watches queued")
-                    except Exception as e:
-                        logger.error(f"Error in background queueing for tag {tag['uuid']}: {e}")
-
-                # Start background thread and return immediately
-                thread = threading.Thread(target=queue_watches_background, daemon=True, name=f"QueueTag-{tag['uuid'][:8]}")
-                thread.start()
-
-                return {'status': f'OK, queueing {len(watches_to_queue)} watches in background'}, 202
+            return f"OK, {i} watches queued", 200
 
         if request.args.get('muted', '') == 'muted':
-            tag['notification_muted'] = True
-            tag.commit()
+            self.datastore.data['settings']['application']['tags'][uuid]['notification_muted'] = True
             return "OK", 200
         elif request.args.get('muted', '') == 'unmuted':
-            tag['notification_muted'] = False
-            tag.commit()
+            self.datastore.data['settings']['application']['tags'][uuid]['notification_muted'] = False
             return "OK", 200
 
-        # Filter out Watch-specific runtime fields that don't apply to Tags (yet)
-        # TODO: Future enhancement - aggregate these values from all Watches that have this tag:
-        #   - check_count: sum of all watches' check_count
-        #   - last_checked: most recent last_checked from all watches
-        #   - last_changed: most recent last_changed from all watches
-        #   - consecutive_filter_failures: count of watches with failures
-        #   - etc.
-        # These come from watch_base inheritance but currently have no meaningful value for Tags
-        watch_only_fields = {
-            'browser_steps_last_error_step', 'check_count', 'consecutive_filter_failures',
-            'content-type', 'fetch_time', 'last_changed', 'last_checked', 'last_error',
-            'last_notification_error', 'last_viewed', 'notification_alert_count',
-            'page_title', 'previous_md5', 'remote_server_reply'
-        }
-
-        # Create clean tag dict without Watch-specific fields
-        clean_tag = {k: v for k, v in tag.items() if k not in watch_only_fields}
-
-        # fetch_backend is a legacy field superseded by browser_profile — omit from API response
-        clean_tag.pop('fetch_backend', None)
-
-        return clean_tag
+        return tag
 
     @auth.check_token
     @validate_openapi_request('deleteTag')
@@ -99,94 +59,41 @@ class Tag(Resource):
 
         # Delete the tag, and any tag reference
         del self.datastore.data['settings']['application']['tags'][uuid]
-
+        
         # Remove tag from all watches
         for watch_uuid, watch in self.datastore.data['watching'].items():
             if watch.get('tags') and uuid in watch['tags']:
                 watch['tags'].remove(uuid)
-                watch.commit()
 
         return 'OK', 204
 
     @auth.check_token
     @validate_openapi_request('updateTag')
+    @expects_json(schema_update_tag)
     def put(self, uuid):
         """Update tag information."""
         tag = self.datastore.data['settings']['application']['tags'].get(uuid)
         if not tag:
             abort(404, message='No tag exists with the UUID of {}'.format(uuid))
 
-        # Make a mutable copy of request.json for modification
-        json_data = dict(request.json)
-
-        # Validate notification_urls if provided
-        if 'notification_urls' in json_data:
-            from wtforms import ValidationError
-            from changedetectionio.api.Notifications import validate_notification_urls
-            try:
-                notification_urls = json_data.get('notification_urls', [])
-                validate_notification_urls(notification_urls)
-            except ValidationError as e:
-                return str(e), 400
-
-        # Filter out readOnly fields (extracted from OpenAPI spec Tag schema)
-        # These are system-managed fields that should never be user-settable
-        from . import get_readonly_tag_fields
-        readonly_fields = get_readonly_tag_fields()
-
-        # Tag model inherits from watch_base but has no @property attributes of its own
-        # So we only need to filter readOnly fields
-        for field in readonly_fields:
-            json_data.pop(field, None)
-
-        # Validate remaining fields - reject truly unknown fields
-        # Get valid fields from Tag schema
-        from . import get_tag_schema_properties
-        valid_fields = set(get_tag_schema_properties().keys())
-
-        # Check for unknown fields
-        unknown_fields = set(json_data.keys()) - valid_fields
-        if unknown_fields:
-            return f"Unknown field(s): {', '.join(sorted(unknown_fields))}", 400
-
-        tag.update(json_data)
-        tag.commit()
-
-        # Clear checksums for all watches using this tag to force reprocessing
-        # Tag changes affect inherited configuration
-        cleared_count = self.datastore.clear_checksums_for_tag(uuid)
-        logger.info(f"Tag {uuid} updated via API, cleared {cleared_count} watch checksums")
+        tag.update(request.json)
+        self.datastore.needs_write_urgent = True
 
         return "OK", 200
 
 
     @auth.check_token
     @validate_openapi_request('createTag')
+    # Only cares for {'title': 'xxxx'}
     def post(self):
         """Create a single tag/group."""
 
         json_data = request.get_json()
         title = json_data.get("title",'').strip()
 
-        # Validate that only valid fields are provided
-        # Get valid fields from Tag schema
-        from . import get_tag_schema_properties
-        valid_fields = set(get_tag_schema_properties().keys())
-
-        # Check for unknown fields
-        unknown_fields = set(json_data.keys()) - valid_fields
-        if unknown_fields:
-            return f"Unknown field(s): {', '.join(sorted(unknown_fields))}", 400
 
         new_uuid = self.datastore.add_tag(title=title)
         if new_uuid:
-            # Apply any extra fields (e.g. processor_config_restock_diff) beyond just title
-            extra = {k: v for k, v in json_data.items() if k != 'title'}
-            if extra:
-                tag = self.datastore.data['settings']['application']['tags'].get(new_uuid)
-                if tag:
-                    tag.update(extra)
-                    tag.commit()
             return {'uuid': new_uuid}, 201
         else:
             return "Invalid or unsupported tag", 400

changedetectionio/api/Watch.py

@@ -1,18 +1,18 @@
 import os
-import threading
 
 from changedetectionio.validate_url import is_safe_valid_url
-from changedetectionio.favicon_utils import get_favicon_mime_type
 
 from . import auth
 from changedetectionio import queuedWatchMetaData, strtobool
-from changedetectionio import worker_pool
+from changedetectionio import worker_handler
 from flask import request, make_response, send_from_directory
+from flask_expects_json import expects_json
 from flask_restful import abort, Resource
 from loguru import logger
 import copy
 
-from . import validate_openapi_request, get_readonly_watch_fields
+# Import schemas from __init__.py
+from . import schema, schema_create_watch, schema_update_watch, validate_openapi_request
 from ..notification import valid_notification_formats
 from ..notification.handler import newline_re
 
@@ -57,56 +57,41 @@ class Watch(Resource):
         self.update_q = kwargs['update_q']
 
     # Get information about a single watch, excluding the history list (can be large)
-    # curl http://localhost:5000/api/v1/watch/<uuid_str:uuid>
+    # curl http://localhost:5000/api/v1/watch/<string:uuid>
     # @todo - version2 - ?muted and ?paused should be able to be called together, return the watch struct not "OK"
     # ?recheck=true
     @auth.check_token
     @validate_openapi_request('getWatch')
     def get(self, uuid):
         """Get information about a single watch, recheck, pause, or mute."""
-        # Get watch reference first (for pause/mute operations)
-        watch_obj = self.datastore.data['watching'].get(uuid)
-        if not watch_obj:
+        from copy import deepcopy
+        watch = deepcopy(self.datastore.data['watching'].get(uuid))
+        if not watch:
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
 
-        # Create a dict copy for JSON response (with lock for thread safety)
-        # This is much faster than deepcopy and doesn't copy the datastore reference
-        # WARNING: dict() is a SHALLOW copy - nested dicts are shared with original!
-        # Only safe because we only ADD scalar properties (line 97-101), never modify nested dicts
-        # If you need to modify nested dicts, use: from copy import deepcopy; watch = deepcopy(dict(watch_obj))
-        with self.datastore.lock:
-            watch = dict(watch_obj)
-
         if request.args.get('recheck'):
-            worker_pool.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+            worker_handler.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             return "OK", 200
         if request.args.get('paused', '') == 'paused':
-            watch_obj.pause()
-            watch_obj.commit()
+            self.datastore.data['watching'].get(uuid).pause()
             return "OK", 200
         elif request.args.get('paused', '') == 'unpaused':
-            watch_obj.unpause()
-            watch_obj.commit()
+            self.datastore.data['watching'].get(uuid).unpause()
             return "OK", 200
         if request.args.get('muted', '') == 'muted':
-            watch_obj.mute()
-            watch_obj.commit()
+            self.datastore.data['watching'].get(uuid).mute()
             return "OK", 200
         elif request.args.get('muted', '') == 'unmuted':
-            watch_obj.unmute()
-            watch_obj.commit()
+            self.datastore.data['watching'].get(uuid).unmute()
             return "OK", 200
 
         # Return without history, get that via another API call
         # Properties are not returned as a JSON, so add the required props manually
-        watch['history_n'] = watch_obj.history_n
+        watch['history_n'] = watch.history_n
         # attr .last_changed will check for the last written text snapshot on change
-        watch['last_changed'] = watch_obj.last_changed
-        watch['viewed'] = watch_obj.viewed
-        watch['link'] = watch_obj.link,
-
-        # fetch_backend is a legacy field superseded by browser_profile — omit from API response
-        watch.pop('fetch_backend', None)
+        watch['last_changed'] = watch.last_changed
+        watch['viewed'] = watch.viewed
+        watch['link'] = watch.link,
 
         return watch
 
@@ -122,6 +107,7 @@ class Watch(Resource):
 
     @auth.check_token
     @validate_openapi_request('updateWatch')
+    @expects_json(schema_update_watch)
     def put(self, uuid):
         """Update watch information."""
         watch = self.datastore.data['watching'].get(uuid)
@@ -130,86 +116,72 @@ class Watch(Resource):
 
         if request.json.get('proxy'):
             plist = self.datastore.proxy_list
-            if not plist or request.json.get('proxy') not in plist:
-                proxy_list_str = ', '.join(plist) if plist else 'none configured'
-                return f"Invalid proxy choice, currently supported proxies are '{proxy_list_str}'", 400
+            if not request.json.get('proxy') in plist:
+                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
 
         # Validate time_between_check when not using defaults
         validation_error = validate_time_between_check_required(request.json)
         if validation_error:
             return validation_error, 400
 
-        # Validate notification_urls if provided
-        if 'notification_urls' in request.json:
-            from wtforms import ValidationError
-            from changedetectionio.api.Notifications import validate_notification_urls
-            try:
-                notification_urls = request.json.get('notification_urls', [])
-                validate_notification_urls(notification_urls)
-            except ValidationError as e:
-                return str(e), 400
-
-        # XSS etc protection - validate URL if it's being updated
-        if 'url' in request.json:
-            new_url = request.json.get('url')
-
-            # URL must be a non-empty string
-            if new_url is None:
-                return "URL cannot be null", 400
-
-            if not isinstance(new_url, str):
-                return "URL must be a string", 400
-
-            if not new_url.strip():
-                return "URL cannot be empty or whitespace only", 400
-
-            if not is_safe_valid_url(new_url.strip()):
-                return "Invalid or unsupported URL format. URL must use http://, https://, or ftp:// protocol", 400
+        # XSS etc protection
+        if request.json.get('url') and not is_safe_valid_url(request.json.get('url')):
+            return "Invalid URL", 400
 
         # Handle processor-config-* fields separately (save to JSON, not datastore)
         from changedetectionio import processors
+        processor_config_data = {}
+        regular_data = {}
 
-        # Make a mutable copy of request.json for modification
-        json_data = dict(request.json)
-
-        # Extract and remove processor config fields from json_data
-        processor_config_data = processors.extract_processor_config_from_form_data(json_data)
-
-        # Filter out readOnly fields (extracted from OpenAPI spec Watch schema)
-        # These are system-managed fields that should never be user-settable
-        readonly_fields = get_readonly_watch_fields()
-
-        # Also filter out @property attributes (computed/derived values from the model)
-        # These are not stored and should be ignored in PUT requests
-        from changedetectionio.model.Watch import model as WatchModel
-        property_fields = WatchModel.get_property_names()
-
-        # Combine both sets of fields to ignore
-        fields_to_ignore = readonly_fields | property_fields
-
-        # Remove all ignored fields from update data
-        for field in fields_to_ignore:
-            json_data.pop(field, None)
-
-        # Validate remaining fields - reject truly unknown fields
-        # Get valid fields from WatchBase schema
-        from . import get_watch_schema_properties
-        valid_fields = set(get_watch_schema_properties().keys())
-
-        # Also allow last_viewed (explicitly defined in UpdateWatch schema)
-        valid_fields.add('last_viewed')
-
-        # Check for unknown fields
-        unknown_fields = set(json_data.keys()) - valid_fields
-        if unknown_fields:
-            return f"Unknown field(s): {', '.join(sorted(unknown_fields))}", 400
+        for key, value in request.json.items():
+            if key.startswith('processor_config_'):
+                config_key = key.replace('processor_config_', '')
+                if value:  # Only save non-empty values
+                    processor_config_data[config_key] = value
+            else:
+                regular_data[key] = value
 
         # Update watch with regular (non-processor-config) fields
-        watch.update(json_data)
-        watch.commit()
+        watch.update(regular_data)
 
-        # Save processor config to JSON file
-        processors.save_processor_config(self.datastore, uuid, processor_config_data)
+        # Save processor config to JSON file if any config data exists
+        if processor_config_data:
+            try:
+                processor_name = request.json.get('processor', watch.get('processor'))
+                if processor_name:
+                    # Create a processor instance to access config methods
+                    from changedetectionio.processors import difference_detection_processor
+                    processor_instance = difference_detection_processor(self.datastore, uuid)
+                    # Use processor name as filename so each processor keeps its own config
+                    config_filename = f'{processor_name}.json'
+                    processor_instance.update_extra_watch_config(config_filename, processor_config_data)
+                    logger.debug(f"API: Saved processor config to {config_filename}: {processor_config_data}")
+
+                    # Call optional edit_hook if processor has one
+                    try:
+                        import importlib
+                        edit_hook_module_name = f'changedetectionio.processors.{processor_name}.edit_hook'
+
+                        try:
+                            edit_hook = importlib.import_module(edit_hook_module_name)
+                            logger.debug(f"API: Found edit_hook module for {processor_name}")
+
+                            if hasattr(edit_hook, 'on_config_save'):
+                                logger.info(f"API: Calling edit_hook.on_config_save for {processor_name}")
+                                # Call hook and get updated config
+                                updated_config = edit_hook.on_config_save(watch, processor_config_data, self.datastore)
+                                # Save updated config back to file
+                                processor_instance.update_extra_watch_config(config_filename, updated_config)
+                                logger.info(f"API: Edit hook updated config: {updated_config}")
+                            else:
+                                logger.debug(f"API: Edit hook module found but no on_config_save function")
+                        except ModuleNotFoundError:
+                            logger.debug(f"API: No edit_hook module for processor {processor_name} (this is normal)")
+                    except Exception as hook_error:
+                        logger.error(f"API: Edit hook error (non-fatal): {hook_error}", exc_info=True)
+
+            except Exception as e:
+                logger.error(f"API: Failed to save processor config: {e}")
 
         return "OK", 200
 
@@ -220,7 +192,7 @@ class WatchHistory(Resource):
         self.datastore = kwargs['datastore']
 
     # Get a list of available history for a watch by UUID
-    # curl http://localhost:5000/api/v1/watch/<uuid_str:uuid>/history
+    # curl http://localhost:5000/api/v1/watch/<string:uuid>/history
     @auth.check_token
     @validate_openapi_request('getWatchHistory')
     def get(self, uuid):
@@ -250,10 +222,6 @@ class WatchSingleHistory(Resource):
         if timestamp == 'latest':
             timestamp = list(watch.history.keys())[-1]
 
-        # Validate that the timestamp exists in history
-        if timestamp not in watch.history:
-            abort(404, message=f"No history snapshot found for timestamp '{timestamp}'")
-
         if request.args.get('html'):
             content = watch.get_fetched_html(timestamp)
             if content:
@@ -334,28 +302,18 @@ class WatchHistoryDiff(Resource):
         from_version_file_contents = watch.get_history_snapshot(from_timestamp)
         to_version_file_contents = watch.get_history_snapshot(to_timestamp)
 
-        # Get diff preferences from query parameters (matching UI preferences in DIFF_PREFERENCES_CONFIG)
-        # Support both 'type' (UI parameter) and 'word_diff' (API parameter) for backward compatibility
-        diff_type = request.args.get('type', 'diffLines')
-        if diff_type == 'diffWords':
-            word_diff = True
+        # Get diff preferences (using defaults similar to the existing code)
+        diff_prefs = {
+            'diff_ignoreWhitespace': False,
+            'diff_changesOnly': True
+        }
 
-        # Get boolean diff preferences with defaults from DIFF_PREFERENCES_CONFIG
-        changes_only = strtobool(request.args.get('changesOnly', 'false'))
-        ignore_whitespace = strtobool(request.args.get('ignoreWhitespace', 'false'))
-        include_removed = strtobool(request.args.get('removed', 'true'))
-        include_added = strtobool(request.args.get('added', 'true'))
-        include_replaced = strtobool(request.args.get('replaced', 'true'))
-
-        # Generate the diff with all preferences
+        # Generate the diff
         content = diff.render_diff(
             previous_version_file_contents=from_version_file_contents,
             newest_version_file_contents=to_version_file_contents,
-            ignore_junk=ignore_whitespace,
-            include_equal=not changes_only,
-            include_removed=include_removed,
-            include_added=include_added,
-            include_replaced=include_replaced,
+            ignore_junk=diff_prefs.get('diff_ignoreWhitespace'),
+            include_equal=not diff_prefs.get('diff_changesOnly'),
             word_diff=word_diff,
         )
 
@@ -402,11 +360,18 @@ class WatchFavicon(Resource):
 
         favicon_filename = watch.get_favicon_filename()
         if favicon_filename:
-            # Use cached MIME type detection
-            filepath = os.path.join(watch.data_dir, favicon_filename)
-            mime = get_favicon_mime_type(filepath)
+            try:
+                import magic
+                mime = magic.from_file(
+                    os.path.join(watch.watch_data_dir, favicon_filename),
+                    mime=True
+                )
+            except ImportError:
+                # Fallback, no python-magic
+                import mimetypes
+                mime, encoding = mimetypes.guess_type(favicon_filename)
 
-            response = make_response(send_from_directory(watch.data_dir, favicon_filename))
+            response = make_response(send_from_directory(watch.watch_data_dir, favicon_filename))
             response.headers['Content-type'] = mime
             response.headers['Cache-Control'] = 'max-age=300, must-revalidate'  # Cache for 5 minutes, then revalidate
             return response
@@ -422,6 +387,7 @@ class CreateWatch(Resource):
 
     @auth.check_token
     @validate_openapi_request('createWatch')
+    @expects_json(schema_create_watch)
     def post(self):
         """Create a single watch."""
 
@@ -433,33 +399,16 @@ class CreateWatch(Resource):
 
         if json_data.get('proxy'):
             plist = self.datastore.proxy_list
-            if not plist or json_data.get('proxy') not in plist:
-                proxy_list_str = ', '.join(plist) if plist else 'none configured'
-                return f"Invalid proxy choice, currently supported proxies are '{proxy_list_str}'", 400
+            if not json_data.get('proxy') in plist:
+                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
 
         # Validate time_between_check when not using defaults
         validation_error = validate_time_between_check_required(json_data)
         if validation_error:
             return validation_error, 400
 
-        # Validate notification_urls if provided
-        if 'notification_urls' in json_data:
-            from wtforms import ValidationError
-            from changedetectionio.api.Notifications import validate_notification_urls
-            try:
-                notification_urls = json_data.get('notification_urls', [])
-                validate_notification_urls(notification_urls)
-            except ValidationError as e:
-                return str(e), 400
-
-        # Handle processor-config-* fields separately (save to JSON, not watch)
-        from changedetectionio import processors
-
         extras = copy.deepcopy(json_data)
 
-        # Extract and remove processor config fields from extras
-        processor_config_data = processors.extract_processor_config_from_form_data(extras)
-
         # Because we renamed 'tag' to 'tags' but don't want to change the API (can do this in v2 of the API)
         tags = None
         if extras.get('tag'):
@@ -469,25 +418,10 @@ class CreateWatch(Resource):
         del extras['url']
 
         new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags)
-
-        # Save processor config to separate JSON file
-        if new_uuid and processor_config_data:
-            processors.save_processor_config(self.datastore, new_uuid, processor_config_data)
         if new_uuid:
-# Dont queue because the scheduler will check that it hasnt been checked before anyway
-#            worker_pool.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
+            worker_handler.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
             return {'uuid': new_uuid}, 201
         else:
-            # Check if it was a limit issue
-            page_watch_limit = os.getenv('PAGE_WATCH_LIMIT')
-            if page_watch_limit:
-                try:
-                    page_watch_limit = int(page_watch_limit)
-                    current_watch_count = len(self.datastore.data['watching'])
-                    if current_watch_count >= page_watch_limit:
-                        return f"Watch limit reached ({current_watch_count}/{page_watch_limit} watches). Cannot add more watches.", 429
-                except ValueError:
-                    pass
             return "Invalid or unsupported URL", 400
 
     @auth.check_token
@@ -509,65 +443,14 @@ class CreateWatch(Resource):
                 'last_error': watch['last_error'],
                 'link': watch.link,
                 'page_title': watch['page_title'],
-                'tags': [*tags],  # Unpack dict keys to list (can't use list() since variable named 'list')
                 'title': watch['title'],
                 'url': watch['url'],
                 'viewed': watch.viewed
             }
 
         if request.args.get('recheck_all'):
-            # Collect all watches to queue
-            watches_to_queue = self.datastore.data['watching'].keys()
+            for uuid in self.datastore.data['watching'].keys():
+                worker_handler.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+            return {'status': "OK"}, 200
 
-            # If less than 20 watches, queue synchronously for immediate feedback
-            if len(watches_to_queue) < 20:
-                # Get already queued/running UUIDs once (efficient)
-                queued_uuids = set(self.update_q.get_queued_uuids())
-                running_uuids = set(worker_pool.get_running_uuids())
-
-                # Filter out watches that are already queued or running
-                watches_to_queue_filtered = [
-                    uuid for uuid in watches_to_queue
-                    if uuid not in queued_uuids and uuid not in running_uuids
-                ]
-
-                # Queue only the filtered watches
-                for uuid in watches_to_queue_filtered:
-                    worker_pool.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-
-                # Provide feedback about skipped watches
-                skipped_count = len(watches_to_queue) - len(watches_to_queue_filtered)
-                if skipped_count > 0:
-                    return {'status': f'OK, queued {len(watches_to_queue_filtered)} watches for rechecking ({skipped_count} already queued or running)'}, 200
-                else:
-                    return {'status': f'OK, queued {len(watches_to_queue_filtered)} watches for rechecking'}, 200
-            else:
-                # 20+ watches - queue in background thread to avoid blocking API response
-                # Capture queued/running state before background thread
-                queued_uuids = set(self.update_q.get_queued_uuids())
-                running_uuids = set(worker_pool.get_running_uuids())
-
-                def queue_all_watches_background():
-                    """Background thread to queue all watches - discarded after completion."""
-                    try:
-                        queued_count = 0
-                        skipped_count = 0
-                        for uuid in watches_to_queue:
-                            # Check if already queued or running (state captured at start)
-                            if uuid not in queued_uuids and uuid not in running_uuids:
-                                worker_pool.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-                                queued_count += 1
-                            else:
-                                skipped_count += 1
-
-                        logger.info(f"Background queueing complete: {queued_count} watches queued, {skipped_count} skipped (already queued/running)")
-                    except Exception as e:
-                        logger.error(f"Error in background queueing all watches: {e}")
-
-                # Start background thread and return immediately
-                thread = threading.Thread(target=queue_all_watches_background, daemon=True, name="QueueAllWatches-Background")
-                thread.start()
-
-                return {'status': f'OK, queueing {len(watches_to_queue)} watches in background'}, 202
-
-        return list, 200
+        return list, 200

changedetectionio/api/__init__.py

@@ -1,137 +1,50 @@
+import copy
 import functools
 from flask import request, abort
 from loguru import logger
+from . import api_schema
+from ..model import watch_base
 
-@functools.cache
-def build_merged_spec_dict():
-    """
-    Load the base OpenAPI spec and merge in any per-processor api.yaml extensions.
+# Build a JSON Schema atleast partially based on our Watch model
+watch_base_config = watch_base()
+schema = api_schema.build_watch_json_schema(watch_base_config)
 
-    Each processor can provide an api.yaml file alongside its __init__.py that defines
-    additional schemas (e.g., processor_config_restock_diff). These are merged into
-    WatchBase.properties so the spec accurately reflects what the API accepts.
+schema_create_watch = copy.deepcopy(schema)
+schema_create_watch['required'] = ['url']
+del schema_create_watch['properties']['last_viewed']
 
-    Plugin processors (via pluggy) are also supported - they just need an api.yaml
-    next to their processor module.
+schema_update_watch = copy.deepcopy(schema)
+schema_update_watch['additionalProperties'] = False
 
-    Returns the merged dict (cached - do not mutate the returned value).
-    """
-    import os
-    import yaml
-
-    spec_path = os.path.join(os.path.dirname(__file__), '../../docs/api-spec.yaml')
-    if not os.path.exists(spec_path):
-        spec_path = os.path.join(os.path.dirname(__file__), '../docs/api-spec.yaml')
-
-    with open(spec_path, 'r', encoding='utf-8') as f:
-        spec_dict = yaml.safe_load(f)
-
-    try:
-        from changedetectionio.processors import find_processors, get_parent_module
-        for module, proc_name in find_processors():
-            parent = get_parent_module(module)
-            if not parent or not hasattr(parent, '__file__'):
-                continue
-            api_yaml_path = os.path.join(os.path.dirname(parent.__file__), 'api.yaml')
-            if not os.path.exists(api_yaml_path):
-                continue
-            with open(api_yaml_path, 'r', encoding='utf-8') as f:
-                proc_spec = yaml.safe_load(f)
-            # Merge schemas
-            proc_schemas = proc_spec.get('components', {}).get('schemas', {})
-            spec_dict['components']['schemas'].update(proc_schemas)
-            # Inject processor_config_{name} into WatchBase if the schema is defined
-            schema_key = f'processor_config_{proc_name}'
-            if schema_key in proc_schemas:
-                spec_dict['components']['schemas']['WatchBase']['properties'][schema_key] = {
-                    '$ref': f'#/components/schemas/{schema_key}'
-                }
-            # Append x-code-samples from processor paths into existing path operations
-            for path, path_item in proc_spec.get('paths', {}).items():
-                if path not in spec_dict.get('paths', {}):
-                    continue
-                for method, operation in path_item.items():
-                    if method not in spec_dict['paths'][path]:
-                        continue
-                    if 'x-code-samples' in operation:
-                        existing = spec_dict['paths'][path][method].get('x-code-samples', [])
-                        spec_dict['paths'][path][method]['x-code-samples'] = existing + operation['x-code-samples']
-    except Exception as e:
-        logger.warning(f"Failed to merge processor API specs: {e}")
-
-    return spec_dict
+# Tag schema is also based on watch_base since Tag inherits from it
+schema_tag = copy.deepcopy(schema)
+schema_create_tag = copy.deepcopy(schema_tag)
+schema_create_tag['required'] = ['title']
+schema_update_tag = copy.deepcopy(schema_tag)
+schema_update_tag['additionalProperties'] = False
 
+schema_notification_urls = copy.deepcopy(schema)
+schema_create_notification_urls = copy.deepcopy(schema_notification_urls)
+schema_create_notification_urls['required'] = ['notification_urls']
+schema_delete_notification_urls = copy.deepcopy(schema_notification_urls)
+schema_delete_notification_urls['required'] = ['notification_urls']
 
 @functools.cache
 def get_openapi_spec():
     """Lazy load OpenAPI spec and dependencies only when validation is needed."""
+    import os
+    import yaml  # Lazy import - only loaded when API validation is actually used
     from openapi_core import OpenAPI  # Lazy import - saves ~10.7 MB on startup
-    return OpenAPI.from_dict(build_merged_spec_dict())
 
-@functools.cache
-def get_openapi_schema_dict():
-    """
-    Get the raw OpenAPI spec dictionary for schema access.
+    spec_path = os.path.join(os.path.dirname(__file__), '../../docs/api-spec.yaml')
+    if not os.path.exists(spec_path):
+        # Possibly for pip3 packages
+        spec_path = os.path.join(os.path.dirname(__file__), '../docs/api-spec.yaml')
 
-    Used by Import endpoint to validate and convert query parameters.
-    Returns the merged YAML dict (not the OpenAPI object).
-    """
-    return build_merged_spec_dict()
-
-@functools.cache
-def _resolve_schema_properties(schema_name):
-    """
-    Generic helper to resolve schema properties, including allOf inheritance.
-
-    Args:
-        schema_name: Name of the schema (e.g., 'WatchBase', 'Watch', 'Tag')
-
-    Returns:
-        dict: All properties including inherited ones from $ref schemas
-    """
-    spec_dict = get_openapi_schema_dict()
-    schema = spec_dict['components']['schemas'].get(schema_name, {})
-
-    properties = {}
-
-    # Handle allOf (schema inheritance)
-    if 'allOf' in schema:
-        for item in schema['allOf']:
-            # Resolve $ref to parent schema
-            if '$ref' in item:
-                ref_path = item['$ref'].split('/')[-1]
-                ref_schema = spec_dict['components']['schemas'].get(ref_path, {})
-                properties.update(ref_schema.get('properties', {}))
-            # Add schema-specific properties
-            if 'properties' in item:
-                properties.update(item['properties'])
-    else:
-        # Direct properties (no inheritance)
-        properties = schema.get('properties', {})
-
-    return properties
-
-
-@functools.cache
-def get_watch_schema_properties():
-    """
-    Extract watch schema properties from OpenAPI spec for Import endpoint.
-
-    Returns WatchBase properties (all writable Watch fields).
-    """
-    return _resolve_schema_properties('WatchBase')
-
-# Import readonly field utilities from shared module (avoids circular dependencies with model layer)
-from changedetectionio.model.schema_utils import get_readonly_watch_fields, get_readonly_tag_fields
-
-@functools.cache
-def get_tag_schema_properties():
-    """
-    Extract Tag schema properties from OpenAPI spec.
-
-    Returns WatchBase properties + Tag-specific properties (overrides_watch).
-    """
-    return _resolve_schema_properties('Tag')
+    with open(spec_path, 'r', encoding='utf-8') as f:
+        spec_dict = yaml.safe_load(f)
+    _openapi_spec = OpenAPI.from_dict(spec_dict)
+    return _openapi_spec
 
 def validate_openapi_request(operation_id):
     """Decorator to validate incoming requests against OpenAPI spec."""
@@ -144,7 +57,6 @@ def validate_openapi_request(operation_id):
                 if request.method.upper() != 'GET':
                     # Lazy import - only loaded when actually validating a request
                     from openapi_core.contrib.flask import FlaskOpenAPIRequest
-                    from openapi_core.templating.paths.exceptions import ServerNotFound, PathNotFound, PathError
 
                     spec = get_openapi_spec()
                     openapi_request = FlaskOpenAPIRequest(request)
@@ -152,29 +64,8 @@ def validate_openapi_request(operation_id):
                     if result.errors:
                         error_details = []
                         for error in result.errors:
-                            # Skip path/server validation errors for reverse proxy compatibility
-                            # Flask routing already validates that endpoints exist (returns 404 if not).
-                            # OpenAPI validation here is primarily for request body schema validation.
-                            # When behind nginx/reverse proxy, URLs may have path prefixes that don't
-                            # match the OpenAPI server definitions, causing false positives.
-                            if isinstance(error, PathError):
-                                logger.debug(f"API Call - Skipping path/server validation (delegated to Flask): {error}")
-                                continue
-
-                            error_str = str(error)
-                            # Extract detailed schema errors from __cause__
-                            if hasattr(error, '__cause__') and hasattr(error.__cause__, 'schema_errors'):
-                                for schema_error in error.__cause__.schema_errors:
-                                    field = '.'.join(str(p) for p in schema_error.path) if schema_error.path else 'body'
-                                    msg = schema_error.message if hasattr(schema_error, 'message') else str(schema_error)
-                                    error_details.append(f"{field}: {msg}")
-                            else:
-                                error_details.append(error_str)
-
-                        # Only raise if we have actual validation errors (not path/server issues)
-                        if error_details:
-                            logger.error(f"API Call - Validation failed: {'; '.join(error_details)}")
-                            raise BadRequest(f"Validation failed: {'; '.join(error_details)}")
+                            error_details.append(str(error))
+                        raise BadRequest(f"OpenAPI validation failed: {error_details}")
             except BadRequest:
                 # Re-raise BadRequest exceptions (validation failures)
                 raise
@@ -191,6 +82,5 @@ from .Watch import Watch, WatchHistory, WatchSingleHistory, WatchHistoryDiff, Cr
 from .Tags import Tags, Tag
 from .Import import Import
 from .SystemInfo import SystemInfo
-from .Spec import Spec
 from .Notifications import Notifications
 

changedetectionio/api/api_schema.py

@@ -0,0 +1,162 @@
+# Responsible for building the storage dict into a set of rules ("JSON Schema") acceptable via the API
+# Probably other ways to solve this when the backend switches to some ORM
+from changedetectionio.notification import valid_notification_formats
+
+
+def build_time_between_check_json_schema():
+    # Setup time between check schema
+    schema_properties_time_between_check = {
+        "type": "object",
+        "additionalProperties": False,
+        "properties": {}
+    }
+    for p in ['weeks', 'days', 'hours', 'minutes', 'seconds']:
+        schema_properties_time_between_check['properties'][p] = {
+            "anyOf": [
+                {
+                    "type": "integer"
+                },
+                {
+                    "type": "null"
+                }
+            ]
+        }
+
+    return schema_properties_time_between_check
+
+def build_watch_json_schema(d):
+    # Base JSON schema
+    schema = {
+        'type': 'object',
+        'properties': {},
+    }
+
+    for k, v in d.items():
+        # @todo 'integer' is not covered here because its almost always for internal usage
+
+        if isinstance(v, type(None)):
+            schema['properties'][k] = {
+                "anyOf": [
+                    {"type": "null"},
+                ]
+            }
+        elif isinstance(v, list):
+            schema['properties'][k] = {
+                "anyOf": [
+                    {"type": "array",
+                     # Always is an array of strings, like text or regex or something
+                     "items": {
+                         "type": "string",
+                         "maxLength": 5000
+                     }
+                     },
+                ]
+            }
+        elif isinstance(v, bool):
+            schema['properties'][k] = {
+                "anyOf": [
+                    {"type": "boolean"},
+                ]
+            }
+        elif isinstance(v, str):
+            schema['properties'][k] = {
+                "anyOf": [
+                    {"type": "string",
+                     "maxLength": 5000},
+                ]
+            }
+
+    # Can also be a string (or None by default above)
+    for v in ['body',
+              'notification_body',
+              'notification_format',
+              'notification_title',
+              'proxy',
+              'tag',
+              'title',
+              'webdriver_js_execute_code'
+              ]:
+        schema['properties'][v]['anyOf'].append({'type': 'string', "maxLength": 5000})
+
+    for v in ['last_viewed']:
+        schema['properties'][v] = {
+            "type": "integer",
+            "description": "Unix timestamp in seconds of the last time the watch was viewed.",
+            "minimum": 0
+        }
+
+    # None or Boolean
+    schema['properties']['track_ldjson_price_data']['anyOf'].append({'type': 'boolean'})
+
+    schema['properties']['method'] = {"type": "string",
+                                      "enum": ["GET", "POST", "DELETE", "PUT"]
+                                      }
+
+    schema['properties']['fetch_backend']['anyOf'].append({"type": "string",
+                                                           "enum": ["html_requests", "html_webdriver"]
+                                                           })
+
+    schema['properties']['processor'] = {"anyOf": [
+        {"type": "string", "enum": ["restock_diff", "text_json_diff"]},
+        {"type": "null"}
+    ]}
+
+    # All headers must be key/value type dict
+    schema['properties']['headers'] = {
+        "type": "object",
+        "patternProperties": {
+            # Should always be a string:string type value
+            ".*": {"type": "string"},
+        }
+    }
+
+    schema['properties']['notification_format'] = {'type': 'string',
+                                                   'enum': list(valid_notification_formats.keys())
+                                                   }
+
+    # Stuff that shouldn't be available but is just state-storage
+    for v in ['previous_md5', 'last_error', 'has_ldjson_price_data', 'previous_md5_before_filters', 'uuid']:
+        del schema['properties'][v]
+
+    schema['properties']['webdriver_delay']['anyOf'].append({'type': 'integer'})
+
+    schema['properties']['time_between_check'] = build_time_between_check_json_schema()
+
+    schema['properties']['time_between_check_use_default'] = {
+        "type": "boolean",
+        "default": True,
+        "description": "Whether to use global settings for time between checks - defaults to true if not set"
+    }
+
+    schema['properties']['browser_steps'] = {
+        "anyOf": [
+            {
+                "type": "array",
+                "items": {
+                    "type": "object",
+                    "properties": {
+                        "operation": {
+                            "type": ["string", "null"],
+                            "maxLength": 5000  # Allows null and any string up to 5000 chars (including "")
+                        },
+                        "selector": {
+                            "type": ["string", "null"],
+                            "maxLength": 5000
+                        },
+                        "optional_value": {
+                            "type": ["string", "null"],
+                            "maxLength": 5000
+                        }
+                    },
+                    "required": ["operation", "selector", "optional_value"],
+                    "additionalProperties": False  # No extra keys allowed
+                }
+            },
+            {"type": "null"},  # Allows null for `browser_steps`
+            {"type": "array", "maxItems": 0}  # Allows empty array []
+        ]
+    }
+
+    # headers ?
+    return schema
+

changedetectionio/async_update_worker.py

@@ -1,15 +1,15 @@
 from blinker import signal
+
 from .processors.exceptions import ProcessorException
 import changedetectionio.content_fetchers.exceptions as content_fetchers_exceptions
 from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
 from changedetectionio import html_tools
-from changedetectionio import worker_pool
-from changedetectionio.queuedWatchMetaData import PrioritizedItem
-from changedetectionio.pluggy_interface import apply_update_handler_alter, apply_update_finalize
+from changedetectionio.flask_app import watch_check_update
 
 import asyncio
+import importlib
 import os
-import sys
+import queue
 import time
 
 from loguru import logger
@@ -17,91 +17,36 @@ from loguru import logger
 # Async version of update_worker
 # Processes jobs from AsyncSignalPriorityQueue instead of threaded queue
 
-IN_PYTEST = "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ
-DEFER_SLEEP_TIME_ALREADY_QUEUED = 0.3 if IN_PYTEST else 10.0
-
-async def async_update_worker(worker_id, q, notification_q, app, datastore, executor=None):
+async def async_update_worker(worker_id, q, notification_q, app, datastore):
     """
     Async worker function that processes watch check jobs from the queue.
-
+    
     Args:
         worker_id: Unique identifier for this worker
         q: AsyncSignalPriorityQueue containing jobs to process
         notification_q: Standard queue for notifications
         app: Flask application instance
         datastore: Application datastore
-        executor: ThreadPoolExecutor for queue operations (optional)
-
-    Returns:
-        "restart" if worker should restart, "shutdown" for clean exit
     """
     # Set a descriptive name for this task
     task = asyncio.current_task()
     if task:
         task.set_name(f"async-worker-{worker_id}")
-
-    # Read restart policy from environment
-    max_jobs = int(os.getenv("WORKER_MAX_JOBS", "10"))
-    max_runtime_seconds = int(os.getenv("WORKER_MAX_RUNTIME", "3600"))  # 1 hour default
-
-    jobs_processed = 0
-    start_time = time.time()
-
-    # Log thread name for debugging
-    import threading
-    thread_name = threading.current_thread().name
-    logger.info(f"Starting async worker {worker_id} on thread '{thread_name}' (max_jobs={max_jobs}, max_runtime={max_runtime_seconds}s)")
-
+    
+    logger.info(f"Starting async worker {worker_id}")
+    
     while not app.config.exit.is_set():
         update_handler = None
         watch = None
-        processing_exception = None  # Reset at start of each iteration to prevent state bleeding
 
         try:
-            # Efficient blocking via run_in_executor (no polling overhead!)
-            # Worker blocks in threading.Queue.get() which uses Condition.wait()
-            # Executor must be sized to match worker count (see worker_pool.py: 50 threads default)
-            # Single timeout (no double-timeout wrapper) = no race condition
-            queued_item_data = await q.async_get(executor=executor, timeout=1.0)
-
-            # CRITICAL: Claim UUID immediately after getting from queue to prevent race condition
-            # in wait_for_all_checks() which checks qsize() and running_uuids separately
-            uuid = queued_item_data.item.get('uuid')
-            if not worker_pool.claim_uuid_for_processing(uuid, worker_id):
-                # Already being processed - re-queue and continue
-                logger.trace(f"Worker {worker_id} detected UUID {uuid} already processing during claim - deferring")
-                await asyncio.sleep(DEFER_SLEEP_TIME_ALREADY_QUEUED)
-                deferred_priority = max(1000, queued_item_data.priority * 10)
-                deferred_item = PrioritizedItem(priority=deferred_priority, item=queued_item_data.item)
-                worker_pool.queue_item_async_safe(q, deferred_item, silent=True)
-                continue
+            # Use native janus async interface - no threads needed!
+            queued_item_data = await asyncio.wait_for(q.async_get(), timeout=1.0)
 
         except asyncio.TimeoutError:
-            # No jobs available - check if we should restart based on time while idle
-            runtime = time.time() - start_time
-            if runtime >= max_runtime_seconds:
-                logger.info(f"Worker {worker_id} idle and reached max runtime ({runtime:.0f}s), restarting")
-                return "restart"
-            continue
-        except RuntimeError as e:
-            # Handle executor shutdown gracefully - this is expected during shutdown
-            if "cannot schedule new futures after shutdown" in str(e):
-                # Executor shut down - exit gracefully without logging in pytest
-                if not IN_PYTEST:
-                    logger.debug(f"Worker {worker_id} detected executor shutdown, exiting")
-                break
-            # Other RuntimeError - log and continue
-            logger.error(f"Worker {worker_id} runtime error: {e}")
-            await asyncio.sleep(0.1)
+            # No jobs available, continue loop
             continue
         except Exception as e:
-            # Handle expected Empty exception from queue timeout
-            import queue
-            if isinstance(e, queue.Empty):
-                # Queue is empty, normal behavior - just continue
-                continue
-
-            # Unexpected exception - log as critical
             logger.critical(f"CRITICAL: Worker {worker_id} failed to get queue item: {type(e).__name__}: {e}")
 
             # Log queue health for debugging
@@ -115,11 +60,26 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
             await asyncio.sleep(0.1)
             continue
 
-        # UUID already claimed above immediately after getting from queue
-        # to prevent race condition with wait_for_all_checks()
+        uuid = queued_item_data.item.get('uuid')
+
+        # RACE CONDITION FIX: Check if this UUID is already being processed by another worker
+        from changedetectionio import worker_handler
+        from changedetectionio.queuedWatchMetaData import PrioritizedItem
+        if worker_handler.is_watch_running(uuid):
+            logger.trace(f"Worker {worker_id} skipping UUID {uuid} - already being processed, re-queuing for later")
+            # Re-queue with MUCH lower priority (higher number = processed later)
+            # This prevents tight loop where high-priority item keeps getting picked immediately
+            deferred_priority = max(1000, queued_item_data.priority * 10)
+            deferred_item = PrioritizedItem(priority=deferred_priority, item=queued_item_data.item)
+            worker_handler.queue_item_async_safe(q, deferred_item, silent=True)
+            await asyncio.sleep(0.1)  # Brief pause to avoid tight loop
+            continue
 
         fetch_start_time = round(time.time())
 
+        # Mark this UUID as being processed
+        worker_handler.set_uuid_processing(uuid, processing=True)
+        
         try:
             if uuid in list(datastore.data['watching'].keys()) and datastore.data['watching'][uuid].get('url'):
                 changed_detected = False
@@ -136,43 +96,29 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                 logger.info(f"Worker {worker_id} processing watch UUID {uuid} Priority {queued_item_data.priority} URL {watch['url']}")
 
                 try:
-                    # Retrieve signal by name to ensure thread-safe access across worker threads
-                    watch_check_update = signal('watch_check_update')
                     watch_check_update.send(watch_uuid=uuid)
 
                     # Processor is what we are using for detecting the "Change"
                     processor = watch.get('processor', 'text_json_diff')
 
                     # Init a new 'difference_detection_processor'
-                    # Use get_processor_module() to support both built-in and plugin processors
-                    from changedetectionio.processors import get_processor_module
-                    processor_module = get_processor_module(processor)
-
-                    if not processor_module:
-                        error_msg = f"Processor module '{processor}' not found."
-                        logger.error(error_msg)
-                        raise ModuleNotFoundError(error_msg)
+                    try:
+                        processor_module = importlib.import_module(f"changedetectionio.processors.{processor}.processor")
+                    except ModuleNotFoundError as e:
+                        print(f"Processor module '{processor}' not found.")
+                        raise e
 
                     update_handler = processor_module.perform_site_check(datastore=datastore,
                                                                          watch_uuid=uuid)
 
-                    # Allow plugins to modify/wrap the update_handler
-                    update_handler = apply_update_handler_alter(update_handler, watch, datastore)
-
                     update_signal = signal('watch_small_status_comment')
                     update_signal.send(watch_uuid=uuid, status="Fetching page..")
 
                     # All fetchers are now async, so call directly
                     await update_handler.call_browser()
 
-                    # Run change detection in executor to avoid blocking event loop
-                    # This includes CPU-intensive operations like HTML parsing (lxml/inscriptis)
-                    # which can take 2-10ms and cause GIL contention across workers
-                    loop = asyncio.get_event_loop()
-                    changed_detected, update_obj, contents = await loop.run_in_executor(
-                        executor,
-                        lambda: update_handler.run_changedetection(watch=watch)
-                    )
+                    # Run change detection (this is synchronous)
+                    changed_detected, update_obj, contents = update_handler.run_changedetection(watch=watch)
 
                 except PermissionError as e:
                     logger.critical(f"File permission error updating file, watch: {uuid}")
@@ -182,10 +128,8 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                 except ProcessorException as e:
                     if e.screenshot:
                         watch.save_screenshot(screenshot=e.screenshot)
-                        e.screenshot = None  # Free memory immediately
                     if e.xpath_data:
                         watch.save_xpath_data(data=e.xpath_data)
-                        e.xpath_data = None  # Free memory immediately
                     datastore.update_watch(uuid=uuid, update_obj={'last_error': e.message})
                     process_changedetection_results = False
 
@@ -205,11 +149,9 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
 
                     if e.screenshot:
                         watch.save_screenshot(screenshot=e.screenshot, as_error=True)
-                        e.screenshot = None  # Free memory immediately
 
                     if e.xpath_data:
                         watch.save_xpath_data(data=e.xpath_data)
-                        e.xpath_data = None  # Free memory immediately
                         
                     process_changedetection_results = False
 
@@ -228,10 +170,8 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
 
                     if e.screenshot:
                         watch.save_screenshot(screenshot=e.screenshot, as_error=True)
-                        e.screenshot = None  # Free memory immediately
                     if e.xpath_data:
                         watch.save_xpath_data(data=e.xpath_data, as_error=True)
-                        e.xpath_data = None  # Free memory immediately
                     if e.page_text:
                         watch.save_error_text(contents=e.page_text)
 
@@ -241,7 +181,6 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                 except FilterNotFoundInResponse as e:
                     if not datastore.data['watching'].get(uuid):
                         continue
-                    logger.debug(f"Received FilterNotFoundInResponse exception for {uuid}")
 
                     err_text = "Warning, no filters were found, no change detection ran - Did the page change layout? update your Visual Filter if necessary."
                     datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
@@ -249,11 +188,9 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                     # Filter wasnt found, but we should still update the visual selector so that they can have a chance to set it up again
                     if e.screenshot:
                         watch.save_screenshot(screenshot=e.screenshot)
-                        e.screenshot = None  # Free memory immediately
 
                     if e.xpath_data:
                         watch.save_xpath_data(data=e.xpath_data)
-                        e.xpath_data = None  # Free memory immediately
 
                     # Only when enabled, send the notification
                     if watch.get('filter_failure_notification_send', False):
@@ -261,19 +198,17 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                         c += 1
                         # Send notification if we reached the threshold?
                         threshold = datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts', 0)
-                        logger.debug(f"FilterNotFoundInResponse - Filter for {uuid} not found, consecutive_filter_failures: {c} of threshold {threshold}")
+                        logger.debug(f"Filter for {uuid} not found, consecutive_filter_failures: {c} of threshold {threshold}")
                         if c >= threshold:
                             if not watch.get('notification_muted'):
-                                logger.debug(f"FilterNotFoundInResponse - Sending filter failed notification for {uuid}")
+                                logger.debug(f"Sending filter failed notification for {uuid}")
                                 await send_filter_failure_notification(uuid, notification_q, datastore)
                             c = 0
-                            logger.debug(f"FilterNotFoundInResponse - Reset filter failure count back to zero")
-                        else:
-                            logger.debug(f"FilterNotFoundInResponse - {c} of threshold {threshold}..")
+                            logger.debug(f"Reset filter failure count back to zero")
 
                         datastore.update_watch(uuid=uuid, update_obj={'consecutive_filter_failures': c})
                     else:
-                        logger.trace(f"FilterNotFoundInResponse - {uuid} - filter_failure_notification_send not enabled, skipping")
+                        logger.trace(f"{uuid} - filter_failure_notification_send not enabled, skipping")
 
                     process_changedetection_results = False
 
@@ -281,12 +216,6 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                     # Yes fine, so nothing todo, don't continue to process.
                     process_changedetection_results = False
                     changed_detected = False
-                    logger.debug(f'[{uuid}] - checksumFromPreviousCheckWasTheSame - Checksum from previous check was the same, nothing todo here.')
-                    # Reset the edited flag since we successfully completed the check
-                    watch.reset_watch_edited_flag()
-                    # Page was fetched successfully - clear any previous error state
-                    datastore.update_watch(uuid=uuid, update_obj={'last_error': False})
-                    cleanup_error_artifacts(uuid, datastore)
                     
                 except content_fetchers_exceptions.BrowserConnectError as e:
                     datastore.update_watch(uuid=uuid,
@@ -353,7 +282,6 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                     err_text = "Error running JS Actions - Page request - "+e.message
                     if e.screenshot:
                         watch.save_screenshot(screenshot=e.screenshot, as_error=True)
-                        e.screenshot = None  # Free memory immediately
                     datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                 'last_check_status': e.status_code})
                     process_changedetection_results = False
@@ -365,7 +293,6 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
 
                     if e.screenshot:
                         watch.save_screenshot(screenshot=e.screenshot, as_error=True)
-                        e.screenshot = None  # Free memory immediately
 
                     datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                 'last_check_status': e.status_code,
@@ -378,15 +305,9 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                     process_changedetection_results = False
                     logger.error(f"Exception (BrowserStepsInUnsupportedFetcher) reached processing watch UUID: {uuid}")
 
-                except KeyError as e:
-                    # Watch was deleted between being queued and processed — skip
-                    logger.warning(f"Worker {worker_id} skipping UUID {uuid}: {e}")
-                    process_changedetection_results = False
-
                 except Exception as e:
-                    import traceback
                     logger.error(f"Worker {worker_id} exception processing watch UUID: {uuid}")
-                    logger.exception(f"Worker {worker_id} full exception details:")
+                    logger.error(str(e))
                     datastore.update_watch(uuid=uuid, update_obj={'last_error': "Exception: " + str(e)})
                     process_changedetection_results = False
 
@@ -394,7 +315,7 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                     if not datastore.data['watching'].get(uuid):
                         continue
 
-                    update_obj['content-type'] = str(update_handler.fetcher.get_all_headers().get('content-type', '') or "").lower()
+                    update_obj['content-type'] = update_handler.fetcher.get_all_headers().get('content-type', '').lower()
 
                     if not watch.get('ignore_status_codes'):
                         update_obj['consecutive_filter_failures'] = 0
@@ -405,27 +326,17 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                 if not datastore.data['watching'].get(uuid):
                     continue
 
-                logger.debug(f"Processing watch UUID: {uuid} - xpath_data length returned {len(update_handler.xpath_data) if update_handler and update_handler.xpath_data else 'empty.'}")
-                if update_handler and process_changedetection_results:
+                logger.debug(f"Processing watch UUID: {uuid} - xpath_data length returned {len(update_handler.xpath_data) if update_handler.xpath_data else 'empty.'}")
+                if process_changedetection_results:
                     try:
-                        # Reset the edited flag BEFORE update_watch (which calls watch.update() and would set it again)
-                        watch.reset_watch_edited_flag()
                         datastore.update_watch(uuid=uuid, update_obj=update_obj)
 
                         if changed_detected or not watch.history_n:
                             if update_handler.screenshot:
                                 watch.save_screenshot(screenshot=update_handler.screenshot)
-                                # Free screenshot memory immediately after saving
-                                update_handler.screenshot = None
-                                if hasattr(update_handler, 'fetcher') and hasattr(update_handler.fetcher, 'screenshot'):
-                                    update_handler.fetcher.screenshot = None
 
                             if update_handler.xpath_data:
                                 watch.save_xpath_data(data=update_handler.xpath_data)
-                                # Free xpath data memory
-                                update_handler.xpath_data = None
-                                if hasattr(update_handler, 'fetcher') and hasattr(update_handler.fetcher, 'xpath_data'):
-                                    update_handler.fetcher.xpath_data = None
 
                             # Ensure unique timestamp for history
                             if watch.newest_history_key and int(fetch_start_time) == int(watch.newest_history_key):
@@ -452,145 +363,102 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                                     await send_content_changed_notification(uuid, notification_q, datastore)
 
                     except Exception as e:
-
                         logger.critical(f"Worker {worker_id} exception in process_changedetection_results")
-                        logger.exception(f"Worker {worker_id} full exception details:")
+                        logger.critical(str(e))
                         datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
 
-
                 # Always record attempt count
                 count = watch.get('check_count', 0) + 1
 
-                final_updates = {'fetch_time': round(time.time() - fetch_start_time, 3),
-                                                                  'check_count': count,
-                                                                  }
+                # Always record page title (used in notifications, and can change even when the content is the same)
+                if update_obj.get('content-type') and 'html' in update_obj.get('content-type'):
+                    try:
+                        page_title = html_tools.extract_title(data=update_handler.fetcher.content)
+                        if page_title:
+                            page_title = page_title.strip()[:2000]
+                            logger.debug(f"UUID: {uuid} Page <title> is '{page_title}'")
+                            datastore.update_watch(uuid=uuid, update_obj={'page_title': page_title})
+                    except Exception as e:
+                        logger.warning(f"UUID: {uuid} Exception when extracting <title> - {str(e)}")
+
                 # Record server header
                 try:
-                    server_header = str(update_handler.fetcher.get_all_headers().get('server', '') or "").strip().lower()[:255]
-                    if server_header:
-                        final_updates['remote_server_reply'] = server_header
+                    server_header = update_handler.fetcher.headers.get('server', '').strip().lower()[:255]
+                    datastore.update_watch(uuid=uuid, update_obj={'remote_server_reply': server_header})
                 except Exception as e:
-                    server_header = None
                     pass
 
-                if update_handler: # Could be none or empty if the processor was not found
-                    # Always record page title (used in notifications, and can change even when the content is the same)
-                    if update_obj.get('content-type') and 'html' in update_obj.get('content-type'):
-                        try:
-                            page_title = html_tools.extract_title(data=update_handler.fetcher.content)
-                            if page_title:
-                                page_title = page_title.strip()[:2000]
-                                logger.debug(f"UUID: {uuid} Page <title> is '{page_title}'")
-                                final_updates['page_title'] = page_title
-                        except Exception as e:
-                            logger.exception(f"Worker {worker_id} full exception details:")
-                            logger.warning(f"UUID: {uuid} Exception when extracting <title> - {str(e)}")
+                # Store favicon if necessary
+                if update_handler.fetcher.favicon_blob and update_handler.fetcher.favicon_blob.get('base64'):
+                    watch.bump_favicon(url=update_handler.fetcher.favicon_blob.get('url'),
+                                       favicon_base_64=update_handler.fetcher.favicon_blob.get('base64')
+                                       )
 
-                    # Store favicon if necessary
-                    if update_handler.fetcher.favicon_blob and update_handler.fetcher.favicon_blob.get('base64'):
-                        watch.bump_favicon(url=update_handler.fetcher.favicon_blob.get('url'),
-                                           favicon_base_64=update_handler.fetcher.favicon_blob.get('base64')
-                                           )
+                datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - fetch_start_time, 3),
+                                                               'check_count': count})
 
-                    datastore.update_watch(uuid=uuid, update_obj=final_updates)
-
-                    # NOW clear fetcher content - after all processing is complete
-                    # This is the last point where we need the fetcher data
-                    if update_handler and hasattr(update_handler, 'fetcher') and update_handler.fetcher:
-                        update_handler.fetcher.clear_content()
-
-                    # Explicitly delete update_handler to free all references
-                    if update_handler:
-                        del update_handler
-                        update_handler = None
-
-                # Force garbage collection
-                import gc
-                gc.collect()
+                # NOW clear fetcher content - after all processing is complete
+                # This is the last point where we need the fetcher data
+                if update_handler and hasattr(update_handler, 'fetcher') and update_handler.fetcher:
+                    update_handler.fetcher.clear_content()
+                    logger.debug(f"Cleared fetcher content for UUID {uuid}")
 
         except Exception as e:
-            # Store the processing exception for plugin finalization hook
-            processing_exception = e
-
             logger.error(f"Worker {worker_id} unexpected error processing {uuid}: {e}")
-            logger.exception(f"Worker {worker_id} full exception details:")
-
+            logger.error(f"Worker {worker_id} traceback:", exc_info=True)
+            
             # Also update the watch with error information
             if datastore and uuid in datastore.data['watching']:
                 datastore.update_watch(uuid=uuid, update_obj={'last_error': f"Worker error: {str(e)}"})
         
         finally:
+
+            try:
+                await update_handler.fetcher.quit(watch=watch)
+            except Exception as e:
+                logger.error(f"Exception while cleaning/quit after calling browser: {e}")
+
             # Always cleanup - this runs whether there was an exception or not
             if uuid:
-                # Capture references for plugin finalize hook BEFORE cleanup
-                # (cleanup may delete these variables, but plugins need the original references)
-                finalize_handler = update_handler  # Capture now, before cleanup deletes it
-                finalize_watch = watch              # Capture now, before any modifications
-
-                # Call quit() as backup (Puppeteer/Playwright have internal cleanup, but this acts as safety net)
                 try:
-                    if update_handler and hasattr(update_handler, 'fetcher') and update_handler.fetcher:
-                        await update_handler.fetcher.quit(watch=watch)
-                except Exception as e:
-                    logger.error(f"Exception while cleaning/quit after calling browser: {e}")
-                    logger.exception(f"Worker {worker_id} full exception details:")
+                    # Mark UUID as no longer being processed
+                    worker_handler.set_uuid_processing(uuid, processing=False)
+                    
+                    # Send completion signal
+                    if watch:
+                        #logger.info(f"Worker {worker_id} sending completion signal for UUID {watch['uuid']}")
+                        watch_check_update.send(watch_uuid=watch['uuid'])
 
-                try:
-
-                    # Clean up all memory references BEFORE garbage collection
+                    # Explicitly clean up update_handler and all its references
                     if update_handler:
+                        # Clear fetcher content using the proper method
                         if hasattr(update_handler, 'fetcher') and update_handler.fetcher:
                             update_handler.fetcher.clear_content()
+
+                        # Clear processor references
                         if hasattr(update_handler, 'content_processor'):
                             update_handler.content_processor = None
-                        del update_handler
+
                         update_handler = None
 
-                    # Clear large content variables
+                    # Clear local contents variable if it still exists
                     if 'contents' in locals():
                         del contents
 
-                    # Force garbage collection after all references are cleared
+                    # Note: We don't set watch = None here because:
+                    # 1. watch is just a local reference to datastore.data['watching'][uuid]
+                    # 2. Setting it to None doesn't affect the datastore
+                    # 3. GC can't collect the object anyway (still referenced by datastore)
+                    # 4. It would just cause confusion
+
+                    # Force garbage collection after cleanup
                     import gc
                     gc.collect()
 
                     logger.debug(f"Worker {worker_id} completed watch {uuid} in {time.time()-fetch_start_time:.2f}s")
                 except Exception as cleanup_error:
                     logger.error(f"Worker {worker_id} error during cleanup: {cleanup_error}")
-                    logger.exception(f"Worker {worker_id} full exception details:")
-
-                # Call plugin finalization hook after all cleanup is done
-                # Use captured references from before cleanup
-                try:
-                    apply_update_finalize(
-                        update_handler=finalize_handler,
-                        watch=finalize_watch,
-                        datastore=datastore,
-                        processing_exception=processing_exception
-                    )
-                except Exception as finalize_error:
-                    logger.error(f"Worker {worker_id} error in finalize hook: {finalize_error}")
-                    logger.exception(f"Worker {worker_id} full exception details:")
-                finally:
-                    # Clean up captured references to allow immediate garbage collection
-                    del finalize_handler
-                    del finalize_watch
-
-                # Release UUID from processing AFTER all cleanup and hooks complete (thread-safe)
-                # This ensures wait_for_all_checks() waits for finalize hooks to complete
-                try:
-                    worker_pool.release_uuid_from_processing(uuid, worker_id=worker_id)
-                except Exception as release_error:
-                    logger.error(f"Worker {worker_id} error releasing UUID: {release_error}")
-                    logger.exception(f"Worker {worker_id} full exception details:")
-                finally:
-                    # Send completion signal - retrieve by name to ensure thread-safe access
-                    if watch:
-                        watch_check_update = signal('watch_check_update')
-                        watch_check_update.send(watch_uuid=watch['uuid'])
-
-            del (uuid)
-
+            
             # Brief pause before continuing to avoid tight error loops (only on error)
             if 'e' in locals():
                 await asyncio.sleep(1.0)
@@ -598,19 +466,6 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                 # Small yield for normal completion
                 await asyncio.sleep(0.01)
 
-            # Job completed - increment counter and check restart conditions
-            jobs_processed += 1
-            runtime = time.time() - start_time
-
-            # Check if we should restart (only when idle, between jobs)
-            should_restart_jobs = jobs_processed >= max_jobs
-            should_restart_time = runtime >= max_runtime_seconds
-
-            if should_restart_jobs or should_restart_time:
-                reason = f"{jobs_processed} jobs" if should_restart_jobs else f"{runtime:.0f}s runtime"
-                logger.info(f"Worker {worker_id} restarting after {reason} ({jobs_processed} jobs, {runtime:.0f}s runtime)")
-                return "restart"
-
         # Check if we should exit
         if app.config.exit.is_set():
             break
@@ -618,12 +473,10 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
     # Check if we're in pytest environment - if so, be more gentle with logging
     import sys
     in_pytest = "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ
-
+    
     if not in_pytest:
         logger.info(f"Worker {worker_id} shutting down")
 
-    return "shutdown"
-
 
 def cleanup_error_artifacts(uuid, datastore):
     """Helper function to clean up error artifacts"""

changedetectionio/blueprint/backups/__init__.py

@@ -13,7 +13,7 @@ from loguru import logger
 BACKUP_FILENAME_FORMAT = "changedetection-backup-{}.zip"
 
 
-def create_backup(datastore_path, watches: dict, tags: dict = None):
+def create_backup(datastore_path, watches: dict):
     logger.debug("Creating backup...")
     import zipfile
     from pathlib import Path
@@ -27,31 +27,15 @@ def create_backup(datastore_path, watches: dict, tags: dict = None):
                          compression=zipfile.ZIP_DEFLATED,
                          compresslevel=8) as zipObj:
 
-        # Add the settings file (supports both formats)
-        # New format: changedetection.json
-        changedetection_json = os.path.join(datastore_path, "changedetection.json")
-        if os.path.isfile(changedetection_json):
-            zipObj.write(changedetection_json, arcname="changedetection.json")
-            logger.debug("Added changedetection.json to backup")
+        # Add the index
+        zipObj.write(os.path.join(datastore_path, "url-watches.json"), arcname="url-watches.json")
 
-        # Legacy format: url-watches.json (for backward compatibility)
-        url_watches_json = os.path.join(datastore_path, "url-watches.json")
-        if os.path.isfile(url_watches_json):
-            zipObj.write(url_watches_json, arcname="url-watches.json")
-            logger.debug("Added url-watches.json to backup")
-
-        # Add tag data directories (each tag has its own {uuid}/tag.json)
-        for uuid, tag in (tags or {}).items():
-            for f in Path(tag.data_dir).glob('*'):
-                zipObj.write(f,
-                             arcname=os.path.join(f.parts[-2], f.parts[-1]),
-                             compress_type=zipfile.ZIP_DEFLATED,
-                             compresslevel=8)
-            logger.debug(f"Added tag '{tag.get('title')}' ({uuid}) to backup")
+        # Add the flask app secret
+        zipObj.write(os.path.join(datastore_path, "secret.txt"), arcname="secret.txt")
 
         # Add any data in the watch data directory.
         for uuid, w in watches.items():
-            for f in Path(w.data_dir).glob('*'):
+            for f in Path(w.watch_data_dir).glob('*'):
                 zipObj.write(f,
                              # Use the full path to access the file, but make the file 'relative' in the Zip.
                              arcname=os.path.join(f.parts[-2], f.parts[-1]),
@@ -92,10 +76,7 @@ def create_backup(datastore_path, watches: dict, tags: dict = None):
 
 
 def construct_blueprint(datastore: ChangeDetectionStore):
-    from .restore import construct_restore_blueprint
-
     backups_blueprint = Blueprint('backups', __name__, template_folder="templates")
-    backups_blueprint.register_blueprint(construct_restore_blueprint(datastore))
     backup_threads = []
 
     @login_optionally_required
@@ -103,25 +84,20 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def request_backup():
         if any(thread.is_alive() for thread in backup_threads):
             flash(gettext("A backup is already running, check back in a few minutes"), "error")
-            return redirect(url_for('backups.create'))
+            return redirect(url_for('backups.index'))
 
         if len(find_backups()) > int(os.getenv("MAX_NUMBER_BACKUPS", 100)):
             flash(gettext("Maximum number of backups reached, please remove some"), "error")
-            return redirect(url_for('backups.create'))
+            return redirect(url_for('backups.index'))
 
-        # With immediate persistence, all data is already saved
-        zip_thread = threading.Thread(
-            target=create_backup,
-            args=(datastore.datastore_path, datastore.data.get("watching")),
-            kwargs={'tags': datastore.data['settings']['application'].get('tags', {})},
-            daemon=True,
-            name="BackupCreator"
-        )
+        # Be sure we're written fresh
+        datastore.sync_to_json()
+        zip_thread = threading.Thread(target=create_backup, args=(datastore.datastore_path, datastore.data.get("watching")))
         zip_thread.start()
         backup_threads.append(zip_thread)
         flash(gettext("Backup building in background, check back in a few minutes."))
 
-        return redirect(url_for('backups.create'))
+        return redirect(url_for('backups.index'))
 
     def find_backups():
         backup_filepath = os.path.join(datastore.datastore_path, BACKUP_FILENAME_FORMAT.format("*"))
@@ -146,34 +122,31 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def download_backup(filename):
         import re
         filename = filename.strip()
-        backup_filename_regex = BACKUP_FILENAME_FORMAT.format(r"\d+")
+        backup_filename_regex = BACKUP_FILENAME_FORMAT.format("\d+")
+
+        full_path = os.path.join(os.path.abspath(datastore.datastore_path), filename)
+        if not full_path.startswith(os.path.abspath(datastore.datastore_path)):
+            abort(404)
 
-        # Resolve 'latest' before any validation so checks run against the real filename.
         if filename == 'latest':
             backups = find_backups()
-            if not backups:
-                abort(404)
             filename = backups[0]['filename']
 
         if not re.match(r"^" + backup_filename_regex + "$", filename):
             abort(400)  # Bad Request if the filename doesn't match the pattern
 
-        full_path = os.path.join(os.path.abspath(datastore.datastore_path), filename)
-        if not full_path.startswith(os.path.abspath(datastore.datastore_path) + os.sep):
-            abort(404)
-
         logger.debug(f"Backup download request for '{full_path}'")
         return send_from_directory(os.path.abspath(datastore.datastore_path), filename, as_attachment=True)
 
     @login_optionally_required
-    @backups_blueprint.route("/", methods=['GET'])
-    @backups_blueprint.route("/create", methods=['GET'])
-    def create():
+    @backups_blueprint.route("", methods=['GET'])
+    def index():
         backups = find_backups()
-        output = render_template("backup_create.html",
+        output = render_template("overview.html",
                                  available_backups=backups,
                                  backup_running=any(thread.is_alive() for thread in backup_threads)
                                  )
+
         return output
 
     @login_optionally_required
@@ -187,6 +160,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         flash(gettext("Backups were deleted."))
 
-        return redirect(url_for('backups.create'))
+        return redirect(url_for('backups.index'))
 
     return backups_blueprint

changedetectionio/blueprint/backups/restore.py

@@ -1,248 +0,0 @@
-import io
-import json
-import os
-import re
-import shutil
-import tempfile
-import threading
-import zipfile
-
-from flask import Blueprint, render_template, flash, url_for, redirect, request
-from flask_babel import gettext, lazy_gettext as _l
-from wtforms import Form, BooleanField, SubmitField
-from flask_wtf.file import FileField, FileAllowed
-from loguru import logger
-
-from changedetectionio.flask_app import login_optionally_required
-
-# Maximum size of the uploaded zip file. Override via env var MAX_RESTORE_UPLOAD_MB.
-_MAX_UPLOAD_BYTES = int(os.getenv("MAX_RESTORE_UPLOAD_MB", 256)) * 1024 * 1024
-# Maximum total uncompressed size of all entries (zip-bomb guard). Override via MAX_RESTORE_DECOMPRESSED_MB.
-_MAX_DECOMPRESSED_BYTES = int(os.getenv("MAX_RESTORE_DECOMPRESSED_MB", 1024)) * 1024 * 1024
-# Only top-level directories whose name is a valid UUID are treated as watch/tag entries.
-_UUID_RE = re.compile(
-    r'^[0-9a-f]{8}-[0-9a-f]{4}-4[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$',
-    re.IGNORECASE,
-)
-
-
-class RestoreForm(Form):
-    zip_file = FileField(_l('Backup zip file'), validators=[
-        FileAllowed(['zip'], _l('Must be a .zip backup file!'))
-    ])
-    include_groups = BooleanField(_l('Include groups'), default=True)
-    include_groups_replace_existing = BooleanField(_l('Replace existing groups of the same UUID'), default=True)
-    include_watches = BooleanField(_l('Include watches'), default=True)
-    include_watches_replace_existing = BooleanField(_l('Replace existing watches of the same UUID'), default=True)
-    submit = SubmitField(_l('Restore backup'))
-
-
-def import_from_zip(zip_stream, datastore, include_groups, include_groups_replace, include_watches, include_watches_replace):
-    """
-    Extract and import watches and groups from a backup zip stream.
-
-    Mirrors the store's _load_watches / _load_tags loading pattern:
-      - UUID dirs with tag.json  → Tag.model + tag_obj.commit()
-      - UUID dirs with watch.json → rehydrate_entity + watch_obj.commit()
-
-    Returns a dict with counts: restored_groups, skipped_groups, restored_watches, skipped_watches.
-    Raises zipfile.BadZipFile if the stream is not a valid zip.
-    """
-    from changedetectionio.model import Tag
-
-    restored_groups = 0
-    skipped_groups = 0
-    restored_watches = 0
-    skipped_watches = 0
-
-    current_tags = datastore.data['settings']['application'].get('tags', {})
-    current_watches = datastore.data['watching']
-
-    with tempfile.TemporaryDirectory() as tmpdir:
-        logger.debug(f"Restore: extracting zip to {tmpdir}")
-        with zipfile.ZipFile(zip_stream, 'r') as zf:
-            total_uncompressed = sum(m.file_size for m in zf.infolist())
-            if total_uncompressed > _MAX_DECOMPRESSED_BYTES:
-                raise ValueError(
-                    f"Backup archive decompressed size ({total_uncompressed // (1024 * 1024)} MB) "
-                    f"exceeds the {_MAX_DECOMPRESSED_BYTES // (1024 * 1024)} MB limit"
-                )
-            resolved_dest = os.path.realpath(tmpdir)
-            for member in zf.infolist():
-                member_dest = os.path.realpath(os.path.join(resolved_dest, member.filename))
-                if not member_dest.startswith(resolved_dest + os.sep) and member_dest != resolved_dest:
-                    raise ValueError(f"Zip Slip path traversal detected in backup archive: {member.filename!r}")
-                zf.extract(member, tmpdir)
-        logger.debug("Restore: zip extracted, scanning UUID directories")
-
-        for entry in os.scandir(tmpdir):
-            if not entry.is_dir():
-                continue
-
-            uuid = entry.name
-            if not _UUID_RE.match(uuid):
-                logger.warning(f"Restore: skipping non-UUID directory {uuid!r}")
-                continue
-            tag_json_path = os.path.join(entry.path, 'tag.json')
-            watch_json_path = os.path.join(entry.path, 'watch.json')
-
-            # --- Tags (groups) ---
-            if include_groups and os.path.exists(tag_json_path):
-                if uuid in current_tags and not include_groups_replace:
-                    logger.debug(f"Restore: skipping existing group {uuid} (replace not requested)")
-                    skipped_groups += 1
-                    continue
-
-                try:
-                    with open(tag_json_path, 'r', encoding='utf-8') as f:
-                        tag_data = json.load(f)
-                except (json.JSONDecodeError, IOError) as e:
-                    logger.error(f"Restore: failed to read tag.json for {uuid}: {e}")
-                    continue
-
-                title = tag_data.get('title', uuid)
-                logger.debug(f"Restore: importing group '{title}' ({uuid})")
-
-                # Mirror _load_tags: set uuid and force processor
-                tag_data['uuid'] = uuid
-                tag_data['processor'] = 'restock_diff'
-
-                # Copy the UUID directory so data_dir exists for commit()
-                dst_dir = os.path.join(datastore.datastore_path, uuid)
-                if os.path.exists(dst_dir):
-                    shutil.rmtree(dst_dir)
-                shutil.copytree(entry.path, dst_dir)
-
-                tag_obj = Tag.model(
-                    datastore_path=datastore.datastore_path,
-                    __datastore=datastore.data,
-                    default=tag_data
-                )
-                current_tags[uuid] = tag_obj
-                tag_obj.commit()
-                restored_groups += 1
-                logger.success(f"Restore: group '{title}' ({uuid}) restored")
-
-            # --- Watches ---
-            elif include_watches and os.path.exists(watch_json_path):
-                if uuid in current_watches and not include_watches_replace:
-                    logger.debug(f"Restore: skipping existing watch {uuid} (replace not requested)")
-                    skipped_watches += 1
-                    continue
-
-                try:
-                    with open(watch_json_path, 'r', encoding='utf-8') as f:
-                        watch_data = json.load(f)
-                except (json.JSONDecodeError, IOError) as e:
-                    logger.error(f"Restore: failed to read watch.json for {uuid}: {e}")
-                    continue
-
-                url = watch_data.get('url', uuid)
-                logger.debug(f"Restore: importing watch '{url}' ({uuid})")
-
-                # Copy UUID directory first so data_dir and history files exist
-                dst_dir = os.path.join(datastore.datastore_path, uuid)
-                if os.path.exists(dst_dir):
-                    shutil.rmtree(dst_dir)
-                shutil.copytree(entry.path, dst_dir)
-
-                # Mirror _load_watches / rehydrate_entity
-                watch_data['uuid'] = uuid
-                watch_obj = datastore.rehydrate_entity(uuid, watch_data)
-                current_watches[uuid] = watch_obj
-                watch_obj.commit()
-                restored_watches += 1
-                logger.success(f"Restore: watch '{url}' ({uuid}) restored")
-
-        logger.debug(f"Restore: scan complete - groups {restored_groups} restored / {skipped_groups} skipped, "
-                     f"watches {restored_watches} restored / {skipped_watches} skipped")
-
-    # Persist changedetection.json (includes the updated tags dict)
-    logger.debug("Restore: committing datastore settings")
-    datastore.commit()
-
-    return {
-        'restored_groups': restored_groups,
-        'skipped_groups': skipped_groups,
-        'restored_watches': restored_watches,
-        'skipped_watches': skipped_watches,
-    }
-
-
-
-def construct_restore_blueprint(datastore):
-    restore_blueprint = Blueprint('restore', __name__, template_folder="templates")
-    restore_threads = []
-
-    @login_optionally_required
-    @restore_blueprint.route("/restore", methods=['GET'])
-    def restore():
-        form = RestoreForm()
-        return render_template("backup_restore.html",
-                               form=form,
-                               restore_running=any(t.is_alive() for t in restore_threads),
-                               max_upload_mb=_MAX_UPLOAD_BYTES // (1024 * 1024),
-                               max_decompressed_mb=_MAX_DECOMPRESSED_BYTES // (1024 * 1024))
-
-    @login_optionally_required
-    @restore_blueprint.route("/restore/start", methods=['POST'])
-    def backups_restore_start():
-        if any(t.is_alive() for t in restore_threads):
-            flash(gettext("A restore is already running, check back in a few minutes"), "error")
-            return redirect(url_for('backups.restore.restore'))
-
-        zip_file = request.files.get('zip_file')
-        if not zip_file or not zip_file.filename:
-            flash(gettext("No file uploaded"), "error")
-            return redirect(url_for('backups.restore.restore'))
-
-        if not zip_file.filename.lower().endswith('.zip'):
-            flash(gettext("File must be a .zip backup file"), "error")
-            return redirect(url_for('backups.restore.restore'))
-
-        # Reject oversized uploads before reading the stream into memory.
-        content_length = request.content_length
-        if content_length and content_length > _MAX_UPLOAD_BYTES:
-            flash(gettext("Backup file is too large (max %(mb)s MB)", mb=_MAX_UPLOAD_BYTES // (1024 * 1024)), "error")
-            return redirect(url_for('backups.restore.restore'))
-
-        # Read into memory now — the request stream is gone once we return.
-        # Read one byte beyond the limit so we can detect truncated-but-still-oversized streams.
-        try:
-            raw = zip_file.read(_MAX_UPLOAD_BYTES + 1)
-            if len(raw) > _MAX_UPLOAD_BYTES:
-                flash(gettext("Backup file is too large (max %(mb)s MB)", mb=_MAX_UPLOAD_BYTES // (1024 * 1024)), "error")
-                return redirect(url_for('backups.restore.restore'))
-            zip_bytes = io.BytesIO(raw)
-            with zipfile.ZipFile(zip_bytes):  # quick validity check before spawning
-                pass
-            zip_bytes.seek(0)
-        except zipfile.BadZipFile:
-            flash(gettext("Invalid or corrupted zip file"), "error")
-            return redirect(url_for('backups.restore.restore'))
-
-        include_groups = request.form.get('include_groups') == 'y'
-        include_groups_replace = request.form.get('include_groups_replace_existing') == 'y'
-        include_watches = request.form.get('include_watches') == 'y'
-        include_watches_replace = request.form.get('include_watches_replace_existing') == 'y'
-
-        restore_thread = threading.Thread(
-            target=import_from_zip,
-            kwargs={
-                'zip_stream': zip_bytes,
-                'datastore': datastore,
-                'include_groups': include_groups,
-                'include_groups_replace': include_groups_replace,
-                'include_watches': include_watches,
-                'include_watches_replace': include_watches_replace,
-            },
-            daemon=True,
-            name="BackupRestore"
-        )
-        restore_thread.start()
-        restore_threads[:] = [t for t in restore_threads if t.is_alive()]
-        restore_threads.append(restore_thread)
-        flash(gettext("Restore started in background, check back in a few minutes."))
-        return redirect(url_for('backups.restore.restore'))
-
-    return restore_blueprint

changedetectionio/blueprint/backups/templates/backup_create.html

@@ -1,49 +0,0 @@
-{% extends 'base.html' %}
-{% block content %}
-    {% from '_helpers.html' import render_simple_field, render_field %}
-
-    <div class="edit-form">
-        <div class="tabs collapsable">
-            <ul>
-                <li class="tab active" id=""><a href="{{ url_for('backups.create') }}">{{ _('Create') }}</a></li>
-                <li class="tab"><a href="{{ url_for('backups.restore.restore') }}">{{ _('Restore') }}</a></li>
-            </ul>
-        </div>
-        <div class="box-wrap inner">
-            <div id="general">
-                {% if backup_running %}
-                    <p>
-                        <span class="spinner"></span>&nbsp;<strong>{{ _('A backup is running!') }}</strong>
-                    </p>
-                {% endif %}
-
-                <p>
-                    {{ _('Here you can download and request a new backup, when a backup is completed you will see it listed below.') }}
-                </p>
-                <br>
-                {% if available_backups %}
-                    <ul>
-                        {% for backup in available_backups %}
-                            <li>
-                                <a href="{{ url_for('backups.download_backup', filename=backup["filename"]) }}">{{ backup["filename"] }}</a> {{ backup["filesize"] }} {{ _('Mb') }}
-                            </li>
-                        {% endfor %}
-                    </ul>
-                {% else %}
-                    <p>
-                        <strong>{{ _('No backups found.') }}</strong>
-                    </p>
-                {% endif %}
-
-                <a class="pure-button pure-button-primary"
-                   href="{{ url_for('backups.request_backup') }}">{{ _('Create backup') }}</a>
-                {% if available_backups %}
-                    <a class="pure-button button-small button-error "
-                       href="{{ url_for('backups.remove_backups') }}">{{ _('Remove backups') }}</a>
-                {% endif %}
-
-            </div>
-
-        </div>
-    </div>
-{% endblock %}

changedetectionio/blueprint/backups/templates/backup_restore.html

@@ -1,62 +0,0 @@
-{% extends 'base.html' %}
-{% block content %}
-    {% from '_helpers.html' import render_field, render_checkbox_field %}
-
-    <div class="edit-form">
-        <div class="tabs collapsable">
-            <ul>
-                <li class="tab"><a href="{{ url_for('backups.create') }}">{{ _('Create') }}</a></li>
-                <li class="tab active"><a href="{{ url_for('backups.restore.restore') }}">{{ _('Restore') }}</a></li>
-            </ul>
-        </div>
-        <div class="box-wrap inner">
-            <div id="general">
-                {% if restore_running %}
-                    <p>
-                        <span class="spinner"></span>&nbsp;<strong>{{ _('A restore is running!') }}</strong>
-                    </p>
-                {% endif %}
-
-                <p>{{ _('Restore a backup. Must be a .zip backup file created on/after v0.53.1 (new database layout).') }}</p>
-                <p>{{ _('Note: This does not override the main application settings, only watches and groups.') }}</p>
-                <p class="pure-form-message">
-                    {{ _('Max upload size: %(upload)s MB &nbsp;·&nbsp; Max decompressed size: %(decomp)s MB',
-                         upload=max_upload_mb, decomp=max_decompressed_mb) }}
-                </p>
-
-                <form class="pure-form pure-form-stacked settings"
-                      action="{{ url_for('backups.restore.backups_restore_start') }}"
-                      method="POST"
-                      enctype="multipart/form-data">
-                    <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
-
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.include_groups) }}
-                        <span class="pure-form-message-inline">{{ _('Include all groups found in backup?') }}</span>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.include_groups_replace_existing) }}
-                        <span class="pure-form-message-inline">{{ _('Replace any existing groups of the same UUID?') }}</span>
-                    </div>
-
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.include_watches) }}
-                        <span class="pure-form-message-inline">{{ _('Include all watches found in backup?') }}</span>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.include_watches_replace_existing) }}
-                        <span class="pure-form-message-inline">{{ _('Replace any existing watches of the same UUID?') }}</span>
-                    </div>
-
-                    <div class="pure-control-group">
-                        {{ render_field(form.zip_file) }}
-                    </div>
-
-                    <div class="pure-controls">
-                        <button type="submit" class="pure-button pure-button-primary">{{ _('Restore backup') }}</button>
-                    </div>
-                </form>
-            </div>
-        </div>
-    </div>
-{% endblock %}

changedetectionio/blueprint/backups/templates/overview.html

@@ -0,0 +1,36 @@
+{% extends 'base.html' %}
+{% block content %}
+    {% from '_helpers.html' import render_simple_field, render_field %}
+    <div class="edit-form">
+        <div class="box-wrap inner">
+            <h4>{{ _('Backups') }}</h4>
+            {% if backup_running %}
+                <p>
+                    <strong>{{ _('A backup is running!') }}</strong>
+                </p>
+            {% endif %}
+            <p>
+                {{ _('Here you can download and request a new backup, when a backup is completed you will see it listed below.') }}
+            </p>
+            <br>
+                {% if available_backups %}
+                    <ul>
+                    {% for backup in available_backups %}
+                        <li><a href="{{ url_for('backups.download_backup', filename=backup["filename"]) }}">{{ backup["filename"] }}</a> {{  backup["filesize"] }} {{ _('Mb') }}</li>
+                    {% endfor %}
+                    </ul>
+                {% else %}
+                    <p>
+                    <strong>{{ _('No backups found.') }}</strong>
+                    </p>
+                {% endif %}
+
+            <a class="pure-button pure-button-primary" href="{{ url_for('backups.request_backup') }}">{{ _('Create backup') }}</a>
+            {% if available_backups %}
+                <a class="pure-button button-small button-error " href="{{ url_for('backups.remove_backups') }}">{{ _('Remove backups') }}</a>
+            {% endif %}
+        </div>
+    </div>
+
+
+{% endblock %}

changedetectionio/blueprint/browser_steps/__init__.py

@@ -21,247 +21,93 @@ from changedetectionio.flask_app import login_optionally_required
 from loguru import logger
 
 browsersteps_sessions = {}
-browsersteps_watch_to_session = {}  # Maps watch_uuid -> browsersteps_session_id
 io_interface_context = None
 import json
 import hashlib
 from flask import Response
 import asyncio
 import threading
-import time
-
-# Dedicated event loop for ALL browser steps sessions
-_browser_steps_loop = None
-_browser_steps_thread = None
-_browser_steps_loop_lock = threading.Lock()
-
-def _start_browser_steps_loop():
-    """Start a dedicated event loop for browser steps in its own thread"""
-    global _browser_steps_loop
-
-    # Create and set the event loop for this thread
-    loop = asyncio.new_event_loop()
-    asyncio.set_event_loop(loop)
-    _browser_steps_loop = loop
-
-    logger.debug("Browser steps event loop started")
-
-    try:
-        # Run the loop forever - handles all browsersteps sessions
-        loop.run_forever()
-    except Exception as e:
-        logger.error(f"Browser steps event loop error: {e}")
-    finally:
-        try:
-            # Cancel all remaining tasks
-            pending = asyncio.all_tasks(loop)
-            for task in pending:
-                task.cancel()
-
-            # Wait for tasks to finish cancellation
-            if pending:
-                loop.run_until_complete(asyncio.gather(*pending, return_exceptions=True))
-        except Exception as e:
-            logger.debug(f"Error during browser steps loop cleanup: {e}")
-        finally:
-            loop.close()
-            logger.debug("Browser steps event loop closed")
-
-def _ensure_browser_steps_loop():
-    """Ensure the browser steps event loop is running"""
-    global _browser_steps_loop, _browser_steps_thread
-
-    with _browser_steps_loop_lock:
-        if _browser_steps_thread is None or not _browser_steps_thread.is_alive():
-            logger.debug("Starting browser steps event loop thread")
-            _browser_steps_thread = threading.Thread(
-                target=_start_browser_steps_loop,
-                daemon=True,
-                name="BrowserStepsEventLoop"
-            )
-            _browser_steps_thread.start()
-
-            # Wait for the loop to be ready
-            timeout = 5.0
-            start_time = time.time()
-            while _browser_steps_loop is None:
-                if time.time() - start_time > timeout:
-                    raise RuntimeError("Browser steps event loop failed to start")
-                time.sleep(0.01)
-
-            logger.debug("Browser steps event loop thread started and ready")
 
 def run_async_in_browser_loop(coro):
-    """Run async coroutine using the dedicated browser steps event loop"""
-    _ensure_browser_steps_loop()
-
-    if _browser_steps_loop and not _browser_steps_loop.is_closed():
-        logger.debug("Browser steps using dedicated event loop")
-        future = asyncio.run_coroutine_threadsafe(coro, _browser_steps_loop)
+    """Run async coroutine using the existing async worker event loop"""
+    from changedetectionio import worker_handler
+    
+    # Use the existing async worker event loop instead of creating a new one
+    if worker_handler.USE_ASYNC_WORKERS and worker_handler.async_loop and not worker_handler.async_loop.is_closed():
+        logger.debug("Browser steps using existing async worker event loop")
+        future = asyncio.run_coroutine_threadsafe(coro, worker_handler.async_loop)
         return future.result()
     else:
-        raise RuntimeError("Browser steps event loop is not available")
-
-async def _close_session_resources(session_data, label=''):
-    """Close all browser resources for a session in the correct order.
-
-    browserstepper.cleanup() closes page+context but not the browser itself.
-    For CloakBrowser, browser.close() is what stops the local Chromium process via pw.stop().
-    For the default CDP path, playwright_context.stop() shuts down the playwright instance.
-    """
-    browserstepper = session_data.get('browserstepper')
-    if browserstepper:
+        # Fallback: create a new event loop (for sync workers or if async loop not available)
+        logger.debug("Browser steps creating temporary event loop")
+        loop = asyncio.new_event_loop()
+        asyncio.set_event_loop(loop)
         try:
-            await browserstepper.cleanup()
-        except Exception as e:
-            logger.error(f"Error cleaning up browserstepper{label}: {e}")
-
-    browser = session_data.get('browser')
-    if browser:
-        try:
-            await asyncio.wait_for(browser.close(), timeout=5.0)
-        except Exception as e:
-            logger.warning(f"Error closing browser{label}: {e}")
-
-    playwright_context = session_data.get('playwright_context')
-    if playwright_context:
-        try:
-            await playwright_context.stop()
-        except Exception as e:
-            logger.warning(f"Error stopping playwright context{label}: {e}")
-
-
-def cleanup_expired_sessions():
-    """Remove expired browsersteps sessions and cleanup their resources"""
-    global browsersteps_sessions, browsersteps_watch_to_session
-
-    expired_session_ids = []
-
-    # Find expired sessions
-    for session_id, session_data in browsersteps_sessions.items():
-        browserstepper = session_data.get('browserstepper')
-        if browserstepper and browserstepper.has_expired:
-            expired_session_ids.append(session_id)
-
-    # Cleanup expired sessions
-    for session_id in expired_session_ids:
-        logger.debug(f"Cleaning up expired browsersteps session {session_id}")
-        session_data = browsersteps_sessions[session_id]
-
-        try:
-            run_async_in_browser_loop(_close_session_resources(session_data, label=f" for session {session_id}"))
-        except Exception as e:
-            logger.error(f"Error cleaning up session {session_id}: {e}")
-
-        # Remove from sessions dict
-        del browsersteps_sessions[session_id]
-
-        # Remove from watch mapping
-        for watch_uuid, mapped_session_id in list(browsersteps_watch_to_session.items()):
-            if mapped_session_id == session_id:
-                del browsersteps_watch_to_session[watch_uuid]
-                break
-
-    if expired_session_ids:
-        logger.info(f"Cleaned up {len(expired_session_ids)} expired browsersteps session(s)")
-
-def cleanup_session_for_watch(watch_uuid):
-    """Cleanup a specific browsersteps session for a watch UUID"""
-    global browsersteps_sessions, browsersteps_watch_to_session
-
-    session_id = browsersteps_watch_to_session.get(watch_uuid)
-    if not session_id:
-        logger.debug(f"No browsersteps session found for watch {watch_uuid}")
-        return
-
-    logger.debug(f"Cleaning up browsersteps session {session_id} for watch {watch_uuid}")
-
-    session_data = browsersteps_sessions.get(session_id)
-    if session_data:
-        try:
-            run_async_in_browser_loop(_close_session_resources(session_data, label=f" for watch {watch_uuid}"))
-        except Exception as e:
-            logger.error(f"Error cleaning up session {session_id} for watch {watch_uuid}: {e}")
-
-        # Remove from sessions dict
-        del browsersteps_sessions[session_id]
-
-    # Remove from watch mapping
-    del browsersteps_watch_to_session[watch_uuid]
-
-    logger.debug(f"Cleaned up session for watch {watch_uuid}")
-
-    # Opportunistically cleanup any other expired sessions
-    cleanup_expired_sessions()
+            return loop.run_until_complete(coro)
+        finally:
+            loop.close()
 
 def construct_blueprint(datastore: ChangeDetectionStore):
     browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
 
     async def start_browsersteps_session(watch_uuid):
-        from changedetectionio.browser_steps import browser_steps
+        from . import browser_steps
         import time
         from playwright.async_api import async_playwright
 
+        # We keep the playwright session open for many minutes
         keepalive_seconds = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
-        keepalive_ms = ((keepalive_seconds + 3) * 1000)
 
         browsersteps_start_session = {'start_time': time.time()}
 
-        # Build proxy dict first — needed by both the CDP path and fetcher-specific launchers
-        proxy_id = datastore.get_preferred_proxy_for_watch(uuid=watch_uuid)
-        proxy = None
-        if proxy_id:
-            proxy_url = datastore.proxy_list.get(proxy_id, {}).get('url')
-            if proxy_url:
-                from urllib.parse import urlparse
-                parsed = urlparse(proxy_url)
-                proxy = {'server': proxy_url}
-                if parsed.username:
-                    proxy['username'] = parsed.username
-                if parsed.password:
-                    proxy['password'] = parsed.password
-                logger.debug(f"Browser Steps: UUID {watch_uuid} selected proxy {proxy_url}")
+        # Create a new async playwright instance for browser steps
+        playwright_instance = async_playwright()
+        playwright_context = await playwright_instance.start()
 
-        # Resolve the fetcher class for this watch so we can ask it to launch its own browser
-        # if it supports that (e.g. CloakBrowser, which runs locally rather than via CDP)
-        watch = datastore.data['watching'][watch_uuid]
-        from changedetectionio import content_fetchers
-        fetcher_class = content_fetchers.get_fetcher(watch.effective_browser_profile.fetch_backend)
-
-        browser = None
-        playwright_context = None
-
-        # If the fetcher has its own browser launch for the live steps UI, use it.
-        # get_browsersteps_browser(proxy, keepalive_ms) returns (browser, playwright_context_or_None)
-        # or None to fall back to the default CDP path.
-        if fetcher_class and hasattr(fetcher_class, 'get_browsersteps_browser'):
-            result = await fetcher_class.get_browsersteps_browser(proxy=proxy, keepalive_ms=keepalive_ms)
-            if result is not None:
-                browser, playwright_context = result
-                logger.debug(f"Browser Steps: using fetcher-specific browser for '{fetcher_class.__name__}'")
-
-        # Default: connect to the remote Playwright/sockpuppetbrowser via CDP
-        if browser is None:
-            playwright_instance = async_playwright()
-            playwright_context = await playwright_instance.start()
-            base_url = os.getenv('PLAYWRIGHT_DRIVER_URL', '').strip('"')
-            a = "?" if '?' not in base_url else '&'
-            base_url += a + f"timeout={keepalive_ms}"
-            browser = await playwright_context.chromium.connect_over_cdp(base_url, timeout=keepalive_ms)
-            logger.debug(f"Browser Steps: using CDP connection to {base_url}")
+        keepalive_ms = ((keepalive_seconds + 3) * 1000)
+        base_url = os.getenv('PLAYWRIGHT_DRIVER_URL', '').strip('"')
+        a = "?" if not '?' in base_url else '&'
+        base_url += a + f"timeout={keepalive_ms}"
 
+        browser = await playwright_context.chromium.connect_over_cdp(base_url, timeout=keepalive_ms)
         browsersteps_start_session['browser'] = browser
         browsersteps_start_session['playwright_context'] = playwright_context
 
+        proxy_id = datastore.get_preferred_proxy_for_watch(uuid=watch_uuid)
+        proxy = None
+        if proxy_id:
+            proxy_url = datastore.proxy_list.get(proxy_id).get('url')
+            if proxy_url:
+
+                # Playwright needs separate username and password values
+                from urllib.parse import urlparse
+                parsed = urlparse(proxy_url)
+                proxy = {'server': proxy_url}
+
+                if parsed.username:
+                    proxy['username'] = parsed.username
+
+                if parsed.password:
+                    proxy['password'] = parsed.password
+
+                logger.debug(f"Browser Steps: UUID {watch_uuid} selected proxy {proxy_url}")
+
+        # Tell Playwright to connect to Chrome and setup a new session via our stepper interface
         browserstepper = browser_steps.browsersteps_live_ui(
             playwright_browser=browser,
             proxy=proxy,
-            start_url=watch.link,
-            headers=watch.get('headers')
+            start_url=datastore.data['watching'][watch_uuid].link,
+            headers=datastore.data['watching'][watch_uuid].get('headers')
         )
+        
+        # Initialize the async connection
         await browserstepper.connect(proxy=proxy)
+        
         browsersteps_start_session['browserstepper'] = browserstepper
 
+        # For test
+        #await browsersteps_start_session['browserstepper'].action_goto_url(value="http://example.com?time="+str(time.time()))
+
         return browsersteps_start_session
 
 
@@ -269,6 +115,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     @browser_steps_blueprint.route("/browsersteps_start_session", methods=['GET'])
     def browsersteps_start_session():
         # A new session was requested, return sessionID
+        import asyncio
         import uuid
         browsersteps_session_id = str(uuid.uuid4())
         watch_uuid = request.args.get('uuid')
@@ -276,9 +123,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         if not watch_uuid:
             return make_response('No Watch UUID specified', 500)
 
-        # Cleanup any existing session for this watch
-        cleanup_session_for_watch(watch_uuid)
-
         logger.debug("Starting connection with playwright")
         logger.debug("browser_steps.py connecting")
 
@@ -287,10 +131,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             browsersteps_sessions[browsersteps_session_id] = run_async_in_browser_loop(
                 start_browsersteps_session(watch_uuid)
             )
-
-            # Store the mapping of watch_uuid -> browsersteps_session_id
-            browsersteps_watch_to_session[watch_uuid] = browsersteps_session_id
-
         except Exception as e:
             if 'ECONNREFUSED' in str(e):
                 return make_response('Unable to start the Playwright Browser session, is sockpuppetbrowser running? Network configuration is OK?', 401)
@@ -315,8 +155,8 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         watch = datastore.data['watching'].get(uuid)
         filename = f"step_before-{step_n}.jpeg" if request.args.get('type', '') == 'before' else f"step_{step_n}.jpeg"
 
-        if step_n and watch and os.path.isfile(os.path.join(watch.data_dir, filename)):
-            response = make_response(send_from_directory(directory=watch.data_dir, path=filename))
+        if step_n and watch and os.path.isfile(os.path.join(watch.watch_data_dir, filename)):
+            response = make_response(send_from_directory(directory=watch.watch_data_dir, path=filename))
             response.headers['Content-type'] = 'image/jpeg'
             response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
             response.headers['Pragma'] = 'no-cache'
@@ -331,10 +171,11 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     @browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])
     def browsersteps_ui_update():
         import base64
+        import playwright._impl._errors
+        from changedetectionio.blueprint.browser_steps import browser_steps
 
-        remaining = 0
+        remaining =0
         uuid = request.args.get('uuid')
-        goto_website_url_first_step = request.args.get('goto_website_url_first_step')
 
         browsersteps_session_id = request.args.get('browsersteps_session_id')
 
@@ -345,33 +186,33 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             return make_response('No session exists under that ID', 500)
 
         is_last_step = False
-
-        # @todo - should always be an existing session
-        if goto_website_url_first_step:
-            logger.debug("Going to site (requested automatically before stepping)..")
-            step_operation = "Goto site"
-            step_selector = None
-            step_optional_value = None
-        else:
+        # Actions - step/apply/etc, do the thing and return state
+        if request.method == 'POST':
+            # @todo - should always be an existing session
             step_operation = request.form.get('operation')
             step_selector = request.form.get('selector')
             step_optional_value = request.form.get('optional_value')
             is_last_step = strtobool(request.form.get('is_last_step'))
 
-        try:
-            # Run the async call_action method in the dedicated browser steps event loop
-            run_async_in_browser_loop(
-                browsersteps_sessions[browsersteps_session_id]['browserstepper'].call_action(
-                    action_name=step_operation,
-                    selector=step_selector,
-                    optional_value=step_optional_value
+            try:
+                # Run the async call_action method in the dedicated browser steps event loop
+                run_async_in_browser_loop(
+                    browsersteps_sessions[browsersteps_session_id]['browserstepper'].call_action(
+                        action_name=step_operation,
+                        selector=step_selector,
+                        optional_value=step_optional_value
+                    )
                 )
-            )
 
-        except Exception as e:
-            logger.error(f"Exception when calling step operation {step_operation} {str(e)}")
-            # Try to find something of value to give back to the user
-            return make_response(str(e).splitlines()[0], 401)
+            except Exception as e:
+                logger.error(f"Exception when calling step operation {step_operation} {str(e)}")
+                # Try to find something of value to give back to the user
+                return make_response(str(e).splitlines()[0], 401)
+
+
+#        if not this_session.page:
+#            cleanup_playwright_session()
+#            return make_response('Browser session ran out of time :( Please reload this page.', 401)
 
         # Screenshots and other info only needed on requesting a step (POST)
         try:
@@ -379,7 +220,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             (screenshot, xpath_data) = run_async_in_browser_loop(
                 browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
             )
-
+                
             if is_last_step:
                 watch = datastore.data['watching'].get(uuid)
                 u = browsersteps_sessions[browsersteps_session_id]['browserstepper'].page.url

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -8,17 +8,6 @@ from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT
 from changedetectionio.content_fetchers.base import manage_user_agent
 from changedetectionio.jinja2_custom import render as jinja_render
 
-def browser_steps_get_valid_steps(browser_steps: list):
-    if browser_steps is not None and len(browser_steps):
-        valid_steps = list(filter(
-            lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one'),browser_steps))
-
-        # Just incase they selected Goto site by accident with older JS
-        if valid_steps and valid_steps[0]['operation'] == 'Goto site':
-            del(valid_steps[0])
-
-        return valid_steps
-    return []
 
 
 # Two flags, tell the JS which of the "Selector" or "Value" field should be enabled in the front end

changedetectionio/blueprint/check_proxies/__init__.py

@@ -40,14 +40,12 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         contents = ''
         now = time.time()
         try:
-            import asyncio
             processor_module = importlib.import_module("changedetectionio.processors.text_json_diff.processor")
             update_handler = processor_module.perform_site_check(datastore=datastore,
                                                                  watch_uuid=uuid
                                                                  )
 
-            update_handler.preferred_proxy_override = preferred_proxy
-            asyncio.run(update_handler.call_browser())
+            update_handler.call_browser(preferred_proxy_id=preferred_proxy)
         # title, size is len contents not len xfer
         except content_fetcher_exceptions.Non200ErrorCodeReceived as e:
             if e.status_code == 404:
@@ -96,13 +94,13 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         return results
 
     @login_required
-    @check_proxies_blueprint.route("/<uuid_str:uuid>/status", methods=['GET'])
+    @check_proxies_blueprint.route("/<string:uuid>/status", methods=['GET'])
     def get_recheck_status(uuid):
         results = _recalc_check_status(uuid=uuid)
         return results
 
     @login_required
-    @check_proxies_blueprint.route("/<uuid_str:uuid>/start", methods=['GET'])
+    @check_proxies_blueprint.route("/<string:uuid>/start", methods=['GET'])
     def start_check(uuid):
 
         if not datastore.proxy_list:

changedetectionio/blueprint/imports/__init__.py

@@ -1,8 +1,13 @@
 from flask import Blueprint, request, redirect, url_for, flash, render_template
-from loguru import logger
-
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
+from changedetectionio import worker_handler
+from changedetectionio.blueprint.imports.importer import (
+    import_url_list, 
+    import_distill_io_json, 
+    import_xlsx_wachete, 
+    import_xlsx_custom
+)
 
 def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
     import_blueprint = Blueprint('imports', __name__, template_folder="templates")
@@ -12,27 +17,15 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
     def import_page():
         remaining_urls = []
         from changedetectionio import forms
-#
+
         if request.method == 'POST':
-#            from changedetectionio import worker_pool
-
-            from changedetectionio.blueprint.imports.importer import (
-                import_url_list,
-                import_distill_io_json,
-                import_xlsx_wachete,
-                import_xlsx_custom
-            )
-
             # URL List import
             if request.values.get('urls') and len(request.values.get('urls').strip()):
                 # Import and push into the queue for immediate update check
-                from changedetectionio import processors
                 importer_handler = import_url_list()
-                importer_handler.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', processors.get_default_processor()))
-                logger.debug(f"Imported {len(importer_handler.new_uuids)} new UUIDs")
-                # Dont' add to queue because scheduler can see that they haven't been checked and will add them to the queue
-#                for uuid in importer_handler.new_uuids:
-#                    worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                importer_handler.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', 'text_json_diff'))
+                for uuid in importer_handler.new_uuids:
+                    worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
                 if len(importer_handler.remaining_data) == 0:
                     return redirect(url_for('watchlist.index'))
@@ -44,10 +37,8 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                 # Import and push into the queue for immediate update check
                 d_importer = import_distill_io_json()
                 d_importer.run(data=request.values.get('distill-io'), flash=flash, datastore=datastore)
-                # Dont' add to queue because scheduler can see that they haven't been checked and will add them to the queue
-#                for uuid in importer_handler.new_uuids:
-#                    worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-
+                for uuid in d_importer.new_uuids:
+                    worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
             # XLSX importer
             if request.files and request.files.get('xlsx_file'):
@@ -69,10 +60,8 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                     w_importer.import_profile = map
                     w_importer.run(data=file, flash=flash, datastore=datastore)
 
-                # Dont' add to queue because scheduler can see that they haven't been checked and will add them to the queue
-#                for uuid in importer_handler.new_uuids:
-#                    worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-
+                for uuid in w_importer.new_uuids:
+                    worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
         # Could be some remaining, or we could be on GET
         form = forms.importForm(formdata=request.form if request.method == 'POST' else None)

changedetectionio/blueprint/imports/importer.py

@@ -62,7 +62,7 @@ class import_url_list(Importer):
                 extras = None
                 if processor:
                     extras = {'processor': processor}
-                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, save_immediately=False, extras=extras)
+                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False, extras=extras)
 
                 if new_uuid:
                     # Straight into the queue.
@@ -129,7 +129,7 @@ class import_distill_io_json(Importer):
                 new_uuid = datastore.add_watch(url=d['uri'].strip(),
                                                tag=",".join(d.get('tags', [])),
                                                extras=extras,
-                                               save_immediately=False)
+                                               write_to_disk_now=False)
 
                 if new_uuid:
                     # Straight into the queue.
@@ -175,9 +175,9 @@ class import_xlsx_wachete(Importer):
                 dynamic_wachet = str(data.get('dynamic wachet', '')).strip().lower()  # Convert bool to str to cover all cases
                 # libreoffice and others can have it as =FALSE() =TRUE(), or bool(true)
                 if 'true' in dynamic_wachet or dynamic_wachet == '1':
-                    extras['browser_profile'] = 'browser_chromeplaywright'
+                    extras['fetch_backend'] = 'html_webdriver'
                 elif 'false' in dynamic_wachet or dynamic_wachet == '0':
-                    extras['browser_profile'] = 'direct_http_requests'
+                    extras['fetch_backend'] = 'html_requests'
 
                 if data.get('xpath'):
                     # @todo split by || ?
@@ -204,7 +204,7 @@ class import_xlsx_wachete(Importer):
                     new_uuid = datastore.add_watch(url=data['url'].strip(),
                                                    extras=extras,
                                                    tag=data.get('folder'),
-                                                   save_immediately=False)
+                                                   write_to_disk_now=False)
                     if new_uuid:
                         # Straight into the queue.
                         self.new_uuids.append(new_uuid)
@@ -287,7 +287,7 @@ class import_xlsx_custom(Importer):
                     new_uuid = datastore.add_watch(url=url,
                                                    extras=extras,
                                                    tag=tags,
-                                                   save_immediately=False)
+                                                   write_to_disk_now=False)
                     if new_uuid:
                         # Straight into the queue.
                         self.new_uuids.append(new_uuid)

changedetectionio/blueprint/imports/templates/import.html

@@ -16,11 +16,6 @@
         <form class="pure-form" action="{{url_for('imports.import_page')}}" method="POST" enctype="multipart/form-data">
             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
             <div class="tab-pane-inner" id="url-list">
-
-                <p>
-                {{ _('Restoring changedetection.io backups is in the') }}<a href="{{ url_for('backups.restore.restore') }}"> {{ _('backups section') }}</a>.
-                <br>
-                </p>
                 <div class="pure-control-group">
                         {{ _('Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma (,):') }}
                         <br>
@@ -42,6 +37,9 @@
             </div>
 
             <div class="tab-pane-inner" id="distill-io">
+
+
+
                     <div class="pure-control-group">
                         {{ _('Copy and Paste your Distill.io watch \'export\' file, this should be a JSON file.') }}<br>
                         {{ _('This is') }} <i>{{ _('experimental') }}</i>, {{ _('supported fields are') }} <code>name</code>, <code>uri</code>, <code>tags</code>, <code>config:selections</code>, {{ _('the rest (including') }} <code>schedule</code>) {{ _('are ignored.') }}
@@ -51,6 +49,8 @@
                         {{ _('Be sure to set your default fetcher to Chrome if required.') }}<br>
                         </p>
                     </div>
+
+
                     <textarea name="distill-io" class="pure-input-1-2" style="width: 100%;
                                 font-family:monospace;
                                 white-space: pre;
@@ -114,7 +114,6 @@
                 </div>
             </div>
             <button type="submit" class="pure-button pure-input-1-2 pure-button-primary">{{ _('Import') }}</button>
-
         </form>
 
     </div>

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -4,7 +4,7 @@ from flask import Blueprint, flash, redirect, url_for
 from flask_login import login_required
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio import queuedWatchMetaData
-from changedetectionio import worker_pool
+from changedetectionio import worker_handler
 from queue import PriorityQueue
 
 PRICE_DATA_TRACK_ACCEPT = 'accepted'
@@ -15,20 +15,18 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue
     price_data_follower_blueprint = Blueprint('price_data_follower', __name__)
 
     @login_required
-    @price_data_follower_blueprint.route("/<uuid_str:uuid>/accept", methods=['GET'])
+    @price_data_follower_blueprint.route("/<string:uuid>/accept", methods=['GET'])
     def accept(uuid):
         datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_ACCEPT
         datastore.data['watching'][uuid]['processor'] = 'restock_diff'
         datastore.data['watching'][uuid].clear_watch()
-        datastore.data['watching'][uuid].commit()
-        worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+        worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
         return redirect(url_for("watchlist.index"))
 
     @login_required
-    @price_data_follower_blueprint.route("/<uuid_str:uuid>/reject", methods=['GET'])
+    @price_data_follower_blueprint.route("/<string:uuid>/reject", methods=['GET'])
     def reject(uuid):
         datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_REJECT
-        datastore.data['watching'][uuid].commit()
         return redirect(url_for("watchlist.index"))
 
 

changedetectionio/blueprint/rss/single_watch.py

@@ -9,12 +9,11 @@ def construct_single_watch_routes(rss_blueprint, datastore):
         datastore: The ChangeDetectionStore instance
     """
 
-    @rss_blueprint.route("/watch/<uuid_str:uuid>", methods=['GET'])
+    @rss_blueprint.route("/watch/<string:uuid>", methods=['GET'])
     def rss_single_watch(uuid):
         import time
 
-        from flask import make_response, request, Response
-        from flask_babel import lazy_gettext as _l
+        from flask import make_response, request
         from feedgen.feed import FeedGenerator
         from loguru import logger
 
@@ -38,17 +37,18 @@ def construct_single_watch_routes(rss_blueprint, datastore):
 
         rss_content_format = datastore.data['settings']['application'].get('rss_content_format')
 
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
         # Get the watch by UUID
         watch = datastore.data['watching'].get(uuid)
         if not watch:
-            return Response(_l("Watch with UUID %(uuid)s not found", uuid=uuid), status=404, mimetype='text/plain')
+            return f"Watch with UUID {uuid} not found", 404
 
         # Check if watch has at least 2 history snapshots
         dates = list(watch.history.keys())
         if len(dates) < 2:
-            return Response(_l("Watch %(uuid)s does not have enough history snapshots to show changes (need at least 2)", uuid=uuid), status=400, mimetype='text/plain')
+            return f"Watch {uuid} does not have enough history snapshots to show changes (need at least 2)", 400
+
+        # Add uuid to watch for proper functioning
+        watch['uuid'] = uuid
 
         # Get the number of diffs to include (default: 5)
         rss_diff_length = datastore.data['settings']['application'].get('rss_diff_length', 5)
@@ -101,7 +101,7 @@ def construct_single_watch_routes(rss_blueprint, datastore):
                                      date_index_from, date_index_to)
 
             # Create and populate feed entry
-            guid = f"{uuid}/{timestamp_to}"
+            guid = f"{watch['uuid']}/{timestamp_to}"
             fe = fg.add_entry()
             title_suffix = f"Change @ {res['original_context']['change_datetime']}"
             populate_feed_entry(fe, watch, res.get('body', ''), guid, timestamp_to,

changedetectionio/blueprint/rss/tag.py

@@ -7,7 +7,7 @@ def construct_tag_routes(rss_blueprint, datastore):
         datastore: The ChangeDetectionStore instance
     """
 
-    @rss_blueprint.route("/tag/<uuid_str:tag_uuid>", methods=['GET'])
+    @rss_blueprint.route("/tag/<string:tag_uuid>", methods=['GET'])
     def rss_tag_feed(tag_uuid):
 
         from flask import make_response, request, url_for
@@ -63,8 +63,11 @@ def construct_tag_routes(rss_blueprint, datastore):
 
             # Only include unviewed watches
             if not watch.viewed:
-                # Include a link to the diff page (use uuid from loop, don't modify watch dict)
-                diff_link = {'href': url_for('ui.ui_diff.diff_history_page', uuid=uuid, _external=True)}
+                # Add uuid to watch for proper functioning
+                watch['uuid'] = uuid
+
+                # Include a link to the diff page
+                diff_link = {'href': url_for('ui.ui_diff.diff_history_page', uuid=watch['uuid'], _external=True)}
 
                 # Get watch label
                 watch_label = get_watch_label(datastore, watch)

changedetectionio/blueprint/settings/__init__.py

@@ -1,9 +1,8 @@
 import os
 from copy import deepcopy
-from datetime import datetime, timedelta
+from datetime import datetime
 from zoneinfo import ZoneInfo, available_timezones
 import secrets
-import time
 import flask_login
 from flask import Blueprint, render_template, request, redirect, url_for, flash
 from flask_babel import gettext
@@ -15,9 +14,6 @@ from changedetectionio.auth_decorator import login_optionally_required
 def construct_blueprint(datastore: ChangeDetectionStore):
     settings_blueprint = Blueprint('settings', __name__, template_folder="templates")
 
-    from changedetectionio.blueprint.settings.browser_profile import construct_blueprint as construct_browser_profile_blueprint
-    settings_blueprint.register_blueprint(construct_browser_profile_blueprint(datastore), url_prefix='/browsers')
-
     @settings_blueprint.route("", methods=['GET', "POST"])
     @login_optionally_required
     def settings_page():
@@ -78,37 +74,26 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                     del (app_update['password'])
 
                 datastore.data['settings']['application'].update(app_update)
-
+                
                 # Handle dynamic worker count adjustment
                 old_worker_count = datastore.data['settings']['requests'].get('workers', 1)
                 new_worker_count = form.data['requests'].get('workers', 1)
-
+                
                 datastore.data['settings']['requests'].update(form.data['requests'])
-                datastore.commit()
-
-                # Clear all checksums to force reprocessing with new settings
-                # Global settings can affect watch behavior (filters, rendering, etc.)
-                datastore.clear_all_last_checksums()
-
+                
                 # Adjust worker count if it changed
                 if new_worker_count != old_worker_count:
-                    from changedetectionio import worker_pool
+                    from changedetectionio import worker_handler
                     from changedetectionio.flask_app import update_q, notification_q, app, datastore as ds
-
-                    # Check CPU core availability and warn if worker count is high
-                    cpu_count = os.cpu_count()
-                    if cpu_count and new_worker_count >= (cpu_count * 0.9):
-                        flash(gettext("Warning: Worker count ({}) is close to or exceeds available CPU cores ({})").format(
-                            new_worker_count, cpu_count), 'warning')
-
-                    result = worker_pool.adjust_async_worker_count(
+                    
+                    result = worker_handler.adjust_async_worker_count(
                         new_count=new_worker_count,
                         update_q=update_q,
                         notification_q=notification_q,
                         app=app,
                         datastore=ds
                     )
-
+                    
                     if result['status'] == 'success':
                         flash(gettext("Worker count adjusted: {}").format(result['message']), 'notice')
                     elif result['status'] == 'not_supported':
@@ -118,11 +103,13 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
                 if not os.getenv("SALTED_PASS", False) and len(form.application.form.password.encrypted_password):
                     datastore.data['settings']['application']['password'] = form.application.form.password.encrypted_password
-                    datastore.commit()
+                    datastore.needs_write_urgent = True
                     flash(gettext("Password protection enabled."), 'notice')
                     flask_login.logout_user()
                     return redirect(url_for('watchlist.index'))
 
+                datastore.needs_write_urgent = True
+
                 # Also save plugin settings from the same form submission
                 plugin_tabs_list = get_plugin_settings_tabs()
                 for tab in plugin_tabs_list:
@@ -150,9 +137,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         active_plugins = get_active_plugins()
         python_version = f"{sys.version_info.major}.{sys.version_info.minor}.{sys.version_info.micro}"
 
-        # Calculate uptime in seconds
-        uptime_seconds = time.time() - datastore.start_time
-
         # Get plugin settings tabs and instantiate forms
         plugin_tabs = get_plugin_settings_tabs()
         plugin_forms = {}
@@ -171,7 +155,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                                 active_plugins=active_plugins,
                                 api_key=datastore.data['settings']['application'].get('api_access_token'),
                                 python_version=python_version,
-                                uptime_seconds=uptime_seconds,
                                 available_timezones=sorted(available_timezones()),
                                 emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
                                 extra_notification_token_placeholder_info=datastore.get_unique_notification_token_placeholders_available(),
@@ -192,7 +175,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def settings_reset_api_key():
         secret = secrets.token_hex(16)
         datastore.data['settings']['application']['api_access_token'] = secret
-        datastore.commit()
+        datastore.needs_write_urgent = True
         flash(gettext("API Key was regenerated."))
         return redirect(url_for('settings.settings_page')+'#api')
         
@@ -204,32 +187,4 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                                logs=notification_debug_log if len(notification_debug_log) else ["Notification logs are empty - no notifications sent yet."])
         return output
 
-    @settings_blueprint.route("/toggle-all-paused", methods=['GET'])
-    @login_optionally_required
-    def toggle_all_paused():
-        current_state = datastore.data['settings']['application'].get('all_paused', False)
-        datastore.data['settings']['application']['all_paused'] = not current_state
-        datastore.commit()
-
-        if datastore.data['settings']['application']['all_paused']:
-            flash(gettext("Automatic scheduling paused - checks will not be queued."), 'notice')
-        else:
-            flash(gettext("Automatic scheduling resumed - checks will be queued normally."), 'notice')
-
-        return redirect(url_for('watchlist.index'))
-
-    @settings_blueprint.route("/toggle-all-muted", methods=['GET'])
-    @login_optionally_required
-    def toggle_all_muted():
-        current_state = datastore.data['settings']['application'].get('all_muted', False)
-        datastore.data['settings']['application']['all_muted'] = not current_state
-        datastore.commit()
-
-        if datastore.data['settings']['application']['all_muted']:
-            flash(gettext("All notifications muted."), 'notice')
-        else:
-            flash(gettext("All notifications unmuted."), 'notice')
-
-        return redirect(url_for('watchlist.index'))
-
     return settings_blueprint

changedetectionio/blueprint/settings/browser_profile/__init__.py

@@ -1,196 +0,0 @@
-import flask_login
-from flask import Blueprint, render_template, request, redirect, url_for, flash
-from flask_babel import gettext
-
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio.auth_decorator import login_optionally_required
-
-
-def construct_blueprint(datastore: ChangeDetectionStore):
-    settings_browser_profile_blueprint = Blueprint(
-        'settings_browsers',
-        __name__,
-        template_folder="templates"
-    )
-
-    def _render_index(browser_profile_form=None, editing_machine_name=None):
-        from changedetectionio import forms
-        from changedetectionio import content_fetchers as cf
-        from changedetectionio.model.browser_profile import BrowserProfile, RESERVED_MACHINE_NAMES
-
-        # Only browser-capable fetchers are valid profile types
-        fetcher_choices = cf.available_browser_fetchers()
-        if browser_profile_form is None:
-            browser_profile_form = forms.BrowserProfileForm()
-        browser_profile_form.fetch_backend.choices = fetcher_choices
-
-        fetcher_supports_screenshots = {name: True for name, _ in fetcher_choices}
-
-        # Table shows default built-in profiles first, then user-created profiles
-        store_profiles = datastore.data['settings']['application'].get('browser_profiles', {})
-        user_profiles = dict(cf.DEFAULT_BROWSER_PROFILES)
-        for machine_name, raw in store_profiles.items():
-            try:
-                user_profiles[machine_name] = BrowserProfile(**raw) if isinstance(raw, dict) else raw
-            except Exception:
-                pass
-
-        current_default = datastore.data['settings']['application'].get('browser_profile') or 'direct_http_requests'
-
-        return render_template(
-            "browser_profiles.html",
-            browser_profiles=user_profiles,
-            browser_profile_form=browser_profile_form,
-            reserved_browser_profile_names=RESERVED_MACHINE_NAMES,
-            fetcher_choices=fetcher_choices,
-            fetcher_supports_screenshots=fetcher_supports_screenshots,
-            current_default_profile=current_default,
-            editing_machine_name=editing_machine_name,
-        )
-
-    @settings_browser_profile_blueprint.route("", methods=['GET'])
-    @login_optionally_required
-    def index():
-        return _render_index()
-
-    @settings_browser_profile_blueprint.route("/<string:machine_name>/edit", methods=['GET'])
-    @login_optionally_required
-    def edit(machine_name):
-        from changedetectionio import forms
-        from changedetectionio.model.browser_profile import BrowserProfile, RESERVED_MACHINE_NAMES
-
-        if machine_name in RESERVED_MACHINE_NAMES:
-            flash(gettext("Built-in browser profiles cannot be edited."), 'error')
-            return redirect(url_for('settings.settings_browsers.index'))
-
-        store_profiles = datastore.data['settings']['application'].get('browser_profiles', {})
-        raw = store_profiles.get(machine_name)
-        if raw is None:
-            flash(gettext("Browser profile not found."), 'error')
-            return redirect(url_for('settings.settings_browsers.index'))
-
-        profile = BrowserProfile(**raw) if isinstance(raw, dict) else raw
-        form = forms.BrowserProfileForm(data=profile.model_dump())
-        return _render_index(browser_profile_form=form, editing_machine_name=machine_name)
-
-    @settings_browser_profile_blueprint.route("/save", methods=['POST'])
-    @login_optionally_required
-    def save():
-        from changedetectionio import forms
-        from changedetectionio import content_fetchers as cf
-        from changedetectionio.model.browser_profile import BrowserProfile, RESERVED_MACHINE_NAMES
-
-        fetcher_choices = [(name, desc) for name, desc in cf.available_fetchers()]
-        browser_profile_form = forms.BrowserProfileForm(formdata=request.form)
-        browser_profile_form.fetch_backend.choices = fetcher_choices
-
-        if not browser_profile_form.validate():
-            flash(gettext("Browser profile error: {}").format(
-                '; '.join(str(e) for errs in browser_profile_form.errors.values() for e in errs)
-            ), 'error')
-            return redirect(url_for('settings.settings_browsers.index'))
-
-        name = browser_profile_form.name.data.strip()
-        machine_name = BrowserProfile.machine_name_from_str(name)
-
-        if machine_name in RESERVED_MACHINE_NAMES:
-            flash(gettext("Cannot use reserved profile name '{}'. Please choose a different name.").format(name), 'error')
-            return redirect(url_for('settings.settings_browsers.index'))
-
-        original_machine_name = request.form.get('original_machine_name', '').strip()
-        store_profiles = datastore.data['settings']['application'].setdefault('browser_profiles', {})
-
-        if machine_name != original_machine_name and machine_name in store_profiles:
-            flash(gettext("A browser profile named '{}' already exists.").format(name), 'error')
-            return redirect(url_for('settings.settings_browsers.index'))
-
-        profile_data = {
-            'name': name,
-            'fetch_backend': browser_profile_form.fetch_backend.data,
-            'browser_connection_url': browser_profile_form.browser_connection_url.data or None,
-            'viewport_width': browser_profile_form.viewport_width.data or 1280,
-            'viewport_height': browser_profile_form.viewport_height.data or 1000,
-            'block_images': bool(browser_profile_form.block_images.data),
-            'block_fonts': bool(browser_profile_form.block_fonts.data),
-            'ignore_https_errors': bool(browser_profile_form.ignore_https_errors.data),
-            'user_agent': browser_profile_form.user_agent.data or None,
-            'locale': browser_profile_form.locale.data or None,
-            'is_builtin': False,
-        }
-
-        try:
-            BrowserProfile(**profile_data)
-        except Exception as e:
-            flash(gettext("Browser profile validation error: {}").format(str(e)), 'error')
-            return redirect(url_for('settings.settings_browsers.index'))
-
-        # Handle rename: remove old key, cascade-update watches and tags
-        if original_machine_name and original_machine_name != machine_name and original_machine_name in store_profiles:
-            del store_profiles[original_machine_name]
-            for watch in datastore.data['watching'].values():
-                if watch.get('browser_profile') == original_machine_name:
-                    watch['browser_profile'] = machine_name
-            for tag in datastore.data.get('settings', {}).get('application', {}).get('tags', {}).values():
-                if tag.get('browser_profile') == original_machine_name:
-                    tag['browser_profile'] = machine_name
-
-        store_profiles[machine_name] = profile_data
-        datastore.commit()
-        flash(gettext("Browser profile '{}' saved.").format(name), 'notice')
-        return redirect(url_for('settings.settings_browsers.index'))
-
-    @settings_browser_profile_blueprint.route("/<string:machine_name>/delete", methods=['GET'])
-    @login_optionally_required
-    def delete(machine_name):
-        from changedetectionio.model.browser_profile import RESERVED_MACHINE_NAMES
-
-        if machine_name in RESERVED_MACHINE_NAMES:
-            flash(gettext("Built-in browser profiles cannot be deleted."), 'error')
-            return redirect(url_for('settings.settings_browsers.index'))
-
-        store_profiles = datastore.data['settings']['application'].get('browser_profiles', {})
-        if machine_name not in store_profiles:
-            flash(gettext("Browser profile not found."), 'error')
-            return redirect(url_for('settings.settings_browsers.index'))
-
-        raw = store_profiles[machine_name]
-        profile_name = raw.get('name', machine_name) if isinstance(raw, dict) else machine_name
-
-        for watch in datastore.data['watching'].values():
-            if watch.get('browser_profile') == machine_name:
-                watch['browser_profile'] = None
-
-        for tag in datastore.data.get('settings', {}).get('application', {}).get('tags', {}).values():
-            if tag.get('browser_profile') == machine_name:
-                tag['browser_profile'] = None
-
-        if datastore.data['settings']['application'].get('browser_profile') == machine_name:
-            datastore.data['settings']['application']['browser_profile'] = None
-
-        del store_profiles[machine_name]
-        datastore.commit()
-        flash(gettext("Browser profile '{}' deleted.").format(profile_name), 'notice')
-        return redirect(url_for('settings.settings_browsers.index'))
-
-    @settings_browser_profile_blueprint.route("/set-default", methods=['POST'])
-    @login_optionally_required
-    def set_default():
-        from changedetectionio import content_fetchers as cf
-
-        machine_name = request.form.get('machine_name', '').strip()
-        if not machine_name:
-            flash(gettext("No profile specified."), 'error')
-            return redirect(url_for('settings.settings_browsers.index'))
-
-        from changedetectionio.model.browser_profile import get_profile
-        store_profiles = datastore.data['settings']['application'].get('browser_profiles', {})
-        if get_profile(machine_name, store_profiles) is None:
-            flash(gettext("Unknown browser profile '{}'.").format(machine_name), 'error')
-            return redirect(url_for('settings.settings_browsers.index'))
-
-        datastore.data['settings']['application']['browser_profile'] = machine_name
-        datastore.commit()
-        flash(gettext("Default browser profile set to '{}'.").format(machine_name), 'notice')
-        return redirect(url_for('settings.settings_browsers.index'))
-
-    return settings_browser_profile_blueprint

changedetectionio/blueprint/settings/browser_profile/templates/browser_profiles.html

@@ -1,154 +0,0 @@
-{% extends 'base.html' %}
-{% block content %}
-{% from '_helpers.html' import render_field, render_checkbox_field, render_button %}
-
-<div class="edit-form">
-    <div class="box-wrap inner">
-        <h2>{{ _('Browser Profiles') }}</h2>
-        <p>{{ _('Create named profiles to configure browser settings — viewport size, connection URL, image/font blocking, and more. Each profile is based on an available browser type.') }}</p>
-
-        <form id="set-default-form" action="{{ url_for('settings.settings_browsers.set_default') }}" method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
-            <input type="hidden" name="machine_name" id="default-machine-name" value="">
-        </form>
-        {% if browser_profiles %}
-        <table class="pure-table pure-table-striped" style="width:100%; margin-bottom:1.5em;">
-            <thead>
-                <tr>
-                    <th style="width:2.5em; text-align:center;" title="{{ _('System default') }}">{{ _('Default') }}</th>
-                    <th>{{ _('Name') }}</th>
-                    <th>{{ _('Type') }}</th>
-                    <th style="width:3em; text-align:center;"></th>
-                    <th>{{ _('Viewport') }}</th>
-                    <th>{{ _('Options') }}</th>
-                    <th></th>
-                </tr>
-            </thead>
-            <tbody>
-            {% for machine_name, profile in browser_profiles.items() %}
-                <tr>
-                    <td style="text-align:center;">
-                        <input type="radio"
-                               name="default_profile"
-                               value="{{ machine_name }}"
-                               title="{{ _('Set as system default') }}"
-                               {% if machine_name == current_default_profile %}checked{% endif %}
-                               onchange="setDefaultProfile('{{ machine_name }}')">
-                    </td>
-                    <td>{{ profile.name }}</td>
-                    <td><code>{{ profile.fetch_backend }}</code></td>
-                    <td style="text-align:center;">{{ profile.get_fetcher_class_name()|fetcher_status_icons }}</td>
-                    <td>{{ profile.viewport_width }}×{{ profile.viewport_height }}</td>
-                    <td style="font-size:0.8em; line-height:1.6;">
-                        {% if profile.block_images %}{{ _('No images') }}<br>{% endif %}
-                        {% if profile.block_fonts %}{{ _('No fonts') }}<br>{% endif %}
-                        {% if profile.ignore_https_errors %}{{ _('Ignore TLS') }}<br>{% endif %}
-                        {% if profile.browser_connection_url %}<span title="{{ profile.browser_connection_url }}">{{ _('Custom URL') }}</span>{% endif %}
-                    </td>
-                    <td style="white-space:nowrap;">
-                        {% if not profile.is_builtin %}
-                        <a href="{{ url_for('settings.settings_browsers.edit', machine_name=machine_name) }}"
-                           class="pure-button button-small">{{ _('Edit') }}</a>
-                        <a href="{{ url_for('settings.settings_browsers.delete', machine_name=machine_name) }}"
-                           class="pure-button button-small button-error"
-                           onclick="return confirm('{{ _('Delete this browser profile?') }}')">{{ _('Delete') }}</a>
-                        {% endif %}
-                    </td>
-                </tr>
-            {% endfor %}
-            </tbody>
-        </table>
-        {% else %}
-        <p style="color:#888; font-style:italic;">{{ _('No browser profiles configured yet. Add one below.') }}</p>
-        {% endif %}
-
-        <div class="border-fieldset">
-            <h3 id="profile-form-heading">{{ _('Edit browser profile') if editing_machine_name else _('Add new browser profile') }}</h3>
-            {% if not editing_machine_name %}
-            <p style="font-size:0.9em; color:#666;">{{ _('Choose a browser type, give it a name, and configure its settings. You can create multiple profiles from the same type with different connection URLs or options.') }}</p>
-            {% endif %}
-            <form class="pure-form pure-form-stacked"
-                  id="browser-profile-form"
-                  action="{{ url_for('settings.settings_browsers.save') }}"
-                  method="POST">
-                <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
-                <input type="hidden" name="original_machine_name" id="original_machine_name" value="{{ editing_machine_name or '' }}">
-                <fieldset>
-                    <div class="pure-control-group">
-                        {{ render_field(browser_profile_form.name) }}
-                    </div>
-                    <div class="pure-control-group inline-radio">
-                        {{ render_field(browser_profile_form.fetch_backend, id="profile-fetch-backend") }}
-                    </div>
-                    <div class="pure-control-group browser-only-field">
-                        {{ render_field(browser_profile_form.browser_connection_url) }}
-                        <span class="pure-form-message-inline">{{ _('Optional — override the system CDP/WebSocket URL for this profile only (e.g.') }} <code>ws://my-chrome:3000</code>).</span>
-                    </div>
-                    <div class="pure-control-group browser-only-field" style="display:flex; gap:1em; flex-wrap:wrap;">
-                        <div>{{ render_field(browser_profile_form.viewport_width) }}</div>
-                        <div>{{ render_field(browser_profile_form.viewport_height) }}</div>
-                    </div>
-                    <div class="pure-control-group browser-only-field">
-                        {{ render_checkbox_field(browser_profile_form.block_images) }}
-                        <span class="pure-form-message-inline">{{ _('Block image downloads — speeds up loads on image-heavy pages.') }}</span>
-                    </div>
-                    <div class="pure-control-group browser-only-field">
-                        {{ render_checkbox_field(browser_profile_form.block_fonts) }}
-                        <span class="pure-form-message-inline">{{ _('Block web font downloads.') }}</span>
-                    </div>
-                    <div class="pure-control-group browser-only-field">
-                        {{ render_checkbox_field(browser_profile_form.ignore_https_errors) }}
-                        <span class="pure-form-message-inline">{{ _('Ignore TLS/HTTPS certificate errors (useful for self-signed certs on staging sites).') }}</span>
-                    </div>
-                    <div class="pure-control-group browser-only-field">
-                        {{ render_field(browser_profile_form.user_agent) }}
-                        <span class="pure-form-message-inline">{{ _("Leave blank to use the fetcher's default User-Agent.") }}</span>
-                    </div>
-                    <div class="pure-control-group browser-only-field">
-                        {{ render_field(browser_profile_form.locale) }}
-                        <span class="pure-form-message-inline">{{ _('Sets Accept-Language and navigator.language (e.g. en-US, de-DE).') }}</span>
-                    </div>
-                    <div class="pure-control-group">
-                        <button type="submit" class="pure-button pure-button-primary" id="profile-submit-btn">{{ _('Save profile') }}</button>
-                        {% if editing_machine_name %}
-                        <a href="{{ url_for('settings.settings_browsers.index') }}" class="pure-button button-cancel">{{ _('Cancel') }}</a>
-                        {% endif %}
-                        <a href="{{ url_for('settings.settings_page') }}" class="pure-button button-cancel">{{ _('Back to Settings') }}</a>
-                    </div>
-                </fieldset>
-            </form>
-        </div>
-    </div>
-</div>
-
-<script>
-function setDefaultProfile(machineName) {
-    document.getElementById('default-machine-name').value = machineName;
-    document.getElementById('set-default-form').submit();
-}
-
-const fetcherSupportsBrowser = {{ fetcher_supports_screenshots | tojson }};
-
-function updateBrowserFieldVisibility() {
-    const fetchBackend = document.getElementById('profile-fetch-backend').value;
-    const isBrowser = !!fetcherSupportsBrowser[fetchBackend];
-    document.querySelectorAll('.browser-only-field').forEach(function(el) {
-        el.style.display = isBrowser ? '' : 'none';
-    });
-}
-
-document.addEventListener('DOMContentLoaded', function() {
-    const sel = document.getElementById('profile-fetch-backend');
-    if (sel) {
-        sel.addEventListener('change', updateBrowserFieldVisibility);
-        updateBrowserFieldVisibility();
-    }
-});
-
-{% if editing_machine_name %}
-document.addEventListener('DOMContentLoaded', function() {
-    document.getElementById('browser-profile-form').scrollIntoView({behavior: 'smooth'});
-});
-{% endif %}
-</script>
-{% endblock %}

changedetectionio/blueprint/settings/templates/settings.html

@@ -25,10 +25,8 @@
             <li class="tab"><a href="#ui-options">{{ _('UI Options') }}</a></li>
             <li class="tab"><a href="#api">{{ _('API') }}</a></li>
             <li class="tab"><a href="#rss">{{ _('RSS') }}</a></li>
-            <li class="tab"><a href="{{ url_for('backups.create') }}">{{ _('Backups') }}</a></li>
             <li class="tab"><a href="#timedate">{{ _('Time & Date') }}</a></li>
             <li class="tab"><a href="#proxies">{{ _('CAPTCHA & Proxies') }}</a></li>
-            <li class="tab"><a href="{{ url_for('settings.settings_browsers.index') }}">{{ _('Browsers') }}</a></li>
             {% if plugin_tabs %}
                 {% for tab in plugin_tabs %}
             <li class="tab"><a href="#plugin-{{ tab.plugin_id }}">{{ tab.tab_label }}</a></li>
@@ -55,72 +53,64 @@
                     </div>
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.filter_failure_notification_threshold_attempts, class="filter_failure_notification_threshold_attempts") }}
-                        <span class="pure-form-message-inline">{{ _('After this many consecutive times that the CSS/xPath filter is missing, send a notification') }}
+                        <span class="pure-form-message-inline">After this many consecutive times that the CSS/xPath filter is missing, send a notification
                             <br>
-                        {{ _('Set to') }} <strong>0</strong> {{ _('to disable') }}
+                        Set to <strong>0</strong> to disable
                         </span>
                     </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.application.form.history_snapshot_max_length, class="history_snapshot_max_length") }}
-                        <span class="pure-form-message-inline">{{ _('Limit collection of history snapshots for each watch to this number of history items.') }}
-                            <br>
-                        {{ _('Set to empty to disable / no limit') }}
-                        </span>
-                    </div>
-
                     <div class="pure-control-group">
                         {% if not hide_remove_pass %}
                             {% if current_user.is_authenticated %}
                                 {{ render_button(form.application.form.removepassword_button) }}
                             {% else %}
                             {{ render_field(form.application.form.password) }}
-                            <span class="pure-form-message-inline">{{ _('Password protection for your changedetection.io application.') }}</span>
+                            <span class="pure-form-message-inline">Password protection for your changedetection.io application.</span>
                             {% endif %}
                         {% else %}
-                            <span class="pure-form-message-inline">{{ _('Password is locked.') }}</span>
+                            <span class="pure-form-message-inline">Password is locked.</span>
                         {% endif %}
                     </div>
 
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.shared_diff_access, class="shared_diff_access") }}
-                        <span class="pure-form-message-inline">{{ _('Allow access to the watch change history page when password is enabled (Good for sharing the diff page)') }}</span>
+                        <span class="pure-form-message-inline">Allow access to the watch change history page when password is enabled (Good for sharing the diff page)
+                        </span>
                     </div>
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.empty_pages_are_a_change) }}
-                        <span class="pure-form-message-inline">{{ _('When a request returns no content, or the HTML does not contain any text, is this considered a change?') }}</span>
+                        <span class="pure-form-message-inline">When a request returns no content, or the HTML does not contain any text, is this considered a change?</span>
                     </div>
-                {% if form.requests.proxy %}
-                    <div>
-                    <br>
-                        <div class="inline-radio">
-                            {{ render_field(form.requests.form.proxy, class="fetch-backend-proxy") }}
-                            <span class="pure-form-message-inline">{{ _('Choose a default proxy for all watches') }}</span>
-                        </div>
-                    </div>
-                {% endif %}
-
                 </fieldset>
             </div>
 
             <div class="tab-pane-inner" id="notifications">
                 <fieldset>
-                    {{ render_common_settings_form(form.application.form, emailprefix, settings_application, extra_notification_token_placeholder_info) }}
+                    <div class="field-group">
+                        {{ render_common_settings_form(form.application.form, emailprefix, settings_application, extra_notification_token_placeholder_info) }}
+                    </div>
                 </fieldset>
                 <div class="pure-control-group" id="notification-base-url">
                     {{ render_field(form.application.form.base_url, class="m-d") }}
                     <span class="pure-form-message-inline">
-                        {{ _('Base URL used for the') }} <code>{{ '{{ base_url }}' }}</code> {{ _('token in notification links.') }}<br>
-                        {{ _('Default value is the system environment variable') }} '<code>BASE_URL</code>' - <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">{{ _('read more here') }}</a>.
+                        Base URL used for the <code>{{ '{{ base_url }}' }}</code> token in notification links.<br>
+                        Default value is the system environment variable '<code>BASE_URL</code>' - <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">read more here</a>.
                     </span>
                 </div>
             </div>
 
             <div class="tab-pane-inner" id="fetching">
-                <fieldset class="pure-group" id="webdriver-override-options">
+                <div class="pure-control-group inline-radio">
+                    {{ render_field(form.application.form.fetch_backend, class="fetch-backend") }}
+                    <span class="pure-form-message-inline">
+                        <p>Use the <strong>Basic</strong> method (default) where your watched sites don't need Javascript to render.</p>
+                        <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
+                    </span>
+                </div>
+                <fieldset class="pure-group" id="webdriver-override-options" data-visible-for="application-fetch_backend=html_webdriver">
                     <div class="pure-form-message-inline">
-                        <strong>{{ _('If you\'re having trouble waiting for the page to be fully rendered (text missing etc), try increasing the \'wait\' time here.') }}</strong>
+                        <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
                         <br>
-                        {{ _('This will wait') }} <i>n</i> {{ _('seconds before extracting the text.') }}
+                        This will wait <i>n</i> seconds before extracting the text.
                     </div>
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.webdriver_delay) }}
@@ -129,27 +119,28 @@
                 <div class="pure-control-group">
                     {{ render_field(form.requests.form.workers) }}
                     {% set worker_info = get_worker_status_info() %}
-                    <span class="pure-form-message-inline">{{ _('Number of concurrent workers to process watches. More workers = faster processing but higher memory usage.') }}<br>
-                    {{ _('Currently running:') }} <strong>{{ worker_info.count }}</strong> {{ _('operational') }} {{ worker_info.type }} {{ _('workers') }}{% if worker_info.active_workers > 0 %} ({{ worker_info.active_workers }} {{ _('actively processing') }}){% endif %}.</span>
+                    <span class="pure-form-message-inline">Number of concurrent workers to process watches. More workers = faster processing but higher memory usage.<br>
+                    Currently running: <strong>{{ worker_info.count }}</strong> operational {{ worker_info.type }} workers{% if worker_info.active_workers > 0 %} ({{ worker_info.active_workers }} actively processing){% endif %}.</span>
                 </div>
                 <div class="pure-control-group">
                     {{ render_field(form.requests.form.jitter_seconds, class="jitter_seconds") }}
-                    <span class="pure-form-message-inline">{{ _('Example - 3 seconds random jitter could trigger up to 3 seconds earlier or up to 3 seconds later') }}</span>
+                    <span class="pure-form-message-inline">Example - 3 seconds random jitter could trigger up to 3 seconds earlier or up to 3 seconds later</span>
                 </div>
                 <div class="pure-control-group">
                     {{ render_field(form.requests.form.timeout) }}
-                    <span class="pure-form-message-inline">{{ _('For regular plain requests (not chrome based), maximum number of seconds until timeout, 1-999.') }}</span><br>
+                    <span class="pure-form-message-inline">For regular plain requests (not chrome based), maximum number of seconds until timeout, 1-999.<br>
                 </div>
                 <div class="pure-control-group inline-radio">
                     {{ render_field(form.requests.form.default_ua) }}
                     <span class="pure-form-message-inline">
-                        {{ _('Applied to all requests.') }}<br><br>
-                        {{ _('Note: Simply changing the User-Agent often does not defeat anti-robot technologies, it\'s important to consider') }} <a href="https://changedetection.io/tutorial/what-are-main-types-anti-robot-mechanisms">{{ _('all of the ways that the browser is detected') }}</a>.
+                        Applied to all requests.<br><br>
+                        Note: Simply changing the User-Agent often does not defeat anti-robot technologies, it's important to consider <a href="https://changedetection.io/tutorial/what-are-main-types-anti-robot-mechanisms">all of the ways that the browser is detected</a>.
                     </span>
                 </div>
                 <div class="pure-control-group">
-                <br>
-                    {{ _('Tip:') }} <a href="{{ url_for('settings.settings_page')}}#proxies">{{ _('Connect using Bright Data proxies, find out more here.') }}</a>
+                                        <br>
+                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
+
                 </div>
             </div>
 
@@ -157,15 +148,15 @@
 
                     <fieldset class="pure-group">
                     {{ render_checkbox_field(form.application.form.ignore_whitespace) }}
-                    <span class="pure-form-message-inline">{{ _('Ignore whitespace, tabs and new-lines/line-feeds when considering if a change was detected.') }}<br>
-                    <i>{{ _('Note:') }}</i> {{ _('Changing this will change the status of your existing watches, possibly trigger alerts etc.') }}
+                    <span class="pure-form-message-inline">Ignore whitespace, tabs and new-lines/line-feeds when considering if a change was detected.<br>
+                    <i>Note:</i> Changing this will change the status of your existing watches, possibly trigger alerts etc.
                     </span>
                     </fieldset>
                 <fieldset class="pure-group">
                     {{ render_checkbox_field(form.application.form.render_anchor_tag_content) }}
-                    <span class="pure-form-message-inline">{{ _('Render anchor tag content, default disabled, when enabled renders links as') }} <code>(link text)[https://somesite.com]</code>
+                    <span class="pure-form-message-inline">Render anchor tag content, default disabled, when enabled renders links as <code>(link text)[https://somesite.com]</code>
                         <br>
-                    <i>{{ _('Note:') }}</i> {{ _('Changing this could affect the content of your existing watches, possibly trigger alerts etc.') }}
+                    <i>Note:</i> Changing this could affect the content of your existing watches, possibly trigger alerts etc.
                     </span>
                     </fieldset>
                     <fieldset class="pure-group">
@@ -176,9 +167,9 @@ nav
 //*[contains(text(), 'Advertisement')]") }}
                       <span class="pure-form-message-inline">
                         <ul>
-                          <li> {{ _('Remove HTML element(s) by CSS and XPath selectors before text conversion.') }} </li>
-                          <li> {{ _('Don\'t paste HTML here, use only CSS and XPath selectors') }} </li>
-                          <li> {{ _('Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML.') }} </li>
+                          <li> Remove HTML element(s) by CSS and XPath selectors before text conversion. </li>
+                          <li> Don't paste HTML here, use only CSS and XPath selectors </li>
+                          <li> Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML. </li>
                         </ul>
                       </span>
                     </fieldset>
@@ -186,50 +177,50 @@ nav
                     {{ render_field(form.application.form.global_ignore_text, rows=5, placeholder="Some text to ignore in a line
 /some.regex\d{2}/ for case-INsensitive regex
                     ") }}
-                    <span class="pure-form-message-inline">{{ _('Note: This is applied globally in addition to the per-watch rules.') }}</span><br>
+                    <span class="pure-form-message-inline">Note: This is applied globally in addition to the per-watch rules.</span><br>
                     <span class="pure-form-message-inline">
                         <ul>
-                            <li>{{ _('Matching text will be') }} <strong>{{ _('ignored') }}</strong> {{ _('in the text snapshot (you can still see it but it wont trigger a change)') }}</li>
-                            <li>{{ _('Note: This is applied globally in addition to the per-watch rules.') }}</li>
-                            <li>{{ _('Each line processed separately, any line matching will be ignored (removed before creating the checksum)') }}</li>
-                            <li>{{ _('Regular Expression support, wrap the entire line in forward slash') }} <code>/regex/</code></li>
-                            <li>{{ _('Changing this will affect the comparison checksum which may trigger an alert') }}</li>
+                            <li>Matching text will be <strong>ignored</strong> in the text snapshot (you can still see it but it wont trigger a change)</li>
+                            <li>Note: This is applied globally in addition to the per-watch rules.</li>
+                            <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
+                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
+                            <li>Changing this will affect the comparison checksum which may trigger an alert</li>
                         </ul>
                      </span>
                     </fieldset>
                     <fieldset class="pure-group">
                         {{ render_checkbox_field(form.application.form.strip_ignored_lines) }}
-                        <span class="pure-form-message-inline">{{ _('Remove any text that appears in the "Ignore text" from the output (otherwise its just ignored for change-detection)') }}<br>
-                        <i>{{ _('Note:') }}</i> {{ _('Changing this will change the status of your existing watches, possibly trigger alerts etc.') }}
+                        <span class="pure-form-message-inline">Remove any text that appears in the "Ignore text" from the output (otherwise its just ignored for change-detection)<br>
+                        <i>Note:</i> Changing this will change the status of your existing watches, possibly trigger alerts etc.
                         </span>
                     </fieldset>
            </div>
 
             <div class="tab-pane-inner" id="api">
-                <h4>{{ _('API Access') }}</h4>
-                <p>{{ _('Drive your changedetection.io via API, More about') }} <a href="https://changedetection.io/docs/api_v1/index.html">{{ _('API access and examples here') }}</a>.</p>
+                <h4>API Access</h4>
+                <p>Drive your changedetection.io via API, More about <a href="https://changedetection.io/docs/api_v1/index.html">API access and examples here</a>.</p>
 
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.api_access_token_enabled) }}
-                    <div class="pure-form-message-inline">{{ _('Restrict API access limit by using') }} <code>x-api-key</code> {{ _('header - required for the Chrome Extension to work') }}</div><br>
-                    <div class="pure-form-message-inline"><br>{{ _('API Key') }} <span id="api-key">{{api_key}}</span>
-                        <span style="display:none;" id="api-key-copy" >{{ _('copy') }}</span>
+                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header - required for the Chrome Extension to work</div><br>
+                    <div class="pure-form-message-inline"><br>API Key <span id="api-key">{{api_key}}</span>
+                        <span style="display:none;" id="api-key-copy" >copy</span>
                     </div>
                 </div>
                 <div class="pure-control-group">
-                    <a href="{{url_for('settings.settings_reset_api_key')}}" class="pure-button button-small button-cancel">{{ _('Regenerate API key') }}</a>
+                    <a href="{{url_for('settings.settings_reset_api_key')}}" class="pure-button button-small button-cancel">Regenerate API key</a>
                 </div>
                 <div class="pure-control-group">
-                    <h4>{{ _('Chrome Extension') }}</h4>
-                    <p>{{ _('Easily add any web-page to your changedetection.io installation from within Chrome.') }}</p>
-                    <strong>{{ _('Step 1') }}</strong> {{ _('Install the extension,') }} <strong>{{ _('Step 2') }}</strong> {{ _('Navigate to this page,') }}
-                    <strong>{{ _('Step 3') }}</strong> {{ _('Open the extension from the toolbar and click') }} "<i>{{ _('Sync API Access') }}</i>"
+                    <h4>Chrome Extension</h4>
+                    <p>Easily add any web-page to your changedetection.io installation from within Chrome.</p>
+                    <strong>Step 1</strong> Install the extension, <strong>Step 2</strong> Navigate to this page,
+                    <strong>Step 3</strong> Open the extension from the toolbar and click "<i>Sync API Access</i>"
                     <p>
                         <a id="chrome-extension-link"
-                           title="{{ _('Try our new Chrome Extension!') }}"
+                           title="Try our new Chrome Extension!"
                            href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
-                            <img alt="{{ _('Chrome store icon') }}" src="{{ url_for('static_content', group='images', filename='google-chrome-icon.png') }}" >
-                            {{ _('Chrome Webstore') }}
+                            <img alt="Chrome store icon" src="{{ url_for('static_content', group='images', filename='google-chrome-icon.png') }}" alt="Chrome">
+                            Chrome Webstore
                         </a>
                     </p>
                 </div>
@@ -240,20 +231,20 @@ nav
                 </div>
                 <div class="pure-control-group">
                     {{ render_field(form.application.form.rss_diff_length) }}
-                    <span class="pure-form-message-inline">{{ _('Maximum number of history snapshots to include in the watch specific RSS feed.') }}</span>
+                    <span class="pure-form-message-inline">Maximum number of history snapshots to include in the watch specific RSS feed.</span>
                 </div>
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.rss_reader_mode) }}
-                    <span class="pure-form-message-inline">{{ _('For watching other RSS feeds - When watching RSS/Atom feeds, convert them into clean text for better change detection.') }}</span>
+                    <span class="pure-form-message-inline">For watching other RSS feeds - When watching RSS/Atom feeds, convert them into clean text for better change detection.</span>
                 </div>
                 <div class="pure-control-group grey-form-border">
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.rss_content_format) }}
-                        <span class="pure-form-message-inline">{{ _('Does your reader support HTML? Set it here') }}</span>
+                        <span class="pure-form-message-inline">Does your reader support HTML? Set it here</span>
                     </div>
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.rss_template_type) }}
-                        <span class="pure-form-message-inline">{{ _('\'System default\' for the same template for all items, or re-use your "Notification Body" as the template.') }}</span>
+                        <span class="pure-form-message-inline">'System default' for the same template for all items, or re-use your "Notification Body" as the template.</span>
                     </div>
                     <div>
                        {{ render_field(form.application.form.rss_template_override) }}
@@ -266,38 +257,38 @@ nav
             </div>
                 <div class="tab-pane-inner" id="timedate">
                 <div class="pure-control-group">
-                    {{ _('Ensure the settings below are correct, they are used to manage the time schedule for checking your web page watches.') }}
+                    Ensure the settings below are correct, they are used to manage the time schedule for checking your web page watches.
                 </div>
                 <div class="pure-control-group">
-                    <p><strong>{{ _('UTC Time & Date from Server:') }}</strong> <span id="utc-time" >{{ utc_time }}</span></p>
-                    <p><strong>{{ _('Local Time & Date in Browser:') }}</strong> <span class="local-time" data-utc="{{ utc_time }}"></span></p>
-                    <div>
+                    <p><strong>UTC Time &amp Date from Server:</strong> <span id="utc-time" >{{ utc_time }}</span></p>
+                    <p><strong>Local Time &amp Date in Browser:</strong> <span class="local-time" data-utc="{{ utc_time }}"></span></p>
+                    <p>
                        {{ render_field(form.application.form.scheduler_timezone_default) }}
                         <datalist id="timezones" style="display: none;">
                             {%- for timezone in available_timezones -%}<option value="{{ timezone }}">{{ timezone }}</option>{%- endfor -%}
                         </datalist>
-                    </div>
+                    </p>
                 </div>
             </div>
             <div class="tab-pane-inner" id="ui-options">
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.ui.form.open_diff_in_new_tab, class="open_diff_in_new_tab") }}
-                    <span class="pure-form-message-inline">{{ _('Enable this setting to open the diff page in a new tab. If disabled, the diff page will open in the current tab.') }}</span>
+                    <span class="pure-form-message-inline">Enable this setting to open the diff page in a new tab. If disabled, the diff page will open in the current tab.</span>
                 </div>
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.ui.form.socket_io_enabled, class="socket_io_enabled") }}
-                    <span class="pure-form-message-inline">{{ _('Realtime UI Updates Enabled - (Restart required if this is changed)') }}</span>
+                    <span class="pure-form-message-inline">Realtime UI Updates Enabled - (Restart required if this is changed)</span>
                 </div>
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.ui.form.favicons_enabled, class="") }}
-                    <span class="pure-form-message-inline">{{ _('Enable or Disable Favicons next to the watch list') }}</span>
+                    <span class="pure-form-message-inline">Enable or Disable Favicons next to the watch list</span>
                 </div>
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.ui.use_page_title_in_list) }}
                 </div>
                 <div class="pure-control-group">
                     {{ render_field(form.application.form.pager_size) }}
-                    <span class="pure-form-message-inline">{{ _('Number of items per page in the watch overview list, 0 to disable.') }}</span>
+                    <span class="pure-form-message-inline">Number of items per page in the watch overview list, 0 to disable.</span>
                 </div>
 
             </div>
@@ -345,12 +336,21 @@ nav
                     </div>
                 </div>
 
-                <p><strong>{{ _('Tip') }}</strong>: {{ _('"Residential" and "Mobile" proxy type can be more successful than "Data Center" for blocked websites.') }}</p>
+               <p><strong>Tip</strong>: "Residential" and "Mobile" proxy type can be more successfull than "Data Center" for blocked websites.
 
                 <div class="pure-control-group" id="extra-proxies-setting">
                 {{ render_fieldlist_with_inline_errors(form.requests.form.extra_proxies) }}
-                <span class="pure-form-message-inline">{{ _('"Name" will be used for selecting the proxy in the Watch Edit settings') }}</span><br>
-                <span class="pure-form-message-inline">{{ _('SOCKS5 proxies with authentication are only supported with \'plain requests\' fetcher, for other fetchers you should whitelist the IP access instead') }}</span>
+                <span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span><br>
+                <span class="pure-form-message-inline">SOCKS5 proxies with authentication are only supported with 'plain requests' fetcher, for other fetchers you should whitelist the IP access instead</span>
+                {% if form.requests.proxy %}
+                <div>
+                <br>
+                    <div class="inline-radio">
+                        {{ render_field(form.requests.form.proxy, class="fetch-backend-proxy") }}
+                        <span class="pure-form-message-inline">Choose a default proxy for all watches</span>
+                    </div>
+                </div>
+                {% endif %}
                 </div>
                 <div class="pure-control-group" id="extra-browsers-setting">
                     <p>
@@ -387,7 +387,6 @@ nav
                 {% endfor %}
             {% endif %}
             <div class="tab-pane-inner" id="info">
-                <p><strong>{{ _('Uptime:') }}</strong> {{ uptime_seconds|format_duration }}</p>
                 <p><strong>{{ _('Python version:') }}</strong> {{ python_version }}</p>
                 <p><strong>{{ _('Plugins active:') }}</strong></p>
                 {% if active_plugins %}

changedetectionio/blueprint/tags/__init__.py

@@ -1,7 +1,5 @@
-import threading
 from flask import Blueprint, request, render_template, flash, url_for, redirect
 from flask_babel import gettext
-from loguru import logger
 
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.flask_app import login_optionally_required
@@ -54,94 +52,52 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         return redirect(url_for('tags.tags_overview_page'))
 
-    @tags_blueprint.route("/mute/<uuid_str:uuid>", methods=['GET'])
+    @tags_blueprint.route("/mute/<string:uuid>", methods=['GET'])
     @login_optionally_required
     def mute(uuid):
-        tag = datastore.data['settings']['application']['tags'].get(uuid)
-        if tag:
-            tag['notification_muted'] = not tag['notification_muted']
-            tag.commit()
+        if datastore.data['settings']['application']['tags'].get(uuid):
+            datastore.data['settings']['application']['tags'][uuid]['notification_muted'] = not datastore.data['settings']['application']['tags'][uuid]['notification_muted']
         return redirect(url_for('tags.tags_overview_page'))
 
-    @tags_blueprint.route("/delete/<uuid_str:uuid>", methods=['GET'])
+    @tags_blueprint.route("/delete/<string:uuid>", methods=['GET'])
     @login_optionally_required
     def delete(uuid):
-        # Delete the tag from settings immediately
+        removed = 0
+        # Delete the tag, and any tag reference
         if datastore.data['settings']['application']['tags'].get(uuid):
             del datastore.data['settings']['application']['tags'][uuid]
 
-        # Remove tag from all watches in background thread to avoid blocking
-        def remove_tag_background(tag_uuid):
-            """Background thread to remove tag from watches - discarded after completion."""
-            removed_count = 0
-            try:
-                for watch_uuid, watch in datastore.data['watching'].items():
-                    if watch.get('tags') and tag_uuid in watch['tags']:
-                        watch['tags'].remove(tag_uuid)
-                        watch.commit()
-                        removed_count += 1
-                logger.info(f"Background: Tag {tag_uuid} removed from {removed_count} watches")
-            except Exception as e:
-                logger.error(f"Error removing tag from watches: {e}")
+        for watch_uuid, watch in datastore.data['watching'].items():
+            if watch.get('tags') and uuid in watch['tags']:
+                removed += 1
+                watch['tags'].remove(uuid)
 
-        # Start daemon thread
-        threading.Thread(target=remove_tag_background, args=(uuid,), daemon=True).start()
-
-        flash(gettext("Tag deleted, removing from watches in background"))
+        flash(gettext("Tag deleted and removed from {} watches").format(removed))
         return redirect(url_for('tags.tags_overview_page'))
 
-    @tags_blueprint.route("/unlink/<uuid_str:uuid>", methods=['GET'])
+    @tags_blueprint.route("/unlink/<string:uuid>", methods=['GET'])
     @login_optionally_required
     def unlink(uuid):
-        # Unlink tag from all watches in background thread to avoid blocking
-        def unlink_tag_background(tag_uuid):
-            """Background thread to unlink tag from watches - discarded after completion."""
-            unlinked_count = 0
-            try:
-                for watch_uuid, watch in datastore.data['watching'].items():
-                    if watch.get('tags') and tag_uuid in watch['tags']:
-                        watch['tags'].remove(tag_uuid)
-                        watch.commit()
-                        unlinked_count += 1
-                logger.info(f"Background: Tag {tag_uuid} unlinked from {unlinked_count} watches")
-            except Exception as e:
-                logger.error(f"Error unlinking tag from watches: {e}")
+        unlinked = 0
+        for watch_uuid, watch in datastore.data['watching'].items():
+            if watch.get('tags') and uuid in watch['tags']:
+                unlinked += 1
+                watch['tags'].remove(uuid)
 
-        # Start daemon thread
-        threading.Thread(target=unlink_tag_background, args=(uuid,), daemon=True).start()
-
-        flash(gettext("Unlinking tag from watches in background"))
+        flash(gettext("Tag unlinked removed from {} watches").format(unlinked))
         return redirect(url_for('tags.tags_overview_page'))
 
     @tags_blueprint.route("/delete_all", methods=['GET'])
     @login_optionally_required
     def delete_all():
+        for watch_uuid, watch in datastore.data['watching'].items():
+            watch['tags'] = []
+        datastore.data['settings']['application']['tags'] = {}
 
-        for tag_uuid in list(datastore.data['settings']['application']['tags'].keys()):
-# TagsDict 'del' handler will remove the dir
-            del datastore.data['settings']['application']['tags'][tag_uuid]
-
-
-        # Clear tags from all watches in background thread to avoid blocking
-        def clear_all_tags_background():
-            """Background thread to clear tags from all watches - discarded after completion."""
-            cleared_count = 0
-            try:
-                for watch_uuid, watch in datastore.data['watching'].items():
-                    watch['tags'] = []
-                    watch.commit()
-                    cleared_count += 1
-                logger.info(f"Background: Cleared tags from {cleared_count} watches")
-            except Exception as e:
-                logger.error(f"Error clearing tags from watches: {e}")
-
-        # Start daemon thread
-        threading.Thread(target=clear_all_tags_background, daemon=True).start()
-
-        flash(gettext("All tags deleted, clearing from watches in background"))
+        flash(gettext("All tags deleted"))
         return redirect(url_for('tags.tags_overview_page'))
 
-    @tags_blueprint.route("/edit/<uuid_str:uuid>", methods=['GET'])
+    @tags_blueprint.route("/edit/<string:uuid>", methods=['GET'])
     @login_optionally_required
     def form_tag_edit(uuid):
         from changedetectionio.blueprint.tags.form import group_restock_settings_form
@@ -160,21 +116,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                                        default_system_settings = datastore.data['settings'],
                                        )
 
-        # Bridge API-stored processor_config_* values into the form's FormField sub-forms.
-        # The API stores processor_config_restock_diff in the tag dict; find the matching
-        # FormField by checking which one's sub-fields cover the config keys.
-        from wtforms.fields.form import FormField as WTFormField
-        for key, value in default.items():
-            if not key.startswith('processor_config_') or not isinstance(value, dict):
-                continue
-            for form_field in form:
-                if isinstance(form_field, WTFormField) and all(k in form_field.form._fields for k in value):
-                    for sub_key, sub_value in value.items():
-                        sub_field = form_field.form._fields.get(sub_key)
-                        if sub_field is not None:
-                            sub_field.data = sub_value
-                    break
-
         template_args = {
             'data': default,
             'form': form,
@@ -218,17 +159,17 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         return output
 
 
-    @tags_blueprint.route("/edit/<uuid_str:uuid>", methods=['POST'])
+    @tags_blueprint.route("/edit/<string:uuid>", methods=['POST'])
     @login_optionally_required
     def form_tag_edit_submit(uuid):
         from changedetectionio.blueprint.tags.form import group_restock_settings_form
         if uuid == 'first':
             uuid = list(datastore.data['settings']['application']['tags'].keys()).pop()
 
-        tag = datastore.data['settings']['application']['tags'].get(uuid)
+        default = datastore.data['settings']['application']['tags'].get(uuid)
 
         form = group_restock_settings_form(formdata=request.form if request.method == 'POST' else None,
-                               data=tag,
+                               data=default,
                                extra_notification_tokens=datastore.get_unique_notification_tokens_available()
                                )
         # @todo subclass form so validation works
@@ -237,18 +178,15 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 #                flash(','.join(l), 'error')
 #           return redirect(url_for('tags.form_tag_edit_submit', uuid=uuid))
 
-        tag.update(form.data)
-        tag['processor'] = 'restock_diff'
-        tag.commit()
-
-        # Clear checksums for all watches using this tag to force reprocessing
-        # Tag changes affect inherited configuration
-        cleared_count = datastore.clear_checksums_for_tag(uuid)
-        logger.info(f"Tag {uuid} updated, cleared {cleared_count} watch checksums")
-
+        datastore.data['settings']['application']['tags'][uuid].update(form.data)
+        datastore.data['settings']['application']['tags'][uuid]['processor'] = 'restock_diff'
+        datastore.needs_write_urgent = True
         flash(gettext("Updated"))
 
         return redirect(url_for('tags.tags_overview_page'))
 
 
+    @tags_blueprint.route("/delete/<string:uuid>", methods=['GET'])
+    def form_tag_delete(uuid):
+        return redirect(url_for('tags.tags_overview_page'))
     return tags_blueprint

changedetectionio/blueprint/tags/templates/groups-overview.html

@@ -50,8 +50,7 @@
                 <td>{{ "{:,}".format(tag_count[uuid]) if uuid in tag_count else 0 }}</td>
                 <td class="title-col inline"> <a href="{{url_for('watchlist.index', tag=uuid) }}">{{ tag.title }}</a></td>
                 <td>
-                    <a class="pure-button pure-button-primary" href="{{ url_for('tags.form_tag_edit', uuid=uuid) }}">{{ _('Edit') }}</a>
-                    <a href="{{ url_for('ui.form_watch_checknow', tag=uuid) }}" class="pure-button pure-button-primary" >{{ _('Recheck') }}</a>
+                    <a class="pure-button pure-button-primary" href="{{ url_for('tags.form_tag_edit', uuid=uuid) }}">{{ _('Edit') }}</a>&nbsp;
                     <a class="pure-button button-error"
                        href="{{ url_for('tags.delete', uuid=uuid) }}"
                        data-requires-confirm

changedetectionio/blueprint/ui/__init__.py

@@ -1,6 +1,5 @@
 import time
-import threading
-from flask import Blueprint, request, redirect, url_for, flash, render_template, session, current_app
+from flask import Blueprint, request, redirect, url_for, flash, render_template, session
 from flask_babel import gettext
 from loguru import logger
 
@@ -10,7 +9,7 @@ from changedetectionio.blueprint.ui.notification import construct_blueprint as c
 from changedetectionio.blueprint.ui.views import construct_blueprint as construct_views_blueprint
 from changedetectionio.blueprint.ui import diff, preview
 
-def _handle_operations(op, uuids, datastore, worker_pool, update_q, queuedWatchMetaData, watch_check_update, extra_data=None, emit_flash=True):
+def _handle_operations(op, uuids, datastore, worker_handler, update_q, queuedWatchMetaData, watch_check_update, extra_data=None, emit_flash=True):
     from flask import request, flash
 
     if op == 'delete':
@@ -24,7 +23,6 @@ def _handle_operations(op, uuids, datastore, worker_pool, update_q, queuedWatchM
         for uuid in uuids:
             if datastore.data['watching'].get(uuid):
                 datastore.data['watching'][uuid]['paused'] = True
-                datastore.data['watching'][uuid].commit()
         if emit_flash:
             flash(gettext("{} watches paused").format(len(uuids)))
 
@@ -32,7 +30,6 @@ def _handle_operations(op, uuids, datastore, worker_pool, update_q, queuedWatchM
         for uuid in uuids:
             if datastore.data['watching'].get(uuid):
                 datastore.data['watching'][uuid.strip()]['paused'] = False
-                datastore.data['watching'][uuid].commit()
         if emit_flash:
             flash(gettext("{} watches unpaused").format(len(uuids)))
 
@@ -47,7 +44,6 @@ def _handle_operations(op, uuids, datastore, worker_pool, update_q, queuedWatchM
         for uuid in uuids:
             if datastore.data['watching'].get(uuid):
                 datastore.data['watching'][uuid]['notification_muted'] = True
-                datastore.data['watching'][uuid].commit()
         if emit_flash:
             flash(gettext("{} watches muted").format(len(uuids)))
 
@@ -55,7 +51,6 @@ def _handle_operations(op, uuids, datastore, worker_pool, update_q, queuedWatchM
         for uuid in uuids:
             if datastore.data['watching'].get(uuid):
                 datastore.data['watching'][uuid]['notification_muted'] = False
-                datastore.data['watching'][uuid].commit()
         if emit_flash:
             flash(gettext("{} watches un-muted").format(len(uuids)))
 
@@ -63,7 +58,7 @@ def _handle_operations(op, uuids, datastore, worker_pool, update_q, queuedWatchM
         for uuid in uuids:
             if datastore.data['watching'].get(uuid):
                 # Recheck and require a full reprocessing
-                worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
         if emit_flash:
             flash(gettext("{} watches queued for rechecking").format(len(uuids)))
 
@@ -71,7 +66,6 @@ def _handle_operations(op, uuids, datastore, worker_pool, update_q, queuedWatchM
         for uuid in uuids:
             if datastore.data['watching'].get(uuid):
                 datastore.data['watching'][uuid]["last_error"] = False
-                datastore.data['watching'][uuid].commit()
         if emit_flash:
             flash(gettext("{} watches errors cleared").format(len(uuids)))
 
@@ -92,7 +86,6 @@ def _handle_operations(op, uuids, datastore, worker_pool, update_q, queuedWatchM
                 datastore.data['watching'][uuid]['notification_body'] = None
                 datastore.data['watching'][uuid]['notification_urls'] = []
                 datastore.data['watching'][uuid]['notification_format'] = USE_SYSTEM_DEFAULT_NOTIFICATION_FORMAT_FOR_WATCH
-                datastore.data['watching'][uuid].commit()
         if emit_flash:
             flash(gettext("{} watches set to use default notification settings").format(len(uuids)))
 
@@ -108,7 +101,6 @@ def _handle_operations(op, uuids, datastore, worker_pool, update_q, queuedWatchM
                             datastore.data['watching'][uuid]['tags'] = []
 
                         datastore.data['watching'][uuid]['tags'].append(tag_uuid)
-                        datastore.data['watching'][uuid].commit()
         if emit_flash:
             flash(gettext("{} watches were tagged").format(len(uuids)))
 
@@ -116,7 +108,7 @@ def _handle_operations(op, uuids, datastore, worker_pool, update_q, queuedWatchM
         for uuid in uuids:
             watch_check_update.send(watch_uuid=uuid)
 
-def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool, queuedWatchMetaData, watch_check_update):
+def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_handler, queuedWatchMetaData, watch_check_update):
     ui_blueprint = Blueprint('ui', __name__, template_folder="templates")
     
     # Register the edit blueprint
@@ -141,7 +133,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
     # Import the login decorator
     from changedetectionio.auth_decorator import login_optionally_required
 
-    @ui_blueprint.route("/clear_history/<uuid_str:uuid>", methods=['GET'])
+    @ui_blueprint.route("/clear_history/<string:uuid>", methods=['GET'])
     @login_optionally_required
     def clear_watch_history(uuid):
         try:
@@ -156,27 +148,12 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
     @login_optionally_required
     def clear_all_history():
         if request.method == 'POST':
-            confirmtext = request.form.get('confirmtext', '')
+            confirmtext = request.form.get('confirmtext')
 
-            if confirmtext.strip().lower() == gettext('clear').strip().lower():
-                # Run in background thread to avoid blocking
-                def clear_history_background():
-                    # Capture UUIDs first to avoid race conditions
-                    watch_uuids = list(datastore.data['watching'].keys())
-                    logger.info(f"Background: Clearing history for {len(watch_uuids)} watches")
-
-                    for uuid in watch_uuids:
-                        try:
-                            datastore.clear_watch_history(uuid)
-                        except Exception as e:
-                            logger.error(f"Error clearing history for watch {uuid}: {e}")
-
-                    logger.info("Background: Completed clearing history")
-
-                # Start daemon thread
-                threading.Thread(target=clear_history_background, daemon=True).start()
-
-                flash(gettext("History clearing started in background"))
+            if confirmtext == 'clear':
+                for uuid in datastore.data['watching'].keys():
+                    datastore.clear_watch_history(uuid)
+                flash(gettext("Cleared snapshot history for all watches"))
             else:
                 flash(gettext('Incorrect confirmation text.'), 'error')
 
@@ -192,37 +169,17 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
         # Save the current newest history as the most recently viewed
         with_errors = request.args.get('with_errors') == "1"
         tag_limit = request.args.get('tag')
+        logger.debug(f"Limiting to tag {tag_limit}")
         now = int(time.time())
+        for watch_uuid, watch in datastore.data['watching'].items():
+            if with_errors and not watch.get('last_error'):
+                continue
 
-        # Mark watches as viewed - use background thread only for large watch counts
-        def mark_viewed_impl():
-            """Mark watches as viewed - can run synchronously or in background thread."""
-            marked_count = 0
-            try:
-                for watch_uuid, watch in datastore.data['watching'].items():
-                    if with_errors and not watch.get('last_error'):
-                        continue
+            if tag_limit and ( not watch.get('tags') or tag_limit not in watch['tags'] ):
+                logger.debug(f"Skipping watch {watch_uuid}")
+                continue
 
-                    if tag_limit and (not watch.get('tags') or tag_limit not in watch['tags']):
-                        continue
-
-                    datastore.set_last_viewed(watch_uuid, now)
-                    marked_count += 1
-
-                logger.info(f"Marking complete: {marked_count} watches marked as viewed")
-            except Exception as e:
-                logger.error(f"Error marking as viewed: {e}")
-
-        # For small watch counts (< 10), run synchronously to avoid race conditions in tests
-        # For larger counts, use background thread to avoid blocking the UI
-        watch_count = len(datastore.data['watching'])
-        if watch_count < 10:
-            # Run synchronously for small watch counts
-            mark_viewed_impl()
-        else:
-            # Start background thread for large watch counts
-            thread = threading.Thread(target=mark_viewed_impl, daemon=True)
-            thread.start()
+            datastore.set_last_viewed(watch_uuid, now)
 
         return redirect(url_for('watchlist.index', tag=tag_limit))
 
@@ -230,14 +187,14 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
     @login_optionally_required
     def form_delete():
         uuid = request.args.get('uuid')
-        # More for testing, possible to return the first/only
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
 
         if uuid != 'all' and not uuid in datastore.data['watching'].keys():
             flash(gettext('The watch by UUID {} does not exist.').format(uuid), 'error')
             return redirect(url_for('watchlist.index'))
 
+        # More for testing, possible to return the first/only
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
         datastore.delete(uuid)
         flash(gettext('Deleted.'))
 
@@ -247,14 +204,14 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
     @login_optionally_required
     def form_clone():
         uuid = request.args.get('uuid')
-
+        # More for testing, possible to return the first/only
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
 
         new_uuid = datastore.clone(uuid)
 
         if not datastore.data['watching'].get(uuid).get('paused'):
-            worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid}))
+            worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid}))
 
         flash(gettext('Cloned, you are editing the new watch.'))
 
@@ -268,81 +225,38 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
         uuid = request.args.get('uuid')
         with_errors = request.args.get('with_errors') == "1"
 
+        i = 0
+
+        running_uuids = worker_handler.get_running_uuids()
+
         if uuid:
-            # Single watch - check if already queued or running
-            if worker_pool.is_watch_running(uuid) or uuid in update_q.get_queued_uuids():
-                flash(gettext("Watch is already queued or being checked."))
-            else:
-                worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-                flash(gettext("Queued 1 watch for rechecking."))
+            if uuid not in running_uuids:
+                worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                i += 1
+
         else:
-            # Multiple watches - first count how many need to be queued
-            watches_to_queue = []
+            # Recheck all, including muted
+            # Get most overdue first
             for k in sorted(datastore.data['watching'].items(), key=lambda item: item[1].get('last_checked', 0)):
                 watch_uuid = k[0]
                 watch = k[1]
-                if not watch['paused'] and watch_uuid:
-                    if with_errors and not watch.get('last_error'):
-                        continue
-                    if tag != None and tag not in watch['tags']:
-                        continue
-                    watches_to_queue.append(watch_uuid)
+                if not watch['paused']:
+                    if watch_uuid not in running_uuids:
+                        if with_errors and not watch.get('last_error'):
+                            continue
 
-            # If less than 20 watches, queue synchronously for immediate feedback
-            if len(watches_to_queue) < 20:
-                # Get already queued/running UUIDs once (efficient)
-                queued_uuids = set(update_q.get_queued_uuids())
-                running_uuids = set(worker_pool.get_running_uuids())
+                        if tag != None and tag not in watch['tags']:
+                            continue
 
-                # Filter out watches that are already queued or running
-                watches_to_queue_filtered = []
-                for watch_uuid in watches_to_queue:
-                    if watch_uuid not in queued_uuids and watch_uuid not in running_uuids:
-                        watches_to_queue_filtered.append(watch_uuid)
+                        worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
+                        i += 1
 
-                # Queue only the filtered watches
-                for watch_uuid in watches_to_queue_filtered:
-                    worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
-
-                # Provide feedback about skipped watches
-                skipped_count = len(watches_to_queue) - len(watches_to_queue_filtered)
-                if skipped_count > 0:
-                    flash(gettext("Queued {} watches for rechecking ({} already queued or running).").format(
-                        len(watches_to_queue_filtered), skipped_count))
-                else:
-                    if len(watches_to_queue_filtered) == 1:
-                        flash(gettext("Queued 1 watch for rechecking."))
-                    else:
-                        flash(gettext("Queued {} watches for rechecking.").format(len(watches_to_queue_filtered)))
-            else:
-                # 20+ watches - queue in background thread to avoid blocking HTTP response
-                # Capture queued/running state before background thread
-                queued_uuids = set(update_q.get_queued_uuids())
-                running_uuids = set(worker_pool.get_running_uuids())
-
-                def queue_watches_background():
-                    """Background thread to queue watches - discarded after completion."""
-                    try:
-                        queued_count = 0
-                        skipped_count = 0
-                        for watch_uuid in watches_to_queue:
-                            # Check if already queued or running (state captured at start)
-                            if watch_uuid not in queued_uuids and watch_uuid not in running_uuids:
-                                worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
-                                queued_count += 1
-                            else:
-                                skipped_count += 1
-
-                        logger.info(f"Background queueing complete: {queued_count} watches queued, {skipped_count} skipped (already queued/running)")
-                    except Exception as e:
-                        logger.error(f"Error in background queueing: {e}")
-
-                # Start background thread and return immediately
-                thread = threading.Thread(target=queue_watches_background, daemon=True, name="QueueWatches-Background")
-                thread.start()
-
-                # Return immediately with approximate message
-                flash(gettext("Queueing watches for rechecking in background..."))
+        if i == 1:
+            flash(gettext("Queued 1 watch for rechecking."))
+        if i > 1:
+            flash(gettext("Queued {} watches for rechecking.").format(i))
+        if i == 0:
+            flash(gettext("No watches available to recheck."))
 
         return redirect(url_for('watchlist.index', **({'tag': tag} if tag else {})))
 
@@ -357,7 +271,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
             extra_data=extra_data,
             queuedWatchMetaData=queuedWatchMetaData,
             uuids=uuids,
-            worker_pool=worker_pool,
+            worker_handler=worker_handler,
             update_q=update_q,
             watch_check_update=watch_check_update,
             op=op,
@@ -366,7 +280,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
         return redirect(url_for('watchlist.index'))
 
 
-    @ui_blueprint.route("/share-url/<uuid_str:uuid>", methods=['GET'])
+    @ui_blueprint.route("/share-url/<string:uuid>", methods=['GET'])
     @login_optionally_required
     def form_share_put_watch(uuid):
         """Given a watch UUID, upload the info and return a share-link
@@ -375,6 +289,9 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
         import json
         from copy import deepcopy
 
+        # more for testing
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
 
         # copy it to memory as trim off what we dont need (history)
         watch = deepcopy(datastore.data['watching'].get(uuid))
@@ -414,25 +331,4 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
 
         return redirect(url_for('watchlist.index'))
 
-    @ui_blueprint.route("/language/auto-detect", methods=['GET'])
-    def delete_locale_language_session_var_if_it_exists():
-        """Clear the session locale preference to auto-detect from browser Accept-Language header"""
-        if 'locale' in session:
-            session.pop('locale', None)
-            # Refresh Flask-Babel to clear cached locale
-            from flask_babel import refresh
-            refresh()
-            flash(gettext("Language set to auto-detect from browser"))
-
-        # Check if there's a redirect parameter to return to the same page
-        redirect_url = request.args.get('redirect')
-
-        # If redirect is provided and safe, use it
-        from changedetectionio.is_safe_url import is_safe_url
-        if redirect_url and is_safe_url(redirect_url, current_app):
-            return redirect(redirect_url)
-
-        # Otherwise redirect to watchlist
-        return redirect(url_for('watchlist.index'))
-
     return ui_blueprint

changedetectionio/blueprint/ui/diff.py

@@ -66,7 +66,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         return Markup(result)
 
-    @diff_blueprint.route("/diff/<uuid_str:uuid>", methods=['GET'])
+    @diff_blueprint.route("/diff/<string:uuid>", methods=['GET'])
     @login_optionally_required
     def diff_history_page(uuid):
         """
@@ -83,6 +83,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         If a processor doesn't have a difference module, falls back to text_json_diff.
         """
 
+        # More for testing, possible to return the first/only
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
 
@@ -100,21 +101,23 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         # Get the processor type for this watch
         processor_name = watch.get('processor', 'text_json_diff')
 
-        # Try to get the processor's difference module (works for both built-in and plugin processors)
-        from changedetectionio.processors import get_processor_submodule
-        processor_module = get_processor_submodule(processor_name, 'difference')
+        try:
+            # Try to import the processor's difference module
+            processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.difference')
 
-        # Call the processor's render() function
-        if processor_module and hasattr(processor_module, 'render'):
-            return processor_module.render(
-                watch=watch,
-                datastore=datastore,
-                request=request,
-                url_for=url_for,
-                render_template=render_template,
-                flash=flash,
-                redirect=redirect
-            )
+            # Call the processor's render() function
+            if hasattr(processor_module, 'render'):
+                return processor_module.render(
+                    watch=watch,
+                    datastore=datastore,
+                    request=request,
+                    url_for=url_for,
+                    render_template=render_template,
+                    flash=flash,
+                    redirect=redirect
+                )
+        except (ImportError, ModuleNotFoundError) as e:
+            logger.warning(f"Processor {processor_name} does not have a difference module, falling back to text_json_diff: {e}")
 
         # Fallback: if processor doesn't have difference module, use text_json_diff as default
         from changedetectionio.processors.text_json_diff.difference import render as default_render
@@ -128,7 +131,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             redirect=redirect
         )
 
-    @diff_blueprint.route("/diff/<uuid_str:uuid>/extract", methods=['GET'])
+    @diff_blueprint.route("/diff/<string:uuid>/extract", methods=['GET'])
     @login_optionally_required
     def diff_history_page_extract_GET(uuid):
         """
@@ -141,10 +144,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         Each processor implements processors/{type}/extract.py::render_form()
         If a processor doesn't have an extract module, falls back to text_json_diff.
         """
-
-
+        # More for testing, possible to return the first/only
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
+
         try:
             watch = datastore.data['watching'][uuid]
         except KeyError:
@@ -154,21 +157,23 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         # Get the processor type for this watch
         processor_name = watch.get('processor', 'text_json_diff')
 
-        # Try to get the processor's extract module (works for both built-in and plugin processors)
-        from changedetectionio.processors import get_processor_submodule
-        processor_module = get_processor_submodule(processor_name, 'extract')
+        try:
+            # Try to import the processor's extract module
+            processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.extract')
 
-        # Call the processor's render_form() function
-        if processor_module and hasattr(processor_module, 'render_form'):
-            return processor_module.render_form(
-                watch=watch,
-                datastore=datastore,
-                request=request,
-                url_for=url_for,
-                render_template=render_template,
-                flash=flash,
-                redirect=redirect
-            )
+            # Call the processor's render_form() function
+            if hasattr(processor_module, 'render_form'):
+                return processor_module.render_form(
+                    watch=watch,
+                    datastore=datastore,
+                    request=request,
+                    url_for=url_for,
+                    render_template=render_template,
+                    flash=flash,
+                    redirect=redirect
+                )
+        except (ImportError, ModuleNotFoundError) as e:
+            logger.warning(f"Processor {processor_name} does not have an extract module, falling back to base extractor: {e}")
 
         # Fallback: if processor doesn't have extract module, use base processors.extract as default
         from changedetectionio.processors.extract import render_form as default_render_form
@@ -182,7 +187,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             redirect=redirect
         )
 
-    @diff_blueprint.route("/diff/<uuid_str:uuid>/extract", methods=['POST'])
+    @diff_blueprint.route("/diff/<string:uuid>/extract", methods=['POST'])
     @login_optionally_required
     def diff_history_page_extract_POST(uuid):
         """
@@ -195,7 +200,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         Each processor implements processors/{type}/extract.py::process_extraction()
         If a processor doesn't have an extract module, falls back to text_json_diff.
         """
-
+        # More for testing, possible to return the first/only
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
 
@@ -208,22 +213,24 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         # Get the processor type for this watch
         processor_name = watch.get('processor', 'text_json_diff')
 
-        # Try to get the processor's extract module (works for both built-in and plugin processors)
-        from changedetectionio.processors import get_processor_submodule
-        processor_module = get_processor_submodule(processor_name, 'extract')
+        try:
+            # Try to import the processor's extract module
+            processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.extract')
 
-        # Call the processor's process_extraction() function
-        if processor_module and hasattr(processor_module, 'process_extraction'):
-            return processor_module.process_extraction(
-                watch=watch,
-                datastore=datastore,
-                request=request,
-                url_for=url_for,
-                make_response=make_response,
-                send_from_directory=send_from_directory,
-                flash=flash,
-                redirect=redirect
-            )
+            # Call the processor's process_extraction() function
+            if hasattr(processor_module, 'process_extraction'):
+                return processor_module.process_extraction(
+                    watch=watch,
+                    datastore=datastore,
+                    request=request,
+                    url_for=url_for,
+                    make_response=make_response,
+                    send_from_directory=send_from_directory,
+                    flash=flash,
+                    redirect=redirect
+                )
+        except (ImportError, ModuleNotFoundError) as e:
+            logger.warning(f"Processor {processor_name} does not have an extract module, falling back to base extractor: {e}")
 
         # Fallback: if processor doesn't have extract module, use base processors.extract as default
         from changedetectionio.processors.extract import process_extraction as default_process_extraction
@@ -238,7 +245,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             redirect=redirect
         )
 
-    @diff_blueprint.route("/diff/<uuid_str:uuid>/processor-asset/<string:asset_name>", methods=['GET'])
+    @diff_blueprint.route("/diff/<string:uuid>/processor-asset/<string:asset_name>", methods=['GET'])
     @login_optionally_required
     def processor_asset(uuid, asset_name):
         """
@@ -260,7 +267,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         - /diff/{uuid}/processor-asset/after
         - /diff/{uuid}/processor-asset/rendered_diff
         """
-
+        # More for testing, possible to return the first/only
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
 
@@ -273,33 +280,38 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         # Get the processor type for this watch
         processor_name = watch.get('processor', 'text_json_diff')
 
-        # Try to get the processor's difference module (works for both built-in and plugin processors)
-        from changedetectionio.processors import get_processor_submodule
-        processor_module = get_processor_submodule(processor_name, 'difference')
+        try:
+            # Try to import the processor's difference module
+            processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.difference')
 
-        # Call the processor's get_asset() function
-        if processor_module and hasattr(processor_module, 'get_asset'):
-            result = processor_module.get_asset(
-                asset_name=asset_name,
-                watch=watch,
-                datastore=datastore,
-                request=request
-            )
+            # Call the processor's get_asset() function
+            if hasattr(processor_module, 'get_asset'):
+                result = processor_module.get_asset(
+                    asset_name=asset_name,
+                    watch=watch,
+                    datastore=datastore,
+                    request=request
+                )
 
-            if result is None:
+                if result is None:
+                    from flask import abort
+                    abort(404, description=f"Asset '{asset_name}' not found")
+
+                binary_data, content_type, cache_control = result
+
+                response = make_response(binary_data)
+                response.headers['Content-Type'] = content_type
+                if cache_control:
+                    response.headers['Cache-Control'] = cache_control
+                return response
+            else:
+                logger.warning(f"Processor {processor_name} does not implement get_asset()")
                 from flask import abort
-                abort(404, description=f"Asset '{asset_name}' not found")
+                abort(404, description=f"Processor '{processor_name}' does not support assets")
 
-            binary_data, content_type, cache_control = result
-
-            response = make_response(binary_data)
-            response.headers['Content-Type'] = content_type
-            if cache_control:
-                response.headers['Cache-Control'] = cache_control
-            return response
-        else:
-            logger.warning(f"Processor {processor_name} does not implement get_asset()")
+        except (ImportError, ModuleNotFoundError) as e:
+            logger.warning(f"Processor {processor_name} does not have a difference module: {e}")
             from flask import abort
-            abort(404, description=f"Processor '{processor_name}' does not support assets")
+            abort(404, description=f"Processor '{processor_name}' not found")
 
     return diff_blueprint

changedetectionio/blueprint/ui/edit.py

@@ -9,7 +9,7 @@ from jinja2 import Environment, FileSystemLoader
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
 from changedetectionio.time_handler import is_within_schedule
-from changedetectionio import worker_pool
+from changedetectionio import worker_handler
 
 def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
     edit_blueprint = Blueprint('ui_edit', __name__, template_folder="../ui/templates")
@@ -20,23 +20,24 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             if tag_uuid in watch.get('tags', []) and (tag.get('include_filters') or tag.get('subtractive_selectors')):
                 return True
 
-    @edit_blueprint.route("/edit/<uuid_str:uuid>", methods=['GET', 'POST'])
+    @edit_blueprint.route("/edit/<string:uuid>", methods=['GET', 'POST'])
     @login_optionally_required
     # https://stackoverflow.com/questions/42984453/wtforms-populate-form-with-data-if-data-exists
     # https://wtforms.readthedocs.io/en/3.0.x/forms/#wtforms.form.Form.populate_obj ?
     def edit_page(uuid):
         from changedetectionio import forms
-        from changedetectionio.browser_steps.browser_steps import browser_step_ui_config
+        from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
         from changedetectionio import processors
         import importlib
 
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
         # More for testing, possible to return the first/only
         if not datastore.data['watching'].keys():
             flash(gettext("No watches to edit"), "error")
             return redirect(url_for('watchlist.index'))
 
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+
         if not uuid in datastore.data['watching']:
             flash(gettext("No watch with the UUID {} found.").format(uuid), "error")
             return redirect(url_for('watchlist.index'))
@@ -51,13 +52,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                     redirect(url_for('ui_edit.edit_page', uuid=uuid))
 
         # be sure we update with a copy instead of accidently editing the live object by reference
-        default = None
-        while not default:
-            try:
-                default = deepcopy(datastore.data['watching'][uuid])
-            except RuntimeError as e:
-                # Dictionary changed
-                continue
+        default = deepcopy(datastore.data['watching'][uuid])
 
         # Defaults for proxy choice
         if datastore.proxy_list is not None:  # When enabled
@@ -67,21 +62,12 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                 default['proxy'] = ''
         # proxy_override set to the json/text list of the items
 
-        # browser_profile: None means "use system default" — map to 'system' so the radio pre-selects correctly
-        if not default.get('browser_profile'):
-            default['browser_profile'] = 'system'
-
         # Does it use some custom form? does one exist?
         processor_name = datastore.data['watching'][uuid].get('processor', '')
         processor_classes = next((tpl for tpl in processors.find_processors() if tpl[1] == processor_name), None)
         if not processor_classes:
-            flash(gettext("Could not load '{}' processor, processor plugin might be missing. Please select a different processor.").format(processor_name), 'error')
-            # Fall back to default processor so user can still edit and change processor
-            processor_classes = next((tpl for tpl in processors.find_processors() if tpl[1] == 'text_json_diff'), None)
-            if not processor_classes:
-                # If even text_json_diff is missing, something is very wrong
-                flash(gettext("Could not load '{}' processor, processor plugin might be missing.").format(processor_name), 'error')
-                return redirect(url_for('watchlist.index'))
+            flash(gettext("Cannot load the edit form for processor/plugin '{}', plugin missing?").format(processor_classes[1]), 'error')
+            return redirect(url_for('watchlist.index'))
 
         parent_module = processors.get_parent_module(processor_classes[0])
 
@@ -121,59 +107,19 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                 processor_config = processor_instance.get_extra_watch_config(config_filename)
 
                 if processor_config:
-                    from wtforms.fields.form import FormField
                     # Populate processor-config-* fields from JSON
                     for config_key, config_value in processor_config.items():
-                        if not isinstance(config_value, dict):
-                            continue
-                        # Try exact API-named field first (e.g., processor_config_restock_diff)
-                        target_field = getattr(form, f'processor_config_{config_key}', None)
-                        # Fallback: find any FormField sub-form whose fields cover config_value keys
-                        if target_field is None:
-                            for form_field in form:
-                                if isinstance(form_field, FormField) and all(k in form_field.form._fields for k in config_value):
-                                    target_field = form_field
-                                    break
-                        if target_field is not None:
-                            for sub_key, sub_value in config_value.items():
-                                sub_field = target_field.form._fields.get(sub_key)
-                                if sub_field is not None:
-                                    sub_field.data = sub_value
-                                    logger.debug(f"Loaded processor config from {config_filename}: {sub_key} = {sub_value}")
+                        field_name = f'processor_config_{config_key}'
+                        if hasattr(form, field_name):
+                            getattr(form, field_name).data = config_value
+                            logger.debug(f"Loaded processor config from {config_filename}: {field_name} = {config_value}")
             except Exception as e:
                 logger.warning(f"Failed to load processor config: {e}")
 
-        from changedetectionio.model.browser_profile import BrowserProfile
-        from changedetectionio import content_fetchers as cf
-        store_profiles = datastore.data['settings']['application'].get('browser_profiles', {})
+        for p in datastore.extra_browsers:
+            form.fetch_backend.choices.append(p)
 
-        # Resolve the name of the system-level default profile for the label
-        from changedetectionio.model.browser_profile import get_profile
-        _system_default_machine_name = datastore.data['settings']['application'].get('browser_profile') or 'direct_http_requests'
-        _all_store_profiles = datastore.data['settings']['application'].get('browser_profiles', {})
-        _default_profile = get_profile(_system_default_machine_name, _all_store_profiles)
-        if _default_profile:
-            _system_label = gettext('System settings default') + ' \u2013 ' + _default_profile.name
-        else:
-            _system_label = gettext('System settings default')
-
-        # Choices: system default + always-present defaults (requests) + user-created profiles
-        form.browser_profile.choices = [('system', _system_label)] + [
-            (p.get_machine_name(), p.name)
-            for p in cf.DEFAULT_BROWSER_PROFILES.values()
-        ] + [
-            (machine_name, raw.get('name', machine_name) if isinstance(raw, dict) else machine_name)
-            for machine_name, raw in store_profiles.items()
-        ]
-
-        # Build a map of machine_name → fetcher class name for the JS visibility system
-        all_profiles = dict(cf.DEFAULT_BROWSER_PROFILES)
-        for machine_name, raw in store_profiles.items():
-            try:
-                all_profiles[machine_name] = BrowserProfile(**raw) if isinstance(raw, dict) else raw
-            except Exception:
-                pass
-        browser_profile_fetchers = {mn: p.get_fetcher_class_name() for mn, p in all_profiles.items()}
+        form.fetch_backend.choices.append(("system", 'System settings default'))
 
         # form.browser_steps[0] can be assumed that we 'goto url' first
 
@@ -198,10 +144,58 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
             extra_update_obj['time_between_check'] = form.time_between_check.data
 
-            # Handle processor-config-* fields separately (save to JSON, not datastore)
-            # IMPORTANT: These must NOT be saved to url-watches.json, only to the processor-specific JSON file
-            processor_config_data = processors.extract_processor_config_from_form_data(form.data)
-            processors.save_processor_config(datastore, uuid, processor_config_data)
+             # Handle processor-config-* fields separately (save to JSON, not datastore)
+            processor_config_data = {}
+            fields_to_remove = []
+            for field_name, field_value in form.data.items():
+                if field_name.startswith('processor_config_'):
+                    config_key = field_name.replace('processor_config_', '')
+                    if field_value:  # Only save non-empty values
+                        processor_config_data[config_key] = field_value
+                    fields_to_remove.append(field_name)
+
+            # Save processor config to JSON file if any config data exists
+            if processor_config_data:
+                try:
+                    processor_name = form.data.get('processor')
+                    # Create a processor instance to access config methods
+                    processor_instance = processors.difference_detection_processor(datastore, uuid)
+                    # Use processor name as filename so each processor keeps its own config
+                    config_filename = f'{processor_name}.json'
+                    processor_instance.update_extra_watch_config(config_filename, processor_config_data)
+                    logger.debug(f"Saved processor config to {config_filename}: {processor_config_data}")
+
+                    # Call optional edit_hook if processor has one
+                    try:
+                        # Try to import the edit_hook module from the processor package
+                        import importlib
+                        edit_hook_module_name = f'changedetectionio.processors.{processor_name}.edit_hook'
+
+                        try:
+                            edit_hook = importlib.import_module(edit_hook_module_name)
+                            logger.debug(f"Found edit_hook module for {processor_name}")
+
+                            if hasattr(edit_hook, 'on_config_save'):
+                                logger.info(f"Calling edit_hook.on_config_save for {processor_name}")
+                                watch_obj = datastore.data['watching'][uuid]
+                                # Call hook and get updated config
+                                updated_config = edit_hook.on_config_save(watch_obj, processor_config_data, datastore)
+                                # Save updated config back to file
+                                processor_instance.update_extra_watch_config(config_filename, updated_config)
+                                logger.info(f"Edit hook updated config: {updated_config}")
+                            else:
+                                logger.debug(f"Edit hook module found but no on_config_save function")
+                        except ModuleNotFoundError:
+                            logger.debug(f"No edit_hook module for processor {processor_name} (this is normal)")
+                    except Exception as hook_error:
+                        logger.error(f"Edit hook error (non-fatal): {hook_error}", exc_info=True)
+
+                except Exception as e:
+                    logger.error(f"Failed to save processor config: {e}")
+
+            # Remove processor-config-* fields from form.data before updating datastore
+            for field_name in fields_to_remove:
+                form.data.pop(field_name, None)
 
             # Ignore text
             form_ignore_text = form.ignore_text.data
@@ -241,19 +235,12 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
             # Recast it if need be to right data Watch handler
             watch_class = processors.get_custom_watch_obj_for_processor(form.data.get('processor'))
-            datastore.data['watching'][uuid] = watch_class(datastore_path=datastore.datastore_path, __datastore=datastore, default=datastore.data['watching'][uuid])
-
-            # Save the watch immediately
-            datastore.data['watching'][uuid].commit()
-
+            datastore.data['watching'][uuid] = watch_class(datastore_path=datastore.datastore_path, default=datastore.data['watching'][uuid])
             flash(gettext("Updated watch - unpaused!") if request.args.get('unpause_on_save') else gettext("Updated watch."))
 
-            # Cleanup any browsersteps session for this watch
-            try:
-                from changedetectionio.blueprint.browser_steps import cleanup_session_for_watch
-                cleanup_session_for_watch(uuid)
-            except Exception as e:
-                logger.debug(f"Error cleaning up browsersteps session: {e}")
+            # Re #286 - We wait for syncing new data to disk in another thread every 60 seconds
+            # But in the case something is added we should save straight away
+            datastore.needs_write_urgent = True
 
             # Do not queue on edit if its not within the time range
 
@@ -283,7 +270,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             #############################
             if not datastore.data['watching'][uuid].get('paused') and is_in_schedule:
                 # Queue the watch for immediate recheck, with a higher priority
-                worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
             # Diff page [edit] link should go back to diff page
             if request.args.get("next") and request.args.get("next") == 'diff':
@@ -311,23 +298,15 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
             # Get fetcher capabilities instead of hardcoded logic
             capabilities = get_fetcher_capabilities(watch, datastore)
-
-            # Add processor capabilities from module
-            capabilities['supports_visual_selector'] = getattr(parent_module, 'supports_visual_selector', False)
-            capabilities['supports_text_filters_and_triggers'] = getattr(parent_module, 'supports_text_filters_and_triggers', False)
-            capabilities['supports_text_filters_and_triggers_elements'] = getattr(parent_module, 'supports_text_filters_and_triggers_elements', False)
-            capabilities['supports_request_type'] = getattr(parent_module, 'supports_request_type', False)
-
             app_rss_token = datastore.data['settings']['application'].get('rss_access_token'),
 
             c = [f"processor-{watch.get('processor')}"]
-            if worker_pool.is_watch_running(uuid):
+            if worker_handler.is_watch_running(uuid):
                 c.append('checking-now')
 
             template_args = {
                 'available_processors': processors.available_processors(),
                 'available_timezones': sorted(available_timezones()),
-                'browser_profile_fetchers': browser_profile_fetchers,
                 'browser_steps_config': browser_step_ui_config,
                 'emailprefix': os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
                 'extra_classes': ' '.join(c),
@@ -346,6 +325,8 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                     'url': url_for('rss.rss_single_watch', uuid=watch['uuid'], token=app_rss_token)
                 },
                 'settings_application': datastore.data['settings']['application'],
+                'system_has_playwright_configured': os.getenv('PLAYWRIGHT_DRIVER_URL'),
+                'system_has_webdriver_configured': os.getenv('WEBDRIVER_URL'),
                 'ui_edit_stats_extras': collect_ui_edit_stats_extras(watch),
                 'visual_selector_data_ready': datastore.visualselector_data_is_ready(watch_uuid=uuid),
                 'timezone_default_config': datastore.data['settings']['application'].get('scheduler_timezone_default'),
@@ -372,19 +353,17 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
         return output
 
-    @edit_blueprint.route("/edit/<uuid_str:uuid>/get-html", methods=['GET'])
+    @edit_blueprint.route("/edit/<string:uuid>/get-html", methods=['GET'])
     @login_optionally_required
     def watch_get_latest_html(uuid):
         from io import BytesIO
         from flask import send_file
         import brotli
 
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
         watch = datastore.data['watching'].get(uuid)
-        if watch and watch.history.keys() and os.path.isdir(watch.data_dir):
+        if watch and watch.history.keys() and os.path.isdir(watch.watch_data_dir):
             latest_filename = list(watch.history.keys())[-1]
-            html_fname = os.path.join(watch.data_dir, f"{latest_filename}.html.br")
+            html_fname = os.path.join(watch.watch_data_dir, f"{latest_filename}.html.br")
             with open(html_fname, 'rb') as f:
                 if html_fname.endswith('.br'):
                     # Read and decompress the Brotli file
@@ -399,65 +378,12 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
         # Return a 500 error
         abort(500)
 
-    @edit_blueprint.route("/edit/<uuid_str:uuid>/get-data-package", methods=['GET'])
-    @login_optionally_required
-    def watch_get_data_package(uuid):
-        """Download all data for a single watch as a zip file"""
-        from io import BytesIO
-        from flask import send_file
-        import zipfile
-        from pathlib import Path
-        import datetime
-
-        watch = datastore.data['watching'].get(uuid)
-        if not watch:
-            abort(404)
-
-        # Create zip in memory
-        memory_file = BytesIO()
-
-        with zipfile.ZipFile(memory_file, 'w',
-                           compression=zipfile.ZIP_DEFLATED,
-                           compresslevel=8) as zipObj:
-
-            # Add the watch's JSON file if it exists
-            watch_json_path = os.path.join(watch.data_dir, 'watch.json')
-            if os.path.isfile(watch_json_path):
-                zipObj.write(watch_json_path,
-                           arcname=os.path.join(uuid, 'watch.json'),
-                           compress_type=zipfile.ZIP_DEFLATED,
-                           compresslevel=8)
-
-            # Add all files in the watch data directory
-            if os.path.isdir(watch.data_dir):
-                for f in Path(watch.data_dir).glob('*'):
-                    if f.is_file() and f.name != 'watch.json':  # Skip watch.json since we already added it
-                        zipObj.write(f,
-                                   arcname=os.path.join(uuid, f.name),
-                                   compress_type=zipfile.ZIP_DEFLATED,
-                                   compresslevel=8)
-
-        # Seek to beginning of file
-        memory_file.seek(0)
-
-        # Generate filename with timestamp
-        timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
-        filename = f"watch-data-{uuid[:8]}-{timestamp}.zip"
-
-        return send_file(memory_file,
-                        as_attachment=True,
-                        download_name=filename,
-                        mimetype='application/zip')
-
     # Ajax callback
-    @edit_blueprint.route("/edit/<uuid_str:uuid>/preview-rendered", methods=['POST'])
+    @edit_blueprint.route("/edit/<string:uuid>/preview-rendered", methods=['POST'])
     @login_optionally_required
     def watch_get_preview_rendered(uuid):
         '''For when viewing the "preview" of the rendered text from inside of Edit'''
         from flask import jsonify
-
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
         from changedetectionio.processors.text_json_diff import prepare_filter_prevew
         result = prepare_filter_prevew(watch_uuid=uuid, form_data=request.form, datastore=datastore)
         return jsonify(result)
@@ -481,9 +407,6 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                     s = re.sub(r'[0-9]+', r'\\d+', s)
                     datastore.data["watching"][uuid]['ignore_text'].append('/' + s + '/')
 
-            # Save the updated ignore_text
-            datastore.data["watching"][uuid].commit()
-
         return f"<a href={url_for('ui.ui_preview.preview_page', uuid=uuid)}>Click to preview</a>"
     
     return edit_blueprint

changedetectionio/blueprint/ui/notification.py

@@ -118,7 +118,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             sent_obj = process_notification(n_object, datastore)
 
         except Exception as e:
-            logger.error(e)
             e_str = str(e)
             # Remove this text which is not important and floods the container
             e_str = e_str.replace(

changedetectionio/blueprint/ui/preview.py

@@ -10,8 +10,7 @@ from changedetectionio import html_tools
 def construct_blueprint(datastore: ChangeDetectionStore):
     preview_blueprint = Blueprint('ui_preview', __name__, template_folder="../ui/templates")
 
-
-    @preview_blueprint.route("/preview/<uuid_str:uuid>", methods=['GET', 'POST'])
+    @preview_blueprint.route("/preview/<string:uuid>", methods=['GET'])
     @login_optionally_required
     def preview_page(uuid):
         """
@@ -27,9 +26,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         Each processor implements processors/{type}/preview.py::render()
         If a processor doesn't have a preview module, falls back to default text preview.
         """
-
+        # More for testing, possible to return the first/only
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
+
         try:
             watch = datastore.data['watching'][uuid]
         except KeyError:
@@ -39,29 +39,36 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         # Get the processor type for this watch
         processor_name = watch.get('processor', 'text_json_diff')
 
-        # Try to get the processor's preview module (works for both built-in and plugin processors)
-        from changedetectionio.processors import get_processor_submodule
-        processor_module = get_processor_submodule(processor_name, 'preview')
+        try:
+            # Try to import the processor's preview module
+            import importlib
+            processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.preview')
 
-        # Call the processor's render() function
-        if processor_module and hasattr(processor_module, 'render'):
-            return processor_module.render(
-                watch=watch,
-                datastore=datastore,
-                request=request,
-                url_for=url_for,
-                render_template=render_template,
-                flash=flash,
-                redirect=redirect
-            )
+            # Call the processor's render() function
+            if hasattr(processor_module, 'render'):
+                return processor_module.render(
+                    watch=watch,
+                    datastore=datastore,
+                    request=request,
+                    url_for=url_for,
+                    render_template=render_template,
+                    flash=flash,
+                    redirect=redirect
+                )
+        except (ImportError, ModuleNotFoundError) as e:
+            logger.debug(f"Processor {processor_name} does not have a preview module, using default preview: {e}")
 
         # Fallback: if processor doesn't have preview module, use default text preview
         content = []
         versions = []
         timestamp = None
 
+        system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
         extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
-        fetcher_supports_screenshots = watch.fetcher_supports_screenshots
+
+        is_html_webdriver = False
+        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
+            is_html_webdriver = True
 
         triggered_line_numbers = []
         ignored_line_numbers = []
@@ -71,9 +78,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             flash(gettext("Preview unavailable - No fetch/check completed or triggers not reached"), "error")
         else:
             # So prepare the latest preview or not
-            preferred_version = request.values.get('version') if request.method == 'POST' else request.args.get('version')
-
-
+            preferred_version = request.args.get('version')
             versions = list(watch.history.keys())
             timestamp = versions[-1]
             if preferred_version and preferred_version in versions:
@@ -112,7 +117,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                                  highlight_triggered_line_numbers=triggered_line_numbers,
                                  highlight_blocked_line_numbers=blocked_line_numbers,
                                  history_n=watch.history_n,
-                                 fetcher_supports_screenshots=fetcher_supports_screenshots,
+                                 is_html_webdriver=is_html_webdriver,
                                  last_error=watch['last_error'],
                                  last_error_screenshot=watch.get_error_snapshot(),
                                  last_error_text=watch.get_error_text(),
@@ -124,7 +129,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         return output
 
-    @preview_blueprint.route("/preview/<uuid_str:uuid>/processor-asset/<string:asset_name>", methods=['GET'])
+    @preview_blueprint.route("/preview/<string:uuid>/processor-asset/<string:asset_name>", methods=['GET'])
     @login_optionally_required
     def processor_asset(uuid, asset_name):
         """
@@ -145,8 +150,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         """
         from flask import make_response
 
+        # More for testing, possible to return the first/only
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
+
         try:
             watch = datastore.data['watching'][uuid]
         except KeyError:
@@ -156,33 +163,39 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         # Get the processor type for this watch
         processor_name = watch.get('processor', 'text_json_diff')
 
-        # Try to get the processor's preview module (works for both built-in and plugin processors)
-        from changedetectionio.processors import get_processor_submodule
-        processor_module = get_processor_submodule(processor_name, 'preview')
+        try:
+            # Try to import the processor's preview module
+            import importlib
+            processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.preview')
 
-        # Call the processor's get_asset() function
-        if processor_module and hasattr(processor_module, 'get_asset'):
-            result = processor_module.get_asset(
-                asset_name=asset_name,
-                watch=watch,
-                datastore=datastore,
-                request=request
-            )
+            # Call the processor's get_asset() function
+            if hasattr(processor_module, 'get_asset'):
+                result = processor_module.get_asset(
+                    asset_name=asset_name,
+                    watch=watch,
+                    datastore=datastore,
+                    request=request
+                )
 
-            if result is None:
+                if result is None:
+                    from flask import abort
+                    abort(404, description=f"Asset '{asset_name}' not found")
+
+                binary_data, content_type, cache_control = result
+
+                response = make_response(binary_data)
+                response.headers['Content-Type'] = content_type
+                if cache_control:
+                    response.headers['Cache-Control'] = cache_control
+                return response
+            else:
+                logger.warning(f"Processor {processor_name} does not implement get_asset()")
                 from flask import abort
-                abort(404, description=f"Asset '{asset_name}' not found")
+                abort(404, description=f"Processor '{processor_name}' does not support assets")
 
-            binary_data, content_type, cache_control = result
-
-            response = make_response(binary_data)
-            response.headers['Content-Type'] = content_type
-            if cache_control:
-                response.headers['Cache-Control'] = cache_control
-            return response
-        else:
-            logger.warning(f"Processor {processor_name} does not implement get_asset()")
+        except (ImportError, ModuleNotFoundError) as e:
+            logger.warning(f"Processor {processor_name} does not have a preview module: {e}")
             from flask import abort
-            abort(404, description=f"Processor '{processor_name}' does not support assets")
+            abort(404, description=f"Processor '{processor_name}' not found")
 
     return preview_blueprint

changedetectionio/blueprint/ui/templates/diff.html

@@ -87,7 +87,7 @@
     </form>
 </div>
 
-<div id="diff-jump" style="display:none;"><!-- disabled for now -->
+<div id="diff-jump">
     <a id="jump-next-diff" title="{{ _('Jump to next difference') }}">{{ _('Jump') }}</a>
 </div>
 
@@ -143,7 +143,7 @@
          <div class="tip">
              {{ _('For now, Differences are performed on text, not graphically, only the latest screenshot is available.') }}
          </div>
-         {% if fetcher_supports_screenshots %}
+         {% if is_html_webdriver %}
            {% if screenshot %}
             <div class="snapshot-age">{{watch_a.snapshot_screenshot_ctime|format_timestamp_timeago}}</div>
             <img style="max-width: 80%" id="screenshot-img" alt="{{ _('Current screenshot from most recent request') }}" >

changedetectionio/blueprint/ui/templates/edit.html

@@ -27,8 +27,7 @@
     const proxy_recheck_status_url="{{url_for('check_proxies.get_recheck_status', uuid=uuid)}}";
     const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
     const watch_visual_selector_data_url="{{url_for('static_content', group='visual_selector_data', filename=uuid)}}";
-    const default_system_fetch_backend = {{ (browser_profile_fetchers.get(settings_application.get('browser_profile') or 'direct_http_requests', 'requests')) | tojson }};
-    const browserProfileFetcherMap = {{ browser_profile_fetchers | tojson }};
+    const default_system_fetch_backend="{{ settings_application['fetch_backend'] }}";
 </script>
 <script src="{{url_for('static_content', group='js', filename='plugins.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
@@ -46,19 +45,14 @@
     <div class="tabs collapsable">
         <ul>
             <li class="tab"><a href="#general">{{ _('General') }}</a></li>
-            {% if capabilities.supports_request_type %}
             <li class="tab"><a href="#request">{{ _('Request') }}</a></li>
-            {% endif %}
             {% if extra_tab_content %}
             <li class="tab"><a href="#extras_tab">{{ extra_tab_content }}</a></li>
             {% endif %}
-            {% if capabilities.supports_browser_steps %}
             <li class="tab"><a id="browsersteps-tab" href="#browser-steps">{{ _('Browser Steps') }}</a></li>
-            {% endif %}
-            {% if capabilities.supports_visual_selector %}
+        <!-- should goto extra forms? -->
+            {% if watch['processor'] == 'text_json_diff' or watch['processor'] == 'image_ssim_diff' %}
             <li class="tab"><a id="visualselector-tab" href="#visualselector">{{ _('Visual Filter Selector') }}</a></li>
-            {% endif %}
-            {% if capabilities.supports_text_filters_and_triggers %}
             <li class="tab" id="filters-and-triggers-tab"><a href="#filters-and-triggers">{{ _('Filters & Triggers') }}</a></li>
             <li class="tab" id="conditions-tab"><a href="#conditions">{{ _('Conditions') }}</a></li>
             {% endif %}
@@ -116,35 +110,19 @@
                          {{ _('Sends a notification when the filter can no longer be seen on the page, good for knowing when the page changed and your filter will not work anymore.') }}
                         </span>
                     </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.history_snapshot_max_length, class="history_snapshot_max_length") }}
-                        <span class="pure-form-message-inline">{{ _('Limit collection of history snapshots for each watch to this number of history items.') }}
-                        <br>
-                        {{ _('Set to empty to use system settings default') }}
-                        </span>
-                    </div>
                     <div class="pure-control-group">
                         {{ render_ternary_field(form.use_page_title_in_list) }}
                     </div>
                 </fieldset>
             </div>
 
-            {% if capabilities.supports_request_type %}
             <div class="tab-pane-inner" id="request">
                     <div class="pure-control-group inline-radio">
-                        <div><label for="browser_profile">{{ form.browser_profile.label.text }}</label></div>
-                        <div><ul class="fetch-backend" id="browser_profile">
-                        {%- for subfield in form.browser_profile %}
-                            <li>
-                                {{ subfield() }}
-                                {{ browser_profile_fetchers.get(subfield.data, '')|fetcher_status_icons }}
-                                <label for="{{ subfield.id }}">{{ subfield.label.text }}</label>
-                            </li>
-                        {%- endfor %}
-                        </ul></div>
+                        {{ render_field(form.fetch_backend, class="fetch-backend") }}
                         <span class="pure-form-message-inline">
-                            <p>{{ _('Choose how this watch fetches its target URL. \'System settings default\' inherits the global setting.') }}</p>
-                            <p>{{ _('Manage browser profiles in') }} <a href="{{ url_for('settings.settings_browsers.index') }}">{{ _('Settings → Browsers') }}</a>.</p>
+                            <p>{{ _('Use the') }} <strong>{{ _('Basic') }}</strong> {{ _('method (default) where your watched site doesn\'t need Javascript to render.') }}</p>
+                            <p>{{ _('The') }} <strong>{{ _('Chrome/Javascript') }}</strong> {{ _('method requires a network connection to a running WebDriver+Chrome server, set by the ENV var \'WEBDRIVER_URL\'.') }} </p>
+                            {{ _('Tip:') }} <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">{{ _('Connect using Bright Data and Oxylabs Proxies, find out more here.') }}</a>
                         </span>
                     </div>
                 {% if form.proxy %}
@@ -158,7 +136,7 @@
                 {% endif %}
 
                 <!-- webdriver always -->
-                <fieldset data-visible-for="fetch_backend=playwright fetch_backend=selenium fetch_backend=puppeteer fetch_backend=cloakbrowser"  style="display: none;">
+                <fieldset data-visible-for="fetch_backend=html_webdriver"  style="display: none;">
                     <div class="pure-control-group">
                         {{ render_field(form.webdriver_delay) }}
                         <div class="pure-form-message-inline">
@@ -181,8 +159,8 @@
                         </div>
                     </div>
                 </fieldset>
-                <!-- requests always -->
-                <fieldset data-visible-for="fetch_backend=requests">
+                <!-- html requests always -->
+                <fieldset data-visible-for="fetch_backend=html_requests">
                     <div class="pure-control-group">
                         <a class="pure-button button-secondary button-xsmall show-advanced">{{ _('Show advanced options') }}</a>
                     </div>
@@ -219,17 +197,16 @@ Math: {{ 1 + 1 }}") }}
                             ({{ _('Not supported by Selenium browser') }})
                         </div>
                     </div>
-            <fieldset data-visible-for="fetch_backend=requests fetch_backend=playwright fetch_backend=selenium fetch_backend=puppeteer fetch_backend=cloakbrowser" >
+            <fieldset data-visible-for="fetch_backend=html_requests fetch_backend=html_webdriver" >
                     <div class="pure-control-group inline-radio advanced-options"  style="display: none;">
                     {{ render_checkbox_field(form.ignore_status_codes) }}
                     </div>
             </fieldset>
             </div>
-            {% endif %}
 
             <div class="tab-pane-inner" id="browser-steps">
             {% if capabilities.supports_browser_steps %}
-               {% if true %}
+               {% if visual_selector_data_ready %}
                 <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
                 <fieldset>
                     <div class="pure-control-group">
@@ -306,7 +283,8 @@ Math: {{ 1 + 1 }}") }}
                 </fieldset>
             </div>
 
-            {% if capabilities.supports_text_filters_and_triggers %}
+            {% if watch['processor'] == 'text_json_diff' or watch['processor'] == 'image_ssim_diff' %}
+
             <div class="tab-pane-inner" id="conditions">
                     <script>
                         const verify_condition_rule_url="{{url_for('conditions.verify_condition_single_rule', watch_uuid=uuid)}}";
@@ -325,9 +303,7 @@ Math: {{ 1 + 1 }}") }}
                 <span id="activate-text-preview" class="pure-button pure-button-primary button-xsmall">{{ _('Activate preview') }}</span>
               <div>
               <div id="edit-text-filter">
-
-{% if capabilities.supports_text_filters_and_triggers_elements %}
-                        <div class="pure-control-group" id="pro-tips">
+                    <div class="pure-control-group" id="pro-tips">
                             <strong>{{ _('Pro-tips:') }}</strong><br>
                             <ul>
                                 <li>
@@ -338,8 +314,8 @@ Math: {{ 1 + 1 }}") }}
                                 </li>
                             </ul>
                     </div>
+
 {% include "edit/include_subtract.html" %}
-{% endif %}
                 <div class="text-filtering border-fieldset">
                 <fieldset class="pure-group" id="text-filtering-type-options">
                     <h3>{{ _('Text filtering') }}</h3>
@@ -398,7 +374,7 @@ Math: {{ 1 + 1 }}") }}
             {{ extra_form_content|safe }}
             </div>
         {% endif %}
-            {% if capabilities.supports_visual_selector %}
+            {% if watch['processor'] == 'text_json_diff' or watch['processor'] == 'image_ssim_diff' %}
             <div class="tab-pane-inner visual-selector-ui" id="visualselector">
                 <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
 
@@ -410,7 +386,7 @@ Math: {{ 1 + 1 }}") }}
                                     {{ _('The Visual Selector tool lets you select the') }} <i>{{ _('text') }}</i> {{ _('elements that will be used for the change detection. It automatically fills-in the filters in the "CSS/JSONPath/JQ/XPath Filters" box of the') }} <a href="#filters-and-triggers">{{ _('Filters & Triggers') }}</a> {{ _('tab. Use') }} <strong>{{ _('Shift+Click') }}</strong> {{ _('to select multiple items.') }}
                                 </span>
 
-                                {% if watch['processor'] == 'image_ssim_diff' %} {# @todo, integrate with image_ssim_diff selector better, use some extra form ? #}
+                                {% if watch['processor'] == 'image_ssim_diff' %}
                                 <div id="selection-mode-controls" style="margin: 10px 0; padding: 10px; background: var(--color-background-tab); border-radius: 5px;">
                                     <label style="font-weight: 600; margin-right: 15px;">{{ _('Selection Mode:') }}</label>
                                     <label style="margin-right: 15px;">
@@ -497,7 +473,6 @@ Math: {{ 1 + 1 }}") }}
                     {% if watch.history_n %}
                         <p>
                              <a href="{{url_for('ui.ui_edit.watch_get_latest_html', uuid=uuid)}}" class="pure-button button-small">{{ _('Download latest HTML snapshot') }}</a>
-                             <a href="{{url_for('ui.ui_edit.watch_get_data_package', uuid=uuid)}}" class="pure-button button-small">{{ _('Download watch data package') }}</a>
                         </p>
                     {% endif %}
 

changedetectionio/blueprint/ui/templates/preview.html

@@ -17,7 +17,7 @@
     <script src="{{ url_for('static_content', group='js', filename='tabs.js') }}" defer></script>
     {% if versions|length >= 2 %}
         <div id="diff-form" style="text-align: center;">
-            <form class="pure-form "  action="{{url_for('ui.ui_preview.preview_page', uuid=uuid)}}" method="POST">
+            <form class="pure-form " action="" method="POST">
                 <fieldset>
                     <label for="preview-version">{{ _('Select timestamp') }}</label> <select id="preview-version"
                                                                                  name="from_version"
@@ -28,7 +28,6 @@
                         </option>
                     {% endfor %}
                 </select>
-                    <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
                     <button type="submit" class="pure-button pure-button-primary">{{ _('Go') }}</button>
 
                 </fieldset>

changedetectionio/blueprint/ui/views.py

@@ -2,7 +2,7 @@ from flask import Blueprint, request, redirect, url_for, flash
 from flask_babel import gettext
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
-from changedetectionio import worker_pool
+from changedetectionio import worker_handler
 
 
 def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData, watch_check_update):
@@ -24,9 +24,8 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             flash(gettext('Warning, URL {} already exists').format(url), "notice")
 
         add_paused = request.form.get('edit_and_watch_submit_button') != None
-        from changedetectionio import processors
-        processor = request.form.get('processor', processors.get_default_processor())
-        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tags','').strip(), extras={'paused': add_paused, 'processor': processor})
+        processor = request.form.get('processor', 'text_json_diff')
+        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tags').strip(), extras={'paused': add_paused, 'processor': processor})
 
         if new_uuid:
             if add_paused:
@@ -34,9 +33,9 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                 return redirect(url_for('ui.ui_edit.edit_page', uuid=new_uuid, unpause_on_save=1, tag=request.args.get('tag')))
             else:
                 # Straight into the queue.
-                worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
+                worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
                 flash(gettext("Watch added."))
 
         return redirect(url_for('watchlist.index', tag=request.args.get('tag','')))
 
-    return views_blueprint
+    return views_blueprint

changedetectionio/blueprint/watchlist/__init__.py

@@ -2,8 +2,8 @@ import os
 import time
 
 from flask import Blueprint, request, make_response, render_template, redirect, url_for, flash, session
+from flask_login import current_user
 from flask_paginate import Pagination, get_page_parameter
-from flask_babel import gettext as _
 
 from changedetectionio import forms
 from changedetectionio import processors
@@ -39,7 +39,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             elif op == 'mute':
                 datastore.data['watching'][uuid].toggle_mute()
 
-            datastore.data['watching'][uuid].commit()
+            datastore.needs_write = True
             return redirect(url_for('watchlist.index', tag = active_tag_uuid))
 
         # Sort by last_changed and add the uuid which is usually the key..
@@ -74,14 +74,10 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
         pagination = Pagination(page=page,
                                 total=total_count,
-                                per_page=datastore.data['settings']['application'].get('pager_size', 50),
-                                css_framework="semantic",
-                                display_msg=_('displaying <b>{start} - {end}</b> {record_name} in total <b>{total}</b>'),
-                                record_name=_('records'))
+                                per_page=datastore.data['settings']['application'].get('pager_size', 50), css_framework="semantic")
 
         sorted_tags = sorted(datastore.data['settings']['application'].get('tags').items(), key=lambda x: x[1]['title'])
 
-        proxy_list = datastore.proxy_list
         output = render_template(
             "watch-overview.html",
             active_tag=active_tag,
@@ -89,38 +85,25 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             app_rss_token=datastore.data['settings']['application'].get('rss_access_token'),
             datastore=datastore,
             errored_count=errored_count,
-            extra_classes='has-queue' if not update_q.empty() else '',
             form=form,
-            generate_tag_colors=processors.generate_processor_badge_colors,
             guid=datastore.data['app_guid'],
-            has_proxies=proxy_list,
+            has_proxies=datastore.proxy_list,
             hosted_sticky=os.getenv("SALTED_PASS", False) == False,
             now_time_server=round(time.time()),
             pagination=pagination,
-            processor_badge_css=processors.get_processor_badge_css(),
             processor_badge_texts=processors.get_processor_badge_texts(),
             processor_descriptions=processors.get_processor_descriptions(),
-            queue_size=update_q.qsize(),
-            queued_uuids=update_q.get_queued_uuids(),
+            processor_badge_css=processors.get_processor_badge_css(),
+            queued_uuids=[q_uuid.item['uuid'] for q_uuid in update_q.queue],
             search_q=request.args.get('q', '').strip(),
             sort_attribute=request.args.get('sort') if request.args.get('sort') else request.cookies.get('sort'),
             sort_order=request.args.get('order') if request.args.get('order') else request.cookies.get('order'),
-            system_default_fetcher=datastore.data['settings']['application'].get('browser_profile'),
+            system_default_fetcher=datastore.data['settings']['application'].get('fetch_backend'),
             tags=sorted_tags,
             unread_changes_count=datastore.unread_changes_count,
             watches=sorted_watches
         )
 
-        # Return freed template-building memory to the OS immediately.
-        # render_template allocates ~20MB of intermediate strings that are freed on return,
-        # but glibc keeps those pages mapped in its arenas as RSS. malloc_trim() forces
-        # glibc to release them, preventing RSS growth from concurrent Chrome connections.
-        try:
-            import ctypes
-            ctypes.CDLL('libc.so.6').malloc_trim(0)
-        except Exception:
-            pass
-
         if session.get('share-link'):
             del (session['share-link'])
 

changedetectionio/blueprint/watchlist/templates/watch-overview.html

@@ -1,9 +1,5 @@
 {%- extends 'base.html' -%}
 {%- block content -%}
-{%- set tips = [
-    _("Changedetection.io can monitor more than just web-pages! See our plugins!") ~ ' <a href="https://changedetection.io/plugins">' ~ _('More info') ~ '</a>',
-    _("You can also add 'shared' watches.") ~ ' <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">' ~ _('More info') ~ '</a>'
-] -%}
 {%- from '_helpers.html' import render_simple_field, render_field, render_nolabel_field, sort_by_title -%}
 <script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
 <script src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
@@ -14,46 +10,6 @@
 // Initialize Feather icons after the page loads
 document.addEventListener('DOMContentLoaded', function() {
     feather.replace();
-
-    // Intersection Observer for lazy loading favicons
-    // Only load favicon images when they enter the viewport
-    if ('IntersectionObserver' in window) {
-        const faviconObserver = new IntersectionObserver((entries, observer) => {
-            entries.forEach(entry => {
-                if (entry.isIntersecting) {
-                    const img = entry.target;
-                    const src = img.getAttribute('data-src');
-
-                    if (src) {
-                        // Load the actual favicon
-                        img.src = src;
-                        img.removeAttribute('data-src');
-                    }
-
-                    // Stop observing this image
-                    observer.unobserve(img);
-                }
-            });
-        }, {
-            // Start loading slightly before the image enters viewport
-            rootMargin: '50px',
-            threshold: 0.01
-        });
-
-        // Observe all lazy favicon images
-        document.querySelectorAll('.lazy-favicon').forEach(img => {
-            faviconObserver.observe(img);
-        });
-    } else {
-        // Fallback for older browsers: load all favicons immediately
-        document.querySelectorAll('.lazy-favicon').forEach(img => {
-            const src = img.getAttribute('data-src');
-            if (src) {
-                img.src = src;
-                img.removeAttribute('data-src');
-            }
-        });
-    }
 });
 </script>
 <style>
@@ -66,33 +22,6 @@ document.addEventListener('DOMContentLoaded', function() {
 
 /* Auto-generated processor badge colors */
 {{ processor_badge_css|safe }}
-
-/* Auto-generated tag colors */
-{%- for uuid, tag in tags -%}
-{%- if tag and tag.title -%}
-{%- set class_name = tag.title|sanitize_tag_class -%}
-{%- set colors = generate_tag_colors(tag.title) -%}
-.button-tag.tag-{{ class_name }} {
-  background-color: {{ colors['light']['bg'] }};
-  color: {{ colors['light']['color'] }};
-}
-
-.watch-tag-list.tag-{{ class_name }} {
-  background-color: {{ colors['light']['bg'] }};
-  color: {{ colors['light']['color'] }};
-}
-
-html[data-darkmode="true"] .button-tag.tag-{{ class_name }} {
-  background-color: {{ colors['dark']['bg'] }};
-  color: {{ colors['dark']['color'] }};
-}
-
-html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
-  background-color: {{ colors['dark']['bg'] }};
-  color: {{ colors['dark']['color'] }};
-}
-{%- endif -%}
-{%- endfor -%}
 </style>
 <div class="box" id="form-quick-watch-add">
 
@@ -106,16 +35,14 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
                     {{ render_nolabel_field(form.edit_and_watch_submit_button, title=_("Edit first then Watch") ) }}
             </div>
             <div id="watch-group-tag">
-               {{ render_field(form.tags, value=active_tag.title if active_tag_uuid else '', placeholder=_("Watch group / tag"), class="transparent-field") }}
+               {{ render_field(form.tags, value=active_tag.title if active_tag_uuid else '', placeholder="Watch group / tag", class="transparent-field") }}
             </div>
             <div id="quick-watch-processor-type">
                 {{ render_simple_field(form.processor) }}
             </div>
 
         </fieldset>
-        <span style="color:#eee; font-size: 80%;">
-            <strong>Tip: </strong> {{ tips | random | safe }}
-        </span>
+        <span style="color:#eee; font-size: 80%;"><img alt="{{ _('Create a shareable link') }}" style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread-white.svg')}}" > {{ _("Tip: You can also add 'shared' watches.") }} <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">{{ _('More info') }}</a></span>
     </form>
 </div>
 <div class="box">
@@ -145,14 +72,9 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
                        data-confirm-message="{{ _('<p>Are you sure you want to delete the selected watches?</strong></p><p>This action cannot be undone.</p>') }}"
                        data-confirm-button="{{ _('Delete') }}"><i data-feather="trash" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>{{ _('Delete') }}</button>
     </div>
-
-    <div id="stats_row">
-        <div class="left">{%- if watches|length >= pagination.per_page -%}{{ pagination.info }}{%- endif -%}</div>
-        <div class="right" >{{ _('Queued size') }}: <span id="queue-size-int">{{ queue_size }}</span></div>
-    </div>
-
-
-
+    {%- if watches|length >= pagination.per_page -%}
+        {{ pagination.info }}
+    {%- endif -%}
     {%- if search_q -%}<div id="search-result-info">{{ _('Searching') }} "<strong><i>{{search_q}}</i></strong>"</div>{%- endif -%}
     <div>
         <a href="{{url_for('watchlist.index')}}" class="pure-button button-tag {{'active' if not active_tag_uuid }}">{{ _('All') }}</a>
@@ -160,7 +82,7 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
     <!-- tag list -->
     {%- for uuid, tag in tags -%}
         {%- if tag != "" -%}
-            <a href="{{url_for('watchlist.index', tag=uuid) }}" class="pure-button button-tag tag-{{ tag.title|sanitize_tag_class }} {{'active' if active_tag_uuid == uuid }}">{{ tag.title }}</a>
+            <a href="{{url_for('watchlist.index', tag=uuid) }}" class="pure-button button-tag {{'active' if active_tag_uuid == uuid }}">{{ tag.title }}</a>
         {%- endif -%}
     {%- endfor -%}
     </div>
@@ -205,7 +127,7 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
             <tbody>
             {%- if not watches|length -%}
             <tr>
-                <td colspan="{{ cols_required }}" style="text-wrap: wrap;">{{ _('No web page change detection watches configured, please add a URL in the box above, or') }} <a href="{{ url_for('imports.import_page')}}" >{{ _('import a list') }}</a>.</td>
+                <td colspan="{{ cols_required }}" style="text-wrap: wrap;">{{ _('No website watches configured, please add a URL in the box above, or') }} <a href="{{ url_for('imports.import_page')}}" >{{ _('import a list') }}</a>.</td>
             </tr>
             {%- endif -%}
 
@@ -213,13 +135,12 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
                 {%- set checking_now = is_checking_now(watch) -%}
                 {%- set history_n = watch.history_n -%}
                 {%- set favicon = watch.get_favicon_filename() -%}
-                {%- set error_texts = watch.compile_error_texts(has_proxies=has_proxies) -%}
                 {%- set system_use_url_watchlist = datastore.data['settings']['application']['ui'].get('use_page_title_in_list')  -%}
                 {#  Class settings mirrored in changedetectionio/static/js/realtime.js for the frontend #}
                 {%- set row_classes = [
                     loop.cycle('pure-table-odd', 'pure-table-even'),
                     'processor-' ~ watch['processor'],
-                    'has-error' if error_texts|length > 2 else '',
+                    'has-error' if watch.compile_error_texts()|length > 2 else '',
                     'paused' if watch.paused is defined and watch.paused != False else '',
                     'unviewed' if watch.has_unviewed else '',
                     'has-restock-info' if watch.has_restock_info else 'no-restock-info',
@@ -247,45 +168,38 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
                 <td class="title-col inline">
                     <div class="flex-wrapper">
                     {% if 'favicons_enabled' not in ui_settings or ui_settings['favicons_enabled'] %}
-                        <div>
-                            {# Intersection Observer lazy loading: store real URL in data-src, load only when visible in viewport #}
-                            <img alt="Favicon thumbnail"
-                                 class="favicon lazy-favicon"
-                                 loading="lazy"
-                                 decoding="async"
-                                 fetchpriority="low"
-                                 {% if favicon %}
-                                 data-src="{{url_for('static_content', group='favicon', filename=watch.uuid)}}"
-                                 {% endif %}
-                                 src='data:image/svg+xml;utf8,%3Csvg xmlns="http://www.w3.org/2000/svg" width="7.087" height="7.087" viewBox="0 0 7.087 7.087"%3E%3Ccircle cx="3.543" cy="3.543" r="3.279" stroke="%23e1e1e1" stroke-width="0.45" fill="none" opacity="0.74"/%3E%3C/svg%3E'>
+                        <div>{# A page might have hundreds of these images, set IMG options for lazy loading, don't set SRC if we dont have it so it doesnt fetch the placeholder'  #}
+                            <img alt="Favicon thumbnail" class="favicon" loading="lazy" decoding="async" fetchpriority="low" {% if favicon %} src="{{url_for('static_content', group='favicon', filename=watch.uuid)}}" {% else %} src='data:image/svg+xml;utf8,%3Csvg xmlns="http://www.w3.org/2000/svg" width="7.087" height="7.087" viewBox="0 0 7.087 7.087"%3E%3Ccircle cx="3.543" cy="3.543" r="3.279" stroke="%23e1e1e1" stroke-width="0.45" fill="none" opacity="0.74"/%3E%3C/svg%3E' {%  endif %} />
                         </div>
                     {%  endif %}
                         <div>
-                            {%- if watch['processor'] and watch['processor'] in processor_badge_texts -%}
-                                <span class="processor-badge processor-badge-{{ watch['processor'] }}" title="{{ processor_descriptions.get(watch['processor'], watch['processor']) }}">{{ processor_badge_texts[watch['processor']] }}</span>
-                            {%- endif -%}
-                            <span class="watch-title">
-                                {% if system_use_url_watchlist or watch.get('use_page_title_in_list') %}
-                                    {{ watch.label }}
-                                {% else %}
-                                    {{ watch.get('title') or watch.link }}
-                                {% endif %}
-                               <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}">&nbsp;</a>
-                            </span>
-                            <div class="error-text" style="display:none;">{{ error_texts|safe }}</div>
+                        <span class="watch-title">
+                            {% if system_use_url_watchlist or watch.get('use_page_title_in_list') %}
+                                {{ watch.label }}
+                            {% else %}
+                                {{ watch.get('title') or watch.link }}
+                            {% endif %}
+                           <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}">&nbsp;</a>
+                        </span>
+                            <div class="error-text" style="display:none;">{{ watch.compile_error_texts(has_proxies=datastore.proxy_list)|safe }}</div>
                             {%- if watch['processor'] == 'text_json_diff'  -%}
                                 {%- if watch['has_ldjson_price_data'] and not watch['track_ldjson_price_data']  -%}
                                 <div class="ldjson-price-track-offer">Switch to Restock & Price watch mode? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
                                 {%- endif -%}
                             {%- endif -%}
-
+                            {%- if watch['processor'] and watch['processor'] in processor_badge_texts -%}
+                                <span class="processor-badge processor-badge-{{ watch['processor'] }}" title="{{ processor_descriptions.get(watch['processor'], watch['processor']) }}">{{ processor_badge_texts[watch['processor']] }}</span>
+                            {%- endif -%}
                             {%- for watch_tag_uuid, watch_tag in datastore.get_all_tags_for_watch(watch['uuid']).items() -%}
-                              <a href="{{url_for('watchlist.index', tag=watch_tag_uuid) }}" class="watch-tag-list tag-{{ watch_tag.title|sanitize_tag_class }}">{{ watch_tag.title }}</a>
+                              <span class="watch-tag-list">{{ watch_tag.title }}</span>
                             {%- endfor -%}
                         </div>
                     <div class="status-icons">
                             <a class="link-spread" href="{{url_for('ui.form_share_put_watch', uuid=watch.uuid)}}"><img src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" ></a>
-                            {{ watch.effective_browser_profile.get_fetcher_class_name()|fetcher_status_icons }}
+                            {%- set effective_fetcher = watch.get_fetch_backend if watch.get_fetch_backend != "system" else system_default_fetcher -%}
+                            {%- if effective_fetcher and ("html_webdriver" in effective_fetcher or "html_" in effective_fetcher or "extra_browser_" in effective_fetcher) -%}
+                                {{ effective_fetcher|fetcher_status_icons }}
+                            {%- endif -%}
                             {%- if watch.is_pdf  -%}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" alt="Converting PDF to text" >{%- endif -%}
                             {%- if watch.has_browser_steps -%}<img class="status-icon status-browsersteps" src="{{url_for('static_content', group='images', filename='steps.svg')}}" alt="Browser Steps is enabled" >{%- endif -%}
 
@@ -302,20 +216,11 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
                             </span>
                         {%- endif -%}
 
-                        {%- if watch.get('restock') and watch['restock'].get('price') -%}
-                            {%- set restock = watch['restock'] -%}
-                            {%- set price = restock.get('price') -%}
-                            {%- set cur = restock.get('currency','') -%}
-
-                            {%- if price is not none and (price|string)|regex_search('\d') -%}
-                              <span class="restock-label price" title="{{ _('Price') }}">
-                              {# @todo: make parse_currency/parse_decimal aware of the locale of the actual web page and use that instead changedetectionio/processors/restock_diff/__init__.py #}
-                                {%- if price is number -%}{# It's a number so we can convert it to their locale' #}
-                                  {{ price|format_number_locale }} {{ cur }}<!-- as number -->
-                                {%- else -%}{# It's totally fine if it arrives as something else, the website might be something weird in this field #}
-                                  {{ price }} {{ cur }}<!-- as string -->
-                                {%- endif -%}
-                              </span>
+                        {%- if watch.get('restock') and watch['restock']['price'] != None -%}
+                            {%- if watch['restock']['price'] != None -%}
+                                <span class="restock-label price" title="{{ _('Price') }}">
+                                {{ watch['restock']['price']|format_number_locale if watch['restock'].get('price') else '' }} {{ watch['restock'].get('currency','') }}
+                                </span>
                             {%- endif -%}
                         {%- elif not watch.has_restock_info -%}
                             <span class="restock-label error">{{ _('No information') }}</span>

changedetectionio/content_fetchers/__init__.py

@@ -25,88 +25,87 @@ SCREENSHOT_MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_
 # Most modern GPUs support 16384x16384 textures, so 1280x10000 is safe
 SCREENSHOT_SIZE_STITCH_THRESHOLD = int(os.getenv("SCREENSHOT_CHUNK_HEIGHT", 10000))
 
+# available_fetchers() will scan this implementation looking for anything starting with html_
+# this information is used in the form selections
+from changedetectionio.content_fetchers.requests import fetcher as html_requests
+
+
 import importlib.resources
 XPATH_ELEMENT_JS = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text(encoding='utf-8')
 INSTOCK_DATA_JS = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text(encoding='utf-8')
 FAVICON_FETCHER_JS = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('favicon-fetcher.js').read_text(encoding='utf-8')
 
 
-# Registry: clean fetcher name → fetcher class (e.g. 'requests', 'playwright', 'cloakbrowser')
-FETCHERS: dict = {}
-
-
-def register_fetcher(name: str, cls) -> None:
-    """Register a fetcher class under its clean name (no html_ prefix)."""
-    FETCHERS[name] = cls
-
-
-def get_fetcher(name: str):
-    """Return the fetcher class for a clean name, or None."""
-    return FETCHERS.get(name)
-
-
 def available_fetchers():
-    """Return list of (name, description) for all registered fetchers."""
-    return [(name, cls.fetcher_description) for name, cls in FETCHERS.items()
-            if hasattr(cls, 'fetcher_description')]
+    # See the if statement at the bottom of this file for how we switch between playwright and webdriver
+    import inspect
+    p = []
+
+    # Get built-in fetchers (but skip plugin fetchers that were added via setattr)
+    for name, obj in inspect.getmembers(sys.modules[__name__], inspect.isclass):
+        if inspect.isclass(obj):
+            # @todo html_ is maybe better as fetcher_ or something
+            # In this case, make sure to edit the default one in store.py and fetch_site_status.py
+            if name.startswith('html_'):
+                # Skip plugin fetchers that were already registered
+                if name not in _plugin_fetchers:
+                    t = tuple([name, obj.fetcher_description])
+                    p.append(t)
+
+    # Get plugin fetchers from cache (already loaded at module init)
+    for name, fetcher_class in _plugin_fetchers.items():
+        if hasattr(fetcher_class, 'fetcher_description'):
+            t = tuple([name, fetcher_class.fetcher_description])
+            p.append(t)
+        else:
+            logger.warning(f"Plugin fetcher '{name}' does not have fetcher_description attribute")
+
+    return p
 
 
-def available_browser_fetchers():
-    """Return list of (name, description) for fetchers that support screenshots (browser-type fetchers)."""
-    return [(name, cls.fetcher_description) for name, cls in FETCHERS.items()
-            if cls.supports_screenshots]
+def get_plugin_fetchers():
+    """Load and return all plugin fetchers from the centralized plugin manager."""
+    from changedetectionio.pluggy_interface import plugin_manager
 
-
-def _load_fetchers():
-    """Load all fetchers (built-ins + plugins) into the FETCHERS registry."""
-    from changedetectionio.pluggy_interface import plugin_manager, register_builtin_fetchers
-
-    # Built-ins must be registered first
-    register_builtin_fetchers()
-
-    # Then external plugins
+    fetchers = {}
     try:
+        # Call the register_content_fetcher hook from all registered plugins
         results = plugin_manager.hook.register_content_fetcher()
         for result in results:
             if result:
                 name, fetcher_class = result
-                register_fetcher(name, fetcher_class)
-                logger.info(f"Registered fetcher: {name} - {getattr(fetcher_class, 'fetcher_description', '?')}")
+                fetchers[name] = fetcher_class
+                # Register in current module so hasattr() checks work
+                setattr(sys.modules[__name__], name, fetcher_class)
+                logger.info(f"Registered plugin fetcher: {name} - {getattr(fetcher_class, 'fetcher_description', 'No description')}")
     except Exception as e:
         logger.error(f"Error loading plugin fetchers: {e}")
 
-
-def get_active_browser_fetcher_name() -> str:
-    """Return the clean name of the browser fetcher activated by environment config.
-
-    - ``PLAYWRIGHT_DRIVER_URL`` set + ``FAST_PUPPETEER_CHROME_FETCHER=False`` → ``playwright_cdp``
-    - ``PLAYWRIGHT_DRIVER_URL`` set + ``FAST_PUPPETEER_CHROME_FETCHER=True``  → ``puppeteer``
-    - Neither set → ``selenium``
-    """
-    if os.getenv('PLAYWRIGHT_DRIVER_URL', False):
-        if not strtobool(os.getenv('FAST_PUPPETEER_CHROME_FETCHER', 'False')):
-            return 'playwright_cdp'
-        return 'puppeteer'
-    return 'selenium'
+    return fetchers
 
 
-# Default browser profiles always shown in the browser profiles table (keyed by machine name)
-DEFAULT_BROWSER_PROFILES: dict = {}
+# Initialize plugins at module load time
+_plugin_fetchers = get_plugin_fetchers()
 
 
-def _register_default_browser_profiles():
-    """Register browser profiles that are always present in the profiles table."""
-    from changedetectionio.model.browser_profile import BUILTIN_REQUESTS
-    DEFAULT_BROWSER_PROFILES[BUILTIN_REQUESTS.get_machine_name()] = BUILTIN_REQUESTS
+# Decide which is the 'real' HTML webdriver, this is more a system wide config
+# rather than site-specific.
+use_playwright_as_chrome_fetcher = os.getenv('PLAYWRIGHT_DRIVER_URL', False)
+if use_playwright_as_chrome_fetcher:
+    # @note - For now, browser steps always uses playwright
+    if not strtobool(os.getenv('FAST_PUPPETEER_CHROME_FETCHER', 'False')):
+        logger.debug('Using Playwright library as fetcher')
+        from .playwright import fetcher as html_webdriver
+    else:
+        logger.debug('Using direct Python Puppeteer library as fetcher')
+        from .puppeteer import fetcher as html_webdriver
+
+else:
+    logger.debug("Falling back to selenium as fetcher")
+    from .webdriver_selenium import fetcher as html_webdriver
 
 
-# Populate the registry at module load time
-_load_fetchers()
-
-# Backwards-compat alias: stored data may reference 'playwright' (pre-refactor name).
-# Map it to playwright_cdp which is the CDP-based fetcher that replaced it.
-if 'playwright_cdp' in FETCHERS and 'playwright' not in FETCHERS:
-    FETCHERS['playwright'] = FETCHERS['playwright_cdp']
-
-_register_default_browser_profiles()
+# Register built-in fetchers as plugins after all imports are complete
+from changedetectionio.pluggy_interface import register_builtin_fetchers
+register_builtin_fetchers()
 

changedetectionio/content_fetchers/base.py

@@ -38,6 +38,7 @@ def manage_user_agent(headers, current_ua=''):
 
     return None
 
+
 class Fetcher():
     browser_connection_is_custom = None
     browser_connection_url = None
@@ -70,38 +71,28 @@ class Fetcher():
     supports_screenshots = False        # Can capture page screenshots
     supports_xpath_element_data = False # Can extract xpath element positions/data for visual selector
 
-    # Icon shown in the watch list when this fetcher is the effective fetcher.
-    # Set to a dict with 'filename', 'alt', 'title' keys (image served from static/images/).
-    # None means no icon is shown (e.g. plain HTTP requests fetcher).
-    status_icon = None
-
-    # Screenshot element locking - prevents layout shifts during screenshot capture
-    # Only needed for visual comparison (image_ssim_diff processor)
-    # Locks element dimensions in the first viewport to prevent headers/ads from resizing
-    lock_viewport_elements = False      # Default: disabled for performance
-
-    # BrowserProfile-derived settings — applied by browser fetchers, ignored by html_requests
-    viewport_width: int = 1280
-    viewport_height: int = 1000
-    block_images: bool = False
-    block_fonts: bool = False
-    profile_user_agent: str = None   # Profile-level UA; lower priority than request_headers User-Agent
-    ignore_https_errors: bool = False
-    locale: str = None
-
     def __init__(self, **kwargs):
         if kwargs and 'screenshot_format' in kwargs:
             self.screenshot_format = kwargs.get('screenshot_format')
 
-        if kwargs and 'lock_viewport_elements' in kwargs:
-            self.lock_viewport_elements = kwargs.get('lock_viewport_elements')
 
-        # BrowserProfile fields — store whatever was passed, subclasses use them
-        for field in ('viewport_width', 'viewport_height', 'block_images', 'block_fonts',
-                      'profile_user_agent', 'ignore_https_errors', 'locale'):
-            if field in kwargs:
-                setattr(self, field, kwargs[field])
+    @classmethod
+    def get_status_icon_data(cls):
+        """Return data for status icon to display in the watch overview.
 
+        This method can be overridden by subclasses to provide custom status icons.
+
+        Returns:
+            dict or None: Dictionary with icon data:
+                {
+                    'filename': 'icon-name.svg',  # Icon filename
+                    'alt': 'Alt text',            # Alt attribute
+                    'title': 'Tooltip text',      # Title attribute
+                    'style': 'height: 1em;'       # Optional inline CSS
+                }
+                Or None if no icon
+        """
+        return None
 
     def clear_content(self):
         """
@@ -163,16 +154,30 @@ class Fetcher():
         """
         return {k.lower(): v for k, v in self.headers.items()}
 
+    def browser_steps_get_valid_steps(self):
+        if self.browser_steps is not None and len(self.browser_steps):
+            valid_steps = list(filter(
+                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one'),
+                self.browser_steps))
+
+            # Just incase they selected Goto site by accident with older JS
+            if valid_steps and valid_steps[0]['operation'] == 'Goto site':
+                del(valid_steps[0])
+
+            return valid_steps
+
+        return None
+
     async def iterate_browser_steps(self, start_url=None):
-        from changedetectionio.browser_steps.browser_steps import steppable_browser_interface, browser_steps_get_valid_steps
+        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
         from playwright._impl._errors import TimeoutError, Error
         from changedetectionio.jinja2_custom import render as jinja_render
         step_n = 0
 
-        if self.browser_steps:
+        if self.browser_steps is not None and len(self.browser_steps):
             interface = steppable_browser_interface(start_url=start_url)
             interface.page = self.page
-            valid_steps = browser_steps_get_valid_steps(self.browser_steps)
+            valid_steps = self.browser_steps_get_valid_steps()
 
             for step in valid_steps:
                 step_n += 1
@@ -199,16 +204,6 @@ class Fetcher():
                     # Stop processing here
                     raise BrowserStepsStepException(step_n=step_n, original_e=e)
 
-    def disk_cleanup_after_fetch(self):
-        """Remove any temporary files written to disk during a fetch.
-
-        The default implementation is a no-op.  Browser-based fetchers
-        override this to delete browser-step screenshots and any other
-        ephemeral files they create.  Called by the processor after
-        ``quit()`` regardless of whether the fetch succeeded or failed.
-        """
-        pass
-
     # It's always good to reset these
     def delete_browser_steps_screenshots(self):
         import glob

changedetectionio/content_fetchers/playwright.py

@@ -0,0 +1,406 @@
+import json
+import os
+from urllib.parse import urlparse
+
+from loguru import logger
+
+from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT, visualselector_xpath_selectors, \
+    SCREENSHOT_SIZE_STITCH_THRESHOLD, SCREENSHOT_MAX_TOTAL_HEIGHT, XPATH_ELEMENT_JS, INSTOCK_DATA_JS, FAVICON_FETCHER_JS
+from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
+from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, ScreenshotUnavailable
+
+async def capture_full_page_async(page, screenshot_format='JPEG'):
+    import os
+    import time
+    import multiprocessing
+
+    start = time.time()
+
+    page_height = await page.evaluate("document.documentElement.scrollHeight")
+    page_width = await page.evaluate("document.documentElement.scrollWidth")
+    original_viewport = page.viewport_size
+
+    logger.debug(f"Playwright viewport size {page.viewport_size} page height {page_height} page width {page_width}")
+
+    # Use an approach similar to puppeteer: set a larger viewport and take screenshots in chunks
+    step_size = SCREENSHOT_SIZE_STITCH_THRESHOLD # Size that won't cause GPU to overflow
+    screenshot_chunks = []
+    y = 0
+    elements_locked = False
+
+    if page_height > page.viewport_size['height']:
+
+        # Lock all element dimensions BEFORE screenshot to prevent CSS media queries from resizing
+        # capture_full_page_async() changes viewport height which triggers @media (min-height) rules
+        lock_elements_js_path = os.path.join(os.path.dirname(__file__), 'res', 'lock-elements-sizing.js')
+        with open(lock_elements_js_path, 'r') as f:
+            lock_elements_js = f.read()
+        await page.evaluate(lock_elements_js)
+        elements_locked = True
+
+        logger.debug("Element dimensions locked before screenshot capture")
+
+        if page_height < step_size:
+            step_size = page_height # Incase page is bigger than default viewport but smaller than proposed step size
+        logger.debug(f"Setting bigger viewport to step through large page width W{page.viewport_size['width']}xH{step_size} because page_height > viewport_size")
+        # Set viewport to a larger size to capture more content at once
+        await page.set_viewport_size({'width': page.viewport_size['width'], 'height': step_size})
+
+    # Capture screenshots in chunks up to the max total height
+    # Use PNG for better quality (no compression artifacts), JPEG for smaller size
+    screenshot_type = screenshot_format.lower() if screenshot_format else 'jpeg'
+    # PNG should use quality 100, JPEG uses configurable quality
+    screenshot_quality = 100 if screenshot_type == 'png' else int(os.getenv("SCREENSHOT_QUALITY", 72))
+
+    while y < min(page_height, SCREENSHOT_MAX_TOTAL_HEIGHT):
+        # Only scroll if not at the top (y > 0)
+        if y > 0:
+            await page.evaluate(f"window.scrollTo(0, {y})")
+
+        # Request GC only before screenshot (not 3x per chunk)
+        await page.request_gc()
+
+        screenshot_kwargs = {
+            'type': screenshot_type,
+            'full_page': False
+        }
+        # Only pass quality parameter for jpeg (PNG doesn't support it in Playwright)
+        if screenshot_type == 'jpeg':
+            screenshot_kwargs['quality'] = screenshot_quality
+
+        screenshot_chunks.append(await page.screenshot(**screenshot_kwargs))
+        y += step_size
+
+    # Restore original viewport size
+    await page.set_viewport_size({'width': original_viewport['width'], 'height': original_viewport['height']})
+
+    # Unlock element dimensions if they were locked
+    if elements_locked:
+        unlock_elements_js_path = os.path.join(os.path.dirname(__file__), 'res', 'unlock-elements-sizing.js')
+        with open(unlock_elements_js_path, 'r') as f:
+            unlock_elements_js = f.read()
+        await page.evaluate(unlock_elements_js)
+        logger.debug("Element dimensions unlocked after screenshot capture")
+
+    # If we have multiple chunks, stitch them together
+    if len(screenshot_chunks) > 1:
+        logger.debug(f"Screenshot stitching {len(screenshot_chunks)} chunks together")
+
+        # For small number of chunks (2-3), stitch inline to avoid multiprocessing overhead
+        # Only use separate process for many chunks (4+) to avoid blocking the event loop
+        if len(screenshot_chunks) <= 3:
+            from changedetectionio.content_fetchers.screenshot_handler import stitch_images_inline
+            screenshot = stitch_images_inline(screenshot_chunks, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT)
+        else:
+            # Use separate process for many chunks to avoid blocking
+            # Always use spawn for thread safety - consistent behavior in tests and production
+            from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker
+            ctx = multiprocessing.get_context('spawn')
+            parent_conn, child_conn = ctx.Pipe()
+            p = ctx.Process(target=stitch_images_worker, args=(child_conn, screenshot_chunks, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
+            p.start()
+            screenshot = parent_conn.recv_bytes()
+            p.join()
+            # Explicit cleanup
+            del p
+            del parent_conn, child_conn
+
+        logger.debug(
+            f"Screenshot (chunked/stitched) - Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
+        # Explicit cleanup
+        del screenshot_chunks
+        screenshot_chunks = None
+        return screenshot
+
+    logger.debug(
+        f"Screenshot Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
+
+    return screenshot_chunks[0]
+
+class fetcher(Fetcher):
+    fetcher_description = "Playwright {}/Javascript".format(
+        os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
+    )
+    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
+        fetcher_description += " via '{}'".format(os.getenv("PLAYWRIGHT_DRIVER_URL"))
+
+    browser_type = ''
+    command_executor = ''
+
+    # Configs for Proxy setup
+    # In the ENV vars, is prefixed with "playwright_proxy_", so it is for example "playwright_proxy_server"
+    playwright_proxy_settings_mappings = ['bypass', 'server', 'username', 'password']
+
+    proxy = None
+
+    # Capability flags
+    supports_browser_steps = True
+    supports_screenshots = True
+    supports_xpath_element_data = True
+
+    @classmethod
+    def get_status_icon_data(cls):
+        """Return Chrome browser icon data for Playwright fetcher."""
+        return {
+            'filename': 'google-chrome-icon.png',
+            'alt': 'Using a Chrome browser',
+            'title': 'Using a Chrome browser'
+        }
+
+    def __init__(self, proxy_override=None, custom_browser_connection_url=None, **kwargs):
+        super().__init__(**kwargs)
+
+        self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
+
+        if custom_browser_connection_url:
+            self.browser_connection_is_custom = True
+            self.browser_connection_url = custom_browser_connection_url
+        else:
+            # Fallback to fetching from system
+            # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+            self.browser_connection_url = os.getenv("PLAYWRIGHT_DRIVER_URL", 'ws://playwright-chrome:3000').strip('"')
+
+        # If any proxy settings are enabled, then we should setup the proxy object
+        proxy_args = {}
+        for k in self.playwright_proxy_settings_mappings:
+            v = os.getenv('playwright_proxy_' + k, False)
+            if v:
+                proxy_args[k] = v.strip('"')
+
+        if proxy_args:
+            self.proxy = proxy_args
+
+        # allow per-watch proxy selection override
+        if proxy_override:
+            self.proxy = {'server': proxy_override}
+
+        if self.proxy:
+            # Playwright needs separate username and password values
+            parsed = urlparse(self.proxy.get('server'))
+            if parsed.username:
+                self.proxy['username'] = parsed.username
+                self.proxy['password'] = parsed.password
+
+    async def screenshot_step(self, step_n=''):
+        super().screenshot_step(step_n=step_n)
+        screenshot = await capture_full_page_async(page=self.page, screenshot_format=self.screenshot_format)
+
+
+        if self.browser_steps_screenshot_path is not None:
+            destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.jpeg'.format(step_n))
+            logger.debug(f"Saving step screenshot to {destination}")
+            with open(destination, 'wb') as f:
+                f.write(screenshot)
+
+    async def save_step_html(self, step_n):
+        super().save_step_html(step_n=step_n)
+        content = await self.page.content()
+        destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.html'.format(step_n))
+        logger.debug(f"Saving step HTML to {destination}")
+        with open(destination, 'w', encoding='utf-8') as f:
+            f.write(content)
+
+    async def run(self,
+                  fetch_favicon=True,
+                  current_include_filters=None,
+                  empty_pages_are_a_change=False,
+                  ignore_status_codes=False,
+                  is_binary=False,
+                  request_body=None,
+                  request_headers=None,
+                  request_method=None,
+                  screenshot_format=None,
+                  timeout=None,
+                  url=None,
+                  watch_uuid=None,
+                  ):
+
+        from playwright.async_api import async_playwright
+        import playwright._impl._errors
+        import time
+        self.delete_browser_steps_screenshots()
+        response = None
+
+        async with async_playwright() as p:
+            browser_type = getattr(p, self.browser_type)
+
+            # Seemed to cause a connection Exception even tho I can see it connect
+            # self.browser = browser_type.connect(self.command_executor, timeout=timeout*1000)
+            # 60,000 connection timeout only
+            browser = await browser_type.connect_over_cdp(self.browser_connection_url, timeout=60000)
+
+            # SOCKS5 with authentication is not supported (yet)
+            # https://github.com/microsoft/playwright/issues/10567
+
+            # Set user agent to prevent Cloudflare from blocking the browser
+            # Use the default one configured in the App.py model that's passed from fetch_site_status.py
+            context = await browser.new_context(
+                accept_downloads=False,  # Should never be needed
+                bypass_csp=True,  # This is needed to enable JavaScript execution on GitHub and others
+                extra_http_headers=request_headers,
+                ignore_https_errors=True,
+                proxy=self.proxy,
+                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'), # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
+                user_agent=manage_user_agent(headers=request_headers),
+            )
+
+            self.page = await context.new_page()
+
+            # Listen for all console events and handle errors
+            self.page.on("console", lambda msg: logger.debug(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
+
+            # Re-use as much code from browser steps as possible so its the same
+            from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+            browsersteps_interface = steppable_browser_interface(start_url=url)
+            browsersteps_interface.page = self.page
+
+            response = await browsersteps_interface.action_goto_url(value=url)
+
+            if response is None:
+                await context.close()
+                await browser.close()
+                logger.debug("Content Fetcher > Response object from the browser communication was none")
+                raise EmptyReply(url=url, status_code=None)
+
+            # In async_playwright, all_headers() returns a coroutine
+            try:
+                self.headers = await response.all_headers()
+            except TypeError:
+                # Fallback for sync version
+                self.headers = response.all_headers()
+
+            try:
+                if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
+                    await browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
+            except playwright._impl._errors.TimeoutError as e:
+                await context.close()
+                await browser.close()
+                # This can be ok, we will try to grab what we could retrieve
+                pass
+            except Exception as e:
+                logger.debug(f"Content Fetcher > Other exception when executing custom JS code {str(e)}")
+                await context.close()
+                await browser.close()
+                raise PageUnloadable(url=url, status_code=None, message=str(e))
+
+            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+            await self.page.wait_for_timeout(extra_wait * 1000)
+
+            try:
+                self.status_code = response.status
+            except Exception as e:
+                # https://github.com/dgtlmoon/changedetection.io/discussions/2122#discussioncomment-8241962
+                logger.critical(f"Response from the browser/Playwright did not have a status_code! Response follows.")
+                logger.critical(response)
+                await context.close()
+                await browser.close()
+                raise PageUnloadable(url=url, status_code=None, message=str(e))
+
+            if fetch_favicon:
+                try:
+                    self.favicon_blob = await self.page.evaluate(FAVICON_FETCHER_JS)
+                    await self.page.request_gc()
+                except Exception as e:
+                    logger.error(f"Error fetching FavIcon info {str(e)}, continuing.")
+
+            if self.status_code != 200 and not ignore_status_codes:
+                screenshot = await capture_full_page_async(self.page, screenshot_format=self.screenshot_format)
+                raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
+
+            if not empty_pages_are_a_change and len((await self.page.content()).strip()) == 0:
+                logger.debug("Content Fetcher > Content was empty, empty_pages_are_a_change = False")
+                await context.close()
+                await browser.close()
+                raise EmptyReply(url=url, status_code=response.status)
+
+            # Run Browser Steps here
+            if self.browser_steps_get_valid_steps():
+                await self.iterate_browser_steps(start_url=url)
+
+            await self.page.wait_for_timeout(extra_wait * 1000)
+
+            now = time.time()
+            # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
+            if current_include_filters is not None:
+                await self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
+            else:
+                await self.page.evaluate("var include_filters=''")
+            await self.page.request_gc()
+
+            # request_gc before and after evaluate to free up memory
+            # @todo browsersteps etc
+            MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
+            self.xpath_data = await self.page.evaluate(XPATH_ELEMENT_JS, {
+                "visualselector_xpath_selectors": visualselector_xpath_selectors,
+                "max_height": MAX_TOTAL_HEIGHT
+            })
+            await self.page.request_gc()
+
+            self.instock_data = await self.page.evaluate(INSTOCK_DATA_JS)
+            await self.page.request_gc()
+
+            self.content = await self.page.content()
+            await self.page.request_gc()
+            logger.debug(f"Scrape xPath element data in browser done in {time.time() - now:.2f}s")
+
+
+            # Bug 3 in Playwright screenshot handling
+            # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
+            # JPEG is better here because the screenshots can be very very large
+
+            # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
+            # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
+            # acceptable screenshot quality here
+            try:
+                # The actual screenshot - this always base64 and needs decoding! horrible! huge CPU usage
+                self.screenshot = await capture_full_page_async(page=self.page, screenshot_format=self.screenshot_format)
+
+            except Exception as e:
+                # It's likely the screenshot was too long/big and something crashed
+                raise ScreenshotUnavailable(url=url, status_code=self.status_code)
+            finally:
+                # Request garbage collection one more time before closing
+                try:
+                    await self.page.request_gc()
+                except:
+                    pass
+                
+                # Clean up resources properly
+                try:
+                    await self.page.request_gc()
+                except:
+                    pass
+
+                try:
+                    await self.page.close()
+                except:
+                    pass
+                self.page = None
+
+                try:
+                    await context.close()
+                except:
+                    pass
+                context = None
+
+                try:
+                    await browser.close()
+                except:
+                    pass
+                browser = None
+
+
+# Plugin registration for built-in fetcher
+class PlaywrightFetcherPlugin:
+    """Plugin class that registers the Playwright fetcher as a built-in plugin."""
+
+    def register_content_fetcher(self):
+        """Register the Playwright fetcher"""
+        return ('html_webdriver', fetcher)
+
+
+# Create module-level instance for plugin registration
+playwright_plugin = PlaywrightFetcherPlugin()
+
+
+

changedetectionio/content_fetchers/playwright/CDP.py

@@ -1,41 +0,0 @@
-"""
-Playwright CDP fetcher — connects to a remote browser via Chrome DevTools Protocol.
-
-This is the original "playwright" fetcher, renamed to make the connection
-method explicit. The PLAYWRIGHT_DRIVER_URL env var (or per-profile
-browser_connection_url) points to a running Chrome/Chromium container that
-exposes the CDP WebSocket endpoint (e.g. ws://playwright-chrome:3000).
-"""
-import os
-
-from changedetectionio.pluggy_interface import hookimpl
-from changedetectionio.content_fetchers.playwright import PlaywrightBaseFetcher
-
-
-class fetcher(PlaywrightBaseFetcher):
-    fetcher_description = "Playwright Chrome (CDP/Remote)"
-
-    def __init__(self, proxy_override=None, custom_browser_connection_url=None, **kwargs):
-        super().__init__(proxy_override=proxy_override, custom_browser_connection_url=custom_browser_connection_url, **kwargs)
-
-        if custom_browser_connection_url:
-            self.browser_connection_is_custom = True
-            self.browser_connection_url = custom_browser_connection_url
-        else:
-            self.browser_connection_url = os.getenv("PLAYWRIGHT_DRIVER_URL", 'ws://playwright-chrome:3000').strip('"')
-
-        # CDP always talks to Chromium; respect PLAYWRIGHT_BROWSER_TYPE for exotic setups
-        self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
-
-    async def _connect_browser(self, p):
-        browser_type = getattr(p, self.browser_type)
-        return await browser_type.connect_over_cdp(self.browser_connection_url, timeout=60_000)
-
-
-class PlaywrightCDPPlugin:
-    @hookimpl
-    def register_content_fetcher(self):
-        return ('playwright_cdp', fetcher)
-
-
-cdp_plugin = PlaywrightCDPPlugin()

changedetectionio/content_fetchers/playwright/__init__.py

@@ -1,398 +0,0 @@
-"""
-Playwright-based content fetchers.
-
-Submodules:
-  cdp     — connect to a remote browser via Chrome DevTools Protocol (CDP/WebSocket)
-  chrome  — launch a local Chromium browser
-  firefox — launch a local Firefox browser
-  webkit  — launch a local WebKit (Safari-engine) browser
-"""
-
-import asyncio
-import gc
-import json
-import os
-import re
-from urllib.parse import urlparse
-
-from loguru import logger
-
-from changedetectionio.content_fetchers import (
-    SCREENSHOT_MAX_HEIGHT_DEFAULT,
-    SCREENSHOT_MAX_TOTAL_HEIGHT,
-    SCREENSHOT_SIZE_STITCH_THRESHOLD,
-    FAVICON_FETCHER_JS,
-    INSTOCK_DATA_JS,
-    XPATH_ELEMENT_JS,
-    visualselector_xpath_selectors,
-)
-from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
-from changedetectionio.content_fetchers.exceptions import (
-    BrowserStepsStepException,
-    EmptyReply,
-    Non200ErrorCodeReceived,
-    PageUnloadable,
-    ScreenshotUnavailable,
-)
-
-
-async def capture_full_page_async(page, screenshot_format='JPEG', watch_uuid=None, lock_viewport_elements=False):
-    import time
-
-    start = time.time()
-    watch_info = f"[{watch_uuid}] " if watch_uuid else ""
-
-    setup_start = time.time()
-    page_height = await page.evaluate("document.documentElement.scrollHeight")
-    page_width = await page.evaluate("document.documentElement.scrollWidth")
-    original_viewport = page.viewport_size
-    dimensions_time = time.time() - setup_start
-
-    logger.debug(f"{watch_info}Playwright viewport size {page.viewport_size} page height {page_height} page width {page_width} (got dimensions in {dimensions_time:.2f}s)")
-
-    step_size = SCREENSHOT_SIZE_STITCH_THRESHOLD
-    screenshot_chunks = []
-    y = 0
-    elements_locked = False
-
-    if lock_viewport_elements and page_height > page.viewport_size['height']:
-        lock_start = time.time()
-        lock_elements_js_path = os.path.join(os.path.dirname(__file__), '..', 'res', 'lock-elements-sizing.js')
-        with open(lock_elements_js_path, 'r') as f:
-            lock_elements_js = f.read()
-        await page.evaluate(lock_elements_js)
-        elements_locked = True
-        logger.debug(f"{watch_info}Viewport element locking enabled (took {time.time() - lock_start:.2f}s)")
-
-    if page_height > page.viewport_size['height']:
-        if page_height < step_size:
-            step_size = page_height
-        await page.set_viewport_size({'width': page.viewport_size['width'], 'height': step_size})
-
-    capture_start = time.time()
-    chunk_times = []
-    screenshot_type = screenshot_format.lower() if screenshot_format else 'jpeg'
-    screenshot_quality = 100 if screenshot_type == 'png' else int(os.getenv("SCREENSHOT_QUALITY", 72))
-
-    while y < min(page_height, SCREENSHOT_MAX_TOTAL_HEIGHT):
-        if y > 0:
-            await page.evaluate(f"window.scrollTo(0, {y})")
-
-        await _safe_request_gc(page)
-
-        screenshot_kwargs = {'type': screenshot_type, 'full_page': False}
-        if screenshot_type == 'jpeg':
-            screenshot_kwargs['quality'] = screenshot_quality
-
-        chunk_start = time.time()
-        screenshot_chunks.append(await page.screenshot(**screenshot_kwargs))
-        chunk_time = time.time() - chunk_start
-        chunk_times.append(chunk_time)
-        logger.debug(f"{watch_info}Chunk {len(screenshot_chunks)} captured in {chunk_time:.2f}s")
-        y += step_size
-
-    await page.set_viewport_size({'width': original_viewport['width'], 'height': original_viewport['height']})
-
-    if elements_locked:
-        unlock_elements_js_path = os.path.join(os.path.dirname(__file__), '..', 'res', 'unlock-elements-sizing.js')
-        with open(unlock_elements_js_path, 'r') as f:
-            unlock_elements_js = f.read()
-        await page.evaluate(unlock_elements_js)
-
-    capture_time = time.time() - capture_start
-
-    if len(screenshot_chunks) > 1:
-        stitch_start = time.time()
-        from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker_raw_bytes
-        import multiprocessing
-        import struct
-
-        ctx = multiprocessing.get_context('spawn')
-        parent_conn, child_conn = ctx.Pipe()
-        p = ctx.Process(target=stitch_images_worker_raw_bytes, args=(child_conn, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
-        p.start()
-
-        parent_conn.send_bytes(struct.pack('I', len(screenshot_chunks)))
-        for chunk in screenshot_chunks:
-            parent_conn.send_bytes(chunk)
-
-        screenshot = parent_conn.recv_bytes()
-        p.join()
-        parent_conn.close()
-        child_conn.close()
-        del p, parent_conn, child_conn
-
-        stitch_time = time.time() - stitch_start
-        total_time = time.time() - start
-        setup_time = total_time - capture_time - stitch_time
-        logger.debug(
-            f"{watch_info}Screenshot complete - Page height: {page_height}px | "
-            f"Setup: {setup_time:.2f}s, Capture: {capture_time:.2f}s, Stitching: {stitch_time:.2f}s, Total: {total_time:.2f}s")
-        return screenshot
-
-    total_time = time.time() - start
-    logger.debug(
-        f"{watch_info}Screenshot complete - Page height: {page_height}px | "
-        f"Setup: {total_time - capture_time:.2f}s, Single chunk: {capture_time:.2f}s, Total: {total_time:.2f}s")
-    return screenshot_chunks[0]
-
-
-async def _safe_request_gc(page):
-    """Request browser GC — Chromium-specific, silently ignored on Firefox/WebKit."""
-    try:
-        await page.request_gc()
-    except Exception:
-        pass
-
-
-class PlaywrightBaseFetcher(Fetcher):
-    """
-    Shared base for all Playwright fetchers.
-
-    Subclasses implement ``_connect_browser(playwright_instance)`` to return a
-    connected-or-launched browser object.  Everything else — context creation,
-    page interaction, screenshot capture, browser-steps execution — lives here.
-    """
-
-    playwright_proxy_settings_mappings = ['bypass', 'server', 'username', 'password']
-
-    proxy = None
-
-    # Capability flags
-    supports_browser_steps = True
-    supports_screenshots = True
-    supports_xpath_element_data = True
-
-    status_icon = {'filename': 'google-chrome-icon.png', 'alt': 'Using a Chrome browser', 'title': 'Using a Chrome browser'}
-
-    def __init__(self, proxy_override=None, custom_browser_connection_url=None, **kwargs):
-        super().__init__(**kwargs)
-
-        # Subclasses may use this (e.g. CDP); others ignore it
-        self._custom_browser_connection_url = custom_browser_connection_url
-
-        proxy_args = {}
-        for k in self.playwright_proxy_settings_mappings:
-            v = os.getenv('playwright_proxy_' + k, False)
-            if v:
-                proxy_args[k] = v.strip('"')
-
-        if proxy_args:
-            self.proxy = proxy_args
-
-        if proxy_override:
-            self.proxy = {'server': proxy_override}
-
-        if self.proxy:
-            parsed = urlparse(self.proxy.get('server', ''))
-            if parsed.username:
-                self.proxy['username'] = parsed.username
-                self.proxy['password'] = parsed.password
-
-    def disk_cleanup_after_fetch(self):
-        """Delete browser-step screenshots written during this fetch."""
-        self.delete_browser_steps_screenshots()
-
-    async def _connect_browser(self, playwright_instance):
-        """Return an open browser object.  Must be overridden by each subclass."""
-        raise NotImplementedError(f"{type(self).__name__} must implement _connect_browser()")
-
-    async def screenshot_step(self, step_n=''):
-        super().screenshot_step(step_n=step_n)
-        watch_uuid = getattr(self, 'watch_uuid', None)
-        screenshot = await capture_full_page_async(
-            page=self.page,
-            screenshot_format=self.screenshot_format,
-            watch_uuid=watch_uuid,
-            lock_viewport_elements=self.lock_viewport_elements,
-        )
-        await _safe_request_gc(self.page)
-
-        if self.browser_steps_screenshot_path is not None:
-            destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.jpeg'.format(step_n))
-            logger.debug(f"Saving step screenshot to {destination}")
-            with open(destination, 'wb') as f:
-                f.write(screenshot)
-            del screenshot
-            gc.collect()
-
-    async def save_step_html(self, step_n):
-        super().save_step_html(step_n=step_n)
-        content = await self.page.content()
-        await _safe_request_gc(self.page)
-
-        destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.html'.format(step_n))
-        logger.debug(f"Saving step HTML to {destination}")
-        with open(destination, 'w', encoding='utf-8') as f:
-            f.write(content)
-        del content
-        gc.collect()
-
-    async def run(self,
-                  fetch_favicon=True,
-                  current_include_filters=None,
-                  empty_pages_are_a_change=False,
-                  ignore_status_codes=False,
-                  is_binary=False,
-                  request_body=None,
-                  request_headers=None,
-                  request_method=None,
-                  screenshot_format=None,
-                  timeout=None,
-                  url=None,
-                  watch_uuid=None,
-                  ):
-        from playwright.async_api import async_playwright
-        import playwright._impl._errors
-        import time
-
-        self.delete_browser_steps_screenshots()
-        self.watch_uuid = watch_uuid
-        response = None
-
-        async with async_playwright() as p:
-            browser = await self._connect_browser(p)
-
-            ua = manage_user_agent(headers=request_headers) or self.profile_user_agent or None
-
-            context_kwargs = dict(
-                accept_downloads=False,
-                bypass_csp=True,
-                extra_http_headers=request_headers,
-                ignore_https_errors=self.ignore_https_errors,
-                proxy=self.proxy,
-                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
-                user_agent=ua,
-                viewport={'width': self.viewport_width, 'height': self.viewport_height},
-            )
-            if self.locale:
-                context_kwargs['locale'] = self.locale
-
-            context = await browser.new_context(**context_kwargs)
-
-            if self.block_images:
-                await context.route(
-                    re.compile(r'\.(png|jpe?g|gif|svg|ico|webp|avif|bmp)(\?.*)?$', re.IGNORECASE),
-                    lambda route: route.abort()
-                )
-            if self.block_fonts:
-                await context.route(
-                    re.compile(r'\.(woff2?|ttf|otf|eot)(\?.*)?$', re.IGNORECASE),
-                    lambda route: route.abort()
-                )
-
-            self.page = await context.new_page()
-            self.page.on("console", lambda msg: logger.debug(f"Playwright console: {url} {msg.type}: {msg.text}"))
-
-            from changedetectionio.browser_steps.browser_steps import steppable_browser_interface
-            browsersteps_interface = steppable_browser_interface(start_url=url)
-            browsersteps_interface.page = self.page
-
-            response = await browsersteps_interface.action_goto_url(value=url)
-
-            if response is None:
-                await context.close()
-                await browser.close()
-                raise EmptyReply(url=url, status_code=None)
-
-            try:
-                self.headers = await response.all_headers()
-            except TypeError:
-                self.headers = response.all_headers()
-
-            try:
-                if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
-                    await browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
-            except playwright._impl._errors.TimeoutError:
-                await context.close()
-                await browser.close()
-                pass
-            except Exception as e:
-                await context.close()
-                await browser.close()
-                raise PageUnloadable(url=url, status_code=None, message=str(e))
-
-            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-            await self.page.wait_for_timeout(extra_wait * 1000)
-
-            try:
-                self.status_code = response.status
-            except Exception as e:
-                await context.close()
-                await browser.close()
-                raise PageUnloadable(url=url, status_code=None, message=str(e))
-
-            if fetch_favicon:
-                try:
-                    self.favicon_blob = await self.page.evaluate(FAVICON_FETCHER_JS)
-                    await _safe_request_gc(self.page)
-                except Exception as e:
-                    logger.error(f"Error fetching favicon: {e}")
-
-            if self.status_code != 200 and not ignore_status_codes:
-                screenshot = await capture_full_page_async(self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
-                raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
-
-            if not empty_pages_are_a_change and len((await self.page.content()).strip()) == 0:
-                await context.close()
-                await browser.close()
-                raise EmptyReply(url=url, status_code=response.status)
-
-            try:
-                if self.browser_steps:
-                    try:
-                        await self.iterate_browser_steps(start_url=url)
-                    except BrowserStepsStepException:
-                        raise
-                    await self.page.wait_for_timeout(extra_wait * 1000)
-
-                now = time.time()
-                if current_include_filters is not None:
-                    await self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
-                else:
-                    await self.page.evaluate("var include_filters=''")
-                await _safe_request_gc(self.page)
-
-                MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
-                self.xpath_data = await self.page.evaluate(XPATH_ELEMENT_JS, {
-                    "visualselector_xpath_selectors": visualselector_xpath_selectors,
-                    "max_height": MAX_TOTAL_HEIGHT
-                })
-                await _safe_request_gc(self.page)
-
-                self.instock_data = await self.page.evaluate(INSTOCK_DATA_JS)
-                await _safe_request_gc(self.page)
-
-                self.content = await self.page.content()
-                await _safe_request_gc(self.page)
-                logger.debug(f"Scrape xPath element data done in {time.time() - now:.2f}s")
-
-                self.screenshot = await capture_full_page_async(
-                    page=self.page,
-                    screenshot_format=self.screenshot_format,
-                    watch_uuid=watch_uuid,
-                    lock_viewport_elements=self.lock_viewport_elements,
-                )
-                await _safe_request_gc(self.page)
-                gc.collect()
-
-            except ScreenshotUnavailable:
-                raise ScreenshotUnavailable(url=url, status_code=self.status_code)
-
-            finally:
-                for obj, name, close_coro in [
-                    (self.page if hasattr(self, 'page') and self.page else None, 'page', lambda: self.page.close() if self.page else asyncio.sleep(0)),
-                    (context, 'context', lambda: context.close() if context else asyncio.sleep(0)),
-                    (browser, 'browser', lambda: browser.close() if browser else asyncio.sleep(0)),
-                ]:
-                    try:
-                        await asyncio.wait_for(close_coro(), timeout=5.0)
-                    except asyncio.TimeoutError:
-                        logger.warning(f"Timed out closing {name} for {url}")
-                    except Exception as e:
-                        logger.warning(f"Error closing {name} for {url}: {e}")
-
-                self.page = None
-                context = None
-                browser = None
-                gc.collect()

changedetectionio/content_fetchers/playwright/chrome.py

@@ -1,27 +0,0 @@
-"""
-Playwright Chrome fetcher — launches a local Chromium browser directly.
-
-No external browser container is required.  Playwright must be installed
-with Chromium browsers: ``playwright install chromium``.
-"""
-from changedetectionio.pluggy_interface import hookimpl
-from changedetectionio.content_fetchers.playwright import PlaywrightBaseFetcher
-
-
-class fetcher(PlaywrightBaseFetcher):
-    fetcher_description = "Playwright Chrome (local)"
-
-    async def _connect_browser(self, p):
-        launch_kwargs = {'headless': True}
-        if self.proxy:
-            launch_kwargs['proxy'] = self.proxy
-        return await p.chromium.launch(**launch_kwargs)
-
-
-class PlaywrightChromePlugin:
-    @hookimpl
-    def register_content_fetcher(self):
-        return ('playwright_chrome', fetcher)
-
-
-chrome_plugin = PlaywrightChromePlugin()

changedetectionio/content_fetchers/playwright/firefox.py

@@ -1,33 +0,0 @@
-"""
-Playwright Firefox fetcher — launches a local Firefox browser directly.
-
-No external browser container is required.  Playwright must be installed
-with Firefox browsers: ``playwright install firefox``.
-
-Note: ``page.request_gc()`` is Chromium-specific and is silently skipped
-on Firefox — this is handled transparently by ``_safe_request_gc()`` in
-the base package.
-"""
-from changedetectionio.pluggy_interface import hookimpl
-from changedetectionio.content_fetchers.playwright import PlaywrightBaseFetcher
-
-
-class fetcher(PlaywrightBaseFetcher):
-    fetcher_description = "Playwright Firefox (local)"
-
-    status_icon = {'filename': 'firefox-icon.svg', 'alt': 'Using Firefox', 'title': 'Using Firefox'}
-
-    async def _connect_browser(self, p):
-        launch_kwargs = {'headless': True}
-        if self.proxy:
-            launch_kwargs['proxy'] = self.proxy
-        return await p.firefox.launch(**launch_kwargs)
-
-
-class PlaywrightFirefoxPlugin:
-    @hookimpl
-    def register_content_fetcher(self):
-        return ('playwright_firefox', fetcher)
-
-
-firefox_plugin = PlaywrightFirefoxPlugin()

changedetectionio/content_fetchers/playwright/webkit.py

@@ -1,30 +0,0 @@
-"""
-Playwright WebKit fetcher — launches a local WebKit (Safari-engine) browser.
-
-No external browser container is required.  Playwright must be installed
-with WebKit browsers: ``playwright install webkit``.
-
-Note: ``page.request_gc()`` is Chromium-specific and is silently skipped
-on WebKit — handled transparently by ``_safe_request_gc()`` in the base package.
-"""
-from changedetectionio.pluggy_interface import hookimpl
-from changedetectionio.content_fetchers.playwright import PlaywrightBaseFetcher
-
-
-class fetcher(PlaywrightBaseFetcher):
-    fetcher_description = "Playwright WebKit/Safari (local)"
-
-    async def _connect_browser(self, p):
-        launch_kwargs = {'headless': True}
-        if self.proxy:
-            launch_kwargs['proxy'] = self.proxy
-        return await p.webkit.launch(**launch_kwargs)
-
-
-class PlaywrightWebKitPlugin:
-    @hookimpl
-    def register_content_fetcher(self):
-        return ('playwright_webkit', fetcher)
-
-
-webkit_plugin = PlaywrightWebKitPlugin()

changedetectionio/content_fetchers/puppeteer.py

@@ -1,5 +1,4 @@
 import asyncio
-import gc
 import json
 import os
 import websockets.exceptions
@@ -7,7 +6,6 @@ from urllib.parse import urlparse
 
 from loguru import logger
 
-from changedetectionio.pluggy_interface import hookimpl
 from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT, visualselector_xpath_selectors, \
     SCREENSHOT_SIZE_STITCH_THRESHOLD, SCREENSHOT_DEFAULT_QUALITY, XPATH_ELEMENT_JS, INSTOCK_DATA_JS, \
     SCREENSHOT_MAX_TOTAL_HEIGHT, FAVICON_FETCHER_JS
@@ -22,20 +20,18 @@ from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200
 # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
 # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
 # acceptable screenshot quality here
-async def capture_full_page(page, screenshot_format='JPEG', watch_uuid=None, lock_viewport_elements=False):
+async def capture_full_page(page, screenshot_format='JPEG'):
     import os
     import time
+    import multiprocessing
 
     start = time.time()
-    watch_info = f"[{watch_uuid}] " if watch_uuid else ""
 
-    setup_start = time.time()
     page_height = await page.evaluate("document.documentElement.scrollHeight")
     page_width = await page.evaluate("document.documentElement.scrollWidth")
     original_viewport = page.viewport
-    dimensions_time = time.time() - setup_start
 
-    logger.debug(f"{watch_info}Puppeteer viewport size {page.viewport} page height {page_height} page width {page_width} (got dimensions in {dimensions_time:.2f}s)")
+    logger.debug(f"Puppeteer viewport size {page.viewport} page height {page_height} page width {page_width}")
 
     # Bug 3 in Playwright screenshot handling
     # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
@@ -54,41 +50,26 @@ async def capture_full_page(page, screenshot_format='JPEG', watch_uuid=None, loc
     screenshot_chunks = []
     y = 0
     elements_locked = False
-
-    # Only lock viewport elements if explicitly enabled (for image_ssim_diff processor)
-    # This prevents headers/ads from resizing when viewport changes
-    if lock_viewport_elements and page_height > page.viewport['height']:
-        lock_start = time.time()
+    if page_height > page.viewport['height']:
+        # Lock all element dimensions BEFORE screenshot to prevent CSS media queries from resizing
+        # capture_full_page() changes viewport height which triggers @media (min-height) rules
         lock_elements_js_path = os.path.join(os.path.dirname(__file__), 'res', 'lock-elements-sizing.js')
-        file_read_start = time.time()
         with open(lock_elements_js_path, 'r') as f:
             lock_elements_js = f.read()
-        file_read_time = time.time() - file_read_start
-
-        evaluate_start = time.time()
         await page.evaluate(lock_elements_js)
-        evaluate_time = time.time() - evaluate_start
-
         elements_locked = True
-        lock_time = time.time() - lock_start
-        logger.debug(f"{watch_info}Viewport element locking enabled - File read: {file_read_time:.3f}s, Browser evaluate: {evaluate_time:.2f}s, Total: {lock_time:.2f}s")
+        logger.debug("Element dimensions locked before screenshot capture")
 
-    if page_height > page.viewport['height']:
         if page_height < step_size:
             step_size = page_height # Incase page is bigger than default viewport but smaller than proposed step size
-        viewport_start = time.time()
         await page.setViewport({'width': page.viewport['width'], 'height': step_size})
-        viewport_time = time.time() - viewport_start
-        logger.debug(f"{watch_info}Viewport changed to {page.viewport['width']}x{step_size} (took {viewport_time:.2f}s)")
 
-    capture_start = time.time()
-    chunk_times = []
     while y < min(page_height, SCREENSHOT_MAX_TOTAL_HEIGHT):
         # better than scrollTo incase they override it in the page
         await page.evaluate(
             """(y) => {
-                const el = document.scrollingElement;
-                if (el) el.scrollTop = y;
+                document.documentElement.scrollTop = y;
+                document.body.scrollTop = y;
             }""",
             y
         )
@@ -101,11 +82,7 @@ async def capture_full_page(page, screenshot_format='JPEG', watch_uuid=None, loc
         if screenshot_type == 'jpeg':
             screenshot_kwargs['quality'] = screenshot_quality
 
-        chunk_start = time.time()
         screenshot_chunks.append(await page.screenshot(**screenshot_kwargs))
-        chunk_time = time.time() - chunk_start
-        chunk_times.append(chunk_time)
-        logger.debug(f"{watch_info}Chunk {len(screenshot_chunks)} captured in {chunk_time:.2f}s")
         y += step_size
 
     await page.setViewport({'width': original_viewport['width'], 'height': original_viewport['height']})
@@ -116,58 +93,35 @@ async def capture_full_page(page, screenshot_format='JPEG', watch_uuid=None, loc
         with open(unlock_elements_js_path, 'r') as f:
             unlock_elements_js = f.read()
         await page.evaluate(unlock_elements_js)
-        logger.debug(f"{watch_info}Element dimensions unlocked after screenshot capture")
-
-    capture_time = time.time() - capture_start
-    total_capture_time = sum(chunk_times)
-    logger.debug(f"{watch_info}All {len(screenshot_chunks)} chunks captured in {capture_time:.2f}s (total chunk time: {total_capture_time:.2f}s)")
+        logger.debug("Element dimensions unlocked after screenshot capture")
 
     if len(screenshot_chunks) > 1:
-        stitch_start = time.time()
-        logger.debug(f"{watch_info}Starting stitching of {len(screenshot_chunks)} chunks")
-
-        # Always use spawn subprocess for ANY stitching (2+ chunks)
-        # PIL allocates at C level and Python GC never releases it - subprocess exit forces OS to reclaim
-        # Trade-off: 35MB resource_tracker vs 500MB+ PIL leak in main process
-        from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker_raw_bytes
-        import multiprocessing
-        import struct
-
+        # Always use spawn for thread safety - consistent behavior in tests and production
+        from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker
+        logger.debug(f"Screenshot stitching {len(screenshot_chunks)} chunks together")
         ctx = multiprocessing.get_context('spawn')
         parent_conn, child_conn = ctx.Pipe()
-        p = ctx.Process(target=stitch_images_worker_raw_bytes, args=(child_conn, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
+        p = ctx.Process(target=stitch_images_worker, args=(child_conn, screenshot_chunks, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
         p.start()
-
-        # Send via raw bytes (no pickle)
-        parent_conn.send_bytes(struct.pack('I', len(screenshot_chunks)))
-        for chunk in screenshot_chunks:
-            parent_conn.send_bytes(chunk)
-
         screenshot = parent_conn.recv_bytes()
         p.join()
-
-        parent_conn.close()
-        child_conn.close()
-        del p, parent_conn, child_conn
-
-        stitch_time = time.time() - stitch_start
-        total_time = time.time() - start
-        setup_time = total_time - capture_time - stitch_time
         logger.debug(
-            f"{watch_info}Screenshot complete - Page height: {page_height}px, Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT}px | "
-            f"Setup: {setup_time:.2f}s, Capture: {capture_time:.2f}s, Stitching: {stitch_time:.2f}s, Total: {total_time:.2f}s")
+            f"Screenshot (chunked/stitched) - Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
+
+        screenshot_chunks = None
         return screenshot
 
-    total_time = time.time() - start
-    setup_time = total_time - capture_time
     logger.debug(
-        f"{watch_info}Screenshot complete - Page height: {page_height}px, Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT}px | "
-        f"Setup: {setup_time:.2f}s, Single chunk: {capture_time:.2f}s, Total: {total_time:.2f}s")
+        f"Screenshot Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
     return screenshot_chunks[0]
 
 
 class fetcher(Fetcher):
-    fetcher_description = "Puppeteer Chromium"
+    fetcher_description = "Puppeteer/direct {}/Javascript".format(
+        os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
+    )
+    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
+        fetcher_description += " via '{}'".format(os.getenv("PLAYWRIGHT_DRIVER_URL"))
 
     browser = None
     browser_type = ''
@@ -179,10 +133,14 @@ class fetcher(Fetcher):
     supports_screenshots = True
     supports_xpath_element_data = True
 
-    status_icon = {'filename': 'google-chrome-icon.png', 'alt': 'Using a Chrome browser', 'title': 'Using a Chrome browser'}
-
-    def disk_cleanup_after_fetch(self):
-        self.delete_browser_steps_screenshots()
+    @classmethod
+    def get_status_icon_data(cls):
+        """Return Chrome browser icon data for Puppeteer fetcher."""
+        return {
+            'filename': 'google-chrome-icon.png',
+            'alt': 'Using a Chrome browser',
+            'title': 'Using a Chrome browser'
+        }
 
     def __init__(self, proxy_override=None, custom_browser_connection_url=None, **kwargs):
         super().__init__(**kwargs)
@@ -215,36 +173,19 @@ class fetcher(Fetcher):
                 self.browser_connection_url += f"{r}--proxy-server={proxy_url}"
 
     async def quit(self, watch=None):
-        watch_uuid = watch.get('uuid') if watch else 'unknown'
-
-        # Close page
         try:
-            if hasattr(self, 'page') and self.page:
-                await asyncio.wait_for(self.page.close(), timeout=5.0)
-                logger.debug(f"[{watch_uuid}] Page closed successfully")
-        except asyncio.TimeoutError:
-            logger.warning(f"[{watch_uuid}] Timed out closing page (5s)")
+            await self.page.close()
+            del self.page
         except Exception as e:
-            logger.warning(f"[{watch_uuid}] Error closing page: {e}")
-        finally:
-            self.page = None
+            pass
 
-        # Close browser connection
         try:
-            if hasattr(self, 'browser') and self.browser:
-                await asyncio.wait_for(self.browser.close(), timeout=5.0)
-                logger.debug(f"[{watch_uuid}] Browser closed successfully")
-        except asyncio.TimeoutError:
-            logger.warning(f"[{watch_uuid}] Timed out closing browser (5s)")
+            await self.browser.close()
+            del self.browser
         except Exception as e:
-            logger.warning(f"[{watch_uuid}] Error closing browser: {e}")
-        finally:
-            self.browser = None
+            pass
 
-        logger.info(f"[{watch_uuid}] Cleanup puppeteer complete")
-
-        # Force garbage collection to release resources
-        gc.collect()
+        logger.info("Cleanup puppeteer complete.")
 
     async def fetch_page(self,
                          current_include_filters,
@@ -263,7 +204,7 @@ class fetcher(Fetcher):
         import re
         self.delete_browser_steps_screenshots()
 
-        n = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 12)) + self.render_extract_delay
+        n = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
         extra_wait = min(n, 15)
 
         logger.debug(f"Extra wait set to {extra_wait}s, requested was {n}s.")
@@ -274,11 +215,9 @@ class fetcher(Fetcher):
         # Connect directly using the specified browser_ws_endpoint
         # @todo timeout
         try:
-            logger.debug(f"[{watch_uuid}] Connecting to browser at {self.browser_connection_url}")
             self.browser = await pyppeteer_instance.connect(browserWSEndpoint=self.browser_connection_url,
                                                             ignoreHTTPSErrors=True
                                                             )
-            logger.debug(f"[{watch_uuid}] Browser connected successfully")
         except websockets.exceptions.InvalidStatusCode as e:
             raise BrowserConnectError(msg=f"Error while trying to connect the browser, Code {e.status_code} (check your access, whitelist IP, password etc)")
         except websockets.exceptions.InvalidURI:
@@ -287,20 +226,7 @@ class fetcher(Fetcher):
             raise BrowserConnectError(msg=f"Error connecting to the browser - Exception '{str(e)}'")
 
         # more reliable is to just request a new page
-        try:
-            logger.debug(f"[{watch_uuid}] Creating new page")
-            self.page = await self.browser.newPage()
-            logger.debug(f"[{watch_uuid}] Page created successfully")
-        except Exception as e:
-            logger.error(f"[{watch_uuid}] Failed to create new page: {e}")
-            # Browser is connected but page creation failed - must cleanup browser
-            try:
-                await asyncio.wait_for(self.browser.close(), timeout=3.0)
-            except Exception as cleanup_error:
-                logger.error(f"[{watch_uuid}] Failed to cleanup browser after page creation failure: {cleanup_error}")
-            finally:
-                self.browser = None
-            raise
+        self.page = await self.browser.newPage()
         
         # Add console handler to capture console.log from favicon fetcher
         #self.page.on('console', lambda msg: logger.debug(f"Browser console [{msg.type}]: {msg.text}"))
@@ -362,33 +288,28 @@ class fetcher(Fetcher):
         # Enable Network domain to detect when first bytes arrive
         await self.page._client.send('Network.enable')
 
-        # Now set up the frame navigation handlers
-        async def handle_frame_navigation(event=None):
-            # Wait n seconds after the frameStartedLoading, not from any frameStartedLoading/frameStartedNavigating
-            logger.debug(f"Frame navigated: {event}")
-            w = extra_wait - 2 if extra_wait > 4 else 2
-            logger.debug(f"Waiting {w} seconds before calling Page.stopLoading...")
-            await asyncio.sleep(w)
-
-            # Check if page still exists (might have been closed due to error during sleep)
-            if not self.page or not hasattr(self.page, '_client'):
-                logger.debug("Page already closed, skipping stopLoading")
-                return
-
-            logger.debug("Issuing stopLoading command...")
-            await self.page._client.send('Page.stopLoading')
-            logger.debug("stopLoading command sent!")
-
         async def setup_frame_handlers_on_first_response(event):
             # Only trigger for the main document response
             if event.get('type') == 'Document':
                 logger.debug("First response received, setting up frame handlers for forced page stop load.")
+
+                # De-register this listener - we only need it once
+                self.page._client.remove_listener('Network.responseReceived', setup_frame_handlers_on_first_response)
+
+                # Now set up the frame navigation handlers
+                async def handle_frame_navigation(event):
+                    # Wait n seconds after the frameStartedLoading, not from any frameStartedLoading/frameStartedNavigating
+                    logger.debug(f"Frame navigated: {event}")
+                    w = extra_wait - 2 if extra_wait > 4 else 2
+                    logger.debug(f"Waiting {w} seconds before calling Page.stopLoading...")
+                    await asyncio.sleep(w)
+                    logger.debug("Issuing stopLoading command...")
+                    await self.page._client.send('Page.stopLoading')
+                    logger.debug("stopLoading command sent!")
+
                 self.page._client.on('Page.frameStartedNavigating', lambda e: asyncio.create_task(handle_frame_navigation(e)))
                 self.page._client.on('Page.frameStartedLoading', lambda e: asyncio.create_task(handle_frame_navigation(e)))
                 self.page._client.on('Page.frameStoppedLoading', lambda e: logger.debug(f"Frame stopped loading: {e}"))
-                logger.debug("First response received, setting up frame handlers for forced page stop load DONE SETUP")
-                # De-register this listener - we only need it once
-                self.page._client.remove_listener('Network.responseReceived', setup_frame_handlers_on_first_response)
 
         # Listen for first response to trigger frame handler setup
         self.page._client.on('Network.responseReceived', setup_frame_handlers_on_first_response)
@@ -397,13 +318,8 @@ class fetcher(Fetcher):
         attempt=0
         while not response:
             logger.debug(f"Attempting page fetch {url} attempt {attempt}")
-            asyncio.create_task(handle_frame_navigation())
             response = await self.page.goto(url, timeout=0)
             await asyncio.sleep(1 + extra_wait)
-            # Check if page still exists before sending command
-            if self.page and hasattr(self.page, '_client'):
-                await self.page._client.send('Page.stopLoading')
-
             if response:
                 break
             if not response:
@@ -439,7 +355,7 @@ class fetcher(Fetcher):
                 logger.error(f"Error fetching FavIcon info {str(e)}, continuing.")
 
         if self.status_code != 200 and not ignore_status_codes:
-            screenshot = await capture_full_page(page=self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
+            screenshot = await capture_full_page(page=self.page, screenshot_format=self.screenshot_format)
 
             raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
 
@@ -451,7 +367,7 @@ class fetcher(Fetcher):
 
         # Run Browser Steps here
         # @todo not yet supported, we switch to playwright in this case
-        #            if self.browser_steps:
+        #            if self.browser_steps_get_valid_steps():
         #                self.iterate_browser_steps()
 
 
@@ -469,11 +385,7 @@ class fetcher(Fetcher):
 
         # Now take screenshot (scrolling may trigger layout changes, but measurements are already captured)
         logger.debug(f"Screenshot format {self.screenshot_format}")
-        self.screenshot = await capture_full_page(page=self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
-
-        # Force garbage collection - pyppeteer base64 decode creates temporary buffers
-        import gc
-        gc.collect()
+        self.screenshot = await capture_full_page(page=self.page, screenshot_format=self.screenshot_format)
         self.xpath_data = await self.page.evaluate(XPATH_ELEMENT_JS, {
             "visualselector_xpath_selectors": visualselector_xpath_selectors,
             "max_height": MAX_TOTAL_HEIGHT
@@ -527,24 +439,15 @@ class fetcher(Fetcher):
             )
         except asyncio.TimeoutError:
             raise (BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))
-        finally:
-            # Internal cleanup on any exception/timeout - call quit() immediately
-            # This prevents connection leaks during exception bursts
-            # Worker.py's quit() call becomes a redundant safety net (idempotent)
-            try:
-                await self.quit(watch={'uuid': watch_uuid} if watch_uuid else None)
-            except Exception as cleanup_error:
-                logger.error(f"[{watch_uuid}] Error during internal quit() cleanup: {cleanup_error}")
 
 
 # Plugin registration for built-in fetcher
 class PuppeteerFetcherPlugin:
     """Plugin class that registers the Puppeteer fetcher as a built-in plugin."""
 
-    @hookimpl
     def register_content_fetcher(self):
         """Register the Puppeteer fetcher"""
-        return ('puppeteer', fetcher)
+        return ('html_webdriver', fetcher)
 
 
 # Create module-level instance for plugin registration

changedetectionio/content_fetchers/requests.py

@@ -1,15 +1,12 @@
 from loguru import logger
-from urllib.parse import urljoin, urlparse
 import hashlib
 import os
 import re
 import asyncio
-
+from functools import partial
 from changedetectionio import strtobool
 from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
 from changedetectionio.content_fetchers.base import Fetcher
-from changedetectionio.pluggy_interface import hookimpl
-from changedetectionio.validate_url import is_private_hostname
 
 
 # "html_requests" is listed as the default fetcher in store.py!
@@ -39,7 +36,7 @@ class fetcher(Fetcher):
         import requests
         from requests.exceptions import ProxyError, ConnectionError, RequestException
 
-        if self.browser_steps:
+        if self.browser_steps_get_valid_steps():
             raise BrowserStepsInUnsupportedFetcher(url=url)
 
         proxies = {}
@@ -58,72 +55,18 @@ class fetcher(Fetcher):
 
         session = requests.Session()
 
-        # Configure retry adapter for low-level network errors only
-        # Retries connection timeouts, read timeouts, connection resets - not HTTP status codes
-        # Especially helpful in parallel test execution when servers are slow/overloaded
-        # Configurable via REQUESTS_RETRY_MAX_COUNT (default: 3 attempts)
-        from requests.adapters import HTTPAdapter
-        from urllib3.util.retry import Retry
-
-        max_retries = int(os.getenv("REQUESTS_RETRY_MAX_COUNT", "6"))
-        retry_strategy = Retry(
-            total=max_retries,
-            connect=max_retries,  # Retry connection timeouts
-            read=max_retries,     # Retry read timeouts
-            status=0,             # Don't retry on HTTP status codes
-            backoff_factor=0.5,   # Wait 0.3s, 0.6s, 1.2s between retries
-            allowed_methods=["HEAD", "GET", "OPTIONS", "POST"],
-            raise_on_status=False
-        )
-        adapter = HTTPAdapter(max_retries=retry_strategy)
-        session.mount("http://", adapter)
-        session.mount("https://", adapter)
 
         if strtobool(os.getenv('ALLOW_FILE_URI', 'false')) and url.startswith('file://'):
             from requests_file import FileAdapter
             session.mount('file://', FileAdapter())
-
-        allow_iana_restricted = strtobool(os.getenv('ALLOW_IANA_RESTRICTED_ADDRESSES', 'false'))
-
         try:
-            # Fresh DNS check at fetch time — catches DNS rebinding regardless of add-time cache.
-            if not allow_iana_restricted:
-                parsed_initial = urlparse(url)
-                if parsed_initial.hostname and is_private_hostname(parsed_initial.hostname):
-                    raise Exception(f"Fetch blocked: '{url}' resolves to a private/reserved IP address. "
-                                    f"Set ALLOW_IANA_RESTRICTED_ADDRESSES=true to allow.")
-
             r = session.request(method=request_method,
                                 data=request_body.encode('utf-8') if type(request_body) is str else request_body,
                                 url=url,
                                 headers=request_headers,
                                 timeout=timeout,
                                 proxies=proxies,
-                                verify=False,
-                                allow_redirects=False)
-
-            # Manually follow redirects so each hop's resolved IP can be validated,
-            # preventing SSRF via an open redirect on a public host.
-            current_url = url
-            for _ in range(10):
-                if not r.is_redirect:
-                    break
-                location = r.headers.get('Location', '')
-                redirect_url = urljoin(current_url, location)
-                if not allow_iana_restricted:
-                    parsed_redirect = urlparse(redirect_url)
-                    if parsed_redirect.hostname and is_private_hostname(parsed_redirect.hostname):
-                        raise Exception(f"Redirect blocked: '{redirect_url}' resolves to a private/reserved IP address.")
-                current_url = redirect_url
-                r = session.request('GET', redirect_url,
-                                    headers=request_headers,
-                                    timeout=timeout,
-                                    proxies=proxies,
-                                    verify=False,
-                                    allow_redirects=False)
-            else:
-                raise Exception("Too many redirects")
-
+                                verify=False)
         except Exception as e:
             msg = str(e)
             if proxies and 'SOCKSHTTPSConnectionPool' in msg:
@@ -149,32 +92,10 @@ class fetcher(Fetcher):
                         # Default to UTF-8 for XML if no encoding found
                         r.encoding = 'utf-8'
                 else:
-                    # No charset in HTTP header - sniff encoding in priority order matching browsers
-                    # (WHATWG encoding sniffing algorithm):
-                    # 1. BOM - highest confidence, check before anything else
-                    # 2. <meta charset> in first 2kb
-                    # 3. chardet statistical detection - last resort
-                    # See: https://github.com/dgtlmoon/changedetection.io/issues/3952
-                    boms = [
-                        (b'\xef\xbb\xbf', 'utf-8-sig'),
-                        (b'\xff\xfe', 'utf-16-le'),
-                        (b'\xfe\xff', 'utf-16-be'),
-                    ]
-                    bom_encoding = next((enc for bom, enc in boms if r.content.startswith(bom)), None)
-                    if bom_encoding:
-                        logger.info(f"URL: {url} Using encoding '{bom_encoding}' detected from BOM")
-                        r.encoding = bom_encoding
-                    else:
-                        meta_charset_match = re.search(rb'<meta[^>]+charset\s*=\s*["\']?\s*([^"\'\s;>]+)', r.content[:2000], re.IGNORECASE)
-                        if meta_charset_match:
-                            encoding = meta_charset_match.group(1).decode('ascii', errors='ignore')
-                            logger.info(f"URL: {url} No content-type encoding in HTTP headers - Using encoding '{encoding}' from HTML meta charset tag")
-                            r.encoding = encoding
-                        else:
-                            encoding = chardet.detect(r.content)['encoding']
-                            logger.warning(f"URL: {url} No charset in headers or meta tag, guessed encoding as '{encoding}' via chardet")
-                            if encoding:
-                                r.encoding = encoding
+                    # For other content types, use chardet
+                    encoding = chardet.detect(r.content)['encoding']
+                    if encoding:
+                        r.encoding = encoding
 
         self.headers = r.headers
 
@@ -221,11 +142,10 @@ class fetcher(Fetcher):
                   watch_uuid=None,
                   ):
         """Async wrapper that runs the synchronous requests code in a thread pool"""
-
+        
         loop = asyncio.get_event_loop()
-
+        
         # Run the synchronous _run_sync in a thread pool to avoid blocking the event loop
-        # Retry logic is handled by requests' HTTPAdapter (see _run_sync for configuration)
         await loop.run_in_executor(
             None,  # Use default ThreadPoolExecutor
             lambda: self._run_sync(
@@ -243,6 +163,7 @@ class fetcher(Fetcher):
         )
 
     async def quit(self, watch=None):
+
         # In case they switched to `requests` fetcher from something else
         # Then the screenshot could be old, in any case, it's not used here.
         # REMOVE_REQUESTS_OLD_SCREENSHOTS - Mainly used for testing
@@ -259,10 +180,9 @@ class fetcher(Fetcher):
 class RequestsFetcherPlugin:
     """Plugin class that registers the requests fetcher as a built-in plugin."""
 
-    @hookimpl
     def register_content_fetcher(self):
         """Register the requests fetcher"""
-        return ('requests', fetcher)
+        return ('html_requests', fetcher)
 
 
 # Create module-level instance for plugin registration

changedetectionio/content_fetchers/res/lock-elements-sizing.js

@@ -1,5 +1,5 @@
 /**
- * Lock Element Dimensions for Screenshot Capture (First Viewport Only)
+ * Lock Element Dimensions for Screenshot Capture
  *
  * THE PROBLEM:
  * When taking full-page screenshots of tall pages, Chrome/Puppeteer/Playwright need to:
@@ -10,31 +10,40 @@
  * However, changing the viewport height triggers CSS media queries like:
  *   @media (min-height: 860px) { .ad { height: 250px; } }
  *
- * This causes elements (especially ads/headers) to resize during screenshot capture.
+ * This causes elements (especially ads) to resize during screenshot capture, creating a mismatch:
+ * - Screenshot shows element at NEW size (after media query triggered)
+ * - xpath element coordinates measured at OLD size (before viewport change)
+ * - Visual selector overlays don't align with screenshot
+ *
+ * EXAMPLE BUG:
+ * - Initial viewport: 1280x800, ad height: 138px, article position: 279px ✓
+ * - Viewport changes to 1280x3809 for screenshot
+ * - Media query triggers: ad expands to 250px
+ * - All content below shifts down by 112px (250-138)
+ * - Article now at position: 391px (279+112)
+ * - But xpath data says 279px → 112px mismatch! ✗
  *
  * THE SOLUTION:
- * Lock element dimensions in the FIRST VIEWPORT ONLY with !important inline styles.
- * This prevents headers, navigation, and top ads from resizing when viewport changes.
- * We only lock the visible portion because:
- * - Most layout shifts happen in headers/navbars/top ads
- * - Locking only visible elements is 100x+ faster (100-200 elements vs 10,000+)
- * - Below-fold content shifts don't affect visual comparison accuracy
+ * Before changing viewport, lock ALL element dimensions with !important inline styles.
+ * Inline styles with !important override media query CSS, preventing layout changes.
  *
  * WHAT THIS SCRIPT DOES:
- * 1. Gets current viewport height
- * 2. Finds elements within first viewport (top of page to bottom of screen)
- * 3. Locks their dimensions with !important inline styles
+ * 1. Iterates through every element on the page
+ * 2. Captures current computed dimensions (width, height)
+ * 3. Sets inline styles with !important to freeze those dimensions
  * 4. Disables ResizeObserver API (for JS-based resizing)
+ * 5. When viewport changes for screenshot, media queries can't resize anything
+ * 6. Layout remains consistent → xpath coordinates match screenshot ✓
  *
  * USAGE:
  * Execute this script BEFORE calling capture_full_page() / screenshot functions.
- * Only enabled for image_ssim_diff processor (visual comparison).
- * Default: OFF for performance.
+ * The page must be fully loaded and settled at its initial viewport size.
+ * No need to restore state afterward - page is closed after screenshot.
  *
  * PERFORMANCE:
- * - Only processes 100-300 elements (first viewport) vs 10,000+ (entire page)
- * - Typically completes in 10-50ms
- * - 100x+ faster than locking entire page
+ * - Iterates all DOM elements (can be 1000s on complex pages)
+ * - Typically completes in 50-200ms
+ * - One-time cost before screenshot, well worth it for coordinate accuracy
  *
  * @see https://github.com/dgtlmoon/changedetection.io/issues/XXXX
  */
@@ -43,34 +52,11 @@
     // Store original styles in a global WeakMap for later restoration
     window.__elementSizingRestore = new WeakMap();
 
-    const start = performance.now();
-
-    // Get current viewport height (visible portion of page)
-    const viewportHeight = window.innerHeight;
-
-    // Get all elements and filter to FIRST VIEWPORT ONLY
-    // This dramatically reduces elements to process (100-300 vs 10,000+)
-    const allElements = Array.from(document.querySelectorAll('*'));
-
-    // BATCH READ PHASE: Get bounding rects and filter to viewport
-    const measurements = allElements.map(el => {
-        const rect = el.getBoundingClientRect();
+    // Lock ALL element dimensions to prevent media query layout changes
+    document.querySelectorAll('*').forEach(el => {
         const computed = window.getComputedStyle(el);
+        const rect = el.getBoundingClientRect();
 
-        // Only lock elements in the first viewport (visible on initial page load)
-        // rect.top < viewportHeight means element starts within visible area
-        const inViewport = rect.top < viewportHeight && rect.top >= 0;
-        const hasSize = rect.height > 0 && rect.width > 0;
-
-        return inViewport && hasSize ? { el, computed, rect } : null;
-    }).filter(Boolean);  // Remove null entries
-
-    const elapsed = performance.now() - start;
-    console.log(`Locked first viewport elements: ${measurements.length} of ${allElements.length} total elements (viewport height: ${viewportHeight}px, took ${elapsed.toFixed(0)}ms)`);
-
-    // BATCH WRITE PHASE: Apply all inline styles without triggering layout
-    // No interleaved reads means browser can optimize style application
-    measurements.forEach(({el, computed, rect}) => {
         // Save original inline style values BEFORE locking
         const properties = ['height', 'min-height', 'max-height', 'width', 'min-width', 'max-width'];
         const originalStyles = {};
@@ -103,5 +89,5 @@
         disconnect() {}
     };
 
-    console.log(`✓ Element dimensions locked (${measurements.length} elements) to prevent media query changes during screenshot`);
+    console.log('✓ Element dimensions locked to prevent media query changes during screenshot');
 })();

changedetectionio/content_fetchers/screenshot_handler.py

@@ -8,42 +8,92 @@ from loguru import logger
 
 from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT, SCREENSHOT_DEFAULT_QUALITY
 
-def stitch_images_worker_raw_bytes(pipe_conn, original_page_height, capture_height):
+# Cache font to avoid loading on every stitch
+_cached_font = None
+
+def _get_caption_font():
+    """Get or create cached font for caption text."""
+    global _cached_font
+    if _cached_font is None:
+        from PIL import ImageFont
+        try:
+            _cached_font = ImageFont.truetype("arial.ttf", 35)
+        except IOError:
+            _cached_font = ImageFont.load_default()
+    return _cached_font
+
+
+def stitch_images_inline(chunks_bytes, original_page_height, capture_height):
     """
-    Stitch image chunks together in a separate process.
-
-    Uses spawn multiprocessing to isolate PIL's C-level memory allocation.
-    When the subprocess exits, the OS reclaims ALL memory including C-level allocations
-    that Python's GC cannot release. This prevents the ~50MB per stitch from accumulating
-    in the main process.
-
-    Trade-off: Adds 35MB resource_tracker subprocess, but prevents 500MB+ memory leak
-    in main process (much better at scale: 35GB vs 500GB for 1000 instances).
+    Stitch image chunks together inline (no multiprocessing).
+    Optimized for small number of chunks (2-3) to avoid process creation overhead.
 
     Args:
-        pipe_conn: Pipe connection to receive data and send result
+        chunks_bytes: List of JPEG image bytes
         original_page_height: Original page height in pixels
         capture_height: Maximum capture height
+
+    Returns:
+        bytes: Stitched JPEG image
+    """
+    import os
+    import io
+    from PIL import Image, ImageDraw
+
+    # Load images from byte chunks
+    images = [Image.open(io.BytesIO(b)) for b in chunks_bytes]
+    total_height = sum(im.height for im in images)
+    max_width = max(im.width for im in images)
+
+    # Create stitched image
+    stitched = Image.new('RGB', (max_width, total_height))
+    y_offset = 0
+    for im in images:
+        stitched.paste(im, (0, y_offset))
+        y_offset += im.height
+        im.close()  # Close immediately after pasting
+
+    # Draw caption only if page was trimmed
+    if original_page_height > capture_height:
+        draw = ImageDraw.Draw(stitched)
+        caption_text = f"WARNING: Screenshot was {original_page_height}px but trimmed to {capture_height}px because it was too long"
+        padding = 10
+        font = _get_caption_font()
+
+        bbox = draw.textbbox((0, 0), caption_text, font=font)
+        text_width = bbox[2] - bbox[0]
+        text_height = bbox[3] - bbox[1]
+
+        # Draw white background rectangle
+        draw.rectangle([(0, 0), (max_width, text_height + 2 * padding)], fill=(255, 255, 255))
+
+        # Draw text centered
+        text_x = (max_width - text_width) // 2
+        draw.text((text_x, padding), caption_text, font=font, fill=(255, 0, 0))
+
+    # Encode to JPEG
+    output = io.BytesIO()
+    stitched.save(output, format="JPEG", quality=int(os.getenv("SCREENSHOT_QUALITY", SCREENSHOT_DEFAULT_QUALITY)), optimize=True)
+    result = output.getvalue()
+
+    # Cleanup
+    stitched.close()
+
+    return result
+
+
+def stitch_images_worker(pipe_conn, chunks_bytes, original_page_height, capture_height):
+    """
+    Stitch image chunks together in a separate process.
+    Used for large number of chunks (4+) to avoid blocking the main event loop.
     """
     import os
     import io
-    import struct
     from PIL import Image, ImageDraw, ImageFont
 
     try:
-        # Receive chunk count as 4-byte integer (no pickle!)
-        count_bytes = pipe_conn.recv_bytes()
-        chunk_count = struct.unpack('I', count_bytes)[0]
-
-        # Receive each chunk as raw bytes (no pickle!)
-        chunks_bytes = []
-        for _ in range(chunk_count):
-            chunks_bytes.append(pipe_conn.recv_bytes())
-
         # Load images from byte chunks
         images = [Image.open(io.BytesIO(b)) for b in chunks_bytes]
-        del chunks_bytes
-
         total_height = sum(im.height for im in images)
         max_width = max(im.width for im in images)
 
@@ -53,14 +103,15 @@ def stitch_images_worker_raw_bytes(pipe_conn, original_page_height, capture_heig
         for im in images:
             stitched.paste(im, (0, y_offset))
             y_offset += im.height
-            im.close()
-        del images
+            im.close()  # Close immediately after pasting
 
         # Draw caption only if page was trimmed
         if original_page_height > capture_height:
             draw = ImageDraw.Draw(stitched)
             caption_text = f"WARNING: Screenshot was {original_page_height}px but trimmed to {capture_height}px because it was too long"
             padding = 10
+
+            # Try to load font
             try:
                 font = ImageFont.truetype("arial.ttf", 35)
             except IOError:
@@ -69,26 +120,23 @@ def stitch_images_worker_raw_bytes(pipe_conn, original_page_height, capture_heig
             bbox = draw.textbbox((0, 0), caption_text, font=font)
             text_width = bbox[2] - bbox[0]
             text_height = bbox[3] - bbox[1]
+
+            # Draw white background rectangle
             draw.rectangle([(0, 0), (max_width, text_height + 2 * padding)], fill=(255, 255, 255))
+
+            # Draw text centered
             text_x = (max_width - text_width) // 2
             draw.text((text_x, padding), caption_text, font=font, fill=(255, 0, 0))
 
-        # Encode and send
+        # Encode and send image with optimization
         output = io.BytesIO()
         stitched.save(output, format="JPEG", quality=int(os.getenv("SCREENSHOT_QUALITY", SCREENSHOT_DEFAULT_QUALITY)), optimize=True)
-        result_bytes = output.getvalue()
+        pipe_conn.send_bytes(output.getvalue())
 
         stitched.close()
-        del stitched
-        output.close()
-        del output
-
-        pipe_conn.send_bytes(result_bytes)
-        del result_bytes
-
     except Exception as e:
-        logger.error(f"Error in stitch_images_worker_raw_bytes: {e}")
-        error_msg = f"error:{e}".encode('utf-8')
-        pipe_conn.send_bytes(error_msg)
+        pipe_conn.send(f"error:{e}")
     finally:
         pipe_conn.close()
+
+

changedetectionio/content_fetchers/webdriver_selenium.py

@@ -3,21 +3,30 @@ import time
 
 from loguru import logger
 from changedetectionio.content_fetchers.base import Fetcher
-from changedetectionio.pluggy_interface import hookimpl
 
 
 class fetcher(Fetcher):
-    fetcher_description = "Selenium WebDriver Chrome"
+    if os.getenv("WEBDRIVER_URL"):
+        fetcher_description = f"WebDriver Chrome/Javascript via \"{os.getenv('WEBDRIVER_URL', '')}\""
+    else:
+        fetcher_description = "WebDriver Chrome/Javascript"
 
     proxy = None
     proxy_url = None
 
     # Capability flags
-    supports_browser_steps = False
+    supports_browser_steps = True
     supports_screenshots = True
     supports_xpath_element_data = True
 
-    status_icon = {'filename': 'google-chrome-icon.png', 'alt': 'Using a Chrome browser', 'title': 'Using a Chrome browser'}
+    @classmethod
+    def get_status_icon_data(cls):
+        """Return Chrome browser icon data for WebDriver fetcher."""
+        return {
+            'filename': 'google-chrome-icon.png',
+            'alt': 'Using a Chrome browser',
+            'title': 'Using a Chrome browser'
+        }
 
     def __init__(self, proxy_override=None, custom_browser_connection_url=None, **kwargs):
         super().__init__(**kwargs)
@@ -147,19 +156,6 @@ class fetcher(Fetcher):
                     from PIL import Image
                     import io
                     img = Image.open(io.BytesIO(screenshot_png))
-                    # Convert to RGB if needed (JPEG doesn't support transparency)
-                    # Always convert non-RGB modes to RGB to ensure JPEG compatibility
-                    if img.mode in ('RGBA', 'LA', 'P', 'PA'):
-                        # Handle transparency by compositing onto white background
-                        if img.mode == 'P':
-                            img = img.convert('RGBA')
-                        background = Image.new('RGB', img.size, (255, 255, 255))
-                        if img.mode in ('RGBA', 'LA', 'PA'):
-                            background.paste(img, mask=img.split()[-1])  # Use alpha channel as mask
-                        img = background
-                    elif img.mode != 'RGB':
-                        # For other modes, direct conversion
-                        img = img.convert('RGB')
                     jpeg_buffer = io.BytesIO()
                     img.save(jpeg_buffer, format='JPEG', quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
                     self.screenshot = jpeg_buffer.getvalue()
@@ -181,10 +177,9 @@ class fetcher(Fetcher):
 class WebDriverSeleniumFetcherPlugin:
     """Plugin class that registers the WebDriver Selenium fetcher as a built-in plugin."""
 
-    @hookimpl
     def register_content_fetcher(self):
         """Register the WebDriver Selenium fetcher"""
-        return ('selenium', fetcher)
+        return ('html_webdriver', fetcher)
 
 
 # Create module-level instance for plugin registration

changedetectionio/custom_queue.py

@@ -57,15 +57,14 @@ class SignalPriorityQueue(queue.PriorityQueue):
     def put(self, item, block=True, timeout=None):
         # Call the parent's put method first
         super().put(item, block, timeout)
-
+        
         # After putting the item in the queue, check if it has a UUID and emit signal
         if hasattr(item, 'item') and isinstance(item.item, dict) and 'uuid' in item.item:
             uuid = item.item['uuid']
             # Get the signal and send it if it exists
             watch_check_update = signal('watch_check_update')
             if watch_check_update:
-                # NOTE: This would block other workers from .put/.get while this signal sends
-                # Signal handlers may iterate the queue/datastore while holding locks
+                # Send the watch_uuid parameter
                 watch_check_update.send(watch_uuid=uuid)
         
         # Send queue_length signal with current queue size
@@ -313,15 +312,14 @@ class AsyncSignalPriorityQueue(asyncio.PriorityQueue):
     async def put(self, item):
         # Call the parent's put method first
         await super().put(item)
-
+        
         # After putting the item in the queue, check if it has a UUID and emit signal
         if hasattr(item, 'item') and isinstance(item.item, dict) and 'uuid' in item.item:
             uuid = item.item['uuid']
             # Get the signal and send it if it exists
             watch_check_update = signal('watch_check_update')
             if watch_check_update:
-                # NOTE: This would block other workers from .put/.get while this signal sends
-                # Signal handlers may iterate the queue/datastore while holding locks
+                # Send the watch_uuid parameter
                 watch_check_update.send(watch_uuid=uuid)
         
         # Send queue_length signal with current queue size

changedetectionio/favicon_utils.py

@@ -1,43 +0,0 @@
-"""
-Favicon utilities for changedetection.io
-Handles favicon MIME type detection with caching
-"""
-
-from functools import lru_cache
-
-
-@lru_cache(maxsize=1000)
-def get_favicon_mime_type(filepath):
-    """
-    Detect MIME type of favicon by reading file content using puremagic.
-    Results are cached to avoid repeatedly reading the same files.
-
-    Args:
-        filepath: Full path to the favicon file
-
-    Returns:
-        MIME type string (e.g., 'image/png')
-    """
-    mime = None
-
-    try:
-        import puremagic
-        with open(filepath, 'rb') as f:
-            content_bytes = f.read(200)  # Read first 200 bytes
-
-        detections = puremagic.magic_string(content_bytes)
-        if detections:
-            mime = detections[0].mime_type
-    except Exception:
-        pass
-
-    # Fallback to mimetypes if puremagic fails
-    if not mime:
-        import mimetypes
-        mime, _ = mimetypes.guess_type(filepath)
-
-    # Final fallback based on extension
-    if not mime:
-        mime = 'image/x-icon' if filepath.endswith('.ico') else 'image/png'
-
-    return mime

changedetectionio/flask_app.py

@@ -4,18 +4,16 @@ import flask_login
 import locale
 import os
 import queue
-import re
 import sys
 import threading
 import time
 import timeago
 from blinker import signal
-from pathlib import Path
 
 from changedetectionio.strtobool import strtobool
 from threading import Event
 from changedetectionio.queue_handlers import RecheckPriorityQueue, NotificationQueue
-from changedetectionio import worker_pool
+from changedetectionio import worker_handler
 
 from flask import (
     Flask,
@@ -28,6 +26,8 @@ from flask import (
     session,
     url_for,
 )
+from flask_compress import Compress as FlaskCompress
+from flask_login import current_user
 from flask_restful import abort, Api
 from flask_cors import CORS
 
@@ -40,13 +40,10 @@ from loguru import logger
 
 from changedetectionio import __version__
 from changedetectionio import queuedWatchMetaData
-from changedetectionio.api import Watch, WatchHistory, WatchSingleHistory, WatchHistoryDiff, CreateWatch, Import, SystemInfo, Tag, Tags, Notifications, WatchFavicon, Spec
+from changedetectionio.api import Watch, WatchHistory, WatchSingleHistory, WatchHistoryDiff, CreateWatch, Import, SystemInfo, Tag, Tags, Notifications, WatchFavicon
 from changedetectionio.api.Search import Search
 from .time_handler import is_within_schedule
 from changedetectionio.languages import get_available_languages, get_language_codes, get_flag_for_locale, get_timeago_locale
-from changedetectionio.favicon_utils import get_favicon_mime_type
-
-IN_PYTEST = "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ
 
 datastore = None
 
@@ -57,7 +54,7 @@ extra_stylesheets = []
 # Use bulletproof janus-based queues for sync/async reliability  
 update_q = RecheckPriorityQueue()
 notification_q = NotificationQueue()
-MAX_QUEUE_SIZE = 5000
+MAX_QUEUE_SIZE = 2000
 
 app = Flask(__name__,
             static_url_path="",
@@ -69,43 +66,11 @@ socketio_server = None
 
 # Enable CORS, especially useful for the Chrome extension to operate from anywhere
 CORS(app)
-from werkzeug.routing import BaseConverter, ValidationError
-from uuid import UUID
-
-class StrictUUIDConverter(BaseConverter):
-    # Special sentinel values allowed in addition to strict UUIDs
-    _ALLOWED_SENTINELS = frozenset({'first'})
-
-    def to_python(self, value: str) -> str:
-        if value in self._ALLOWED_SENTINELS:
-            return value
-        try:
-            u = UUID(value)
-        except ValueError as e:
-            raise ValidationError() from e
-        # Reject non-standard formats (braces, URNs, no-hyphens)
-        if str(u) != value.lower():
-            raise ValidationError()
-        return str(u)
-
-    def to_url(self, value) -> str:
-        return str(value)
-
-# app setup (once)
-app.url_map.converters["uuid_str"] = StrictUUIDConverter
-
-# Flask-Compress handles HTTP compression, Socket.IO compression disabled to prevent memory leak.
-# There's also a bug between flask compress and socketio that causes some kind of slow memory leak
-# It's better to use compression on your reverse proxy (nginx etc) instead.
-if strtobool(os.getenv("FLASK_ENABLE_COMPRESSION")):
-    from flask_compress import Compress as FlaskCompress
-    app.config['COMPRESS_MIN_SIZE'] = 2096
-    app.config['COMPRESS_MIMETYPES'] = ['text/html', 'text/css', 'text/javascript', 'application/json', 'application/javascript', 'image/svg+xml']
-    # Use gzip only - smaller memory footprint than zstd/brotli (4-8KB vs 200-500KB contexts)
-    app.config['COMPRESS_ALGORITHM'] = ['gzip']
-    compress = FlaskCompress()
-    compress.init_app(app)
 
+# Super handy for compressing large BrowserSteps responses and others
+FlaskCompress(app)
+app.config['COMPRESS_MIN_SIZE'] = 4096
+app.config['COMPRESS_MIMETYPES'] = ['text/html', 'text/css', 'text/javascript', 'application/json', 'application/javascript', 'image/svg+xml']
 app.config['TEMPLATES_AUTO_RELOAD'] = False
 
 
@@ -118,18 +83,6 @@ app.config['NEW_VERSION_AVAILABLE'] = False
 if os.getenv('FLASK_SERVER_NAME'):
     app.config['SERVER_NAME'] = os.getenv('FLASK_SERVER_NAME')
 
-# Babel/i18n configuration
-app.config['BABEL_TRANSLATION_DIRECTORIES'] = str(Path(__file__).parent / 'translations')
-app.config['BABEL_DEFAULT_LOCALE'] = 'en_GB'
-
-# Session configuration
-# NOTE: Flask session (for locale, etc.) is separate from Flask-Login's remember-me cookie
-# - Flask session stores data like session['locale'] in a signed cookie
-# - Flask-Login's remember=True creates a separate authentication cookie
-# - Setting PERMANENT_SESSION_LIFETIME controls how long the Flask session cookie lasts
-from datetime import timedelta
-app.config['PERMANENT_SESSION_LIFETIME'] = timedelta(days=3650)  # ~10 years (effectively unlimited)
-
 #app.config["EXPLAIN_TEMPLATE_LOADING"] = True
 
 
@@ -218,16 +171,12 @@ def _jinja2_filter_format_number_locale(value: float) -> str:
     "Formats for example 4000.10 to the local locale default of 4,000.10"
     # Format the number with two decimal places (locale format string will return 6 decimal)
     formatted_value = locale.format_string("%.2f", value, grouping=True)
-    return formatted_value
 
-@app.template_filter('regex_search')
-def _jinja2_filter_regex_search(value, pattern):
-    import re
-    return re.search(pattern, str(value)) is not None
+    return formatted_value
 
 @app.template_global('is_checking_now')
 def _watch_is_checking_now(watch_obj, format="%Y-%m-%d %H:%M:%S"):
-    return worker_pool.is_watch_running(watch_obj['uuid'])
+    return worker_handler.is_watch_running(watch_obj['uuid'])
 
 @app.template_global('get_watch_queue_position')
 def _get_watch_queue_position(watch_obj):
@@ -238,13 +187,13 @@ def _get_watch_queue_position(watch_obj):
 @app.template_global('get_current_worker_count')
 def _get_current_worker_count():
     """Get the current number of operational workers"""
-    return worker_pool.get_worker_count()
+    return worker_handler.get_worker_count()
 
 @app.template_global('get_worker_status_info')
 def _get_worker_status_info():
     """Get detailed worker status information for display"""
-    status = worker_pool.get_worker_status()
-    running_uuids = worker_pool.get_running_uuids()
+    status = worker_handler.get_worker_status()
+    running_uuids = worker_handler.get_running_uuids()
     
     return {
         'count': status['worker_count'],
@@ -298,99 +247,54 @@ def _jinja2_filter_seconds_precise(timestamp):
 
     return format(int(time.time()-timestamp), ',d')
 
-@app.template_filter('format_duration')
-def _jinja2_filter_format_duration(seconds):
-    """Format a duration in seconds into human readable string like '5 days, 3 hours, 30 minutes'"""
-    from datetime import timedelta
-
-    if not seconds or seconds < 0:
-        return gettext('0 seconds')
-
-    td = timedelta(seconds=int(seconds))
-
-    # Calculate components
-    years = td.days // 365
-    remaining_days = td.days % 365
-    months = remaining_days // 30
-    remaining_days = remaining_days % 30
-    weeks = remaining_days // 7
-    days = remaining_days % 7
-
-    hours = td.seconds // 3600
-    minutes = (td.seconds % 3600) // 60
-    secs = td.seconds % 60
-
-    # Build parts list
-    parts = []
-    if years > 0:
-        parts.append(f"{years} {gettext('year') if years == 1 else gettext('years')}")
-    if months > 0:
-        parts.append(f"{months} {gettext('month') if months == 1 else gettext('months')}")
-    if weeks > 0:
-        parts.append(f"{weeks} {gettext('week') if weeks == 1 else gettext('weeks')}")
-    if days > 0:
-        parts.append(f"{days} {gettext('day') if days == 1 else gettext('days')}")
-    if hours > 0:
-        parts.append(f"{hours} {gettext('hour') if hours == 1 else gettext('hours')}")
-    if minutes > 0:
-        parts.append(f"{minutes} {gettext('minute') if minutes == 1 else gettext('minutes')}")
-    if secs > 0 or not parts:
-        parts.append(f"{secs} {gettext('second') if secs == 1 else gettext('seconds')}")
-
-    return ", ".join(parts)
-
 @app.template_filter('fetcher_status_icons')
 def _jinja2_filter_fetcher_status_icons(fetcher_name):
-    """Return status icon HTML for a fetcher, or empty string if none.
+    """Get status icon HTML for a given fetcher.
 
-    Built-in fetchers declare their icon via the ``status_icon`` class attribute
-    on their ``Fetcher`` subclass.  Plugin fetchers may still use the pluggy
-    ``collect_fetcher_status_icons`` hook as a fallback.
+    This filter checks both built-in fetchers and plugin fetchers for status icons.
+
+    Args:
+        fetcher_name: The fetcher name (e.g., 'html_webdriver', 'html_js_zyte')
+
+    Returns:
+        str: HTML string containing status icon elements
     """
     from changedetectionio import content_fetchers
+    from changedetectionio.pluggy_interface import collect_fetcher_status_icons
     from markupsafe import Markup
     from flask import url_for
 
     icon_data = None
 
-    fetcher_class = content_fetchers.get_fetcher(fetcher_name)
-    if fetcher_class is not None:
-        icon_data = getattr(fetcher_class, 'status_icon', None)
-        if not icon_data and callable(getattr(fetcher_class, 'get_status_icon_data', None)):
+    # First check if it's a plugin fetcher (plugins have priority)
+    plugin_icon_data = collect_fetcher_status_icons(fetcher_name)
+    if plugin_icon_data:
+        icon_data = plugin_icon_data
+    # Check if it's a built-in fetcher
+    elif hasattr(content_fetchers, fetcher_name):
+        fetcher_class = getattr(content_fetchers, fetcher_name)
+        if hasattr(fetcher_class, 'get_status_icon_data'):
             icon_data = fetcher_class.get_status_icon_data()
 
-    # Fallback: pluggy hook for plugins that implement fetcher_status_icon
-    if not icon_data:
-        from changedetectionio.pluggy_interface import collect_fetcher_status_icons
-        icon_data = collect_fetcher_status_icons(fetcher_name)
+    # Build HTML from icon data
+    if icon_data and isinstance(icon_data, dict):
+        # Use 'group' from icon_data if specified, otherwise default to 'images'
+        group = icon_data.get('group', 'images')
 
-    if not icon_data:
-        return ''
+        # Try to use url_for, but fall back to manual URL building if endpoint not registered yet
+        try:
+            icon_url = url_for('static_content', group=group, filename=icon_data['filename'])
+        except:
+            # Fallback: build URL manually respecting APPLICATION_ROOT
+            from flask import request
+            app_root = request.script_root if hasattr(request, 'script_root') else ''
+            icon_url = f"{app_root}/static/{group}/{icon_data['filename']}"
 
-    group = icon_data.get('group', 'images')
-    icon_url = url_for('static_content', group=group, filename=icon_data['filename'])
-    style_attr = f' style="{icon_data["style"]}"' if icon_data.get('style') else ''
-    return Markup(f'<img class="status-icon" src="{icon_url}" alt="{icon_data["alt"]}" title="{icon_data["title"]}"{style_attr}>')
+        style_attr = f' style="{icon_data["style"]}"' if icon_data.get('style') else ''
+        html = f'<img class="status-icon" src="{icon_url}" alt="{icon_data["alt"]}" title="{icon_data["title"]}"{style_attr}>'
+        return Markup(html)
 
-_RE_SANITIZE_TAG = re.compile(r'[^a-zA-Z0-9]')
-
-@app.template_filter('sanitize_tag_class')
-def _jinja2_filter_sanitize_tag_class(tag_title):
-    """Sanitize a tag title to create a valid CSS class name.
-    Removes all non-alphanumeric characters and converts to lowercase.
-
-    Args:
-        tag_title: The tag title string
-
-    Returns:
-        str: A sanitized string suitable for use as a CSS class name
-    """
-    # Remove all non-alphanumeric characters and convert to lowercase
-    sanitized = _RE_SANITIZE_TAG.sub('', tag_title).lower()
-    # Ensure it starts with a letter (CSS requirement)
-    if sanitized and not sanitized[0].isalpha():
-        sanitized = 'tag' + sanitized
-    return sanitized if sanitized else 'tag'
+    return ''
 
 # Import login_optionally_required from auth_decorator
 from changedetectionio.auth_decorator import login_optionally_required
@@ -446,23 +350,10 @@ def changedetection_app(config=None, datastore_o=None):
     global datastore, socketio_server
     datastore = datastore_o
 
-    # Set datastore reference in notification queue for all_muted checking
-    notification_q.set_datastore(datastore)
-
-    # Import and create a wrapper for is_safe_url that has access to app
-    from changedetectionio.is_safe_url import is_safe_url as _is_safe_url
-
-    def is_safe_url(target):
-        """Wrapper for is_safe_url that passes the app instance"""
-        return _is_safe_url(target, app)
-
     # so far just for read-only via tests, but this will be moved eventually to be the main source
     # (instead of the global var)
     app.config['DATASTORE'] = datastore_o
-
-    # Store batch mode flag to skip background threads when running in batch mode
-    app.config['batch_mode'] = config.get('batch_mode', False) if config else False
-
+    
     # Store the signal in the app config to ensure it's accessible everywhere
     app.config['watch_check_update_SIGNAL'] = watch_check_update
 
@@ -474,21 +365,16 @@ def changedetection_app(config=None, datastore_o=None):
     available_languages = get_available_languages()
     language_codes = get_language_codes()
 
-    _locale_aliases = {
-        'zh-TW': 'zh_Hant_TW',  # Traditional Chinese: browser sends zh-TW, we use zh_Hant_TW
-        'zh_TW': 'zh_Hant_TW',  # Also handle underscore variant
-    }
-    _locale_match_list = language_codes + list(_locale_aliases.keys())
-
     def get_locale():
         # 1. Try to get locale from session (user explicitly selected)
         if 'locale' in session:
-            return session['locale']
-
+            locale = session['locale']
+            logger.trace(f"DEBUG: get_locale() returning from session: {locale}")
+            return locale
         # 2. Fall back to Accept-Language header
-        browser_locale = request.accept_languages.best_match(_locale_match_list)
-        # 3. Map browser locale to our internal locale if needed
-        return _locale_aliases.get(browser_locale, browser_locale)
+        locale = request.accept_languages.best_match(language_codes)
+        logger.trace(f"DEBUG: get_locale() returning from Accept-Language: {locale}")
+        return locale
 
     # Initialize Babel with locale selector
     babel = Babel(app, locale_selector=get_locale)
@@ -540,22 +426,22 @@ def changedetection_app(config=None, datastore_o=None):
 
 
     watch_api.add_resource(WatchHistoryDiff,
-                           '/api/v1/watch/<uuid_str:uuid>/difference/<string:from_timestamp>/<string:to_timestamp>',
+                           '/api/v1/watch/<string:uuid>/difference/<string:from_timestamp>/<string:to_timestamp>',
                            resource_class_kwargs={'datastore': datastore})
     watch_api.add_resource(WatchSingleHistory,
-                           '/api/v1/watch/<uuid_str:uuid>/history/<string:timestamp>',
+                           '/api/v1/watch/<string:uuid>/history/<string:timestamp>',
                            resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
     watch_api.add_resource(WatchFavicon,
-                           '/api/v1/watch/<uuid_str:uuid>/favicon',
+                           '/api/v1/watch/<string:uuid>/favicon',
                            resource_class_kwargs={'datastore': datastore})
     watch_api.add_resource(WatchHistory,
-                           '/api/v1/watch/<uuid_str:uuid>/history',
+                           '/api/v1/watch/<string:uuid>/history',
                            resource_class_kwargs={'datastore': datastore})
 
     watch_api.add_resource(CreateWatch, '/api/v1/watch',
                            resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
 
-    watch_api.add_resource(Watch, '/api/v1/watch/<uuid_str:uuid>',
+    watch_api.add_resource(Watch, '/api/v1/watch/<string:uuid>',
                            resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
 
     watch_api.add_resource(SystemInfo, '/api/v1/systeminfo',
@@ -568,7 +454,7 @@ def changedetection_app(config=None, datastore_o=None):
     watch_api.add_resource(Tags, '/api/v1/tags',
                            resource_class_kwargs={'datastore': datastore})
 
-    watch_api.add_resource(Tag, '/api/v1/tag', '/api/v1/tag/<uuid_str:uuid>',
+    watch_api.add_resource(Tag, '/api/v1/tag', '/api/v1/tag/<string:uuid>',
                            resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
                            
     watch_api.add_resource(Search, '/api/v1/search',
@@ -577,8 +463,6 @@ def changedetection_app(config=None, datastore_o=None):
     watch_api.add_resource(Notifications, '/api/v1/notifications',
                            resource_class_kwargs={'datastore': datastore})
 
-    watch_api.add_resource(Spec, '/api/v1/full-spec')
-
     @login_manager.user_loader
     def user_loader(email):
         user = User()
@@ -587,76 +471,36 @@ def changedetection_app(config=None, datastore_o=None):
 
     @login_manager.unauthorized_handler
     def unauthorized_handler():
-        # Pass the current request path so users are redirected back after login
-        return redirect(url_for('login', redirect=request.path))
+        return redirect(url_for('login', next=url_for('watchlist.index')))
 
     @app.route('/logout')
     def logout():
         flask_login.logout_user()
-
-        # Check if there's a redirect parameter to return to after re-login
-        redirect_url = request.args.get('redirect')
-
-        # If redirect is provided and safe, pass it to login page
-        if redirect_url and is_safe_url(redirect_url):
-            return redirect(url_for('login', redirect=redirect_url))
-
-        # Otherwise just go to watchlist
         return redirect(url_for('watchlist.index'))
 
     @app.route('/set-language/<locale>')
     def set_language(locale):
         """Set the user's preferred language in the session"""
-        if not request.cookies:
-            logger.error("Cannot set language without session cookie")
-            flash("Cannot set language without session cookie", 'error')
-            return redirect(url_for('watchlist.index'))
-
         # Validate the locale against available languages
         if locale in language_codes:
-            # Make session permanent so language preference persists across browser sessions
-            # NOTE: This is the Flask session cookie (separate from Flask-Login's remember-me auth cookie)
-            session.permanent = True
             session['locale'] = locale
-
-            # CRITICAL: Flask-Babel caches the locale in the request context (ctx.babel_locale)
-            # We must refresh to clear this cache so the new locale takes effect immediately
-            # This is especially important for tests where multiple requests happen rapidly
-            from flask_babel import refresh
-            refresh()
         else:
             logger.error(f"Invalid locale {locale}, available: {language_codes}")
 
-        # Check if there's a redirect parameter to return to the same page
-        redirect_url = request.args.get('redirect')
-
-        # If redirect is provided and safe, use it
-        if redirect_url and is_safe_url(redirect_url):
-            return redirect(redirect_url)
-
-        # Otherwise redirect to watchlist
+        # Redirect back to the page they came from, or home
         return redirect(url_for('watchlist.index'))
 
     # https://github.com/pallets/flask/blob/93dd1709d05a1cf0e886df6223377bdab3b077fb/examples/tutorial/flaskr/__init__.py#L39
     # You can divide up the stuff like this
     @app.route('/login', methods=['GET', 'POST'])
     def login():
-        # Extract and validate the redirect parameter
-        redirect_url = request.args.get('redirect') or request.form.get('redirect')
-
-        # Validate the redirect URL - default to watchlist if invalid
-        if redirect_url and is_safe_url(redirect_url):
-            validated_redirect = redirect_url
-        else:
-            validated_redirect = url_for('watchlist.index')
 
         if request.method == 'GET':
             if flask_login.current_user.is_authenticated:
-                # Already logged in - redirect immediately to the target
                 flash(gettext("Already logged in"))
-                return redirect(validated_redirect)
+                return redirect(url_for("watchlist.index"))
             flash(gettext("You must be logged in, please log in."), 'error')
-            output = render_template("login.html", redirect_url=validated_redirect)
+            output = render_template("login.html")
             return output
 
         user = User()
@@ -666,13 +510,23 @@ def changedetection_app(config=None, datastore_o=None):
 
         if (user.check_password(password)):
             flask_login.login_user(user, remember=True)
-            # Redirect to the validated URL after successful login
-            return redirect(validated_redirect)
+
+            # For now there's nothing else interesting here other than the index/list page
+            # It's more reliable and safe to ignore the 'next' redirect
+            # When we used...
+            # next = request.args.get('next')
+            # return redirect(next or url_for('watchlist.index'))
+            # We would sometimes get login loop errors on sites hosted in sub-paths
+
+            # note for the future:
+            #            if not is_safe_valid_url(next):
+            #                return flask.abort(400)
+            return redirect(url_for('watchlist.index'))
 
         else:
             flash(gettext('Incorrect password'), 'error')
 
-        return redirect(url_for('login', redirect=redirect_url if redirect_url else None))
+        return redirect(url_for('login'))
 
     @app.before_request
     def before_request_handle_cookie_x_settings():
@@ -720,14 +574,8 @@ def changedetection_app(config=None, datastore_o=None):
     def static_content(group, filename):
         from flask import make_response
         import re
-
-        # Strict sanitization: only allow a-z, 0-9, and underscore (blocks .. and other traversal)
-        group = re.sub(r'[^a-z0-9_-]+', '', group.lower())
-        filename = filename
-
-        # Additional safety: reject if sanitization resulted in empty strings
-        if not group or not filename:
-            abort(404)
+        group = re.sub(r'[^\w.-]+', '', group.lower())
+        filename = re.sub(r'[^\w.-]+', '', filename.lower())
 
         if group == 'screenshot':
             # Could be sensitive, follow password requirements
@@ -761,11 +609,18 @@ def changedetection_app(config=None, datastore_o=None):
 
             favicon_filename = watch.get_favicon_filename()
             if favicon_filename:
-                # Use cached MIME type detection
-                filepath = os.path.join(watch.data_dir, favicon_filename)
-                mime = get_favicon_mime_type(filepath)
+                try:
+                    import magic
+                    mime = magic.from_file(
+                        os.path.join(watch.watch_data_dir, favicon_filename),
+                        mime=True
+                    )
+                except ImportError:
+                    # Fallback, no python-magic
+                    import mimetypes
+                    mime, encoding = mimetypes.guess_type(favicon_filename)
 
-                response = make_response(send_from_directory(watch.data_dir, favicon_filename))
+                response = make_response(send_from_directory(watch.watch_data_dir, favicon_filename))
                 response.headers['Content-type'] = mime
                 response.headers['Cache-Control'] = 'max-age=300, must-revalidate'  # Cache for 5 minutes, then revalidate
                 return response
@@ -860,15 +715,13 @@ def changedetection_app(config=None, datastore_o=None):
 
     # watchlist UI buttons etc
     import changedetectionio.blueprint.ui as ui
-    app.register_blueprint(ui.construct_blueprint(datastore, update_q, worker_pool, queuedWatchMetaData, watch_check_update))
+    app.register_blueprint(ui.construct_blueprint(datastore, update_q, worker_handler, queuedWatchMetaData, watch_check_update))
 
     import changedetectionio.blueprint.watchlist as watchlist
     app.register_blueprint(watchlist.construct_blueprint(datastore=datastore, update_q=update_q, queuedWatchMetaData=queuedWatchMetaData), url_prefix='')
 
     # Initialize Socket.IO server conditionally based on settings
-    socket_io_enabled = datastore.data['settings']['application'].get('ui', {}).get('socket_io_enabled', True)
-    if socket_io_enabled and app.config.get('batch_mode'):
-        socket_io_enabled = False
+    socket_io_enabled = datastore.data['settings']['application']['ui'].get('socket_io_enabled', True)
     if socket_io_enabled:
         from changedetectionio.realtime.socket_server import init_socketio
         global socketio_server
@@ -897,10 +750,10 @@ def changedetection_app(config=None, datastore_o=None):
         expected_workers = int(os.getenv("FETCH_WORKERS", datastore.data['settings']['requests']['workers']))
         
         # Get basic status
-        status = worker_pool.get_worker_status()
+        status = worker_handler.get_worker_status()
         
         # Perform health check
-        health_result = worker_pool.check_worker_health(
+        health_result = worker_handler.check_worker_health(
             expected_count=expected_workers,
             update_q=update_q,
             notification_q=notification_q,
@@ -964,31 +817,16 @@ def changedetection_app(config=None, datastore_o=None):
     # Can be overridden by ENV or use the default settings
     n_workers = int(os.getenv("FETCH_WORKERS", datastore.data['settings']['requests']['workers']))
     logger.info(f"Starting {n_workers} workers during app initialization")
-    worker_pool.start_workers(n_workers, update_q, notification_q, app, datastore)
+    worker_handler.start_workers(n_workers, update_q, notification_q, app, datastore)
 
-    # Skip background threads in batch mode (just process queue and exit)
-    batch_mode = app.config.get('batch_mode', False)
-    if not batch_mode:
-        # @todo handle ctrl break
-        ticker_thread = threading.Thread(target=ticker_thread_check_time_launch_checks, daemon=True, name="TickerThread-ScheduleChecker").start()
+    # @todo handle ctrl break
+    ticker_thread = threading.Thread(target=ticker_thread_check_time_launch_checks).start()
+    threading.Thread(target=notification_runner).start()
 
-        # Start configurable number of notification workers (default 1)
-        notification_workers = int(os.getenv("NOTIFICATION_WORKERS", "1"))
-        for i in range(notification_workers):
-            threading.Thread(
-                target=notification_runner,
-                args=(i,),
-                daemon=True,
-                name=f"NotificationRunner-{i}"
-            ).start()
-        logger.info(f"Started {notification_workers} notification worker(s)")
-
-        in_pytest = "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ
-        # Check for new release version, but not when running in test/build or pytest
-        if not os.getenv("GITHUB_REF", False) and not strtobool(os.getenv('DISABLE_VERSION_CHECK', 'no')) and not in_pytest:
-            threading.Thread(target=check_for_new_version, daemon=True, name="VersionChecker").start()
-    else:
-        logger.info("Batch mode: Skipping ticker thread, notification runner, and version checker")
+    in_pytest = "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ
+    # Check for new release version, but not when running in test/build or pytest
+    if not os.getenv("GITHUB_REF", False) and not strtobool(os.getenv('DISABLE_VERSION_CHECK', 'no')) and not in_pytest:
+        threading.Thread(target=check_for_new_version).start()
 
     # Return the Flask app - the Socket.IO will be attached to it but initialized separately
     # This avoids circular dependencies
@@ -1001,16 +839,15 @@ def check_for_new_version():
     import urllib3
     urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
-    session = requests.Session()
-    session.verify = False
-
     while not app.config.exit.is_set():
         try:
-            r = session.post("https://changedetection.io/check-ver.php",
+            r = requests.post("https://changedetection.io/check-ver.php",
                               data={'version': __version__,
                                     'app_guid': datastore.data['app_guid'],
                                     'watch_count': len(datastore.data['watching'])
-                                    })
+                                    },
+
+                              verify=False)
         except:
             pass
 
@@ -1024,17 +861,17 @@ def check_for_new_version():
         app.config.exit.wait(86400)
 
 
-def notification_runner(worker_id=0):
+def notification_runner():
     global notification_debug_log
     from datetime import datetime
     import json
     with app.app_context():
         while not app.config.exit.is_set():
             try:
-                # Multiple workers can run concurrently (configurable via NOTIFICATION_WORKERS)
+                # At the moment only one thread runs (single runner)
                 n_object = notification_q.get(block=False)
             except queue.Empty:
-                app.config.exit.wait(1)
+                time.sleep(1)
 
             else:
 
@@ -1057,7 +894,7 @@ def notification_runner(worker_id=0):
                         sent_obj = process_notification(n_object, datastore)
 
                 except Exception as e:
-                    logger.error(f"Notification worker {worker_id} - Watch URL: {n_object['watch_url']}  Error {str(e)}")
+                    logger.error(f"Watch URL: {n_object['watch_url']}  Error {str(e)}")
 
                     # UUID wont be present when we submit a 'test' from the global settings
                     if 'uuid' in n_object:
@@ -1071,7 +908,7 @@ def notification_runner(worker_id=0):
                         app.config['watch_check_update_SIGNAL'].send(app_context=app, watch_uuid=n_object.get('uuid'))
 
                 # Process notifications
-                notification_debug_log+= ["{} - SENDING - {}".format(now.strftime("%c"), json.dumps(sent_obj))]
+                notification_debug_log+= ["{} - SENDING - {}".format(now.strftime("%Y/%m/%d %H:%M:%S,000"), json.dumps(sent_obj))]
                 # Trim the log length
                 notification_debug_log = notification_debug_log[-100:]
 
@@ -1087,10 +924,6 @@ def ticker_thread_check_time_launch_checks():
     logger.debug(f"System env MINIMUM_SECONDS_RECHECK_TIME {recheck_time_minimum_seconds}")
 
     # Workers are now started during app initialization, not here
-    WAIT_TIME_BETWEEN_LOOP = 1.0 if not IN_PYTEST else 0.01
-    if IN_PYTEST:
-        # The time between loops should be less than the first .sleep/wait in def wait_for_all_checks() of tests/util.py
-        logger.warning(f"Looks like we're in PYTEST! Setting time between searching for items to add to the queue to {WAIT_TIME_BETWEEN_LOOP}s")
 
     while not app.config.exit.is_set():
 
@@ -1098,7 +931,7 @@ def ticker_thread_check_time_launch_checks():
         now = time.time()
         if now - last_health_check > 60:
             expected_workers = int(os.getenv("FETCH_WORKERS", datastore.data['settings']['requests']['workers']))
-            health_result = worker_pool.check_worker_health(
+            health_result = worker_handler.check_worker_health(
                 expected_count=expected_workers,
                 update_q=update_q,
                 notification_q=notification_q,
@@ -1108,19 +941,11 @@ def ticker_thread_check_time_launch_checks():
             
             if health_result['status'] != 'healthy':
                 logger.warning(f"Worker health check: {health_result['message']}")
-
+                
             last_health_check = now
 
-        # Check if all checks are paused
-        if datastore.data['settings']['application'].get('all_paused', False):
-            app.config.exit.wait(1)
-            continue
-
         # Get a list of watches by UUID that are currently fetching data
-        running_uuids = worker_pool.get_running_uuids()
-
-        # Build set of queued UUIDs once for O(1) lookup instead of O(n) per watch
-        queued_uuids = {q_item.item['uuid'] for q_item in update_q.queue}
+        running_uuids = worker_handler.get_running_uuids()
 
         # Re #232 - Deepcopy the data incase it changes while we're iterating through it all
         watch_uuid_list = []
@@ -1138,17 +963,16 @@ def ticker_thread_check_time_launch_checks():
             else:
                 break
 
+        # Re #438 - Don't place more watches in the queue to be checked if the queue is already large
+        while update_q.qsize() >= 2000:
+            logger.warning(f"Recheck watches queue size limit reached ({MAX_QUEUE_SIZE}), skipping adding more items")
+            time.sleep(3)
+
+
         recheck_time_system_seconds = int(datastore.threshold_seconds)
 
         # Check for watches outside of the time threshold to put in the thread queue.
-        for watch_index, uuid in enumerate(watch_uuid_list):
-            # Re #438 - Check queue size every 100 watches for CPU efficiency (not every watch)
-            if watch_index % 100 == 0:
-                current_queue_size = update_q.qsize()
-                if current_queue_size >= MAX_QUEUE_SIZE:
-                    logger.debug(f"Queue size limit reached ({current_queue_size}/{MAX_QUEUE_SIZE}), stopping scheduler this iteration.")
-                    break
-
+        for uuid in watch_uuid_list:
             now = time.time()
             watch = datastore.data['watching'].get(uuid)
             if not watch:
@@ -1198,7 +1022,7 @@ def ticker_thread_check_time_launch_checks():
             seconds_since_last_recheck = now - watch['last_checked']
 
             if seconds_since_last_recheck >= (threshold + watch.jitter_seconds) and seconds_since_last_recheck >= recheck_time_minimum_seconds:
-                if not uuid in running_uuids and uuid not in queued_uuids:
+                if not uuid in running_uuids and uuid not in [q_uuid.item['uuid'] for q_uuid in update_q.queue]:
 
                     # Proxies can be set to have a limit on seconds between which they can be called
                     watch_proxy = datastore.get_preferred_proxy_for_watch(uuid=uuid)
@@ -1223,7 +1047,7 @@ def ticker_thread_check_time_launch_checks():
                     priority = int(time.time())
 
                     # Into the queue with you
-                    queued_successfully = worker_pool.queue_item_async_safe(update_q,
+                    queued_successfully = worker_handler.queue_item_async_safe(update_q,
                                                                                queuedWatchMetaData.PrioritizedItem(priority=priority,
                                                                                                                    item={'uuid': uuid})
                                                                                )
@@ -1240,5 +1064,8 @@ def ticker_thread_check_time_launch_checks():
                     # Reset for next time
                     watch.jitter_seconds = 0
 
+        # Wait before checking the list again - saves CPU
+        time.sleep(1)
+
         # Should be low so we can break this out in testing
-        app.config.exit.wait(WAIT_TIME_BETWEEN_LOOP)
+        app.config.exit.wait(1)

changedetectionio/forms.py

@@ -7,6 +7,8 @@ from flask_babel import lazy_gettext as _l, gettext
 from changedetectionio.blueprint.rss import RSS_FORMAT_TYPES, RSS_TEMPLATE_TYPE_OPTIONS, RSS_TEMPLATE_HTML_DEFAULT
 from changedetectionio.conditions.form import ConditionFormRow
 from changedetectionio.notification_service import NotificationContextData
+from changedetectionio.processors.image_ssim_diff import SCREENSHOT_COMPARISON_THRESHOLD_OPTIONS, \
+    SCREENSHOT_COMPARISON_THRESHOLD_OPTIONS_DEFAULT
 from changedetectionio.strtobool import strtobool
 from changedetectionio import processors
 
@@ -35,7 +37,7 @@ from changedetectionio.widgets import TernaryNoneBooleanField
 
 # default
 # each select <option data-enabled="enabled-0-0"
-from changedetectionio.browser_steps.browser_steps import browser_step_ui_config
+from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
 
 from changedetectionio import html_tools, content_fetchers
 
@@ -492,6 +494,7 @@ class ValidateJinja2Template(object):
     Validates that a {token} is from a valid set
     """
     def __call__(self, form, field):
+        from changedetectionio import notification
         from changedetectionio.jinja2_custom import create_jinja_env
         from jinja2 import BaseLoader, TemplateSyntaxError, UndefinedError
         from jinja2.meta import find_undeclared_variables
@@ -608,12 +611,13 @@ class ValidateCSSJSONXPATHInput(object):
                     raise ValidationError("XPath not permitted in this field!")
                 from lxml import etree, html
                 import elementpath
-                from changedetectionio.html_tools import SafeXPath3Parser
+                # xpath 2.0-3.1
+                from elementpath.xpath3 import XPath3Parser
                 tree = html.fromstring("<html></html>")
                 line = line.replace('xpath:', '')
 
                 try:
-                    elementpath.select(tree, line.strip(), parser=SafeXPath3Parser)
+                    elementpath.select(tree, line.strip(), parser=XPath3Parser)
                 except elementpath.ElementPathError as e:
                     message = field.gettext('\'%s\' is not a valid XPath expression. (%s)')
                     raise ValidationError(message % (line, str(e)))
@@ -723,10 +727,10 @@ class ValidateStartsWithRegex(object):
                 raise ValidationError(self.message or _l("Invalid value."))
 
 class quickWatchForm(Form):
-    url = fields.URLField(_l('URL'), validators=[validateURL()])
-    tags = StringTagUUID(_l('Group tag'), validators=[validators.Optional()])
+    url = fields.URLField('URL', validators=[validateURL()])
+    tags = StringTagUUID('Group tag', [validators.Optional()])
     watch_submit_button = SubmitField(_l('Watch'), render_kw={"class": "pure-button pure-button-primary"})
-    processor = RadioField(_l('Processor'), choices=lambda: processors.available_processors(), default=processors.get_default_processor)
+    processor = RadioField(_l('Processor'), choices=lambda: processors.available_processors(), default="text_json_diff")
     edit_and_watch_submit_button = SubmitField(_l('Edit > Watch'), render_kw={"class": "pure-button pure-button-primary"})
 
 
@@ -740,11 +744,12 @@ class commonSettingsForm(Form):
         self.notification_title.extra_notification_tokens = kwargs.get('extra_notification_tokens', {})
         self.notification_urls.extra_notification_tokens = kwargs.get('extra_notification_tokens', {})
 
+    fetch_backend = RadioField(_l('Fetch Method'), choices=content_fetchers.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     notification_body = TextAreaField(_l('Notification Body'), default='{{ watch_url }} had a change.', validators=[validators.Optional(), ValidateJinja2Template()])
     notification_format = SelectField(_l('Notification format'), choices=list(valid_notification_formats.items()))
     notification_title = StringField(_l('Notification Title'), default='ChangeDetection.io Notification - {{ watch_url }}', validators=[validators.Optional(), ValidateJinja2Template()])
     notification_urls = StringListField(_l('Notification URL List'), validators=[validators.Optional(), ValidateAppRiseServers(), ValidateJinja2Template()])
-    processor = RadioField( label=_l("Processor - What do you want to achieve?"), choices=lambda: processors.available_processors(), default=processors.get_default_processor)
+    processor = RadioField( label=_l("Processor - What do you want to achieve?"), choices=lambda: processors.available_processors(), default="text_json_diff")
     scheduler_timezone_default = StringField(_l("Default timezone for watch check scheduler"), render_kw={"list": "timezones"}, validators=[validateTimeZoneName()])
     webdriver_delay = IntegerField(_l('Wait seconds before extracting text'), validators=[validators.Optional(), validators.NumberRange(min=1, message=_l("Should contain one or more seconds"))])
 
@@ -758,7 +763,7 @@ class commonSettingsForm(Form):
 
 
 class importForm(Form):
-    processor = RadioField(_l('Processor'), choices=lambda: processors.available_processors(), default=processors.get_default_processor)
+    processor = RadioField(_l('Processor'), choices=lambda: processors.available_processors(), default="text_json_diff")
     urls = TextAreaField(_l('URLs'))
     xlsx_file = FileField(_l('Upload .xlsx file'), validators=[FileAllowed(['xlsx'], _l('Must be .xlsx file!'))])
     file_mapping = SelectField(_l('File mapping'), [validators.DataRequired()], choices={('wachete', 'Wachete mapping'), ('custom','Custom mapping')})
@@ -776,13 +781,11 @@ class SingleBrowserStep(Form):
 
 class processor_text_json_diff_form(commonSettingsForm):
 
-    browser_profile = RadioField(_l('Browser / Fetch method'), choices=[])  # populated at runtime in edit.py
-    url = fields.URLField('Web Page URL', validators=[validateURL()])
-    tags = StringTagUUID('Group Tag', [validators.Optional()], default='')
+    url = fields.URLField('URL', validators=[validateURL()])
+    tags = StringTagUUID('Group tag', [validators.Optional()], default='')
 
     time_between_check = EnhancedFormField(
         TimeBetweenCheckForm,
-        label=_l('Time Between Check'),
         conditional_field='time_between_check_use_default',
         conditional_message=REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT,
         conditional_test_function=validate_time_between_check_has_values
@@ -816,7 +819,8 @@ class processor_text_json_diff_form(commonSettingsForm):
     filter_text_removed = BooleanField(_l('Removed lines'), default=True)
 
     trigger_text = StringListField(_l('Keyword triggers - Trigger/wait for text'), [validators.Optional(), ValidateListRegex()])
-    browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
+    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
+        browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
     text_should_not_be_present = StringListField(_l('Block change-detection while text matches'), [validators.Optional(), ValidateListRegex()])
     webdriver_js_execute_code = TextAreaField(_l('Execute JavaScript before change detection'), render_kw={"rows": "5"}, validators=[validators.Optional()])
 
@@ -832,8 +836,6 @@ class processor_text_json_diff_form(commonSettingsForm):
     conditions = FieldList(FormField(ConditionFormRow), min_entries=1)  # Add rule logic here
     use_page_title_in_list = TernaryNoneBooleanField(_l('Use page <title> in list'), default=None)
 
-    history_snapshot_max_length = IntegerField(_l('Number of history items per watch to keep'), render_kw={"style": "width: 5em;"}, validators=[validators.Optional(), validators.NumberRange(min=2)])
-
     def extra_tab_content(self):
         return None
 
@@ -938,68 +940,14 @@ class SingleExtraBrowser(Form):
         ValidateSimpleURL()
     ], render_kw={"placeholder": "wss://brightdata... wss://oxylabs etc", "size":50})
 
-
-class BrowserProfileForm(Form):
-    """Create or edit a named BrowserProfile stored in settings.application.browser_profiles."""
-
-    name = StringField(
-        _l('Profile name'),
-        [validators.DataRequired(), validators.Length(max=100)],
-        render_kw={"placeholder": _l("e.g. Mobile Chrome, Bright Data CDP"), "maxlength": "100"}
-    )
-    fetch_backend = SelectField(
-        _l('Fetch method'),
-        choices=[],  # populated at runtime from available_fetchers()
-    )
-    browser_connection_url = StringField(
-        _l('Browser connection URL'),
-        [
-            validators.Optional(),
-            ValidateStartsWithRegex(
-                regex=r'^(wss?|ws)://',
-                flags=re.IGNORECASE,
-                message=_l('Browser connection URL must start with ws:// or wss://')
-            ),
-            ValidateSimpleURL(),
-        ],
-        render_kw={"placeholder": "ws://my-chrome:3000", "size": 50}
-    )
-    viewport_width = IntegerField(
-        _l('Viewport width (px)'),
-        [validators.Optional(), validators.NumberRange(min=100, max=7680)],
-        default=1280,
-        render_kw={"style": "width:5em;"}
-    )
-    viewport_height = IntegerField(
-        _l('Viewport height (px)'),
-        [validators.Optional(), validators.NumberRange(min=100, max=4320)],
-        default=1000,
-        render_kw={"style": "width:5em;"}
-    )
-    block_images = BooleanField(_l('Block images (faster loads)'), default=False)
-    block_fonts = BooleanField(_l('Block web fonts'), default=False)
-    ignore_https_errors = BooleanField(_l('Ignore HTTPS/TLS errors'), default=False)
-    user_agent = StringField(
-        _l('User-Agent override'),
-        [validators.Optional(), validators.Length(max=500)],
-        render_kw={"placeholder": _l("Leave blank to use fetcher default"), "size": 60}
-    )
-    locale = StringField(
-        _l('Locale'),
-        [validators.Optional(), validators.Length(max=20)],
-        render_kw={"placeholder": "en-US, de-DE, fr-FR …", "size": 15}
-    )
-
 class DefaultUAInputForm(Form):
-    requests = StringField(_l('Plaintext requests'), validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
+    html_requests = StringField(_l('Plaintext requests'), validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
     if os.getenv("PLAYWRIGHT_DRIVER_URL") or os.getenv("WEBDRIVER_URL"):
-        playwright = StringField(_l('Chrome/Playwright requests'), validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
-        selenium = StringField(_l('Chrome/Selenium requests'), validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
-        puppeteer = StringField(_l('Chrome/Puppeteer requests'), validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
+        html_webdriver = StringField(_l('Chrome requests'), validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
 
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
-    time_between_check = RequiredFormField(TimeBetweenCheckForm, label=_l('Time Between Check'))
+    time_between_check = RequiredFormField(TimeBetweenCheckForm)
     time_schedule_limit = FormField(ScheduleLimitForm)
     proxy = RadioField(_l('Default proxy'))
     jitter_seconds = IntegerField(_l('Random jitter seconds ± check'),
@@ -1043,6 +991,7 @@ class globalSettingsApplicationForm(commonSettingsForm):
                            render_kw={"placeholder": os.getenv('BASE_URL', 'Not set')}
                            )
     empty_pages_are_a_change =  BooleanField(_l('Treat empty pages as a change?'), default=False)
+    fetch_backend = RadioField(_l('Fetch Method'), default="html_requests", choices=content_fetchers.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     global_ignore_text = StringListField(_l('Ignore Text'), [ValidateListRegex()])
     global_subtractive_selectors = StringListField(_l('Remove elements'), [ValidateCSSJSONXPATHInput(allow_json=False)])
     ignore_whitespace = BooleanField(_l('Ignore whitespace'))
@@ -1058,7 +1007,7 @@ class globalSettingsApplicationForm(commonSettingsForm):
         render_kw={"placeholder": "0.1", "style": "width: 8em;"}
     )
 
-    password = SaltyPasswordField(_l('Password'), render_kw={"autocomplete": "new-password"})
+    password = SaltyPasswordField()
     pager_size = IntegerField(_l('Pager size'),
                               render_kw={"style": "width: 5em;"},
                               validators=[validators.NumberRange(min=0,
@@ -1084,8 +1033,6 @@ class globalSettingsApplicationForm(commonSettingsForm):
                                                                   render_kw={"style": "width: 5em;"},
                                                                   validators=[validators.NumberRange(min=0,
                                                                                                      message=_l("Should contain zero or more attempts"))])
-
-    history_snapshot_max_length = IntegerField(_l('Number of history items per watch to keep'), render_kw={"style": "width: 5em;"}, validators=[validators.Optional(), validators.NumberRange(min=2)])
     ui = FormField(globalSettingsApplicationUIForm)
 
 

changedetectionio/html_tools.py

@@ -23,53 +23,6 @@ class JSONNotFound(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
 
-
-_DEFAULT_UNSAFE_XPATH3_FUNCTIONS = [
-    'unparsed-text',
-    'unparsed-text-lines',
-    'unparsed-text-available',
-    'doc',
-    'doc-available',
-    'environment-variable',
-    'available-environment-variables',
-]
-
-
-def _build_safe_xpath3_parser():
-    """Return an XPath3Parser subclass with filesystem/environment access functions removed.
-
-    XPath 3.0 includes functions that can read arbitrary files or environment variables:
-      - unparsed-text / unparsed-text-lines / unparsed-text-available  (file read)
-      - doc / doc-available                                             (XML fetch from URI)
-      - environment-variable / available-environment-variables         (env var leakage)
-
-    Subclassing gives us an independent symbol_table copy (not shared with the parent class),
-    so removing entries here does not affect XPath3Parser itself.
-
-    Override the blocked list via the XPATH_BLOCKED_FUNCTIONS environment variable
-    (comma-separated, e.g. "unparsed-text,doc,environment-variable").
-    """
-    import os
-    from elementpath.xpath3 import XPath3Parser
-
-    class SafeXPath3Parser(XPath3Parser):
-        pass
-
-    env_override = os.getenv('XPATH_BLOCKED_FUNCTIONS')
-    if env_override is not None:
-        blocked = [f.strip() for f in env_override.split(',') if f.strip()]
-    else:
-        blocked = _DEFAULT_UNSAFE_XPATH3_FUNCTIONS
-
-    for _fn in blocked:
-        SafeXPath3Parser.symbol_table.pop(_fn, None)
-
-    return SafeXPath3Parser
-
-
-# Module-level singleton — built once, reused everywhere.
-SafeXPath3Parser = _build_safe_xpath3_parser()
-
 # Doesn't look like python supports forward slash auto enclosure in re.findall
 # So convert it to inline flag "(?i)foobar" type configuration
 @lru_cache(maxsize=100)
@@ -230,6 +183,8 @@ def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False
     """
     from lxml import etree, html
     import elementpath
+    # xpath 2.0-3.1
+    from elementpath.xpath3 import XPath3Parser
 
     parser = etree.HTMLParser()
     tree = None
@@ -255,7 +210,7 @@ def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False
             # This allows //title to match elements in the default namespace
             namespaces[''] = tree.nsmap[None]
 
-        r = elementpath.select(tree, xpath_filter.strip(), namespaces=namespaces, parser=SafeXPath3Parser)
+        r = elementpath.select(tree, xpath_filter.strip(), namespaces=namespaces, parser=XPath3Parser)
         #@note: //title/text() now works with default namespaces (fixed by registering '' prefix)
         #@note: //title/text() wont work where <title>CDATA.. (use cdata_in_document_to_text first)
 
@@ -280,9 +235,6 @@ def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False
             else:
                 html_block += elementpath_tostring(element)
 
-        # Drop element references before the finally block so tree.clear() can release
-        # the libxml2 document immediately (elements pin the C-level doc via refcount).
-        del r
         return html_block
     finally:
         # Explicitly clear the tree to free memory
@@ -487,25 +439,13 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
         except json.JSONDecodeError as e:
             logger.warning(f"Error processing JSON {content[:20]}...{str(e)})")
     else:
-        # Check for JSONP wrapper: someCallback({...}) or some.namespace({...})
-        # Server may claim application/json but actually return JSONP
-        jsonp_match = re.match(r'^\w[\w.]*\s*\((.+)\)\s*;?\s*$', content.lstrip("\ufeff").strip(), re.DOTALL)
-        if jsonp_match:
-            try:
-                inner = jsonp_match.group(1).strip()
-                logger.warning(f"Content looks like JSONP, attempting to extract inner JSON for filter '{json_filter}'")
-                stripped_text_from_html = _parse_json(json.loads(inner), json_filter)
-            except json.JSONDecodeError as e:
-                logger.warning(f"Error processing JSONP inner content {content[:20]}...{str(e)})")
-
-        if not stripped_text_from_html:
-            # Probably something else, go fish inside for it
-            try:
-                stripped_text_from_html = extract_json_blob_from_html(content=content,
-                                                                      ensure_is_ldjson_info_type=ensure_is_ldjson_info_type,
-                                                                      json_filter=json_filter)
-            except json.JSONDecodeError as e:
-                logger.warning(f"Error processing JSON while extracting JSON from HTML blob {content[:20]}...{str(e)})")
+        # Probably something else, go fish inside for it
+        try:
+            stripped_text_from_html = extract_json_blob_from_html(content=content,
+                                                                  ensure_is_ldjson_info_type=ensure_is_ldjson_info_type,
+                                                                  json_filter=json_filter                                                                  )
+        except json.JSONDecodeError as e:
+            logger.warning(f"Error processing JSON while extracting JSON from HTML blob {content[:20]}...{str(e)})")
 
     if not stripped_text_from_html:
         # Re 265 - Just return an empty string when filter not found
@@ -599,18 +539,6 @@ def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False
 
 
 def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=False, timeout=10) -> str:
-    """
-    Convert HTML content to plain text using inscriptis.
-
-    Thread-Safety: This function uses inscriptis.get_text() which internally calls
-    lxml.html.fromstring() with the default parser. Testing with 50 concurrent threads
-    confirms this approach is thread-safe and produces deterministic output.
-
-    Alternative Approach Rejected: An explicit HTMLParser instance (thread-local or fresh)
-    would also be thread-safe, but was found to break change detection logic in subtle ways
-    (test_check_basic_change_detection_functionality). The default parser provides correct
-    and reliable behavior.
-    """
     from inscriptis import get_text
     from inscriptis.model.config import ParserConfig
 
@@ -621,33 +549,10 @@ def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=Fals
         )
     else:
         parser_config = None
+
     if is_rss:
         html_content = re.sub(r'<title([\s>])', r'<h1\1', html_content)
         html_content = re.sub(r'</title>', r'</h1>', html_content)
-    else:
-        # Use BS4 html.parser to strip bloat — SPA's often dump 10MB+ of CSS/JS into <head>,
-        # causing inscriptis to silently give up. Regex-based stripping is unsafe because tags
-        # can appear inside JSON data attributes with JS-escaped closing tags (e.g. <\/script>),
-        # causing the regex to scan past the intended close and eat real page content.
-        from bs4 import BeautifulSoup
-        soup = BeautifulSoup(html_content, 'html.parser')
-        # Strip tags that inscriptis cannot render as meaningful text and which can be very large.
-        # svg/math: produce path-data/MathML garbage; canvas/iframe/template: no inscriptis handlers.
-        # video/audio/picture are kept — they may contain meaningful fallback text or captions.
-        for tag in soup.find_all(['head', 'script', 'style', 'noscript', 'svg',
-                                  'math', 'canvas', 'iframe', 'template']):
-            tag.decompose()
-
-        # SPAs often use <body style="display:none"> to hide content until JS loads.
-        # inscriptis respects CSS display rules, so strip hiding styles from the body tag.
-        body_tag = soup.find('body')
-        if body_tag and body_tag.get('style'):
-            style = body_tag['style']
-            if re.search(r'\b(?:display\s*:\s*none|visibility\s*:\s*hidden)\b', style, re.IGNORECASE):
-                logger.debug(f"html_to_text: Removing hiding styles from body tag (found: '{style}')")
-                del body_tag['style']
-
-        html_content = str(soup)
 
     text_content = get_text(html_content, config=parser_config)
     return text_content

changedetectionio/is_safe_url.py

@@ -1,113 +0,0 @@
-"""
-URL redirect validation module for preventing open redirect vulnerabilities.
-
-This module provides functionality to safely validate redirect URLs, ensuring they:
-1. Point to internal routes only (no external redirects)
-2. Are properly normalized (preventing browser parsing differences)
-3. Match registered Flask routes (no fake/non-existent pages)
-4. Are fully logged for security monitoring
-
-References:
-- https://flask-login.readthedocs.io/ (safe redirect patterns)
-- https://blog.miguelgrinberg.com/post/the-flask-mega-tutorial-part-v-user-logins
-- https://www.pythonkitchen.com/how-prevent-open-redirect-vulnerab-flask/
-"""
-
-from urllib.parse import urlparse, urljoin
-from flask import request
-from loguru import logger
-
-
-def is_safe_url(target, app):
-    """
-    Validate that a redirect URL is safe to prevent open redirect vulnerabilities.
-
-    This follows Flask/Werkzeug best practices by ensuring the redirect URL:
-    1. Is a relative path starting with exactly one '/'
-    2. Does not start with '//' (double-slash attack)
-    3. Has no external protocol handlers
-    4. Points to a valid registered route in the application
-    5. Is properly normalized to prevent browser parsing differences
-
-    Args:
-        target: The URL to validate (e.g., '/settings', '/login#top')
-        app: The Flask application instance (needed for route validation)
-
-    Returns:
-        bool: True if the URL is safe for redirection, False otherwise
-
-    Examples:
-        >>> is_safe_url('/settings', app)
-        True
-        >>> is_safe_url('//evil.com', app)
-        False
-        >>> is_safe_url('/settings#general', app)
-        True
-        >>> is_safe_url('/fake-page', app)
-        False
-    """
-    if not target:
-        return False
-
-    # Normalize the URL to prevent browser parsing differences
-    # Strip whitespace and replace backslashes (which some browsers interpret as forward slashes)
-    target = target.strip()
-    target = target.replace('\\', '/')
-
-    # First, check if it starts with // or more (double-slash attack)
-    if target.startswith('//'):
-        logger.warning(f"Blocked redirect attempt with double-slash: {target}")
-        return False
-
-    # Parse the URL to check for scheme and netloc
-    parsed = urlparse(target)
-
-    # Block any URL with a scheme (http://, https://, javascript:, etc.)
-    if parsed.scheme:
-        logger.warning(f"Blocked redirect attempt with scheme: {target}")
-        return False
-
-    # Block any URL with a network location (netloc)
-    # This catches patterns like //evil.com, user@host, etc.
-    if parsed.netloc:
-        logger.warning(f"Blocked redirect attempt with netloc: {target}")
-        return False
-
-    # At this point, we have a relative URL with no scheme or netloc
-    # Use urljoin to resolve it and verify it points to the same host
-    ref_url = urlparse(request.host_url)
-    test_url = urlparse(urljoin(request.host_url, target))
-
-    # Check: ensure the resolved URL has the same netloc as current host
-    if not (test_url.scheme in ('http', 'https') and ref_url.netloc == test_url.netloc):
-        logger.warning(f"Blocked redirect attempt with mismatched netloc: {target}")
-        return False
-
-    # Additional validation: Check if the URL matches a registered route
-    # This prevents redirects to non-existent pages or unintended endpoints
-    try:
-        # Get the path without query string and fragment
-        # Fragments (like #general) are automatically stripped by urlparse
-        path = parsed.path
-
-        # Create a URL adapter bound to the server name
-        adapter = app.url_map.bind(ref_url.netloc)
-
-        # Try to match the path to a registered route
-        # This will raise NotFound if the route doesn't exist
-        endpoint, values = adapter.match(path, return_rule=False)
-
-        # Block redirects to static file endpoints - these are catch-all routes
-        # that would match arbitrary paths, potentially allowing unintended redirects
-        if endpoint in ('static_content', 'static', 'static_flags'):
-            logger.warning(f"Blocked redirect to static endpoint: {target}")
-            return False
-
-        # Successfully matched a valid route
-        logger.debug(f"Validated safe redirect to endpoint '{endpoint}': {target}")
-        return True
-
-    except Exception as e:
-        # Route doesn't exist or can't be matched
-        logger.warning(f"Blocked redirect to non-existent route: {target} (error: {e})")
-        return False

changedetectionio/jinja2_custom/safe_jinja.py

@@ -52,13 +52,7 @@ def render(template_str, **args: t.Any) -> str:
     return output[:JINJA2_MAX_RETURN_PAYLOAD_SIZE]
 
 def render_fully_escaped(content):
-    """
-    Escape HTML content safely.
-
-    MEMORY LEAK FIX: Use markupsafe.escape() directly instead of creating
-    Jinja2 environments (was causing 1M+ compilations per page load).
-    Simpler, faster, and no concerns about environment state.
-    """
-    from markupsafe import escape
-    return str(escape(content))
+    env = jinja2.sandbox.ImmutableSandboxedEnvironment(autoescape=True)
+    template = env.from_string("{{ some_html|e }}")
+    return template.render(some_html=content)
 

changedetectionio/languages.py

@@ -29,25 +29,18 @@ def get_timeago_locale(flask_locale):
     """
     locale_map = {
         'zh': 'zh_CN',      # Chinese Simplified
-        # timeago library just hasn't been updated to use the more modern locale naming convention, before BCP 47 / RFC 5646.
-        'zh_TW': 'zh_TW',   # Chinese Traditional (timeago uses zh_TW)
-        'zh_Hant_TW': 'zh_TW',  # Flask-Babel normalizes zh_TW to zh_Hant_TW, map back to timeago's zh_TW
         'pt': 'pt_PT',      # Portuguese (Portugal)
         'sv': 'sv_SE',      # Swedish
         'no': 'nb_NO',      # Norwegian Bokmål
         'hi': 'in_HI',      # Hindi
         'cs': 'en',         # Czech not supported by timeago, fallback to English
-        'uk': 'uk',         # Ukrainian
-        'en_GB': 'en',      # British English - timeago uses 'en'
-        'en_US': 'en',      # American English - timeago uses 'en'
     }
     return locale_map.get(flask_locale, flask_locale)
 
 # Language metadata: flag icon CSS class and native name
 # Using flag-icons library: https://flagicons.lipis.dev/
 LANGUAGE_DATA = {
-    'en_GB': {'flag': 'fi fi-gb fis', 'name': 'English (UK)'},
-    'en_US': {'flag': 'fi fi-us fis', 'name': 'English (US)'},
+    'en': {'flag': 'fi fi-gb fis', 'name': 'English'},
     'de': {'flag': 'fi fi-de fis', 'name': 'Deutsch'},
     'fr': {'flag': 'fi fi-fr fis', 'name': 'Français'},
     'ko': {'flag': 'fi fi-kr fis', 'name': '한국어'},
@@ -57,7 +50,7 @@ LANGUAGE_DATA = {
     'it': {'flag': 'fi fi-it fis', 'name': 'Italiano'},
     'ja': {'flag': 'fi fi-jp fis', 'name': '日本語'},
     'zh': {'flag': 'fi fi-cn fis', 'name': '中文 (简体)'},
-    'zh_Hant_TW': {'flag': 'fi fi-tw fis', 'name': '繁體中文'},
+    'zh_TW': {'flag': 'fi fi-tw fis', 'name': '繁體中文'},
     'ru': {'flag': 'fi fi-ru fis', 'name': 'Русский'},
     'pl': {'flag': 'fi fi-pl fis', 'name': 'Polski'},
     'nl': {'flag': 'fi fi-nl fis', 'name': 'Nederlands'},
@@ -68,7 +61,6 @@ LANGUAGE_DATA = {
     'tr': {'flag': 'fi fi-tr fis', 'name': 'Türkçe'},
     'ar': {'flag': 'fi fi-sa fis', 'name': 'العربية'},
     'hi': {'flag': 'fi fi-in fis', 'name': 'हिन्दी'},
-    'uk': {'flag': 'fi fi-ua fis', 'name': 'Українська'},
 }
 
 
@@ -79,7 +71,10 @@ def get_available_languages():
     """
     translations_dir = Path(__file__).parent / 'translations'
 
-    available = {}
+    # Always include English as base language
+    available = {
+        'en': LANGUAGE_DATA['en']
+    }
 
     # Scan for translation directories
     if translations_dir.exists():
@@ -90,10 +85,6 @@ def get_available_languages():
                 if po_file.exists():
                     available[lang_dir.name] = LANGUAGE_DATA[lang_dir.name]
 
-    # If no English variants found, fall back to adding en_GB as default
-    if 'en_GB' not in available and 'en_US' not in available:
-        available['en_GB'] = LANGUAGE_DATA['en_GB']
-
     return available
 
 

changedetectionio/model/App.py

@@ -2,7 +2,6 @@ from os import getenv
 from copy import deepcopy
 
 from changedetectionio.blueprint.rss import RSS_FORMAT_TYPES, RSS_CONTENT_FORMAT_DEFAULT
-from changedetectionio.model.Tags import TagsDict
 
 from changedetectionio.notification import (
     default_notification_body,
@@ -30,28 +29,21 @@ class model(dict):
                     'proxy': None, # Preferred proxy connection
                     'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
                     'timeout': int(getenv("DEFAULT_SETTINGS_REQUESTS_TIMEOUT", "45")),  # Default 45 seconds
-                    'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "5")),  # Number of threads, lower is better for slow connections
+                    'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "10")),  # Number of threads, lower is better for slow connections
                     'default_ua': {
-                        'requests': getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT", DEFAULT_SETTINGS_HEADERS_USERAGENT),
-                        'playwright': None,
-                        'selenium': None,
-                        'puppeteer': None,
+                        'html_requests': getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT", DEFAULT_SETTINGS_HEADERS_USERAGENT),
+                        'html_webdriver': None,
                     }
                 },
                 'application': {
                     # Custom notification content
-                    'all_paused': False,
-                    'all_muted': False,
                     'api_access_token_enabled': True,
                     'base_url' : None,
                     'empty_pages_are_a_change': False,
-                    'browser_profile': None,           # machine-name of the system-default BrowserProfile
-                    'browser_profiles': {},            # user-defined profiles keyed by machine name
-                    'fetch_backend': getenv("DEFAULT_FETCH_BACKEND", "requests"),
+                    'fetch_backend': getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
                     'filter_failure_notification_threshold_attempts': _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT,
                     'global_ignore_text': [], # List of text to ignore when calculating the comparison checksum
                     'global_subtractive_selectors': [],
-                    'history_snapshot_max_length': None,
                     'ignore_whitespace': True,
                     'ignore_status_codes': False, #@todo implement, as ternary.
                     'ssim_threshold': '0.96',  # Default SSIM threshold for screenshot comparison
@@ -73,7 +65,7 @@ class model(dict):
                     'schema_version' : 0,
                     'shared_diff_access': False,
                     'strip_ignored_lines': False,
-                    'tags': None,  # Initialized in __init__ with real datastore_path
+                    'tags': {}, #@todo use Tag.model initialisers
                     'webdriver_delay': None , # Extra delay in seconds before extracting text
                     'ui': {
                         'use_page_title_in_list': True,
@@ -85,16 +77,10 @@ class model(dict):
             }
         }
 
-    def __init__(self, *arg, datastore_path=None, **kw):
+    def __init__(self, *arg, **kw):
         super(model, self).__init__(*arg, **kw)
-        # Capture any tags data passed in before base_config overwrites the structure
-        existing_tags = self.get('settings', {}).get('application', {}).get('tags') or {}
         # CRITICAL: deepcopy to avoid sharing mutable objects between instances
         self.update(deepcopy(self.base_config))
-        # TagsDict requires the real datastore_path at runtime (cannot be set at class-definition time)
-        if datastore_path is None:
-            raise ValueError("App.model() requires 'datastore_path' keyword argument")
-        self['settings']['application']['tags'] = TagsDict(existing_tags, datastore_path=datastore_path)
 
 
 def parse_headers_from_text_file(filepath):

changedetectionio/model/Tag.py

@@ -1,48 +1,10 @@
-"""
-Tag/Group domain model for organizing and overriding watch settings.
-
-ARCHITECTURE NOTE: Configuration Override Hierarchy
-===================================================
-
-Tags can override Watch settings when overrides_watch=True.
-Current implementation requires manual checking in processors:
-
-    for tag_uuid in watch.get('tags'):
-        tag = datastore['settings']['application']['tags'][tag_uuid]
-        if tag.get('overrides_watch'):
-            restock_settings = tag.get('restock_settings', {})
-            break
-
-With Pydantic, this would be automatic via chain resolution:
-    Watch → Tag (first with overrides_watch) → Global
-
-See: Watch.py model docstring for full Pydantic architecture explanation
-See: processors/restock_diff/processor.py:184-192 for current manual implementation
-"""
 
 from changedetectionio.model import watch_base
-from changedetectionio.model.persistence import EntityPersistenceMixin
 
-class model(EntityPersistenceMixin, watch_base):
-    """
-    Tag domain model - groups watches and can override their settings.
 
-    Tags inherit from watch_base to reuse all the same fields as Watch.
-    When overrides_watch=True, tag settings take precedence over watch settings
-    for all watches in this tag/group.
-
-    Fields:
-        overrides_watch (bool): If True, this tag's settings override watch settings
-        title (str): Display name for this tag/group
-        uuid (str): Unique identifier
-        ... (all fields from watch_base can be set as tag-level overrides)
-
-    Resolution order when overrides_watch=True:
-        Watch.field → Tag.field (if overrides_watch) → Global.field
-    """
+class model(watch_base):
 
     def __init__(self, *arg, **kw):
-        # Parent class (watch_base) handles __datastore and __datastore_path
         super(model, self).__init__(*arg, **kw)
 
         self['overrides_watch'] = kw.get('default', {}).get('overrides_watch')
@@ -50,7 +12,3 @@ class model(EntityPersistenceMixin, watch_base):
         if kw.get('default'):
             self.update(kw['default'])
             del kw['default']
-
-    # _save_to_disk() method provided by EntityPersistenceMixin
-    # commit() and _get_commit_data() methods inherited from watch_base
-    # Tag uses default _get_commit_data() (includes all keys)

changedetectionio/model/Tags.py

@@ -1,39 +0,0 @@
-import os
-import shutil
-from pathlib import Path
-from loguru import logger
-
-_SENTINEL = object()
-
-
-class TagsDict(dict):
-    """Dict subclass that removes the corresponding tag.json file when a tag is deleted."""
-
-    def __init__(self, *args, datastore_path: str | os.PathLike, **kwargs) -> None:
-        self._datastore_path = Path(datastore_path)
-        super().__init__(*args, **kwargs)
-
-    def __delitem__(self, key: str) -> None:
-        super().__delitem__(key)
-        tag_dir = self._datastore_path / key
-        tag_json_file = tag_dir / "tag.json"
-        if not os.path.exists(tag_json_file):
-            logger.critical(f"Aborting deletion of directory '{tag_dir}' because '{tag_json_file}' does not exist.")
-            return
-        try:
-            shutil.rmtree(tag_dir)
-            logger.info(f"Deleted tag directory for tag {key!r}")
-        except FileNotFoundError:
-            pass
-        except OSError as e:
-            logger.error(f"Failed to delete tag directory for tag {key!r}: {e}")
-
-    def pop(self, key: str, default=_SENTINEL):
-        """Remove and return tag, deleting its tag.json file. Raises KeyError if missing and no default given."""
-        if key in self:
-            value = self[key]
-            del self[key]
-            return value
-        if default is _SENTINEL:
-            raise KeyError(key)
-        return default

changedetectionio/model/Watch.py

@@ -1,66 +1,63 @@
-"""
-Watch domain model for change detection monitoring.
-
-ARCHITECTURE NOTE: Configuration Override Hierarchy
-===================================================
-
-This module implements Watch objects that inherit from dict (technical debt).
-The dream architecture would use Pydantic for:
-
-1. CHAIN RESOLUTION (Watch → Tag → Global Settings)
-   - Current: Manual resolution scattered across codebase
-   - Future: @computed_field properties with automatic resolution
-   - Examples: resolved_fetch_backend, resolved_restock_settings, etc.
-
-2. DATABASE BACKEND ABSTRACTION
-   - Current: Domain model tightly coupled to file-based JSON storage
-   - Future: Domain model (Pydantic) separate from persistence layer
-   - Enables: Easy migration to PostgreSQL, MongoDB, etc.
-
-3. TYPE SAFETY & VALIDATION
-   - Current: Dict access with no compile-time checks
-   - Future: Type hints, IDE autocomplete, validation at boundaries
-
-See class model docstring for detailed explanation and examples.
-See: processors/restock_diff/processor.py:184-192 for manual resolution example
-"""
-
 from blinker import signal
 from changedetectionio.validate_url import is_safe_valid_url
 
 from changedetectionio.strtobool import strtobool
 from changedetectionio.jinja2_custom import render as jinja_render
 from . import watch_base
-from .persistence import EntityPersistenceMixin
 import os
 import re
 from pathlib import Path
 from loguru import logger
 
 from .. import jinja2_custom as safe_jinja
+from ..diff import ADDED_PLACEMARKER_OPEN
 from ..html_tools import TRANSLATE_WHITESPACE_TABLE
 
-FAVICON_RESAVE_THRESHOLD_SECONDS=86400
-BROTLI_COMPRESS_SIZE_THRESHOLD = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024*20))
 
-# Module-level favicon filename cache: data_dir → basename (or None)
-# Keyed by data_dir so it survives Watch object recreation, deepcopy, and concurrent requests.
-# Invalidated explicitly in bump_favicon() when a new favicon is saved.
-_FAVICON_FILENAME_CACHE: dict = {}
-
-minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3))
-mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
-
-def _brotli_save(contents, filepath, mode=None, fallback_uncompressed=False):
+def _brotli_compress_worker(conn, filepath, mode=None):
     """
-    Save compressed data using native brotli with streaming compression.
-    Uses chunked compression to minimize peak memory usage and malloc_trim()
-    to force release of C-level memory back to the OS.
+    Worker function to compress data with brotli in a separate process.
+    This isolates memory - when process exits, OS reclaims all memory.
+
+    Args:
+        conn: multiprocessing.Pipe connection to receive data
+        filepath: destination file path
+        mode: brotli compression mode (e.g., brotli.MODE_TEXT)
+    """
+    import brotli
+
+    try:
+        # Receive data from parent process via pipe (avoids pickle overhead)
+        contents = conn.recv()
+
+        if mode is not None:
+            compressed_data = brotli.compress(contents, mode=mode)
+        else:
+            compressed_data = brotli.compress(contents)
+
+        with open(filepath, 'wb') as f:
+            f.write(compressed_data)
+
+        # Send success status back
+        conn.send(True)
+        # No need for explicit cleanup - process exit frees all memory
+    except Exception as e:
+        logger.error(f"Brotli compression worker failed: {e}")
+        conn.send(False)
+    finally:
+        conn.close()
+
+
+def _brotli_subprocess_save(contents, filepath, mode=None, timeout=30, fallback_uncompressed=False):
+    """
+    Save compressed data using subprocess to isolate memory.
+    Uses Pipe to avoid pickle overhead for large data.
 
     Args:
         contents: data to compress (str or bytes)
         filepath: destination file path
         mode: brotli compression mode (e.g., brotli.MODE_TEXT)
+        timeout: subprocess timeout in seconds
         fallback_uncompressed: if True, save uncompressed on failure; if False, raise exception
 
     Returns:
@@ -70,175 +67,100 @@ def _brotli_save(contents, filepath, mode=None, fallback_uncompressed=False):
         Exception: if compression fails and fallback_uncompressed is False
     """
     import brotli
-    import gc
-    import ctypes
+    import multiprocessing
+    import sys
 
     # Ensure contents are bytes
     if isinstance(contents, str):
         contents = contents.encode('utf-8')
 
+    # Use explicit spawn context for thread safety (avoids fork() with multi-threaded parent)
+    # Always use spawn - consistent behavior in tests and production
+    ctx = multiprocessing.get_context('spawn')
+    parent_conn, child_conn = ctx.Pipe()
+
+    # Run compression in subprocess using spawn (not fork)
+    proc = ctx.Process(target=_brotli_compress_worker, args=(child_conn, filepath, mode))
+
+    # Windows-safe: Set daemon=False explicitly to avoid issues with process cleanup
+    proc.daemon = False
+    proc.start()
+
     try:
-        original_size = len(contents)
-        logger.debug(f"Starting brotli streaming compression of {original_size} bytes.")
+        # Send data to subprocess via pipe (avoids pickle)
+        parent_conn.send(contents)
 
-        # Create streaming compressor
-        compressor = brotli.Compressor(quality=6, mode=mode if mode is not None else brotli.MODE_GENERIC)
+        # Wait for result with timeout
+        if parent_conn.poll(timeout):
+            success = parent_conn.recv()
+        else:
+            success = False
+            logger.warning(f"Brotli compression subprocess timed out after {timeout}s")
+            # Graceful termination with platform-aware cleanup
+            try:
+                proc.terminate()
+            except Exception as term_error:
+                logger.debug(f"Process termination issue (may be normal on Windows): {term_error}")
 
-        # Stream compress in chunks to minimize memory usage
-        chunk_size = 65536  # 64KB chunks
-        total_compressed_size = 0
+        parent_conn.close()
+        proc.join(timeout=5)
 
-        with open(filepath, 'wb') as f:
-            # Process data in chunks
-            offset = 0
-            while offset < len(contents):
-                chunk = contents[offset:offset + chunk_size]
-                compressed_chunk = compressor.process(chunk)
-                if compressed_chunk:
-                    f.write(compressed_chunk)
-                    total_compressed_size += len(compressed_chunk)
-                offset += chunk_size
+        # Force kill if still alive after graceful termination
+        if proc.is_alive():
+            try:
+                if sys.platform == 'win32':
+                    # Windows: use kill() which is more forceful
+                    proc.kill()
+                else:
+                    # Unix: terminate() already sent SIGTERM, now try SIGKILL
+                    proc.kill()
+                proc.join(timeout=2)
+            except Exception as kill_error:
+                logger.warning(f"Failed to kill brotli compression process: {kill_error}")
 
-            # Finalize compression - critical for proper cleanup
-            final_chunk = compressor.finish()
-            if final_chunk:
-                f.write(final_chunk)
-                total_compressed_size += len(final_chunk)
-
-        logger.debug(f"Finished brotli compression - From {original_size} to {total_compressed_size} bytes.")
-
-        # Cleanup: Delete compressor, force Python GC, then force C-level memory release
-        del compressor
-        gc.collect()
-
-        # Force release of C-level memory back to OS (since brotli is a C library)
-        try:
-            ctypes.CDLL('libc.so.6').malloc_trim(0)
-        except Exception:
-            pass  # malloc_trim not available on all systems (e.g., macOS)
-
-        return filepath
+        # Check if file was created successfully
+        if success and os.path.exists(filepath):
+            return filepath
 
     except Exception as e:
         logger.error(f"Brotli compression error: {e}")
+        try:
+            parent_conn.close()
+        except:
+            pass
+        try:
+            proc.terminate()
+            proc.join(timeout=2)
+        except:
+            pass
 
-        # Compression failed
-        if fallback_uncompressed:
-            logger.warning(f"Brotli compression failed for {filepath}, saving uncompressed")
-            fallback_path = filepath.replace('.br', '')
-            with open(fallback_path, 'wb') as f:
-                f.write(contents)
-            return fallback_path
-        else:
-            raise Exception(f"Brotli compression failed for {filepath}: {e}")
+    # Compression failed
+    if fallback_uncompressed:
+        logger.warning(f"Brotli compression failed for {filepath}, saving uncompressed")
+        fallback_path = filepath.replace('.br', '')
+        with open(fallback_path, 'wb') as f:
+            f.write(contents)
+        return fallback_path
+    else:
+        raise Exception(f"Brotli compression subprocess failed for {filepath}")
+
+FAVICON_RESAVE_THRESHOLD_SECONDS=86400
 
 
-class model(EntityPersistenceMixin, watch_base):
-    """
-    Watch domain model for monitoring URL changes.
+minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3))
+mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
 
-    Inherits from watch_base (which inherits dict) - see watch_base docstring for field documentation.
-
-    ## Configuration Override Hierarchy (Chain Resolution)
-
-    The dream architecture uses a 3-level resolution chain:
-        Watch settings → Tag/Group settings → Global settings
-
-    Current implementation is MANUAL (see processor.py:184-192 for example):
-        - Processors manually check watch.get('field')
-        - Then loop through watch.tags to find first tag with overrides_watch=True
-        - Finally fall back to datastore['settings']['application']['field']
-
-    FUTURE: Pydantic-based chain resolution would enable:
-
-        ```python
-        # Instead of manual resolution in every processor:
-        restock_settings = watch.get('restock_settings', {})
-        for tag_uuid in watch.get('tags'):
-            tag = datastore['settings']['application']['tags'][tag_uuid]
-            if tag.get('overrides_watch'):
-                restock_settings = tag.get('restock_settings', {})
-                break
-
-        # Clean computed properties with automatic resolution:
-        @computed_field
-        def resolved_restock_settings(self) -> dict:
-            if self.restock_settings:
-                return self.restock_settings
-            for tag_uuid in self.tags:
-                tag = self._datastore.get_tag(tag_uuid)
-                if tag.overrides_watch and tag.restock_settings:
-                    return tag.restock_settings
-            return self._datastore.settings.restock_settings or {}
-
-        # Usage: watch.resolved_restock_settings (automatic, type-safe, tested once)
-        ```
-
-    Benefits of Pydantic migration:
-        1. Single source of truth for resolution logic (not scattered across processors)
-        2. Type safety + IDE autocomplete (watch.resolved_fetch_backend vs dict navigation)
-        3. Database backend abstraction (domain model separate from persistence)
-        4. Automatic validation at boundaries
-        5. Self-documenting via type hints
-        6. Easy to test resolution independently
-
-    Resolution chain examples that would benefit:
-        - fetch_backend: watch → tag → global (see get_fetch_backend property)
-        - notification_urls: watch → tag → global
-        - time_between_check: watch → global (see threshold_seconds)
-        - restock_settings: watch → tag (see processors/restock_diff/processor.py:184-192)
-        - history_snapshot_max_length: watch → global (see save_history_blob:550-556)
-        - All processor_config_* settings could use tag overrides
-
-    ## Database Backend Abstraction with Pydantic
-
-    Current: Watch inherits dict, tightly coupled to file-based JSON storage
-    Future: Domain model (Watch) separate from persistence layer
-
-        ```python
-        # Domain model (database-agnostic)
-        class Watch(BaseModel):
-            uuid: str
-            url: str
-            # ... validation, business logic
-
-        # Pluggable backends
-        class DataStoreBackend(ABC):
-            def save_watch(self, watch: Watch): ...
-            def load_watch(self, uuid: str) -> Watch: ...
-
-        # Implementations: FileBackend, MongoBackend, PostgresBackend, etc.
-        ```
-
-    This would enable:
-        - Easy migration between storage backends (file → postgres → mongodb)
-        - Pydantic handles serialization/deserialization automatically
-        - Domain logic stays clean (no storage concerns in Watch methods)
-
-    ## Migration Path
-
-    Given existing codebase, incremental migration recommended:
-        1. Create Pydantic models alongside existing dict-based models
-        2. Add .to_pydantic() / .from_pydantic() bridge methods
-        3. Gradually migrate code to use Pydantic models
-        4. Remove dict inheritance once migration complete
-
-    See: watch_base docstring for technical debt discussion
-    See: processors/restock_diff/processor.py:184-192 for manual resolution example
-    See: Watch.py:550-556 for nested dict navigation that would become watch.resolved_*
-    """
+class model(watch_base):
     __newest_history_key = None
     __history_n = 0
     jitter_seconds = 0
 
     def __init__(self, *arg, **kw):
-        # Validate __datastore before calling parent (Watch requires it)
-        if not kw.get('__datastore'):
-            raise ValueError("Watch object requires '__datastore' reference - cannot access global settings without it")
-
-        # Parent class (watch_base) handles __datastore and __datastore_path
+        self.__datastore_path = kw.get('datastore_path')
+        if kw.get('datastore_path'):
+            del kw['datastore_path']
+            
         super(model, self).__init__(*arg, **kw)
-
         if kw.get('default'):
             self.update(kw['default'])
             del kw['default']
@@ -249,9 +171,6 @@ class model(EntityPersistenceMixin, watch_base):
         # Be sure the cached timestamp is ready
         bump = self.history
 
-    # Note: __deepcopy__, __getstate__, and __setstate__ are inherited from watch_base
-    # This prevents memory leaks by sharing __datastore reference instead of copying it
-
     @property
     def viewed(self):
         # Don't return viewed when last_viewed is 0 and newest_key is 0
@@ -264,6 +183,11 @@ class model(EntityPersistenceMixin, watch_base):
     def has_unviewed(self):
         return int(self.newest_history_key) > int(self['last_viewed']) and self.__history_n >= 2
 
+    def ensure_data_dir_exists(self):
+        if not os.path.isdir(self.watch_data_dir):
+            logger.debug(f"> Creating data dir {self.watch_data_dir}")
+            os.mkdir(self.watch_data_dir)
+
     @property
     def link(self):
 
@@ -319,8 +243,7 @@ class model(EntityPersistenceMixin, watch_base):
 
         # JSON Data, Screenshots, Textfiles (history index and snapshots), HTML in the future etc
         # But preserve processor config files (they're configuration, not history data)
-        # Use glob not rglob here for safety.
-        for item in pathlib.Path(str(self.data_dir)).glob("*.*"):
+        for item in pathlib.Path(str(self.watch_data_dir)).rglob("*.*"):
             # Skip processor config files
             if item.name in processor_config_files:
                 continue
@@ -340,6 +263,7 @@ class model(EntityPersistenceMixin, watch_base):
             'last_notification_error': False,
             'last_viewed': 0,
             'previous_md5': False,
+            'previous_md5_before_filters': False,
             'remote_server_reply': None,
             'track_ldjson_price_data': None
         })
@@ -353,53 +277,25 @@ class model(EntityPersistenceMixin, watch_base):
     def is_source_type_url(self):
         return self.get('url', '').startswith('source:')
 
-    @property
-    def effective_browser_profile(self):
-        """Resolve the effective BrowserProfile for this watch.
-
-        Walks the chain: watch → tag (overrides_watch=True) → global settings → built-in fallback.
-        Never raises. Returns a BrowserProfile instance.
-        """
-        from changedetectionio.model.browser_profile import resolve_browser_profile, BUILTIN_REQUESTS
-        if not self._datastore:
-            return BUILTIN_REQUESTS
-        try:
-            return resolve_browser_profile(self, self._datastore)
-        except Exception:
-            return BUILTIN_REQUESTS
-
     @property
     def get_fetch_backend(self):
-        """Legacy property — prefer effective_browser_profile.fetch_backend for new code.
-
-        Returns the raw fetch_backend stored on this watch (or 'requests' for PDFs).
-        Does NOT walk the tag/global resolution chain.
         """
+        Like just using the `fetch_backend` key but there could be some logic
+        :return:
+        """
+        # Maybe also if is_image etc?
+        # This is because chrome/playwright wont render the PDF in the browser and we will just fetch it and use pdf2html to see the text.
         if self.is_pdf:
-            return 'requests'
+            return 'html_requests'
+
         return self.get('fetch_backend')
 
-    @property
-    def fetcher_supports_screenshots(self):
-        """Return True if the resolved fetcher for this watch supports screenshots."""
-        from changedetectionio import content_fetchers
-        fetcher_class = content_fetchers.get_fetcher(self.effective_browser_profile.fetch_backend)
-        if fetcher_class is None:
-            return False
-        return bool(getattr(fetcher_class, 'supports_screenshots', False))
-
     @property
     def is_pdf(self):
-        url = str(self.get("url") or "").lower()
-        content_type = str(self.get("content-type") or "").lower()
-
-        if content_type in ("none", "null", ""):
-            content_type = ""
-
-        return (
-                url.endswith(".pdf")
-                or content_type.split(";")[0].strip() == "application/pdf"
-        )
+        # content_type field is set in the future
+        # https://github.com/dgtlmoon/changedetection.io/issues/1392
+        # Not sure the best logic here
+        return self.get('url', '').lower().endswith('.pdf') or 'pdf' in self.get('content_type', '').lower()
 
     @property
     def label(self):
@@ -434,11 +330,11 @@ class model(EntityPersistenceMixin, watch_base):
         tmp_history = {}
 
         # In the case we are only using the watch for processing without history
-        if not self.data_dir:
+        if not self.watch_data_dir:
             return []
 
         # Read the history file as a dict
-        fname = os.path.join(self.data_dir, self.history_index_filename)
+        fname = os.path.join(self.watch_data_dir, self.history_index_filename)
         if os.path.isfile(fname):
             logger.debug(f"Reading watch history index for {self.get('uuid')}")
             with open(fname, "r", encoding='utf-8') as f:
@@ -451,13 +347,13 @@ class model(EntityPersistenceMixin, watch_base):
                         # Cross-platform: check for any path separator (works on Windows and Unix)
                         if os.sep not in v and '/' not in v and '\\' not in v:
                             # Relative filename only, no path separators
-                            v = os.path.join(self.data_dir, v)
+                            v = os.path.join(self.watch_data_dir, v)
                         else:
                             # It's possible that they moved the datadir on older versions
                             # So the snapshot exists but is in a different path
                             # Cross-platform: use os.path.basename instead of split('/')
                             snapshot_fname = os.path.basename(v)
-                            proposed_new_path = os.path.join(self.data_dir, snapshot_fname)
+                            proposed_new_path = os.path.join(self.watch_data_dir, snapshot_fname)
                             if not os.path.exists(v) and os.path.exists(proposed_new_path):
                                 v = proposed_new_path
 
@@ -474,7 +370,7 @@ class model(EntityPersistenceMixin, watch_base):
 
     @property
     def has_history(self):
-        fname = os.path.join(self.data_dir, self.history_index_filename)
+        fname = os.path.join(self.watch_data_dir, self.history_index_filename)
         return os.path.isfile(fname)
 
     @property
@@ -577,49 +473,16 @@ class model(EntityPersistenceMixin, watch_base):
         with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
             return f.read()
 
-    def _write_atomic(self, dest, data, mode='wb'):
+    def _write_atomic(self, dest, data):
         """Write data atomically to dest using a temp file"""
-        import tempfile
-        with tempfile.NamedTemporaryFile(mode, delete=False, dir=self.data_dir) as tmp:
-            tmp.write(data)
-            tmp.flush()
-            os.fsync(tmp.fileno())
-            tmp_path = tmp.name
-        os.replace(tmp_path, dest)
-
-    def history_trim(self, newest_n_items):
-        from pathlib import Path
-        import gc
-        # Sort by timestamp (key)
-        sorted_items = sorted(self.history.items(), key=lambda x: int(x[0]))
-
-        keep_part = dict(sorted_items[-newest_n_items:])
-        delete_part = dict(sorted_items[:-newest_n_items])
-        logger.info( f"[{self.get('uuid')}] Trimming history to most recent {newest_n_items} items, keeping {len(keep_part)} items deleting {len(delete_part)} items.")
-
-        if delete_part:
-            for item in delete_part.items():
-                try:
-                    Path(item[1]).unlink(missing_ok=True)
-                except Exception as e:
-                    logger.critical(f"{str(e)}")
-                finally:
-                    logger.debug(f"[{self.get('uuid')}] Deleted {item[1]} history snapshot")
-        try:
-            dest = os.path.join(self.data_dir, self.history_index_filename)
-            output = "\r\n".join(
-                f"{k},{Path(v).name}"
-                for k, v in keep_part.items()
-            )+"\r\n"
-            self._write_atomic(dest=dest, data=output, mode='w')
-        except Exception as e:
-            logger.critical(f"{str(e)}")
-        finally:
-            logger.debug(f"[{self.get('uuid')}] Updated history index {dest}")
-
-        # reimport
-        bump = self.history
-        gc.collect()
+        if not os.path.exists(dest):
+            import tempfile
+            with tempfile.NamedTemporaryFile('wb', delete=False, dir=self.watch_data_dir) as tmp:
+                tmp.write(data)
+                tmp.flush()
+                os.fsync(tmp.fileno())
+                tmp_path = tmp.name
+            os.replace(tmp_path, dest)
 
     # Save some text file to the appropriate path and bump the history
     # result_obj from fetch_site_status.run()
@@ -628,6 +491,8 @@ class model(EntityPersistenceMixin, watch_base):
         logger.trace(f"{self.get('uuid')} - Updating {self.history_index_filename} with timestamp {timestamp}")
 
         self.ensure_data_dir_exists()
+
+        threshold = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
         skip_brotli = strtobool(os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False'))
 
         # Binary data - detect file type and save without compression
@@ -645,37 +510,37 @@ class model(EntityPersistenceMixin, watch_base):
                 ext = 'bin'
 
             snapshot_fname = f"{snapshot_id}.{ext}"
-            dest = os.path.join(self.data_dir, snapshot_fname)
+            dest = os.path.join(self.watch_data_dir, snapshot_fname)
             self._write_atomic(dest, contents)
             logger.trace(f"Saved binary snapshot as {snapshot_fname} ({len(contents)} bytes)")
 
         # Text data - use brotli compression if enabled and above threshold
         else:
-            if not skip_brotli and len(contents) > BROTLI_COMPRESS_SIZE_THRESHOLD:
+            if not skip_brotli and len(contents) > threshold:
                 # Compressed text
                 import brotli
                 snapshot_fname = f"{snapshot_id}.txt.br"
-                dest = os.path.join(self.data_dir, snapshot_fname)
+                dest = os.path.join(self.watch_data_dir, snapshot_fname)
 
                 if not os.path.exists(dest):
                     try:
-                        actual_dest = _brotli_save(contents, dest, mode=brotli.MODE_TEXT, fallback_uncompressed=True)
+                        actual_dest = _brotli_subprocess_save(contents, dest, mode=brotli.MODE_TEXT, fallback_uncompressed=True)
                         if actual_dest != dest:
                             snapshot_fname = os.path.basename(actual_dest)
                     except Exception as e:
                         logger.error(f"{self.get('uuid')} - Brotli compression failed: {e}")
                         # Fallback to uncompressed
                         snapshot_fname = f"{snapshot_id}.txt"
-                        dest = os.path.join(self.data_dir, snapshot_fname)
+                        dest = os.path.join(self.watch_data_dir, snapshot_fname)
                         self._write_atomic(dest, contents.encode('utf-8'))
             else:
                 # Plain text
                 snapshot_fname = f"{snapshot_id}.txt"
-                dest = os.path.join(self.data_dir, snapshot_fname)
+                dest = os.path.join(self.watch_data_dir, snapshot_fname)
                 self._write_atomic(dest, contents.encode('utf-8'))
 
         # Append to history.txt atomically
-        index_fname = os.path.join(self.data_dir, self.history_index_filename)
+        index_fname = os.path.join(self.watch_data_dir, self.history_index_filename)
         index_line = f"{timestamp},{snapshot_fname}\n"
 
         with open(index_fname, 'a', encoding='utf-8') as f:
@@ -687,17 +552,6 @@ class model(EntityPersistenceMixin, watch_base):
         self.__newest_history_key = timestamp
         self.__history_n += 1
 
-        # MANUAL CHAIN RESOLUTION: Watch → Global
-        # With Pydantic, this would become: maxlen = watch.resolved_history_snapshot_max_length
-        # @computed_field def resolved_history_snapshot_max_length(self) -> Optional[int]:
-        #     if self.history_snapshot_max_length: return self.history_snapshot_max_length
-        #     if tag := self._get_override_tag(): return tag.history_snapshot_max_length
-        #     return self._datastore.settings.history_snapshot_max_length
-        maxlen = self.get('history_snapshot_max_length') or self.get_global_setting('application', 'history_snapshot_max_length')
-
-        if maxlen and self.__history_n and self.__history_n > maxlen:
-            self.history_trim(newest_n_items=maxlen)
-
         # @todo bump static cache of the last timestamp so we dont need to examine the file to set a proper ''viewed'' status
         return snapshot_fname
 
@@ -750,7 +604,7 @@ class model(EntityPersistenceMixin, watch_base):
         return not local_lines.issubset(existing_history)
 
     def get_screenshot(self):
-        fname = os.path.join(self.data_dir, "last-screenshot.png")
+        fname = os.path.join(self.watch_data_dir, "last-screenshot.png")
         if os.path.isfile(fname):
             return fname
 
@@ -765,7 +619,7 @@ class model(EntityPersistenceMixin, watch_base):
         if not favicon_fname:
             return True
         try:
-            fname = next(iter(glob.glob(os.path.join(self.data_dir, "favicon.*"))), None)
+            fname = next(iter(glob.glob(os.path.join(self.watch_data_dir, "favicon.*"))), None)
             logger.trace(f"Favicon file maybe found at {fname}")
             if os.path.isfile(fname):
                 file_age = int(time.time() - os.path.getmtime(fname))
@@ -798,7 +652,7 @@ class model(EntityPersistenceMixin, watch_base):
             base = "favicon"
             extension = "ico"
 
-        fname = os.path.join(self.data_dir, f"favicon.{extension}")
+        fname = os.path.join(self.watch_data_dir, f"favicon.{extension}")
 
         try:
             # validate=True makes sure the string only contains valid base64 chars
@@ -810,10 +664,6 @@ class model(EntityPersistenceMixin, watch_base):
                 try:
                     with open(fname, 'wb') as f:
                         f.write(decoded)
-
-                    # Invalidate module-level favicon filename cache for this watch
-                    _FAVICON_FILENAME_CACHE.pop(self.data_dir, None)
-
                     # A signal that could trigger the socket server to update the browser also
                     watch_check_update = signal('watch_favicon_bump')
                     if watch_check_update:
@@ -827,23 +677,23 @@ class model(EntityPersistenceMixin, watch_base):
 
     def get_favicon_filename(self) -> str | None:
         """
-        Find any favicon.* file in the watch data directory.
-
-        Uses a module-level cache keyed by data_dir to survive Watch object recreation,
-        deepcopy (which drops instance attrs), and concurrent request races.
-        Invalidated by bump_favicon() when a new favicon is saved.
+        Find any favicon.* file in the current working directory
+        and return the contents of the newest one.
 
         Returns:
-            str: Basename of the favicon file, or None if not found.
+            bytes: Contents of the newest favicon file, or None if not found.
         """
-        if self.data_dir in _FAVICON_FILENAME_CACHE:
-            return _FAVICON_FILENAME_CACHE[self.data_dir]
-
         import glob
-        files = glob.glob(os.path.join(self.data_dir, "favicon.*"))
-        fname = os.path.basename(files[0]) if files else None
-        _FAVICON_FILENAME_CACHE[self.data_dir] = fname
-        return fname
+
+        # Search for all favicon.* files
+        files = glob.glob(os.path.join(self.watch_data_dir, "favicon.*"))
+
+        if not files:
+            return None
+
+        # Find the newest by modification time
+        newest_file = max(files, key=os.path.getmtime)
+        return os.path.basename(newest_file)
 
     def get_screenshot_as_thumbnail(self, max_age=3200):
         """Return path to a square thumbnail of the most recent screenshot.
@@ -859,7 +709,7 @@ class model(EntityPersistenceMixin, watch_base):
         import os
         import time
 
-        thumbnail_path = os.path.join(self.data_dir, "thumbnail.jpeg")
+        thumbnail_path = os.path.join(self.watch_data_dir, "thumbnail.jpeg")
         top_trim = 500  # Pixels from top of screenshot to use
 
         screenshot_path = self.get_screenshot()
@@ -910,7 +760,7 @@ class model(EntityPersistenceMixin, watch_base):
             return None
 
     def __get_file_ctime(self, filename):
-        fname = os.path.join(self.data_dir, filename)
+        fname = os.path.join(self.watch_data_dir, filename)
         if os.path.isfile(fname):
             return int(os.path.getmtime(fname))
         return False
@@ -935,9 +785,14 @@ class model(EntityPersistenceMixin, watch_base):
     def snapshot_error_screenshot_ctime(self):
         return self.__get_file_ctime('last-error-screenshot.png')
 
+    @property
+    def watch_data_dir(self):
+        # The base dir of the watch data
+        return os.path.join(self.__datastore_path, self['uuid']) if self.__datastore_path else None
+
     def get_error_text(self):
         """Return the text saved from a previous request that resulted in a non-200 error"""
-        fname = os.path.join(self.data_dir, "last-error.txt")
+        fname = os.path.join(self.watch_data_dir, "last-error.txt")
         if os.path.isfile(fname):
             with open(fname, 'r', encoding='utf-8') as f:
                 return f.read()
@@ -945,7 +800,7 @@ class model(EntityPersistenceMixin, watch_base):
 
     def get_error_snapshot(self):
         """Return path to the screenshot that resulted in a non-200 error"""
-        fname = os.path.join(self.data_dir, "last-error-screenshot.png")
+        fname = os.path.join(self.watch_data_dir, "last-error-screenshot.png")
         if os.path.isfile(fname):
             return fname
         return False
@@ -969,37 +824,6 @@ class model(EntityPersistenceMixin, watch_base):
     def toggle_mute(self):
         self['notification_muted'] ^= True
 
-    def _get_commit_data(self):
-        """
-        Prepare watch data for commit.
-
-        Excludes processor_config_* keys (stored in separate files).
-        Normalizes browser_steps to empty list if no meaningful steps.
-        """
-        import copy
-
-        # Get base snapshot with lock
-        lock = self._datastore.lock if self._datastore and hasattr(self._datastore, 'lock') else None
-
-        if lock:
-            with lock:
-                snapshot = dict(self)
-        else:
-            snapshot = dict(self)
-
-        # Exclude processor config keys (stored separately)
-        watch_dict = {k: copy.deepcopy(v) for k, v in snapshot.items() if not k.startswith('processor_config_')}
-
-        # Normalize browser_steps: if no meaningful steps, save as empty list
-        if not self.has_browser_steps:
-            watch_dict['browser_steps'] = []
-
-        return watch_dict
-
-    # _save_to_disk() method provided by EntityPersistenceMixin
-    # commit() method inherited from watch_base
-
-
     def extra_notification_token_values(self):
         # Used for providing extra tokens
         # return {'widget': 555}
@@ -1029,7 +853,7 @@ class model(EntityPersistenceMixin, watch_base):
                         if not csv_writer:
                             # A file on the disk can be transferred much faster via flask than a string reply
                             csv_output_filename = f"report-{self.get('uuid')}.csv"
-                            f = open(os.path.join(self.data_dir, csv_output_filename), 'w')
+                            f = open(os.path.join(self.watch_data_dir, csv_output_filename), 'w')
                             # @todo some headers in the future
                             #fieldnames = ['Epoch seconds', 'Date']
                             csv_writer = csv.writer(f,
@@ -1071,7 +895,7 @@ class model(EntityPersistenceMixin, watch_base):
 
     def save_error_text(self, contents):
         self.ensure_data_dir_exists()
-        target_path = os.path.join(self.data_dir, "last-error.txt")
+        target_path = os.path.join(self.watch_data_dir, "last-error.txt")
         with open(target_path, 'w', encoding='utf-8') as f:
             f.write(contents)
 
@@ -1080,9 +904,9 @@ class model(EntityPersistenceMixin, watch_base):
         import zlib
 
         if as_error:
-            target_path = os.path.join(str(self.data_dir), "elements-error.deflate")
+            target_path = os.path.join(str(self.watch_data_dir), "elements-error.deflate")
         else:
-            target_path = os.path.join(str(self.data_dir), "elements.deflate")
+            target_path = os.path.join(str(self.watch_data_dir), "elements.deflate")
 
         self.ensure_data_dir_exists()
 
@@ -1097,9 +921,9 @@ class model(EntityPersistenceMixin, watch_base):
     def save_screenshot(self, screenshot: bytes, as_error=False):
 
         if as_error:
-            target_path = os.path.join(self.data_dir, "last-error-screenshot.png")
+            target_path = os.path.join(self.watch_data_dir, "last-error-screenshot.png")
         else:
-            target_path = os.path.join(self.data_dir, "last-screenshot.png")
+            target_path = os.path.join(self.watch_data_dir, "last-screenshot.png")
 
         self.ensure_data_dir_exists()
 
@@ -1110,7 +934,7 @@ class model(EntityPersistenceMixin, watch_base):
 
     def get_last_fetched_text_before_filters(self):
         import brotli
-        filepath = os.path.join(self.data_dir, 'last-fetched.br')
+        filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
 
         if not os.path.isfile(filepath) or os.path.getsize(filepath) == 0:
             # If a previous attempt doesnt yet exist, just snarf the previous snapshot instead
@@ -1125,21 +949,21 @@ class model(EntityPersistenceMixin, watch_base):
 
     def save_last_text_fetched_before_filters(self, contents):
         import brotli
-        filepath = os.path.join(self.data_dir, 'last-fetched.br')
-        _brotli_save(contents, filepath, mode=brotli.MODE_TEXT, fallback_uncompressed=False)
+        filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
+        _brotli_subprocess_save(contents, filepath, mode=brotli.MODE_TEXT, fallback_uncompressed=False)
 
     def save_last_fetched_html(self, timestamp, contents):
         self.ensure_data_dir_exists()
         snapshot_fname = f"{timestamp}.html.br"
-        filepath = os.path.join(self.data_dir, snapshot_fname)
-        _brotli_save(contents, filepath, mode=None, fallback_uncompressed=True)
+        filepath = os.path.join(self.watch_data_dir, snapshot_fname)
+        _brotli_subprocess_save(contents, filepath, mode=None, fallback_uncompressed=True)
         self._prune_last_fetched_html_snapshots()
 
     def get_fetched_html(self, timestamp):
         import brotli
 
         snapshot_fname = f"{timestamp}.html.br"
-        filepath = os.path.join(self.data_dir, snapshot_fname)
+        filepath = os.path.join(self.watch_data_dir, snapshot_fname)
         if os.path.isfile(filepath):
             with open(filepath, 'rb') as f:
                 return (brotli.decompress(f.read()).decode('utf-8'))
@@ -1154,7 +978,7 @@ class model(EntityPersistenceMixin, watch_base):
 
         for index, timestamp in enumerate(dates):
             snapshot_fname = f"{timestamp}.html.br"
-            filepath = os.path.join(self.data_dir, snapshot_fname)
+            filepath = os.path.join(self.watch_data_dir, snapshot_fname)
 
             # Keep only the first 2
             if index > 1 and os.path.isfile(filepath):
@@ -1165,7 +989,7 @@ class model(EntityPersistenceMixin, watch_base):
     def get_browsersteps_available_screenshots(self):
         "For knowing which screenshots are available to show the user in BrowserSteps UI"
         available = []
-        for f in Path(self.data_dir).glob('step_before-*.jpeg'):
+        for f in Path(self.watch_data_dir).glob('step_before-*.jpeg'):
             step_n=re.search(r'step_before-(\d+)', f.name)
             if step_n:
                 available.append(step_n.group(1))
@@ -1174,13 +998,18 @@ class model(EntityPersistenceMixin, watch_base):
     def compile_error_texts(self, has_proxies=None):
         """Compile error texts for this watch.
         Accepts has_proxies parameter to ensure it works even outside app context"""
-        from flask import url_for, has_request_context
+        from flask import url_for
         from markupsafe import Markup
 
         output = []  # Initialize as list since we're using append
         last_error = self.get('last_error','')
 
-        has_app_context = has_request_context()
+        try:
+            url_for('settings.settings_page')
+        except Exception as e:
+            has_app_context = False
+        else:
+            has_app_context = True
 
         # has app+request context, we can use url_for()
         if has_app_context:

changedetectionio/model/__init__.py

@@ -2,175 +2,12 @@ import os
 import uuid
 
 from changedetectionio import strtobool
-from .persistence import EntityPersistenceMixin, _determine_entity_type
-
-__all__ = ['EntityPersistenceMixin', 'watch_base']
-
-from ..browser_steps.browser_steps import browser_steps_get_valid_steps
-
 USE_SYSTEM_DEFAULT_NOTIFICATION_FORMAT_FOR_WATCH = 'System default'
 CONDITIONS_MATCH_LOGIC_DEFAULT = 'ALL'
 
-
 class watch_base(dict):
-    """
-    Base watch domain model (inherits from dict for backward compatibility).
-
-    WARNING: This class inherits from dict, which violates proper encapsulation.
-    Dict inheritance is legacy technical debt that should be refactored to a proper
-    domain model (e.g., Pydantic BaseModel) for better type safety and validation.
-
-    TODO: Migrate to Pydantic BaseModel for:
-          - Type safety and IDE autocomplete
-          - Automatic validation
-          - Clear separation between domain model and serialization
-          - Database backend abstraction (file → postgres → mongodb)
-          - Configuration override chain resolution (Watch → Tag → Global)
-          - Immutability options
-          - Better testing
-          - USE https://docs.pydantic.dev/latest/integrations/datamodel_code_generator TO BUILD THE MODEL FROM THE API-SPEC!!!
-
-    CHAIN RESOLUTION ARCHITECTURE:
-        The dream is a 3-level override hierarchy:
-            Watch settings → Tag/Group settings → Global settings
-
-        Current implementation: MANUAL resolution scattered across codebase
-        - Processors manually check watch.get('field')
-        - Loop through tags to find overrides_watch=True
-        - Fall back to datastore['settings']['application']['field']
-
-        Pydantic implementation: AUTOMATIC resolution via @computed_field
-        - Single source of truth for each setting's resolution logic
-        - Type-safe, testable, self-documenting
-        - Example: watch.resolved_fetch_backend (instead of nested dict navigation)
-
-        See: Watch.py model docstring for detailed Pydantic architecture plan
-        See: Tag.py model docstring for tag override explanation
-        See: processors/restock_diff/processor.py:184-192 for current manual example
-
-    Core Fields:
-        uuid (str): Unique identifier for this watch (auto-generated)
-        url (str): Target URL to monitor for changes
-        title (str|None): Custom display name (overrides page_title if set)
-        page_title (str|None): Title extracted from <title> tag of monitored page
-        tags (List[str]): List of tag UUIDs for categorization
-        tag (str): DEPRECATED - Old single-tag system, use tags instead
-
-    Check Configuration:
-        processor (str): Processor type ('text_json_diff', 'restock_diff', etc.)
-        fetch_backend (str): Fetcher to use ('system', 'html_requests', 'playwright', etc.)
-        method (str): HTTP method ('GET', 'POST', etc.)
-        headers (dict): Custom HTTP headers to send
-        proxy (str|None): Preferred proxy server
-        paused (bool): Whether change detection is paused
-
-    Scheduling:
-        time_between_check (dict): Check interval {'weeks': int, 'days': int, 'hours': int, 'minutes': int, 'seconds': int}
-        time_between_check_use_default (bool): Use global default interval if True
-        time_schedule_limit (dict): Weekly schedule limiting when checks can run
-            Structure: {
-                'enabled': bool,
-                'monday/tuesday/.../sunday': {
-                    'enabled': bool,
-                    'start_time': str ('HH:MM'),
-                    'duration': {'hours': str, 'minutes': str}
-                }
-            }
-
-    Content Filtering:
-        include_filters (List[str]): CSS/XPath selectors to extract content
-        subtractive_selectors (List[str]): Selectors to remove from content
-        ignore_text (List[str]): Text patterns to ignore in change detection
-        trigger_text (List[str]): Text/regex that must be present to trigger change
-        text_should_not_be_present (List[str]): Text that should NOT be present
-        extract_text (List[str]): Regex patterns to extract specific text after filtering
-
-    Text Processing:
-        trim_text_whitespace (bool): Strip leading/trailing whitespace
-        sort_text_alphabetically (bool): Sort lines alphabetically before comparison
-        remove_duplicate_lines (bool): Remove duplicate lines
-        check_unique_lines (bool): Compare against all history for unique lines
-        strip_ignored_lines (bool|None): Remove lines matching ignore patterns
-
-    Change Detection Filters:
-        filter_text_added (bool): Include added text in change detection
-        filter_text_removed (bool): Include removed text in change detection
-        filter_text_replaced (bool): Include replaced text in change detection
-
-    Browser Automation:
-        browser_steps (List[dict]): Browser automation steps for JS-heavy sites
-        browser_steps_last_error_step (int|None): Last step that caused error
-        webdriver_delay (int|None): Seconds to wait after page load
-        webdriver_js_execute_code (str|None): JavaScript to execute before extraction
-
-    Restock Detection:
-        in_stock_only (bool): Only trigger on in-stock transitions
-        follow_price_changes (bool): Monitor price changes
-        has_ldjson_price_data (bool|None): Whether page has LD-JSON price data
-        track_ldjson_price_data (str|None): Track LD-JSON price data ('ACCEPT', 'REJECT', None)
-        price_change_threshold_percent (float|None): Minimum price change % to trigger
-
-    Notifications:
-        notification_urls (List[str]): Apprise URLs for notifications
-        notification_title (str|None): Custom notification title template
-        notification_body (str|None): Custom notification body template
-        notification_format (str): Notification format (e.g., 'System default', 'Text', 'HTML')
-        notification_muted (bool): Disable notifications for this watch
-        notification_screenshot (bool): Include screenshot in notifications
-        notification_alert_count (int): Number of notifications sent
-        last_notification_error (str|None): Last notification error message
-        body (str|None): DEPRECATED? Legacy notification body field
-        filter_failure_notification_send (bool): Send notification on filter failures
-
-    History & State:
-        date_created (int|None): Unix timestamp of watch creation
-        last_checked (int): Unix timestamp of last check
-        last_viewed (int): History snapshot key of last user view
-        last_error (str|bool): Last error message or False if no error
-        check_count (int): Total number of checks performed
-        fetch_time (float): Duration of last fetch in seconds
-        consecutive_filter_failures (int): Counter for consecutive filter match failures
-        previous_md5 (str|bool): MD5 hash of previous content
-        history_snapshot_max_length (int|None): Max history snapshots to keep (None = use global)
-
-    Conditions:
-        conditions (dict): Custom conditions for change detection logic
-        conditions_match_logic (str): Logic operator ('ALL', 'ANY') for conditions
-
-    Metadata:
-        content-type (str|None): Content-Type from last fetch
-        remote_server_reply (str|None): Server header from last response
-        ignore_status_codes (List[int]|None): HTTP status codes to ignore
-        use_page_title_in_list (bool|None): Display page title in watch list (None = use system default)
-
-    Instance Attributes (not serialized):
-        __datastore: Reference to parent DataStore (set externally after creation)
-        data_dir: Filesystem path for this watch's data directory
-
-    Notes:
-        - Many fields default to None to distinguish "not set" from "set to default"
-        - When field is None, system-level defaults are used
-        - Processor-specific configs (e.g., processor_config_*) are NOT stored in watch.json
-          They are stored in separate {processor_name}.json files
-        - This class is used for both Watch and Tag objects (tags reuse the structure)
-    """
 
     def __init__(self, *arg, **kw):
-        # Store datastore reference (common to Watch and Tag)
-        # Use single underscore to avoid name mangling issues in subclasses
-        self._datastore = kw.get('__datastore')
-        if kw.get('__datastore'):
-            del kw['__datastore']
-
-        # Store datastore_path (common to Watch and Tag)
-        self._datastore_path = kw.get('datastore_path')
-        if kw.get('datastore_path'):
-            del kw['datastore_path']
-
-        # IMPORTANT: Don't initialize __watch_was_edited yet!
-        # We'll initialize it AFTER the initial update() call below
-        # This prevents marking the watch as edited during initialization
-
         self.update({
             # Custom notification content
             # Re #110, so then if this is set to None, we know to use the default value instead
@@ -179,7 +16,7 @@ class watch_base(dict):
             'body': None,
             'browser_steps': [],
             'browser_steps_last_error_step': None,
-            'conditions' : [],
+            'conditions' : {},
             'conditions_match_logic': CONDITIONS_MATCH_LOGIC_DEFAULT,
             'check_count': 0,
             'check_unique_lines': False,  # On change-detected, compare against all history if its something new
@@ -187,7 +24,6 @@ class watch_base(dict):
             'content-type': None,
             'date_created': None,
             'extract_text': [],  # Extract text by regex after filters
-            'browser_profile': 'system',  # machine-name key of a BrowserProfile; 'system' → resolve via chain
             'fetch_backend': 'system',  # plaintext, playwright etc
             'fetch_time': 0.0,
             'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
@@ -196,7 +32,6 @@ class watch_base(dict):
             'filter_text_replaced': True,
             'follow_price_changes': True,
             'has_ldjson_price_data': None,
-            'history_snapshot_max_length': None,
             'headers': {},  # Extra headers to send
             'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
             'ignore_status_codes': None,
@@ -217,6 +52,7 @@ class watch_base(dict):
             'page_title': None, # <title> from the page
             'paused': False,
             'previous_md5': False,
+            'previous_md5_before_filters': False,  # Used for skipping changedetection entirely
             'processor': 'text_json_diff',  # could be restock_diff or others from .processors
             'price_change_threshold_percent': None,
             'proxy': None,  # Preferred proxy connection
@@ -302,374 +138,5 @@ class watch_base(dict):
 
         super(watch_base, self).__init__(*arg, **kw)
 
-        # Check if we're being initialized from an existing watch object
-        # that has was_edited=True, so we can preserve the flag
-        preserve_edited_flag = False
         if self.get('default'):
-            # When creating a new watch object from an existing one (e.g., changing processor),
-            # preserve the was_edited flag if it was True
-            default_watch = self.get('default')
-            if hasattr(default_watch, 'was_edited') and default_watch.was_edited:
-                preserve_edited_flag = True
-            del self['default']
-
-        # NOW initialize the edited flag after all initial setup is complete
-        # This ensures initialization doesn't trigger the edited flag
-        # But preserve it if the source watch had it set to True
-        self.__watch_was_edited = preserve_edited_flag
-
-    def _mark_field_as_edited(self, key):
-        """
-        Helper to mark a field as edited if it's writable.
-
-        Internal method used by __setitem__, update(), pop(), etc.
-        """
-        # Don't track edits during initial load or if already edited
-        if not hasattr(self, '_watch_base__watch_was_edited'):
-            return
-        if self.__watch_was_edited:
-            return  # Already marked as edited
-
-        # Import from shared schema utilities (no circular dependency)
-        from .schema_utils import get_readonly_watch_fields
-        readonly_fields = get_readonly_watch_fields()
-
-        # Additional system-managed fields not in OpenAPI spec (yet)
-        # These are set by processors/workers and should not trigger edited flag
-        additional_system_fields = {
-            'last_check_status',  # Set by processors
-            'restock',  # Set by restock processor
-            'last_viewed',  # Set by mark_all_viewed endpoint
-        }
-
-        # Only mark as edited if this is a user-writable field
-        if key not in readonly_fields and key not in additional_system_fields:
-            self.__watch_was_edited = True
-
-    def __setitem__(self, key, value):
-        """
-        Override dict.__setitem__ to track when writable watch fields are modified.
-
-        This enables skipping reprocessing when:
-        1. HTML content is unchanged (checksumFromPreviousCheckWasTheSame)
-        2. AND watch configuration was not edited
-
-        Only sets the edited flag when field is NOT in readonly_fields (from OpenAPI spec).
-        """
-        # Set the value first (always)
-        super().__setitem__(key, value)
-        # Mark as edited if writable field
-        self._mark_field_as_edited(key)
-
-    def __delitem__(self, key):
-        """Override dict.__delitem__ to track deletions of writable fields."""
-        super().__delitem__(key)
-        self._mark_field_as_edited(key)
-
-    def update(self, *args, **kwargs):
-
-        if args and args[0].get('browser_steps'):
-            args[0]['browser_steps'] = browser_steps_get_valid_steps(args[0].get('browser_steps'))
-
-        """Override dict.update() to track modifications to writable fields."""
-        # Call parent update first
-        super().update(*args, **kwargs)
-
-        # Mark as edited for any writable fields that were updated
-        # Handle both update(dict) and update(key=value) forms
-        if args:
-            for key in args[0].keys():
-                self._mark_field_as_edited(key)
-        for key in kwargs.keys():
-            self._mark_field_as_edited(key)
-
-
-    def pop(self, key, *args):
-        """Override dict.pop() to track removal of writable fields."""
-        result = super().pop(key, *args)
-        self._mark_field_as_edited(key)
-        return result
-
-    def setdefault(self, key, default=None):
-        """Override dict.setdefault() to track modifications to writable fields."""
-        # Only marks as edited if key didn't exist (i.e., a new value was set)
-        existed = key in self
-        result = super().setdefault(key, default)
-        if not existed:
-            self._mark_field_as_edited(key)
-        return result
-
-    @property
-    def was_edited(self):
-        """
-        Check if watch configuration was edited since last processing.
-
-        Returns:
-            bool: True if writable fields were modified, False otherwise
-        """
-        return getattr(self, '_watch_base__watch_was_edited', False)
-
-    def reset_watch_edited_flag(self):
-        """
-        Reset the watch edited flag after successful processing.
-
-        Call this after processing completes to allow future content-only change detection.
-        """
-        self.__watch_was_edited = False
-
-    @classmethod
-    def get_property_names(cls):
-        """
-        Get all @property attribute names from this model class using introspection.
-
-        This discovers computed/derived properties that are not stored in the datastore.
-        These properties should be filtered out during PUT/POST requests.
-
-        Returns:
-            frozenset: Immutable set of @property attribute names from the model class
-        """
-        import functools
-
-        # Create a cached version if it doesn't exist
-        if not hasattr(cls, '_cached_get_property_names'):
-            @functools.cache
-            def _get_props():
-                properties = set()
-                # Use introspection to find all @property attributes
-                for name in dir(cls):
-                    # Skip private/magic attributes
-                    if name.startswith('_'):
-                        continue
-                    try:
-                        attr = getattr(cls, name)
-                        # Check if it's a property descriptor
-                        if isinstance(attr, property):
-                            properties.add(name)
-                    except (AttributeError, TypeError):
-                        continue
-                return frozenset(properties)
-
-            cls._cached_get_property_names = _get_props
-
-        return cls._cached_get_property_names()
-
-    def __deepcopy__(self, memo):
-        """
-        Custom deepcopy for all watch_base subclasses (Watch, Tag, etc.).
-
-        CRITICAL FIX: Prevents copying large reference objects like __datastore
-        which would cause exponential memory growth when Watch objects are deepcopied.
-
-        This is called by:
-        - api/Watch.py:76 (API endpoint)
-        - api/Tags.py:28 (Tags API)
-        - processors/base.py:26 (EVERY processor run)
-        - store/__init__.py:544 (clone watch)
-        - And other locations
-        """
-        from copy import deepcopy
-
-        # Create new instance without calling __init__
-        cls = self.__class__
-        new_obj = cls.__new__(cls)
-        memo[id(self)] = new_obj
-
-        # Copy the dict data (all the settings)
-        for key, value in self.items():
-            new_obj[key] = deepcopy(value, memo)
-
-        # Copy instance attributes dynamically
-        # This handles Watch-specific attrs (like __datastore) and any future subclass attrs
-        for attr_name in dir(self):
-            # Skip methods, special attrs, and dict keys
-            if attr_name.startswith('_') and not attr_name.startswith('__'):
-                # This catches _model__datastore, _model__history_n, etc.
-                try:
-                    attr_value = getattr(self, attr_name)
-
-                    # Special handling: Share references to large objects instead of copying
-                    # Examples: _datastore, __datastore, __app_reference, __global_settings, etc.
-                    if (attr_name == '_datastore' or
-                        attr_name.endswith('__datastore') or
-                        attr_name.endswith('__app')):
-                        # Share the reference (don't copy!) to prevent memory leaks
-                        setattr(new_obj, attr_name, attr_value)
-                    # Skip cache attributes - let them regenerate on demand
-                    elif 'cache' in attr_name.lower():
-                        pass  # Don't copy caches
-                    # Copy regular instance attributes
-                    elif not callable(attr_value):
-                        setattr(new_obj, attr_name, attr_value)
-                except AttributeError:
-                    pass  # Attribute doesn't exist in this instance
-
-        return new_obj
-
-    def __getstate__(self):
-        """
-        Custom pickle serialization for all watch_base subclasses.
-
-        Excludes large reference objects (like __datastore) from serialization.
-        """
-        # Get the dict data
-        state = dict(self)
-
-        # Collect instance attributes (excluding methods and large references)
-        instance_attrs = {}
-        for attr_name in dir(self):
-            if attr_name.startswith('_') and not attr_name.startswith('__'):
-                try:
-                    attr_value = getattr(self, attr_name)
-                    # Exclude large reference objects and caches from serialization
-                    if not (attr_name == '_datastore' or
-                           attr_name.endswith('__datastore') or
-                           attr_name.endswith('__app') or
-                           'cache' in attr_name.lower() or
-                           callable(attr_value)):
-                        instance_attrs[attr_name] = attr_value
-                except AttributeError:
-                    pass
-
-        if instance_attrs:
-            state['__instance_metadata__'] = instance_attrs
-
-        return state
-
-    def __setstate__(self, state):
-        """
-        Custom pickle deserialization for all watch_base subclasses.
-
-        WARNING: Large reference objects (like __datastore) are NOT restored!
-        Caller must restore these references after unpickling if needed.
-        """
-        # Extract metadata
-        metadata = state.pop('__instance_metadata__', {})
-
-        # Restore dict data
-        self.update(state)
-
-        # Restore instance attributes
-        for attr_name, attr_value in metadata.items():
-            setattr(self, attr_name, attr_value)
-
-    @property
-    def data_dir(self):
-        """
-        The base directory for this watch/tag data (property, computed from UUID).
-
-        Common property for both Watch and Tag objects.
-        Returns path like: /datastore/{uuid}/
-        """
-        return os.path.join(self._datastore_path, self['uuid']) if self._datastore_path else None
-
-    def ensure_data_dir_exists(self):
-        """
-        Create the data directory if it doesn't exist.
-
-        Common method for both Watch and Tag objects.
-        """
-        from loguru import logger
-        if not os.path.isdir(self.data_dir):
-            logger.debug(f"> Creating data dir {self.data_dir}")
-            os.mkdir(self.data_dir)
-
-    def get_global_setting(self, *path):
-        """
-        Get a setting from the global datastore configuration.
-
-        Args:
-            *path: Path to the setting (e.g., 'application', 'history_snapshot_max_length')
-
-        Returns:
-            The setting value, or None if not found
-
-        Example:
-            maxlen = self.get_global_setting('application', 'history_snapshot_max_length')
-        """
-        if not self._datastore:
-            return None
-
-        try:
-            # _datastore is a ChangeDetectionStore (has .data) or a plain dict (unit tests)
-            store_data = self._datastore.data if hasattr(self._datastore, 'data') else self._datastore
-            value = store_data['settings']
-            for key in path:
-                value = value[key]
-            return value
-        except (KeyError, TypeError):
-            return None
-
-    def _get_commit_data(self):
-        """
-        Prepare data for commit (can be overridden by subclasses).
-
-        Returns:
-            dict: Data to serialize (filtered as needed by subclass)
-        """
-        import copy
-
-        # Acquire datastore lock to prevent concurrent modifications during copy
-        lock = self._datastore.lock if self._datastore and hasattr(self._datastore, 'lock') else None
-
-        if lock:
-            with lock:
-                snapshot = dict(self)
-        else:
-            snapshot = dict(self)
-
-        # Deep copy snapshot (slower, but done outside lock to minimize contention)
-        # Subclasses can override to filter keys (e.g., Watch excludes processor_config_*)
-        return {k: copy.deepcopy(v) for k, v in snapshot.items()}
-
-    def _save_to_disk(self, data_dict, uuid):
-        """
-        Save data to disk (must be implemented by subclasses).
-
-        Args:
-            data_dict: Dictionary to save
-            uuid: UUID for logging
-
-        Raises:
-            NotImplementedError: If subclass doesn't implement
-        """
-        raise NotImplementedError("Subclass must implement _save_to_disk()")
-
-    def commit(self):
-        """
-        Save this watch/tag immediately to disk using atomic write.
-
-        Common commit logic for Watch and Tag objects.
-        Subclasses override _get_commit_data() and _save_to_disk() for specifics.
-
-        Fire-and-forget: Logs errors but does not raise exceptions.
-        Data remains in memory even if save fails, so next commit will retry.
-        """
-        from loguru import logger
-
-        if not self.data_dir:
-            entity_type = self.__class__.__name__
-            logger.error(f"Cannot commit {entity_type} {self.get('uuid')} without datastore_path")
-            return
-
-        uuid = self.get('uuid')
-        if not uuid:
-            entity_type = self.__class__.__name__
-            logger.error(f"Cannot commit {entity_type} without UUID")
-            return
-
-        # Get data from subclass (may filter keys)
-        try:
-            data_dict = self._get_commit_data()
-        except Exception as e:
-            logger.error(f"Failed to prepare commit data for {uuid}: {e}")
-            return
-
-        # Save to disk via subclass implementation
-        try:
-            # Determine entity type from module name (Watch.py -> watch, Tag.py -> tag)
-            entity_type = _determine_entity_type(self.__class__)
-            filename = f"{entity_type}.json"
-            self._save_to_disk(data_dict, uuid)
-            logger.debug(f"Committed {entity_type} {uuid} to {uuid}/{filename}")
-        except Exception as e:
-            logger.error(f"Failed to commit {uuid}: {e}")
+            del self['default']

changedetectionio/model/browser_profile.py

@@ -1,354 +0,0 @@
-"""
-BrowserProfile — named, reusable browser/fetcher configuration.
-
-Storage key
------------
-Profiles are stored in ``settings.application.browser_profiles`` as a plain dict
-keyed by *machine name* — a lowercase, underscore-separated slug derived from the
-human-readable ``name`` field:
-
-    'My Blocking Chrome'        →  'my_blocking_chrome'
-    'Custom CDP — Mobile (375px)' →  'custom_cdp_mobile_375px'
-
-Using the machine name as the key means that deleting a profile and recreating
-it with the same name restores the original key, so all watches that referenced
-it continue to work without any manual re-linking.
-
-Resolution chain
-----------------
-``resolve_browser_profile(watch, datastore)`` walks:
-
-    watch.browser_profile  →  first tag with overrides_watch=True  →
-    settings.application.browser_profile  →  built-in fallback
-
-It never raises.  Stale / missing machine-name references are logged and the
-resolver falls through to the next level.
-
-Built-in profiles
------------------
-``BUILTIN_REQUESTS`` and ``BUILTIN_BROWSER`` are always available and cannot be
-deleted from the UI (``is_builtin=True``).  Their machine names are stored in
-``RESERVED_MACHINE_NAMES`` to block user profiles from shadowing them.
-
-Migration
----------
-``store/updates.py::update_31`` converts the legacy ``fetch_backend`` field on
-watches, tags and global settings into ``browser_profile`` machine-name
-references.  After that migration no legacy paths are needed here.
-"""
-
-from __future__ import annotations
-
-import re
-from typing import Optional
-
-from loguru import logger
-from pydantic import BaseModel, field_validator
-
-# ---------------------------------------------------------------------------
-# Constants
-# ---------------------------------------------------------------------------
-
-NAME_MAX_LEN = 100
-
-
-# ---------------------------------------------------------------------------
-# Model
-# ---------------------------------------------------------------------------
-
-class BrowserProfile(BaseModel):
-    """
-    A named, reusable configuration for how a watch fetches its target URL.
-
-    The *machine name* (see ``get_machine_name()``) is the stable storage key.
-    Updating ``name`` changes the machine name; any watch that referenced the
-    old machine name will then fall back through the resolution chain until it
-    is explicitly re-pointed.  To replace a profile without breaking watches,
-    delete it and recreate it with the *same* name.
-    """
-
-    name: str
-    """Human-readable label shown in the UI.  Max 100 characters."""
-
-    fetch_backend: str = 'requests'
-    """
-    Which fetch engine to use.  This is the *clean* fetcher name without the
-    ``html_`` module prefix (e.g. ``'requests'``, ``'webdriver'``,
-    ``'playwright'``, ``'puppeteer'``, ``'cloakbrowser'``).
-
-    The module-level ``html_`` prefix (``html_requests``, ``html_webdriver``,
-    …) is an implementation detail of ``content_fetchers/``.  Use
-    ``get_fetcher_class_name()`` to obtain the full module attribute name when
-    you need to look up the class.
-
-    Must be non-empty and contain only ``[a-z0-9_]`` characters.
-    """
-
-    is_builtin: bool = False
-    """Built-in profiles are always present and cannot be deleted from the UI."""
-
-    # ------------------------------------------------------------------
-    # Browser-specific settings (silently ignored by html_requests)
-    # ------------------------------------------------------------------
-
-    browser_connection_url: Optional[str] = None
-    """
-    Custom CDP / WebSocket endpoint, e.g. ``ws://my-chrome:3000``.
-    Overrides the system-wide ``PLAYWRIGHT_DRIVER_URL`` for this profile.
-    Only meaningful for ``html_webdriver`` profiles.
-    """
-
-    viewport_width: int = 1280
-    """
-    Browser viewport width in pixels.
-    Common presets: 375 (iPhone), 768 (tablet), 1280 (desktop).
-    """
-
-    viewport_height: int = 1000
-    """
-    Browser viewport height in pixels.
-    Common presets: 812 (iPhone), 1024 (tablet), 1000 (desktop).
-    """
-
-    block_images: bool = False
-    """
-    Block all image requests.  Typically cuts page-load time by 40-70 % on
-    image-heavy sites with no impact on text-based change detection.
-    """
-
-    block_fonts: bool = False
-    """Block web-font requests.  Modest speed gain; rarely affects detection."""
-
-    user_agent: Optional[str] = None
-    """
-    Override the browser User-Agent string.
-    ``None`` keeps the fetcher's built-in default, which already strips
-    obvious headless markers such as ``HeadlessChrome``.
-    """
-
-    ignore_https_errors: bool = False
-    """
-    Proceed even when the server's TLS certificate is invalid or self-signed.
-    Useful for staging / development environments.
-    """
-
-    locale: Optional[str] = None
-    """
-    Browser locale (e.g. ``en-US``, ``de-DE``).
-    Sets the ``Accept-Language`` header and ``navigator.language``.
-    Some sites serve different prices or copy based on locale.
-    """
-
-    model_config = {"frozen": False}
-
-    # ------------------------------------------------------------------
-    # Validators
-    # ------------------------------------------------------------------
-
-    @field_validator('fetch_backend')
-    @classmethod
-    def _validate_fetch_backend(cls, v: str) -> str:
-        v = v.strip()
-        if not v:
-            raise ValueError('fetch_backend cannot be empty')
-        if not re.fullmatch(r'[a-z0-9_]+', v):
-            raise ValueError(
-                f"fetch_backend must contain only lowercase letters, digits and underscores, got {v!r}"
-            )
-        if v.startswith('html_'):
-            raise ValueError(
-                f"fetch_backend should be the clean fetcher name without the 'html_' prefix "
-                f"(e.g. 'requests', 'webdriver', 'playwright'). Got {v!r}. "
-                f"Use get_fetcher_class_name() to obtain the full module attribute name."
-            )
-        return v
-
-    @field_validator('name')
-    @classmethod
-    def _validate_name(cls, v: str) -> str:
-        v = v.strip()
-        if not v:
-            raise ValueError('Name cannot be empty')
-        if len(v) > NAME_MAX_LEN:
-            raise ValueError(f'Name must be {NAME_MAX_LEN} characters or less')
-        return v
-
-    # ------------------------------------------------------------------
-    # Machine-name helpers
-    # ------------------------------------------------------------------
-
-    @staticmethod
-    def machine_name_from_str(name: str) -> str:
-        """
-        Convert a human name to a machine-safe storage key.
-
-        Transformation rules (applied in order):
-
-        1. Strip surrounding whitespace; lower-case.
-        2. Replace runs of whitespace or hyphens with a single ``_``.
-        3. Drop every character that is not ``[a-z0-9_]``.
-        4. Collapse consecutive underscores.
-        5. Strip leading / trailing underscores.
-        6. Truncate to ``NAME_MAX_LEN`` characters.
-
-        Examples::
-
-            'My Blocking Browser Chrome'  →  'my_blocking_browser_chrome'
-            'Custom CDP — Mobile (375px)' →  'custom_cdp_mobile_375px'
-            '  Weird   ---   Name  '      →  'weird_name'
-        """
-        s = name.strip().lower()
-        s = re.sub(r'[\s\-]+', '_', s)    # whitespace / hyphens → underscore
-        s = re.sub(r'[^a-z0-9_]', '', s)  # drop everything else
-        s = re.sub(r'_+', '_', s)         # collapse repeated underscores
-        s = s.strip('_')                   # drop leading / trailing underscores
-        return s[:NAME_MAX_LEN]
-
-    def get_machine_name(self) -> str:
-        """Return the machine-safe storage key derived from this profile's ``name``."""
-        return self.machine_name_from_str(self.name)
-
-    def get_fetcher_class_name(self) -> str:
-        """Return the clean fetcher name for this profile (same as ``fetch_backend``).
-
-        Use with ``content_fetchers.get_fetcher()``::
-
-            from changedetectionio import content_fetchers
-            fetcher_cls = content_fetchers.get_fetcher(profile.get_fetcher_class_name())
-        """
-        return self.fetch_backend
-
-
-# ---------------------------------------------------------------------------
-# Built-in profiles (always present, cannot be deleted)
-# ---------------------------------------------------------------------------
-
-BUILTIN_REQUESTS = BrowserProfile(
-    name='Direct HTTP (requests)',
-    fetch_backend='requests',
-    is_builtin=True,
-)
-
-BUILTIN_PLAYWRIGHT = BrowserProfile(
-    name='Browser (Chrome/Playwright)',
-    fetch_backend='playwright_cdp',
-    is_builtin=True,
-)
-
-BUILTIN_SELENIUM = BrowserProfile(
-    name='Browser (Chrome/Selenium)',
-    fetch_backend='selenium',
-    is_builtin=True,
-)
-
-BUILTIN_PUPPETEER = BrowserProfile(
-    name='Browser (Chrome/Puppeteer)',
-    fetch_backend='puppeteer',
-    is_builtin=True,
-)
-
-# Backwards-compatible alias — code that imported BUILTIN_BROWSER keeps working.
-BUILTIN_BROWSER = BUILTIN_PLAYWRIGHT
-
-# Keyed by machine name for O(1) lookup.
-_BUILTINS: dict[str, BrowserProfile] = {
-    b.get_machine_name(): b
-    for b in (BUILTIN_REQUESTS, BUILTIN_PLAYWRIGHT, BUILTIN_SELENIUM, BUILTIN_PUPPETEER)
-}
-
-# Machine names that cannot be used by user-created profiles.
-RESERVED_MACHINE_NAMES: frozenset[str] = frozenset(_BUILTINS.keys())
-
-
-def get_default_browser_builtin() -> BrowserProfile:
-    """Return the built-in browser profile that matches the current environment.
-
-    Reads the same env vars as ``content_fetchers.get_active_browser_fetcher_name()``:
-
-    * ``PLAYWRIGHT_DRIVER_URL`` set + ``FAST_PUPPETEER_CHROME_FETCHER=False`` → Playwright
-    * ``PLAYWRIGHT_DRIVER_URL`` set + ``FAST_PUPPETEER_CHROME_FETCHER=True``  → Puppeteer
-    * Neither set → Selenium
-    """
-    import os
-    from changedetectionio.strtobool import strtobool
-    if os.getenv('PLAYWRIGHT_DRIVER_URL', False):
-        if not strtobool(os.getenv('FAST_PUPPETEER_CHROME_FETCHER', 'False')):
-            return BUILTIN_PLAYWRIGHT
-        return BUILTIN_PUPPETEER
-    return BUILTIN_SELENIUM
-
-
-# ---------------------------------------------------------------------------
-# Lookup helpers
-# ---------------------------------------------------------------------------
-
-def get_builtin_profiles() -> dict[str, BrowserProfile]:
-    """Return a shallow copy of the built-in profiles dict (keyed by machine name)."""
-    return dict(_BUILTINS)
-
-
-def get_profile(machine_name: str, store_profiles: dict) -> Optional[BrowserProfile]:
-    """
-    Look up a ``BrowserProfile`` by machine name.
-
-    Built-ins are checked first and cannot be shadowed by user profiles.
-    Returns ``None`` when the machine name is unknown or the stored data is
-    corrupt (a warning is logged in the latter case).
-    """
-    if machine_name in _BUILTINS:
-        return _BUILTINS[machine_name]
-
-    raw = store_profiles.get(machine_name)
-    if raw is None:
-        return None
-
-    if isinstance(raw, BrowserProfile):
-        return raw
-
-    try:
-        return BrowserProfile(**raw)
-    except Exception as exc:
-        logger.warning(f"BrowserProfile '{machine_name}': failed to deserialize — {exc}")
-        return None
-
-
-# ---------------------------------------------------------------------------
-# Resolution
-# ---------------------------------------------------------------------------
-
-def resolve_browser_profile(watch, datastore) -> BrowserProfile:
-    """
-    Resolve the effective ``BrowserProfile`` for *watch*.
-
-    Resolution chain
-    ~~~~~~~~~~~~~~~~
-    1. ``watch['browser_profile']`` — explicit machine name set on the watch.
-    2. First tag with ``overrides_watch=True`` that has ``browser_profile`` set.
-    3. ``settings.application['browser_profile']`` — system-wide default.
-    4. Built-in fallback: ``BUILTIN_REQUESTS`` (requests is always the safe default).
-
-    Never raises.  A stale / missing machine-name reference produces a
-    ``logger.warning`` and the resolver continues down the chain.
-    """
-    from changedetectionio.model.resolver import resolve_setting
-
-    store_profiles: dict = datastore.data['settings']['application'].get('browser_profiles', {})
-
-    machine_name = resolve_setting(
-        watch, datastore,
-        field_name='browser_profile',
-        sentinel_values={'system', 'default', ''},
-        default=None,
-        require_tag_override=True,
-    )
-
-    if machine_name:
-        profile = get_profile(machine_name, store_profiles)
-        if profile:
-            return profile
-        logger.warning(
-            f"Watch {watch.get('uuid')!r}: browser_profile {machine_name!r} not found, "
-            f"falling back through the chain"
-        )
-
-    return BUILTIN_REQUESTS

changedetectionio/model/persistence.py

@@ -1,84 +0,0 @@
-"""
-Entity persistence mixin for Watch and Tag models.
-
-Provides file-based persistence using atomic writes.
-"""
-
-import functools
-import inspect
-
-
-@functools.lru_cache(maxsize=None)
-def _determine_entity_type(cls):
-    """
-    Determine entity type from class hierarchy (cached at class level).
-
-    Args:
-        cls: The class to inspect
-
-    Returns:
-        str: Entity type ('watch', 'tag', etc.)
-
-    Raises:
-        ValueError: If entity type cannot be determined
-    """
-    for base_class in inspect.getmro(cls):
-        module_name = base_class.__module__
-        if module_name.startswith('changedetectionio.model.'):
-            # Get last part after dot: "changedetectionio.model.Watch" -> "watch"
-            return module_name.split('.')[-1].lower()
-
-    raise ValueError(
-        f"Cannot determine entity type for {cls.__module__}.{cls.__name__}. "
-        f"Entity must inherit from a class in changedetectionio.model (Watch or Tag)."
-    )
-
-
-class EntityPersistenceMixin:
-    """
-    Mixin providing file persistence for watch_base subclasses (Watch, Tag, etc.).
-
-    This mixin provides the _save_to_disk() method required by watch_base.commit().
-    It automatically determines the correct filename and size limits based on class hierarchy.
-
-    Usage:
-        class model(EntityPersistenceMixin, watch_base):  # in Watch.py
-            pass
-
-        class model(EntityPersistenceMixin, watch_base):  # in Tag.py
-            pass
-    """
-
-    def _save_to_disk(self, data_dict, uuid):
-        """
-        Save entity to disk using atomic write.
-
-        Implements the abstract method required by watch_base.commit().
-        Automatically determines filename and size limits from class hierarchy.
-
-        Args:
-            data_dict: Dictionary to save
-            uuid: UUID for logging
-
-        Raises:
-            ValueError: If entity type cannot be determined from class hierarchy
-        """
-        # Import here to avoid circular dependency
-        from changedetectionio.store.file_saving_datastore import save_entity_atomic
-
-        # Determine entity type (cached at class level, not instance level)
-        entity_type = _determine_entity_type(self.__class__)
-
-        # Set filename and size limits based on entity type
-        filename = f'{entity_type}.json'
-        max_size_mb = 10 if entity_type == 'watch' else 1
-
-        # Save using generic function
-        save_entity_atomic(
-            self.data_dir,
-            uuid,
-            data_dict,
-            filename=filename,
-            entity_type=entity_type,
-            max_size_mb=max_size_mb
-        )

changedetectionio/model/resolver.py

@@ -1,63 +0,0 @@
-"""
-Unified Watch → Tag → Global settings cascade resolver.
-
-All settings resolution follows the same priority order:
-  1. Watch-level setting (if set and not a sentinel "use parent" value)
-  2. First tag with overrides_watch=True that has the field set
-  3. Global application settings
-  4. Caller-supplied default
-
-This replaces the previously scattered manual resolution loops found in
-notification_service.py, processors/base.py, and the restock processor.
-"""
-
-
-def resolve_setting(watch, datastore, field_name, *,
-                    sentinel_values=None,
-                    default=None,
-                    require_tag_override=True):
-    """
-    Resolve a single setting value by walking the Watch → Tag → Global chain.
-
-    Args:
-        watch:               Watch dict / model object.
-        datastore:           App datastore (must have get_all_tags_for_watch() and
-                             data['settings']['application']).
-        field_name:          The setting key to look up at each level.
-        sentinel_values:     Set of values that mean "not configured here, keep looking".
-                             For example {'system'} for fetch_backend.
-        default:             Value returned when nothing is found in the chain.
-        require_tag_override: If True (default), only tags where overrides_watch=True
-                             contribute to the cascade.  Set to False when every tag
-                             that carries the field should be considered (e.g. for
-                             fields that make sense to merge/override at any tag level).
-
-    Returns:
-        The first non-sentinel, non-empty value found, or *default*.
-    """
-    _sentinels = set(sentinel_values) if sentinel_values else set()
-
-    def _is_unset(v):
-        return v is None or v == '' or v in _sentinels
-
-    # 1. Watch level
-    v = watch.get(field_name)
-    if not _is_unset(v):
-        return v
-
-    # 2. Tag level
-    tags = datastore.get_all_tags_for_watch(uuid=watch.get('uuid'))
-    if tags:
-        for tag in tags.values():
-            if require_tag_override and not tag.get('overrides_watch'):
-                continue
-            v = tag.get(field_name)
-            if not _is_unset(v):
-                return v
-
-    # 3. Global application settings
-    v = datastore.data['settings']['application'].get(field_name)
-    if not _is_unset(v):
-        return v
-
-    return default

changedetectionio/model/schema_utils.py

@@ -1,92 +0,0 @@
-"""
-Schema utilities for Watch and Tag models.
-
-Provides functions to extract readonly fields and properties from OpenAPI spec.
-Shared by both the model layer and API layer to avoid circular dependencies.
-"""
-
-import functools
-
-
-@functools.cache
-def get_openapi_schema_dict():
-    """
-    Get the raw OpenAPI spec dictionary for schema access.
-
-    Returns the YAML dict directly (not the OpenAPI object).
-    """
-    import os
-    import yaml
-
-    spec_path = os.path.join(os.path.dirname(__file__), '../../docs/api-spec.yaml')
-    if not os.path.exists(spec_path):
-        spec_path = os.path.join(os.path.dirname(__file__), '../docs/api-spec.yaml')
-
-    with open(spec_path, 'r', encoding='utf-8') as f:
-        return yaml.safe_load(f)
-
-
-@functools.cache
-def _resolve_readonly_fields(schema_name):
-    """
-    Generic helper to resolve readOnly fields, including allOf inheritance.
-
-    Args:
-        schema_name: Name of the schema (e.g., 'Watch', 'Tag')
-
-    Returns:
-        frozenset: All readOnly field names including inherited ones
-    """
-    spec_dict = get_openapi_schema_dict()
-    schema = spec_dict['components']['schemas'].get(schema_name, {})
-
-    readonly_fields = set()
-
-    # Handle allOf (schema inheritance)
-    if 'allOf' in schema:
-        for item in schema['allOf']:
-            # Resolve $ref to parent schema
-            if '$ref' in item:
-                ref_path = item['$ref'].split('/')[-1]
-                ref_schema = spec_dict['components']['schemas'].get(ref_path, {})
-                if 'properties' in ref_schema:
-                    for field_name, field_def in ref_schema['properties'].items():
-                        if field_def.get('readOnly') is True:
-                            readonly_fields.add(field_name)
-            # Check schema-specific properties
-            if 'properties' in item:
-                for field_name, field_def in item['properties'].items():
-                    if field_def.get('readOnly') is True:
-                        readonly_fields.add(field_name)
-    else:
-        # Direct properties (no inheritance)
-        if 'properties' in schema:
-            for field_name, field_def in schema['properties'].items():
-                if field_def.get('readOnly') is True:
-                    readonly_fields.add(field_name)
-
-    return frozenset(readonly_fields)
-
-
-@functools.cache
-def get_readonly_watch_fields():
-    """
-    Extract readOnly field names from Watch schema in OpenAPI spec.
-
-    Returns readOnly fields from WatchBase (uuid, date_created) + Watch-specific readOnly fields.
-
-    Used by:
-    - model/watch_base.py: Track when writable fields are edited
-    - api/Watch.py: Filter readonly fields from PUT requests
-    """
-    return _resolve_readonly_fields('Watch')
-
-
-@functools.cache
-def get_readonly_tag_fields():
-    """
-    Extract readOnly field names from Tag schema in OpenAPI spec.
-
-    Returns readOnly fields from WatchBase (uuid, date_created) + Tag-specific readOnly fields.
-    """
-    return _resolve_readonly_fields('Tag')

changedetectionio/notification_profiles/__init__.py

@@ -1,3 +0,0 @@
-from .registry import registry, NotificationProfileType, AppriseProfileType
-
-__all__ = ['registry', 'NotificationProfileType', 'AppriseProfileType']

changedetectionio/notification_profiles/log.py

@@ -1,73 +0,0 @@
-"""
-Per-profile notification log.
-
-Each profile gets its own log file at:
-  {datastore_path}/notification-logs/{profile_uuid}.log
-
-Entries are stored as JSON-lines (one JSON object per line).
-The file is capped at MAX_ENTRIES lines (oldest pruned first).
-"""
-
-import json
-import os
-from datetime import datetime, timezone
-
-MAX_ENTRIES = 100
-_LOG_DIR = 'notification-logs'
-
-
-def _log_file(datastore_path: str, profile_uuid: str) -> str:
-    return os.path.join(datastore_path, _LOG_DIR, f'{profile_uuid}.log')
-
-
-def write_profile_log(datastore_path: str, profile_uuid: str, *,
-                      watch_url: str = '',
-                      watch_uuid: str = '',
-                      status: str,        # 'ok' | 'error' | 'test'
-                      message: str = ''):
-    """Append one log entry; prune to MAX_ENTRIES."""
-    log_dir = os.path.join(datastore_path, _LOG_DIR)
-    os.makedirs(log_dir, exist_ok=True)
-
-    entry = json.dumps({
-        'ts':         datetime.now(tz=timezone.utc).strftime('%Y-%m-%d %H:%M:%S UTC'),
-        'watch_url':  watch_url[:200],
-        'watch_uuid': watch_uuid,
-        'status':     status,
-        'message':    message[:500],
-    }, ensure_ascii=False)
-
-    path = _log_file(datastore_path, profile_uuid)
-    try:
-        with open(path, 'r', encoding='utf-8') as fh:
-            lines = [l for l in fh.read().splitlines() if l.strip()]
-    except FileNotFoundError:
-        lines = []
-
-    lines.append(entry)
-    lines = lines[-MAX_ENTRIES:]
-
-    with open(path, 'w', encoding='utf-8') as fh:
-        fh.write('\n'.join(lines) + '\n')
-
-
-def read_profile_log(datastore_path: str, profile_uuid: str) -> list:
-    """Return log entries as a list of dicts, newest first."""
-    path = _log_file(datastore_path, profile_uuid)
-    try:
-        with open(path, 'r', encoding='utf-8') as fh:
-            lines = [l.strip() for l in fh if l.strip()]
-    except FileNotFoundError:
-        return []
-
-    entries = []
-    for line in reversed(lines):
-        try:
-            entries.append(json.loads(line))
-        except (json.JSONDecodeError, ValueError):
-            pass
-    return entries
-
-
-def has_log(datastore_path: str, profile_uuid: str) -> bool:
-    return os.path.exists(_log_file(datastore_path, profile_uuid))

changedetectionio/notification_profiles/registry.py

@@ -1,111 +0,0 @@
-"""
-Notification Profile Type plugin registry.
-
-NotificationProfileType is the abstract base — the only contract is send().
-Plugins are free to use any delivery mechanism (Apprise, direct HTTP, SDK, etc.).
-
-Built-in: AppriseProfileType (raw Apprise URL list).
-
-Third-party plugins register additional types:
-
-    from changedetectionio.notification_profiles.registry import registry, NotificationProfileType
-
-    @registry.register
-    class MyProfileType(NotificationProfileType):
-        type_id      = "mytype"
-        display_name = "My Service"
-        icon         = "bell"
-        template     = "my_plugin/notification_profiles/types/mytype.html"
-
-        def send(self, config: dict, n_object: dict, datastore) -> bool:
-            requests.post(config['webhook_url'], json={"text": n_object['notification_body']})
-            return True
-"""
-
-from abc import ABC, abstractmethod
-
-
-class NotificationProfileType(ABC):
-    type_id:      str = NotImplemented
-    display_name: str = NotImplemented
-    icon:         str = "bell"          # feather icon name
-    template:     str = NotImplemented  # Jinja2 partial rendered in the profile edit form
-
-    @abstractmethod
-    def send(self, config: dict, n_object: dict, datastore) -> bool:
-        """
-        Deliver the notification.
-
-        Args:
-            config:    The profile's config dict (type-specific fields).
-            n_object:  Fully-rendered NotificationContextData (title, body, format, etc.).
-            datastore: App datastore for any extra lookups.
-
-        Returns True on success, False on failure (do not raise — log instead).
-        """
-
-    def validate(self, config: dict) -> None:
-        """Raise ValueError with a user-readable message on invalid config."""
-        pass
-
-    def get_url_hint(self, config: dict) -> str:
-        """Short display string shown in the selector chip tooltip / dropdown row."""
-        return ''
-
-
-class AppriseProfileType(NotificationProfileType):
-    """Delivers notifications via Apprise using a raw URL list."""
-
-    type_id      = "apprise"
-    display_name = "Apprise"
-    icon         = "bell"
-    template     = "notification_profiles/types/apprise.html"
-
-    def get_apprise_urls(self, config: dict) -> list:
-        return config.get('notification_urls') or []
-
-    def send(self, config: dict, n_object, datastore) -> bool:
-        from changedetectionio.notification.handler import process_notification
-        from changedetectionio.notification_service import NotificationContextData
-        urls = self.get_apprise_urls(config)
-        if not urls:
-            return False
-        if not isinstance(n_object, NotificationContextData):
-            n_object = NotificationContextData(n_object)
-        n_object['notification_urls']   = urls
-        n_object['notification_title']  = config.get('notification_title') or n_object.get('notification_title')
-        n_object['notification_body']   = config.get('notification_body')  or n_object.get('notification_body')
-        n_object['notification_format'] = config.get('notification_format') or n_object.get('notification_format')
-        process_notification(n_object, datastore)
-        return True
-
-    def get_url_hint(self, config: dict) -> str:
-        urls = config.get('notification_urls') or []
-        if urls:
-            u = urls[0]
-            return (u[:60] + '…') if len(u) > 60 else u
-        return ''
-
-
-class _Registry:
-    def __init__(self):
-        self._types: dict = {}
-
-    def register(self, cls):
-        """Register a NotificationProfileType subclass. Usable as a decorator."""
-        instance = cls()
-        self._types[instance.type_id] = instance
-        return cls
-
-    def get(self, type_id: str) -> NotificationProfileType:
-        return self._types.get(type_id, self._types.get('apprise'))
-
-    def all(self) -> list:
-        return list(self._types.values())
-
-    def choices(self) -> list:
-        return [(t.type_id, t.display_name) for t in self._types.values()]
-
-
-registry = _Registry()
-registry.register(AppriseProfileType)

changedetectionio/notification_profiles/resolver.py

@@ -1,49 +0,0 @@
-"""
-Resolve the full set of NotificationProfile objects that should fire for a given watch.
-
-Merges profile UUIDs from: Watch → Tags → System (union, deduplicated).
-Mute cascade is checked separately via resolve_setting() before calling this.
-"""
-
-from loguru import logger
-
-
-def resolve_notification_profiles(watch, datastore) -> list:
-    """
-    Return list of (profile_dict, NotificationProfileType) tuples to fire for *watch*.
-
-    Profiles are deduplicated by UUID — if the same UUID appears at multiple levels
-    it fires once, not multiple times.
-    """
-    from changedetectionio.notification_profiles.registry import registry
-
-    all_profiles = datastore.data['settings']['application'].get('notification_profile_data', {})
-
-    seen = set()
-    result = []
-
-    def _add(uuids):
-        for uid in (uuids or []):
-            if uid in seen:
-                continue
-            profile = all_profiles.get(uid)
-            if not profile:
-                logger.warning(f"Notification profile UUID {uid!r} not found, skipping")
-                continue
-            seen.add(uid)
-            type_handler = registry.get(profile.get('type', 'apprise'))
-            result.append((profile, type_handler))
-
-    # 1. Watch-level
-    _add(watch.get('notification_profiles', []))
-
-    # 2. Tag/group level
-    tags = datastore.get_all_tags_for_watch(uuid=watch.get('uuid'))
-    if tags:
-        for tag in tags.values():
-            _add(tag.get('notification_profiles', []))
-
-    # 3. System level
-    _add(datastore.data['settings']['application'].get('notification_profiles', []))
-
-    return result

changedetectionio/notification_service.py

@@ -54,128 +54,34 @@ def _check_cascading_vars(datastore, var_name, watch):
     return None
 
 
-class FormattableTimestamp(str):
-    """
-    A str subclass representing a formatted datetime. As a plain string it renders
-    with the default format, but can also be called with a custom format argument
-    in Jinja2 templates:
-
-        {{ change_datetime }}                        → '2024-01-15 10:30:00 UTC'
-        {{ change_datetime(format='%Y') }}           → '2024'
-        {{ change_datetime(format='%A') }}           → 'Monday'
-        {{ change_datetime(format='%Y-%m-%d') }}     → '2024-01-15'
-
-    Being a str subclass means it is natively JSON serializable.
-    """
-    _DEFAULT_FORMAT = '%Y-%m-%d %H:%M:%S %Z'
-
-    def __new__(cls, timestamp):
-        dt = datetime.datetime.fromtimestamp(int(timestamp), tz=pytz.UTC)
-        local_tz = datetime.datetime.now().astimezone().tzinfo
-        dt_local = dt.astimezone(local_tz)
-        try:
-            formatted = dt_local.strftime(cls._DEFAULT_FORMAT)
-        except Exception:
-            formatted = dt_local.isoformat()
-        instance = super().__new__(cls, formatted)
-        instance._dt = dt_local
-        return instance
-
-    def __call__(self, format=_DEFAULT_FORMAT):
-        try:
-            return self._dt.strftime(format)
-        except Exception:
-            return self._dt.isoformat()
-
-
-class FormattableDiff(str):
-    """
-    A str subclass representing a rendered diff. As a plain string it renders
-    with the default options for that variant, but can be called with custom
-    arguments in Jinja2 templates:
-
-        {{ diff }}                                    → default diff output
-        {{ diff(lines=5) }}                           → truncate to 5 lines
-        {{ diff(added_only=true) }}                   → only show added lines
-        {{ diff(removed_only=true) }}                 → only show removed lines
-        {{ diff(context=3) }}                         → 3 lines of context around changes
-        {{ diff(word_diff=false) }}                   → line-level diff instead of word-level
-        {{ diff(lines=10, added_only=true) }}         → combine args
-        {{ diff_added(lines=5) }}                     → works on any diff_* variant too
-
-    Being a str subclass means it is natively JSON serializable.
-    """
-    def __new__(cls, prev_snapshot, current_snapshot, **base_kwargs):
-        if prev_snapshot or current_snapshot:
-            from changedetectionio import diff as diff_module
-            rendered = diff_module.render_diff(prev_snapshot, current_snapshot, **base_kwargs)
-        else:
-            rendered = ''
-        instance = super().__new__(cls, rendered)
-        instance._prev = prev_snapshot
-        instance._current = current_snapshot
-        instance._base_kwargs = base_kwargs
-        return instance
-
-    def __call__(self, lines=None, added_only=False, removed_only=False, context=0,
-                 word_diff=None, case_insensitive=False, ignore_junk=False):
-        from changedetectionio import diff as diff_module
-        kwargs = dict(self._base_kwargs)
-
-        if added_only:
-            kwargs['include_removed'] = False
-        if removed_only:
-            kwargs['include_added'] = False
-        if context:
-            kwargs['context_lines'] = int(context)
-        if word_diff is not None:
-            kwargs['word_diff'] = bool(word_diff)
-        if case_insensitive:
-            kwargs['case_insensitive'] = True
-        if ignore_junk:
-            kwargs['ignore_junk'] = True
-
-        result = diff_module.render_diff(self._prev or '', self._current or '', **kwargs)
-
-        if lines is not None:
-            result = '\n'.join(result.splitlines()[:int(lines)])
-
-        return result
-
-
-
 # What is passed around as notification context, also used as the complete list of valid {{ tokens }}
 class NotificationContextData(dict):
     def __init__(self, initial_data=None, **kwargs):
-        # ValidateJinja2Template() validates against the keynames of this dict to check for valid tokens in the body (user submission)
         super().__init__({
             'base_url': None,
-            'change_datetime': FormattableTimestamp(time.time()),
             'current_snapshot': None,
-            'diff': FormattableDiff('', ''),
-            'diff_clean': FormattableDiff('', '', include_change_type_prefix=False),
-            'diff_added': FormattableDiff('', '', include_removed=False),
-            'diff_added_clean': FormattableDiff('', '', include_removed=False, include_change_type_prefix=False),
-            'diff_full': FormattableDiff('', '', include_equal=True),
-            'diff_full_clean': FormattableDiff('', '', include_equal=True, include_change_type_prefix=False),
-            'diff_patch': FormattableDiff('', '', patch_format=True),
-            'diff_removed': FormattableDiff('', '', include_added=False),
-            'diff_removed_clean': FormattableDiff('', '', include_added=False, include_change_type_prefix=False),
+            'diff': None,
+            'diff_clean': None,
+            'diff_added': None,
+            'diff_added_clean': None,
+            'diff_full': None,
+            'diff_full_clean': None,
+            'diff_patch': None,
+            'diff_removed': None,
+            'diff_removed_clean': None,
             'diff_url': None,
             'markup_text_links_to_html_links': False, # If automatic conversion of plaintext to HTML should happen
             'notification_timestamp': time.time(),
-            'prev_snapshot': None,
             'preview_url': None,
             'screenshot': None,
+            'triggered_text': None,
             'timestamp_from': None,
             'timestamp_to': None,
-            'triggered_text': None,
             'uuid': 'XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX',  # Converted to 'watch_uuid' in create_notification_parameters
             'watch_mime_type': None,
             'watch_tag': None,
             'watch_title': None,
             'watch_url': 'https://WATCH-PLACE-HOLDER/',
-            'watch_uuid': 'XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX',  # Converted to 'watch_uuid' in create_notification_parameters
         })
 
         # Apply any initial data passed in
@@ -197,7 +103,7 @@ class NotificationContextData(dict):
         So we can test the output in the notification body
         """
         for key in self.keys():
-            if key in ['uuid', 'time', 'watch_uuid', 'change_datetime'] or key.startswith('diff'):
+            if key in ['uuid', 'time', 'watch_uuid']:
                 continue
             rand_str = 'RANDOM-PLACEHOLDER-'+''.join(random.choices(string.ascii_letters + string.digits, k=12))
             self[key] = rand_str
@@ -209,6 +115,24 @@ class NotificationContextData(dict):
 
         super().__setitem__(key, value)
 
+def timestamp_to_localtime(timestamp):
+    # Format the date using locale-aware formatting with timezone
+    dt = datetime.datetime.fromtimestamp(int(timestamp))
+    dt = dt.replace(tzinfo=pytz.UTC)
+
+    # Get local timezone-aware datetime
+    local_tz = datetime.datetime.now().astimezone().tzinfo
+    local_dt = dt.astimezone(local_tz)
+
+    # Format date with timezone - using strftime for locale awareness
+    try:
+        formatted_date = local_dt.strftime('%Y-%m-%d %H:%M:%S %Z')
+    except:
+        # Fallback if locale issues
+        formatted_date = local_dt.isoformat()
+
+    return formatted_date
+
 def add_rendered_diff_to_notification_vars(notification_scan_text:str, prev_snapshot:str, current_snapshot:str, word_diff:bool):
     """
     Efficiently renders only the diff placeholders that are actually used in the notification text.
@@ -226,12 +150,13 @@ def add_rendered_diff_to_notification_vars(notification_scan_text:str, prev_snap
     Returns:
         dict: Only the diff placeholders that were found in notification_scan_text, with rendered content
     """
+    from changedetectionio import diff
     import re
+    from functools import lru_cache
 
     now = time.time()
 
-    # Define base kwargs for each diff variant — these become the stored defaults
-    # on the FormattableDiff object, so {{ diff(lines=5) }} overrides on top of them
+    # Define specifications for each diff variant
     diff_specs = {
         'diff': {'word_diff': word_diff},
         'diff_clean': {'word_diff': word_diff, 'include_change_type_prefix': False},
@@ -244,15 +169,22 @@ def add_rendered_diff_to_notification_vars(notification_scan_text:str, prev_snap
         'diff_removed_clean': {'word_diff': word_diff, 'include_added': False, 'include_change_type_prefix': False},
     }
 
+    # Memoize render_diff to avoid duplicate renders with same kwargs
+    @lru_cache(maxsize=4)
+    def cached_render(kwargs_tuple):
+        return diff.render_diff(prev_snapshot, current_snapshot, **dict(kwargs_tuple))
+
     ret = {}
     rendered_count = 0
-    # Only create FormattableDiff objects for diff keys actually used in the notification text
+    # Only check and render diff keys that exist in NotificationContextData
     for key in NotificationContextData().keys():
         if key.startswith('diff') and key in diff_specs:
             # Check if this placeholder is actually used in the notification text
             pattern = rf"(?<![A-Za-z0-9_]){re.escape(key)}(?![A-Za-z0-9_])"
             if re.search(pattern, notification_scan_text, re.IGNORECASE):
-                ret[key] = FormattableDiff(prev_snapshot, current_snapshot, **diff_specs[key])
+                kwargs = diff_specs[key]
+                # Convert dict to sorted tuple for cache key (handles duplicate kwarg combinations)
+                ret[key] = cached_render(tuple(sorted(kwargs.items())))
                 rendered_count += 1
 
     if rendered_count:
@@ -266,7 +198,7 @@ def set_basic_notification_vars(current_snapshot, prev_snapshot, watch, triggere
         'current_snapshot': current_snapshot,
         'prev_snapshot': prev_snapshot,
         'screenshot': watch.get_screenshot() if watch and watch.get('notification_screenshot') else None,
-        'change_datetime': FormattableTimestamp(timestamp_changed) if timestamp_changed else None,
+        'change_datetime': timestamp_to_localtime(timestamp_changed) if timestamp_changed else None,
         'triggered_text': triggered_text,
         'uuid': watch.get('uuid') if watch else None,
         'watch_url': watch.get('url') if watch else None,

changedetectionio/pluggy_interface.py

@@ -105,75 +105,6 @@ class ChangeDetectionSpec:
         """
         pass
 
-    @hookspec
-    def register_processor(self):
-        """Register an external processor plugin.
-
-        External packages can implement this hook to register custom processors
-        that will be discovered alongside built-in processors.
-
-        Returns:
-            dict or None: Dictionary with processor information:
-                {
-                    'processor_name': str,      # Machine name (e.g., 'osint_recon')
-                    'processor_module': module, # Module containing processor.py
-                    'processor_class': class,   # The perform_site_check class
-                    'metadata': {               # Optional metadata
-                        'name': str,            # Display name
-                        'description': str,     # Description
-                        'processor_weight': int,# Sort weight (lower = higher priority)
-                        'list_badge_text': str, # Badge text for UI
-                    }
-                }
-                Return None if this plugin doesn't provide a processor
-        """
-        pass
-
-    @hookspec
-    def update_handler_alter(update_handler, watch, datastore):
-        """Modify or wrap the update_handler before it processes a watch.
-
-        This hook is called after the update_handler (perform_site_check instance) is created
-        but before it calls call_browser() and run_changedetection(). Plugins can use this to:
-        - Wrap the handler to add logging/metrics
-        - Modify handler configuration
-        - Add custom preprocessing logic
-
-        Args:
-            update_handler: The perform_site_check instance that will process the watch
-            watch: The watch dict being processed
-            datastore: The application datastore
-
-        Returns:
-            object or None: Return a modified/wrapped handler, or None to keep the original.
-                           If multiple plugins return handlers, they are chained in registration order.
-        """
-        pass
-
-    @hookspec
-    def update_finalize(update_handler, watch, datastore, processing_exception):
-        """Called after watch processing completes (success or failure).
-
-        This hook is called in the finally block after all processing is complete,
-        allowing plugins to perform cleanup, update metrics, or log final status.
-
-        The plugin can access update_handler.last_logging_insert_id if it was stored
-        during update_handler_alter, and use processing_exception to determine if
-        the processing succeeded or failed.
-
-        Args:
-            update_handler: The perform_site_check instance (may be None if creation failed)
-            watch: The watch dict that was processed (may be None if not loaded)
-            datastore: The application datastore
-            processing_exception: The exception from the main processing block, or None if successful.
-                                 This does NOT include cleanup exceptions - only exceptions from
-                                 the actual watch processing (fetch, diff, etc).
-
-        Returns:
-            None: This hook doesn't return a value
-        """
-        pass
-
 
 # Set up Plugin Manager
 plugin_manager = pluggy.PluginManager(PLUGIN_NAMESPACE)
@@ -237,23 +168,14 @@ def register_builtin_fetchers():
     This is called from content_fetchers/__init__.py after all fetchers are imported
     to avoid circular import issues.
     """
-    from changedetectionio.content_fetchers import requests, puppeteer, webdriver_selenium
-    from changedetectionio.content_fetchers.playwright import CDP, chrome, firefox, webkit
+    from changedetectionio.content_fetchers import requests, playwright, puppeteer, webdriver_selenium
 
+    # Register each built-in fetcher plugin
     if hasattr(requests, 'requests_plugin'):
         plugin_manager.register(requests.requests_plugin, 'builtin_requests')
 
-    if hasattr(CDP, 'cdp_plugin'):
-        plugin_manager.register(CDP.cdp_plugin, 'builtin_playwright_cdp')
-
-    if hasattr(chrome, 'chrome_plugin'):
-        plugin_manager.register(chrome.chrome_plugin, 'builtin_playwright_chrome')
-
-    if hasattr(firefox, 'firefox_plugin'):
-        plugin_manager.register(firefox.firefox_plugin, 'builtin_playwright_firefox')
-
-    if hasattr(webkit, 'webkit_plugin'):
-        plugin_manager.register(webkit.webkit_plugin, 'builtin_playwright_webkit')
+    if hasattr(playwright, 'playwright_plugin'):
+        plugin_manager.register(playwright.playwright_plugin, 'builtin_playwright')
 
     if hasattr(puppeteer, 'puppeteer_plugin'):
         plugin_manager.register(puppeteer.puppeteer_plugin, 'builtin_puppeteer')
@@ -369,28 +291,57 @@ def get_active_plugins():
 
 
 def get_fetcher_capabilities(watch, datastore):
-    """Get capability flags for a watch's resolved fetcher.
+    """Get capability flags for a watch's fetcher.
 
-    Uses the BrowserProfile resolution chain (watch → tag → global → built-in)
-    to determine the actual fetcher class, then reads its capability flags.
+    Args:
+        watch: The watch object/dict
+        datastore: The datastore to resolve 'system' fetcher
 
     Returns:
-        dict: {'supports_browser_steps': bool, 'supports_screenshots': bool,
-               'supports_xpath_element_data': bool}
+        dict: Dictionary with capability flags:
+            {
+                'supports_browser_steps': bool,
+                'supports_screenshots': bool,
+                'supports_xpath_element_data': bool
+            }
     """
-    from changedetectionio.model.browser_profile import resolve_browser_profile
+    # Get the fetcher name from watch
+    fetcher_name = watch.get('fetch_backend', 'system')
+
+    # Resolve 'system' to actual fetcher
+    if fetcher_name == 'system':
+        fetcher_name = datastore.data['settings']['application'].get('fetch_backend', 'html_requests')
+
+    # Get the fetcher class
     from changedetectionio import content_fetchers
 
-    profile = resolve_browser_profile(watch, datastore)
-    fetcher_class = content_fetchers.get_fetcher(profile.fetch_backend)
+    # Try to get from built-in fetchers first
+    if hasattr(content_fetchers, fetcher_name):
+        fetcher_class = getattr(content_fetchers, fetcher_name)
+        return {
+            'supports_browser_steps': getattr(fetcher_class, 'supports_browser_steps', False),
+            'supports_screenshots': getattr(fetcher_class, 'supports_screenshots', False),
+            'supports_xpath_element_data': getattr(fetcher_class, 'supports_xpath_element_data', False)
+        }
 
-    if fetcher_class is None:
-        return {'supports_browser_steps': False, 'supports_screenshots': False, 'supports_xpath_element_data': False}
+    # Try to get from plugin-provided fetchers
+    # Query all plugins for registered fetchers
+    plugin_fetchers = plugin_manager.hook.register_content_fetcher()
+    for fetcher_registration in plugin_fetchers:
+        if fetcher_registration:
+            name, fetcher_class = fetcher_registration
+            if name == fetcher_name:
+                return {
+                    'supports_browser_steps': getattr(fetcher_class, 'supports_browser_steps', False),
+                    'supports_screenshots': getattr(fetcher_class, 'supports_screenshots', False),
+                    'supports_xpath_element_data': getattr(fetcher_class, 'supports_xpath_element_data', False)
+                }
 
+    # Default: no capabilities
     return {
-        'supports_browser_steps': getattr(fetcher_class, 'supports_browser_steps', False),
-        'supports_screenshots': getattr(fetcher_class, 'supports_screenshots', False),
-        'supports_xpath_element_data': getattr(fetcher_class, 'supports_xpath_element_data', False),
+        'supports_browser_steps': False,
+        'supports_screenshots': False,
+        'supports_xpath_element_data': False
     }
 
 
@@ -524,66 +475,4 @@ def get_plugin_template_paths():
                 template_paths.append(templates_dir)
                 logger.debug(f"Added plugin template path: {templates_dir}")
 
-    return template_paths
-
-
-def apply_update_handler_alter(update_handler, watch, datastore):
-    """Apply update_handler_alter hooks from all plugins.
-
-    Allows plugins to wrap or modify the update_handler before it processes a watch.
-    Multiple plugins can chain modifications - each plugin receives the result from
-    the previous plugin.
-
-    Args:
-        update_handler: The perform_site_check instance to potentially modify
-        watch: The watch dict being processed
-        datastore: The application datastore
-
-    Returns:
-        object: The (potentially modified/wrapped) update_handler
-    """
-    # Get all plugins that implement the update_handler_alter hook
-    results = plugin_manager.hook.update_handler_alter(
-        update_handler=update_handler,
-        watch=watch,
-        datastore=datastore
-    )
-
-    # Chain results - each plugin gets the result from the previous one
-    current_handler = update_handler
-    if results:
-        for result in results:
-            if result is not None:
-                logger.debug(f"Plugin modified update_handler for watch {watch.get('uuid')}")
-                current_handler = result
-
-    return current_handler
-
-
-def apply_update_finalize(update_handler, watch, datastore, processing_exception):
-    """Apply update_finalize hooks from all plugins.
-
-    Called in the finally block after watch processing completes, allowing plugins
-    to perform cleanup, update metrics, or log final status.
-
-    Args:
-        update_handler: The perform_site_check instance (may be None)
-        watch: The watch dict that was processed (may be None)
-        datastore: The application datastore
-        processing_exception: The exception from processing, or None if successful
-
-    Returns:
-        None
-    """
-    try:
-        # Call all plugins that implement the update_finalize hook
-        plugin_manager.hook.update_finalize(
-            update_handler=update_handler,
-            watch=watch,
-            datastore=datastore,
-            processing_exception=processing_exception
-        )
-    except Exception as e:
-        # Don't let plugin errors crash the worker
-        logger.error(f"Error in update_finalize hook: {e}")
-        logger.exception(f"update_finalize hook exception details:")
+    return template_paths

changedetectionio/processors/README.md

@@ -9,15 +9,6 @@ Some suggestions for the future
 
 - `graphical` 
 
-## API schema extension (`api.yaml`)
-
-A processor can extend the Watch/Tag API schema by placing an `api.yaml` alongside its `__init__.py`.
-Define a `components.schemas.processor_config_<name>` entry and it will be merged into `WatchBase` at startup,
-making `processor_config_<name>` a valid field on all watch create/update API calls.
-The fully merged spec is served live at `/api/v1/full-spec`.
-
-See `restock_diff/api.yaml` for a working example.
-
 ## Todo
 
 - Make each processor return a extra list of sub-processed (so you could configure a single processor in different ways)

changedetectionio/processors/__init__.py

@@ -1,6 +1,6 @@
 from functools import lru_cache
 from loguru import logger
-from flask_babel import gettext, get_locale
+from flask_babel import gettext
 import importlib
 import inspect
 import os
@@ -17,11 +17,9 @@ def find_sub_packages(package_name):
     return [name for _, name, is_pkg in pkgutil.iter_modules(package.__path__) if is_pkg]
 
 
-@lru_cache(maxsize=1)
 def find_processors():
     """
     Find all subclasses of DifferenceDetectionProcessor in the specified package.
-    Results are cached to avoid repeated discovery.
 
     :param package_name: The name of the package to scan for processor modules.
     :return: A list of (module, class) tuples.
@@ -48,23 +46,6 @@ def find_processors():
         except (ModuleNotFoundError, ImportError) as e:
             logger.warning(f"Failed to import module {module_name}: {e} (find_processors())")
 
-    # Discover plugin processors via pluggy
-    try:
-        from changedetectionio.pluggy_interface import plugin_manager
-        plugin_results = plugin_manager.hook.register_processor()
-
-        for result in plugin_results:
-            if result and isinstance(result, dict):
-                processor_module = result.get('processor_module')
-                processor_name = result.get('processor_name')
-
-                if processor_module and processor_name:
-                    processors.append((processor_module, processor_name))
-                    plugin_path = getattr(processor_module, '__file__', 'unknown location')
-                    logger.info(f"Registered plugin processor: {processor_name} from {plugin_path}")
-    except Exception as e:
-        logger.warning(f"Error loading plugin processors: {e}")
-
     return processors
 
 
@@ -116,138 +97,54 @@ def find_processor_module(processor_name):
     return None
 
 
-def get_processor_module(processor_name):
+def available_processors():
     """
-    Get the actual processor module (with perform_site_check class) by name.
-    Works for both built-in and plugin processors.
-
-    Args:
-        processor_name: Processor machine name (e.g., 'text_json_diff', 'osint_recon')
-
-    Returns:
-        module: The processor module containing perform_site_check, or None if not found
+    Get a list of processors by name and description for the UI elements.
+    Can be filtered via ALLOWED_PROCESSORS environment variable (comma-separated list).
+    :return: A list :)
     """
-    processor_classes = find_processors()
-    processor_tuple = next((tpl for tpl in processor_classes if tpl[1] == processor_name), None)
 
-    if processor_tuple:
-        # Return the actual processor module (first element of tuple)
-        return processor_tuple[0]
-
-    return None
-
-
-def get_processor_submodule(processor_name, submodule_name):
-    """
-    Get an optional submodule from a processor (e.g., 'difference', 'extract', 'preview').
-    Works for both built-in and plugin processors.
-
-    Args:
-        processor_name: Processor machine name (e.g., 'text_json_diff', 'osint_recon')
-        submodule_name: Name of the submodule (e.g., 'difference', 'extract', 'preview')
-
-    Returns:
-        module: The submodule if it exists, or None if not found
-    """
-    processor_classes = find_processors()
-    processor_tuple = next((tpl for tpl in processor_classes if tpl[1] == processor_name), None)
-
-    if not processor_tuple:
-        return None
-
-    processor_module = processor_tuple[0]
-    parent_module = get_parent_module(processor_module)
-
-    if not parent_module:
-        return None
-
-    # Try to import the submodule
-    try:
-        # For built-in processors: changedetectionio.processors.text_json_diff.difference
-        # For plugin processors: changedetectionio_osint.difference
-        parent_module_name = parent_module.__name__
-        submodule_full_name = f"{parent_module_name}.{submodule_name}"
-        return importlib.import_module(submodule_full_name)
-    except (ModuleNotFoundError, ImportError):
-        return None
-
-
-@lru_cache(maxsize=1)
-def get_plugin_processor_metadata():
-    """Get metadata from plugin processors."""
-    metadata = {}
-    try:
-        from changedetectionio.pluggy_interface import plugin_manager
-        plugin_results = plugin_manager.hook.register_processor()
-
-        for result in plugin_results:
-            if result and isinstance(result, dict):
-                processor_name = result.get('processor_name')
-                meta = result.get('metadata', {})
-                if processor_name:
-                    metadata[processor_name] = meta
-    except Exception as e:
-        logger.warning(f"Error getting plugin processor metadata: {e}")
-    return metadata
-
-@lru_cache(maxsize=32)
-def _available_processors_cached(locale_str):
-    """
-    Internal cached function that includes locale in cache key.
-    This ensures translations are cached per-language instead of globally.
-
-    :param locale_str: The locale string (e.g., 'en', 'it', 'zh')
-    :return: A list of tuples (processor_name, translated_description, weight)
-    """
     processor_classes = find_processors()
 
-    # Check if DISABLED_PROCESSORS env var is set
-    disabled_processors_env = os.getenv('DISABLED_PROCESSORS', 'image_ssim_diff').strip()
-    disabled_processors = []
-    if disabled_processors_env:
+    # Check if ALLOWED_PROCESSORS env var is set
+    # For now we disable it, need to make a deploy with lots of new code and this will be an overload
+    allowed_processors_env = os.getenv('ALLOWED_PROCESSORS', 'text_json_diff, restock_diff').strip()
+    allowed_processors = None
+    if allowed_processors_env:
         # Parse comma-separated list and strip whitespace
-        disabled_processors = [p.strip() for p in disabled_processors_env.split(',') if p.strip()]
-        logger.info(f"DISABLED_PROCESSORS set, disabling: {disabled_processors}")
+        allowed_processors = [p.strip() for p in allowed_processors_env.split(',') if p.strip()]
+        logger.info(f"ALLOWED_PROCESSORS set, filtering to: {allowed_processors}")
 
     available = []
-    plugin_metadata = get_plugin_processor_metadata()
-
     for module, sub_package_name in processor_classes:
-        # Skip disabled processors
-        if sub_package_name in disabled_processors:
-            logger.debug(f"Skipping processor '{sub_package_name}' (in DISABLED_PROCESSORS)")
+        # Filter by allowed processors if set
+        if allowed_processors and sub_package_name not in allowed_processors:
+            logger.debug(f"Skipping processor '{sub_package_name}' (not in ALLOWED_PROCESSORS)")
             continue
 
-        # Check if this is a plugin processor
-        if sub_package_name in plugin_metadata:
-            meta = plugin_metadata[sub_package_name]
-            description = gettext(meta.get('name', sub_package_name))
-            # Plugin processors start from weight 10 to separate them from built-in processors
-            weight = 100 + meta.get('processor_weight', 0)
+        # Try to get the 'name' attribute from the processor module first
+        if hasattr(module, 'name'):
+            description = gettext(module.name)
         else:
-            # Try to get the 'name' attribute from the processor module first
-            if hasattr(module, 'name'):
-                description = gettext(module.name)
+            # Fall back to processor_description from parent module's __init__.py
+            parent_module = get_parent_module(module)
+            if parent_module and hasattr(parent_module, 'processor_description'):
+                description = gettext(parent_module.processor_description)
             else:
-                # Fall back to processor_description from parent module's __init__.py
-                parent_module = get_parent_module(module)
-                if parent_module and hasattr(parent_module, 'processor_description'):
-                    description = gettext(parent_module.processor_description)
-                else:
-                    # Final fallback to a readable name
-                    description = sub_package_name.replace('_', ' ').title()
+                # Final fallback to a readable name
+                description = sub_package_name.replace('_', ' ').title()
 
-            # Get weight for sorting (lower weight = higher in list)
-            weight = 0  # Default weight for processors without explicit weight
+        # Get weight for sorting (lower weight = higher in list)
+        weight = 0  # Default weight for processors without explicit weight
 
-            # Check processor module itself first
-            if hasattr(module, 'processor_weight'):
-                weight = module.processor_weight
-            else:
-                # Fall back to parent module (package __init__.py)
-                parent_module = get_parent_module(module)
-                if parent_module and hasattr(parent_module, 'processor_weight'):
-                    weight = parent_module.processor_weight
+        # Check processor module itself first
+        if hasattr(module, 'processor_weight'):
+            weight = module.processor_weight
+        else:
+            # Fall back to parent module (package __init__.py)
+            parent_module = get_parent_module(module)
+            if parent_module and hasattr(parent_module, 'processor_weight'):
+                weight = parent_module.processor_weight
 
         available.append((sub_package_name, description, weight))
 
@@ -257,36 +154,6 @@ def _available_processors_cached(locale_str):
     # Return as tuples without weight (for backwards compatibility)
     return [(name, desc) for name, desc, weight in available]
 
-def available_processors():
-    """
-    Get a list of processors by name and description for the UI elements.
-    Can be filtered via DISABLED_PROCESSORS environment variable (comma-separated list).
-
-    This function delegates to a locale-aware cached version to ensure translations
-    are cached per-language instead of globally.
-
-    :return: A list of tuples (processor_name, translated_description)
-    """
-    # Get current locale and use it as cache key
-    # Convert Babel Locale object to string for use as cache key
-    locale = get_locale()
-    locale_str = str(locale) if locale else 'en'
-    return _available_processors_cached(locale_str)
-
-
-def get_default_processor():
-    """
-    Get the default processor to use when none is specified.
-    Returns the first available processor based on weight (lowest weight = highest priority).
-    This ensures forms auto-select a valid processor even when DISABLED_PROCESSORS filters the list.
-
-    :return: The processor name string (e.g., 'text_json_diff')
-    """
-    available = available_processors()
-    if available:
-        return available[0][0]  # Return the processor name from first tuple
-    return 'text_json_diff'  # Fallback if somehow no processors are available
-
 
 def get_processor_badge_texts():
     """
@@ -412,76 +279,3 @@ def get_processor_badge_css():
 
     return '\n\n'.join(css_rules)
 
-
-def save_processor_config(datastore, watch_uuid, config_data):
-    """
-    Save processor-specific configuration to JSON file.
-
-    This is a shared helper function used by both the UI edit form and API endpoints
-    to consistently handle processor configuration storage.
-
-    Args:
-        datastore: The application datastore instance
-        watch_uuid: UUID of the watch
-        config_data: Dictionary of configuration data to save (with processor_config_* prefix removed)
-
-    Returns:
-        bool: True if saved successfully, False otherwise
-    """
-    if not config_data:
-        return True
-
-    try:
-        from changedetectionio.processors.base import difference_detection_processor
-
-        # Get processor name from watch
-        watch = datastore.data['watching'].get(watch_uuid)
-        if not watch:
-            logger.error(f"Cannot save processor config: watch {watch_uuid} not found")
-            return False
-
-        processor_name = watch.get('processor', 'text_json_diff')
-
-        # Create a processor instance to access config methods
-        processor_instance = difference_detection_processor(datastore, watch_uuid)
-
-        # Use processor name as filename so each processor keeps its own config
-        config_filename = f'{processor_name}.json'
-        processor_instance.update_extra_watch_config(config_filename, config_data)
-
-        logger.debug(f"Saved processor config to {config_filename}: {config_data}")
-        return True
-
-    except Exception as e:
-        logger.error(f"Failed to save processor config: {e}")
-        return False
-
-
-def extract_processor_config_from_form_data(form_data):
-    """
-    Extract processor_config_* fields from form data and return separate dicts.
-
-    This is a shared helper function used by both the UI edit form and API endpoints
-    to consistently handle processor configuration extraction.
-
-    IMPORTANT: This function modifies form_data in-place by removing processor_config_* fields.
-
-    Args:
-        form_data: Dictionary of form data (will be modified in-place)
-
-    Returns:
-        dict: Dictionary of processor config data (with processor_config_* prefix removed)
-    """
-    processor_config_data = {}
-
-    # Use list() to create a copy of keys since we're modifying the dict
-    for field_name in list(form_data.keys()):
-        if field_name.startswith('processor_config_'):
-            config_key = field_name.replace('processor_config_', '')
-            # Save all values (including empty strings) to allow explicit clearing of settings
-            processor_config_data[config_key] = form_data[field_name]
-            # Remove from form_data to prevent it from reaching datastore
-            del form_data[field_name]
-
-    return processor_config_data
-

changedetectionio/processors/base.py

@@ -1,15 +1,10 @@
-import asyncio
 import re
 import hashlib
-
-from changedetectionio.browser_steps.browser_steps import browser_steps_get_valid_steps
 from changedetectionio.content_fetchers.base import Fetcher
 from changedetectionio.strtobool import strtobool
-from changedetectionio.validate_url import is_private_hostname
 from copy import deepcopy
 from abc import abstractmethod
 import os
-from urllib.parse import urlparse
 from loguru import logger
 
 SCREENSHOT_FORMAT_JPEG = 'JPEG'
@@ -23,164 +18,92 @@ class difference_detection_processor():
     watch = None
     xpath_data = None
     preferred_proxy = None
-    preferred_proxy_override = None   # Set externally to force a specific proxy (e.g. proxy checker)
     screenshot_format = SCREENSHOT_FORMAT_JPEG
-    last_raw_content_checksum = None
 
     def __init__(self, datastore, watch_uuid):
         self.datastore = datastore
         self.watch_uuid = watch_uuid
-
-        # Create a stable snapshot of the watch for processing
-        # Why deepcopy?
-        # 1. Prevents "dict changed during iteration" errors if watch is modified during processing
-        # 2. Preserves Watch object with properties (.link, .is_pdf, etc.) - can't use dict()
-        # 3. Safe now: Watch.__deepcopy__() shares datastore ref (no memory leak) but copies dict data
         self.watch = deepcopy(self.datastore.data['watching'].get(watch_uuid))
-        if self.watch is None:
-            raise KeyError(f"Watch UUID {watch_uuid} not found in datastore (deleted before processing?)")
-
         # Generic fetcher that should be extended (requests, playwright etc)
         self.fetcher = Fetcher()
 
-        # Load the last raw content checksum from file
-        self.read_last_raw_content_checksum()
-
-    def update_last_raw_content_checksum(self, checksum):
-        """
-        Save the raw content MD5 checksum to file.
-        This is used for skip logic - avoid reprocessing if raw HTML unchanged.
-        """
-        if not checksum:
-            return
-
-        watch = self.datastore.data['watching'].get(self.watch_uuid)
-        if not watch:
-            return
-
-        data_dir = watch.data_dir
-        if not data_dir:
-            return
-
-        watch.ensure_data_dir_exists()
-        checksum_file = os.path.join(data_dir, 'last-checksum.txt')
-
-        try:
-            with open(checksum_file, 'w', encoding='utf-8') as f:
-                f.write(checksum)
-            self.last_raw_content_checksum = checksum
-        except IOError as e:
-            logger.warning(f"Failed to write checksum file for {self.watch_uuid}: {e}")
-
-    def read_last_raw_content_checksum(self):
-        """
-        Read the last raw content MD5 checksum from file.
-        Returns None if file doesn't exist (first run) or can't be read.
-        """
-        watch = self.datastore.data['watching'].get(self.watch_uuid)
-        if not watch:
-            self.last_raw_content_checksum = None
-            return
-
-        data_dir = watch.data_dir
-        if not data_dir:
-            self.last_raw_content_checksum = None
-            return
-
-        checksum_file = os.path.join(data_dir, 'last-checksum.txt')
-
-        if not os.path.isfile(checksum_file):
-            self.last_raw_content_checksum = None
-            return
-
-        try:
-            with open(checksum_file, 'r', encoding='utf-8') as f:
-                self.last_raw_content_checksum = f.read().strip()
-        except IOError as e:
-            logger.warning(f"Failed to read checksum file for {self.watch_uuid}: {e}")
-            self.last_raw_content_checksum = None
-
-
-    async def validate_iana_url(self):
-        """Pre-flight SSRF check — runs DNS lookup in executor to avoid blocking the event loop.
-        Covers all fetchers (requests, playwright, puppeteer, plugins) since every fetch goes
-        through call_browser().
-        """
-        if strtobool(os.getenv('ALLOW_IANA_RESTRICTED_ADDRESSES', 'false')):
-            return
-        parsed = urlparse(self.watch.link)
-        if not parsed.hostname:
-            return
-        loop = asyncio.get_running_loop()
-        if await loop.run_in_executor(None, is_private_hostname, parsed.hostname):
-            raise Exception(
-                f"Fetch blocked: '{self.watch.link}' resolves to a private/reserved IP address. "
-                f"Set ALLOW_IANA_RESTRICTED_ADDRESSES=true to allow."
-            )
-
-    async def call_browser(self):
+    async def call_browser(self, preferred_proxy_id=None):
 
         from requests.structures import CaseInsensitiveDict
-        from changedetectionio.model.browser_profile import resolve_browser_profile, BUILTIN_REQUESTS
 
         url = self.watch.link
 
-        # Protect against file:, file:/, file:// access
+        # Protect against file:, file:/, file:// access, check the real "link" without any meta "source:" etc prepended.
         if re.search(r'^file:', url.strip(), re.IGNORECASE):
             if not strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
-                raise Exception("file:// type access is denied for security reasons.")
+                raise Exception(
+                    "file:// type access is denied for security reasons."
+                )
 
-        await self.validate_iana_url()
+        # Requests, playwright, other browser via wss:// etc, fetch_extra_something
+        prefer_fetch_backend = self.watch.get('fetch_backend', 'system')
 
-        # Resolve the full browser profile for this watch (watch → tag → global → built-in)
-        profile = resolve_browser_profile(self.watch, self.datastore)
+        # Proxy ID "key"
+        preferred_proxy_id = preferred_proxy_id if preferred_proxy_id else self.datastore.get_preferred_proxy_for_watch(
+            uuid=self.watch.get('uuid'))
 
-        # PDFs always use the requests fetcher — browsers render them in an embedded viewer
+        # Pluggable content self.fetcher
+        if not prefer_fetch_backend or prefer_fetch_backend == 'system':
+            prefer_fetch_backend = self.datastore.data['settings']['application'].get('fetch_backend')
+
+        # In the case that the preferred fetcher was a browser config with custom connection URL..
+        # @todo - on save watch, if its extra_browser_ then it should be obvious it will use playwright (like if its requests now..)
+        custom_browser_connection_url = None
+        if prefer_fetch_backend.startswith('extra_browser_'):
+            (t, key) = prefer_fetch_backend.split('extra_browser_')
+            connection = list(
+                filter(lambda s: (s['browser_name'] == key), self.datastore.data['settings']['requests'].get('extra_browsers', [])))
+            if connection:
+                prefer_fetch_backend = 'html_webdriver'
+                custom_browser_connection_url = connection[0].get('browser_connection_url')
+
+        # PDF should be html_requests because playwright will serve it up (so far) in a embedded page
         # @todo https://github.com/dgtlmoon/changedetection.io/issues/2019
+        # @todo needs test to or a fix
         if self.watch.is_pdf:
-            profile = BUILTIN_REQUESTS
+            prefer_fetch_backend = "html_requests"
 
-        # Resolve proxy — custom browser endpoints skip proxy (connection URL is already routing)
-        proxy_url = None
-        preferred_proxy_id = self.preferred_proxy_override or self.datastore.get_preferred_proxy_for_watch(uuid=self.watch.get('uuid'))
-        if preferred_proxy_id:
-            if not profile.browser_connection_url:
-                proxy_url = self.datastore.proxy_list.get(preferred_proxy_id, {}).get('url')
-                logger.debug(f"Proxy '{preferred_proxy_id}' → '{proxy_url}' for {url}")
-            else:
-                logger.debug("Skipping proxy — custom browser_connection_url is set")
-
-        logger.debug(f"BrowserProfile '{profile.get_machine_name()}' (fetcher={profile.fetch_backend}) for watch {self.watch['uuid']}")
-
-        # Select the fetcher class
+        # Grab the right kind of 'fetcher', (playwright, requests, etc)
         from changedetectionio import content_fetchers
-        fetcher_class_name = profile.get_fetcher_class_name()
+        if hasattr(content_fetchers, prefer_fetch_backend):
+            # @todo TEMPORARY HACK - SWITCH BACK TO PLAYWRIGHT FOR BROWSERSTEPS
+            if prefer_fetch_backend == 'html_webdriver' and self.watch.has_browser_steps:
+                # This is never supported in selenium anyway
+                logger.warning(
+                    "Using playwright fetcher override for possible puppeteer request in browsersteps, because puppetteer:browser steps is incomplete.")
+                from changedetectionio.content_fetchers.playwright import fetcher as playwright_fetcher
+                fetcher_obj = playwright_fetcher
+            else:
+                fetcher_obj = getattr(content_fetchers, prefer_fetch_backend)
+        else:
+            # What it referenced doesnt exist, Just use a default
+            fetcher_obj = getattr(content_fetchers, "html_requests")
 
-        fetcher_obj = content_fetchers.get_fetcher(fetcher_class_name)
-        if fetcher_obj is None:
-            logger.warning(f"Fetcher '{fetcher_class_name}' not found, falling back to requests")
-            fetcher_obj = content_fetchers.get_fetcher('requests')
-        elif self.watch.has_browser_steps and not getattr(fetcher_obj, 'supports_browser_steps', False):
-            # Browser steps require Playwright — override if the resolved fetcher doesn't support them
-            logger.warning(f"Fetcher '{fetcher_class_name}' does not support browser steps, overriding to Playwright")
-            fetcher_obj = content_fetchers.get_fetcher('playwright')
+        proxy_url = None
+        if preferred_proxy_id:
+            # Custom browser endpoints should NOT have a proxy added
+            if not prefer_fetch_backend.startswith('extra_browser_'):
+                proxy_url = self.datastore.proxy_list.get(preferred_proxy_id).get('url')
+                logger.debug(f"Selected proxy key '{preferred_proxy_id}' as proxy URL '{proxy_url}' for {url}")
+            else:
+                logger.debug("Skipping adding proxy data when custom Browser endpoint is specified. ")
 
-        self.fetcher = fetcher_obj(
-            proxy_override=proxy_url,
-            custom_browser_connection_url=profile.browser_connection_url,
-            screenshot_format=self.screenshot_format,
-            # BrowserProfile fields — browser fetchers use these; html_requests ignores them
-            viewport_width=profile.viewport_width,
-            viewport_height=profile.viewport_height,
-            block_images=profile.block_images,
-            block_fonts=profile.block_fonts,
-            profile_user_agent=profile.user_agent,
-            ignore_https_errors=profile.ignore_https_errors,
-            locale=profile.locale,
-        )
+        logger.debug(f"Using proxy '{proxy_url}' for {self.watch['uuid']}")
+
+        # Now call the fetcher (playwright/requests/etc) with arguments that only a fetcher would need.
+        # When browser_connection_url is None, it method should default to working out whats the best defaults (os env vars etc)
+        self.fetcher = fetcher_obj(proxy_override=proxy_url,
+                                   custom_browser_connection_url=custom_browser_connection_url,
+                                   screenshot_format=self.screenshot_format
+                                   )
 
         if self.watch.has_browser_steps:
-            self.fetcher.browser_steps = browser_steps_get_valid_steps(self.watch.get('browser_steps', []))
+            self.fetcher.browser_steps = self.watch.get('browser_steps', [])
             self.fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, self.watch.get('uuid'))
 
         # Tweak the base config with the per-watch ones
@@ -188,8 +111,8 @@ class difference_detection_processor():
         request_headers = CaseInsensitiveDict()
 
         ua = self.datastore.data['settings']['requests'].get('default_ua')
-        if ua and ua.get(fetcher_class_name):
-            request_headers.update({'User-Agent': ua.get(fetcher_class_name)})
+        if ua and ua.get(prefer_fetch_backend):
+            request_headers.update({'User-Agent': ua.get(prefer_fetch_backend)})
 
         request_headers.update(self.watch.get('headers', {}))
         request_headers.update(self.datastore.get_all_base_headers())
@@ -246,17 +169,6 @@ class difference_detection_processor():
 
         # @todo .quit here could go on close object, so we can run JS if change-detected
         await self.fetcher.quit(watch=self.watch)
-        self.fetcher.disk_cleanup_after_fetch()
-
-        # Sanitize lone surrogates - these can appear when servers return malformed/mixed-encoding
-        # content that gets decoded into surrogate characters (e.g. \udcad). Without this,
-        # encode('utf-8') raises UnicodeEncodeError downstream in checksums, diffs, file writes, etc.
-        # Covers all fetchers (requests, playwright, puppeteer, selenium) in one place.
-        # Also note: By this point we SHOULD know the original encoding so it can safely convert to utf-8 for the rest of the app.
-        # See: https://github.com/dgtlmoon/changedetection.io/issues/3952
-
-        if self.fetcher.content and isinstance(self.fetcher.content, str):
-            self.fetcher.content = self.fetcher.content.encode('utf-8', errors='replace').decode('utf-8')
 
         # After init, call run_changedetection() which will do the actual change-detection
 
@@ -274,12 +186,12 @@ class difference_detection_processor():
         import os
 
         watch = self.datastore.data['watching'].get(self.watch_uuid)
-        data_dir = watch.data_dir
+        watch_data_dir = watch.watch_data_dir
 
-        if not data_dir:
+        if not watch_data_dir:
             return {}
 
-        filepath = os.path.join(data_dir, filename)
+        filepath = os.path.join(watch_data_dir, filename)
 
         if not os.path.isfile(filepath):
             return {}
@@ -304,16 +216,16 @@ class difference_detection_processor():
         import os
 
         watch = self.datastore.data['watching'].get(self.watch_uuid)
-        data_dir = watch.data_dir
+        watch_data_dir = watch.watch_data_dir
 
-        if not data_dir:
-            logger.warning(f"Cannot save extra watch config {filename}: no data_dir")
+        if not watch_data_dir:
+            logger.warning(f"Cannot save extra watch config {filename}: no watch_data_dir")
             return
 
         # Ensure directory exists
         watch.ensure_data_dir_exists()
 
-        filepath = os.path.join(data_dir, filename)
+        filepath = os.path.join(watch_data_dir, filename)
 
         try:
             # If merge is enabled, read existing data first
@@ -338,16 +250,8 @@ class difference_detection_processor():
         except IOError as e:
             logger.error(f"Failed to write extra watch config {filename}: {e}")
 
-    def get_raw_document_checksum(self):
-        checksum = None
-
-        if self.fetcher.content:
-            checksum = hashlib.md5(self.fetcher.content.encode('utf-8')).hexdigest()
-
-        return checksum
-
     @abstractmethod
-    def run_changedetection(self, watch, force_reprocess=False):
+    def run_changedetection(self, watch):
         update_obj = {'last_notification_error': False, 'last_error': False}
         some_data = 'xxxxx'
         update_obj["previous_md5"] = hashlib.md5(some_data.encode('utf-8')).hexdigest()

changedetectionio/processors/extract.py

@@ -42,7 +42,10 @@ def render_form(watch, datastore, request, url_for, render_template, flash, redi
     # Get error information for the template
     screenshot_url = watch.get_screenshot()
 
-    fetcher_supports_screenshots = watch.fetcher_supports_screenshots
+    system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
+    is_html_webdriver = False
+    if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
+        is_html_webdriver = True
 
     password_enabled_and_share_is_off = False
     if datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False):
@@ -59,7 +62,7 @@ def render_form(watch, datastore, request, url_for, render_template, flash, redi
         last_error_screenshot=watch.get_error_snapshot(),
         last_error_text=watch.get_error_text(),
         screenshot=screenshot_url,
-        fetcher_supports_screenshots=fetcher_supports_screenshots,
+        is_html_webdriver=is_html_webdriver,
         password_enabled_and_share_is_off=password_enabled_and_share_is_off,
         extra_title=f" - {watch.label} - Extract Data",
         extra_stylesheets=[url_for('static_content', group='styles', filename='diff.css')],

changedetectionio/processors/image_ssim_diff/__init__.py

@@ -12,13 +12,6 @@ processor_description = "Visual/Screenshot change detection (Fast)"
 processor_name = "image_ssim_diff"
 processor_weight = 2  # Lower weight = appears at top, heavier weight = appears lower (bottom)
 
-# Processor capabilities
-supports_visual_selector = True
-supports_browser_steps = True
-supports_text_filters_and_triggers = False
-supports_text_filters_and_triggers_elements = False
-supports_request_type = True
-
 PROCESSOR_CONFIG_NAME = f"{Path(__file__).parent.name}.json"
 
 # Subprocess timeout settings

changedetectionio/processors/image_ssim_diff/difference.py

@@ -130,7 +130,7 @@ def get_asset(asset_name, watch, datastore, request):
                 except Exception as e:
                     exception_container[0] = e
 
-            thread = threading.Thread(target=thread_target, daemon=True, name="ImageDiff-Asset")
+            thread = threading.Thread(target=thread_target)
             thread.start()
             thread.join(timeout=60)
 
@@ -284,7 +284,7 @@ def _draw_bounding_box_if_configured(img_bytes, watch, datastore):
             except Exception as e:
                 exception_container[0] = e
 
-        thread = threading.Thread(target=thread_target, daemon=True, name="ImageDiff-BoundingBox")
+        thread = threading.Thread(target=thread_target)
         thread.start()
         thread.join(timeout=15)
 
@@ -393,7 +393,7 @@ def render(watch, datastore, request, url_for, render_template, flash, redirect)
             except Exception as e:
                 exception_container[0] = e
 
-        thread = threading.Thread(target=thread_target, daemon=True, name="ImageDiff-ChangePercentage")
+        thread = threading.Thread(target=thread_target)
         thread.start()
         thread.join(timeout=60)
 
@@ -414,7 +414,7 @@ def render(watch, datastore, request, url_for, render_template, flash, redirect)
 
     # Load historical data if available (for charts/visualization)
     comparison_data = {}
-    comparison_config_path = os.path.join(watch.data_dir, "visual_comparison_data.json")
+    comparison_config_path = os.path.join(watch.watch_data_dir, "visual_comparison_data.json")
     if os.path.isfile(comparison_config_path):
         try:
             with open(comparison_config_path, 'r') as f:

changedetectionio/processors/image_ssim_diff/edit_hook.py

@@ -90,7 +90,7 @@ def on_config_save(watch, processor_config, datastore):
             processor_config['auto_track_region'] = False
 
             # Remove old template file if exists
-            template_path = os.path.join(watch.data_dir, CROPPED_IMAGE_TEMPLATE_FILENAME)
+            template_path = os.path.join(watch.watch_data_dir, CROPPED_IMAGE_TEMPLATE_FILENAME)
             if os.path.exists(template_path):
                 os.remove(template_path)
                 logger.debug(f"Removed old template file: {template_path}")

changedetectionio/processors/image_ssim_diff/image_handler/isolated_libvips.py

@@ -13,9 +13,14 @@ Research: https://github.com/libvips/pyvips/issues/234
 
 import multiprocessing
 
-# CRITICAL: Use 'spawn' context instead of 'fork' to avoid inheriting parent's
+# CRITICAL: Use 'spawn' instead of 'fork' to avoid inheriting parent's
 # LibVIPS threading state which can cause hangs in gaussblur operations
 # https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods
+try:
+    multiprocessing.set_start_method('spawn', force=False)
+except RuntimeError:
+    # Already set, ignore
+    pass
 
 
 def _worker_generate_diff(conn, img_bytes_from, img_bytes_to, threshold, blur_sigma, max_width, max_height):
@@ -90,10 +95,9 @@ def generate_diff_isolated(img_bytes_from, img_bytes_to, threshold, blur_sigma,
     Returns:
         bytes: JPEG diff image or None on failure
     """
-    ctx = multiprocessing.get_context('spawn')
-    parent_conn, child_conn = ctx.Pipe()
+    parent_conn, child_conn = multiprocessing.Pipe()
 
-    p = ctx.Process(
+    p = multiprocessing.Process(
         target=_worker_generate_diff,
         args=(child_conn, img_bytes_from, img_bytes_to, threshold, blur_sigma, max_width, max_height)
     )
@@ -136,8 +140,7 @@ def calculate_change_percentage_isolated(img_bytes_from, img_bytes_to, threshold
     Returns:
         float: Change percentage
     """
-    ctx = multiprocessing.get_context('spawn')
-    parent_conn, child_conn = ctx.Pipe()
+    parent_conn, child_conn = multiprocessing.Pipe()
 
     def _worker_calculate(conn):
         try:
@@ -182,7 +185,7 @@ def calculate_change_percentage_isolated(img_bytes_from, img_bytes_to, threshold
         finally:
             conn.close()
 
-    p = ctx.Process(target=_worker_calculate, args=(child_conn,))
+    p = multiprocessing.Process(target=_worker_calculate, args=(child_conn,))
     p.start()
 
     result = 0.0
@@ -230,8 +233,7 @@ def compare_images_isolated(img_bytes_from, img_bytes_to, threshold, blur_sigma,
         tuple: (changed_detected, change_percentage)
     """
     print(f"[Parent] Starting compare_images_isolated subprocess", flush=True)
-    ctx = multiprocessing.get_context('spawn')
-    parent_conn, child_conn = ctx.Pipe()
+    parent_conn, child_conn = multiprocessing.Pipe()
 
     def _worker_compare(conn):
         try:
@@ -299,7 +301,7 @@ def compare_images_isolated(img_bytes_from, img_bytes_to, threshold, blur_sigma,
         finally:
             conn.close()
 
-    p = ctx.Process(target=_worker_compare, args=(child_conn,))
+    p = multiprocessing.Process(target=_worker_compare, args=(child_conn,))
     print(f"[Parent] Starting subprocess (pid will be assigned)", flush=True)
     p.start()
     print(f"[Parent] Subprocess started (pid={p.pid}), waiting for result (30s timeout)", flush=True)

changedetectionio/processors/image_ssim_diff/processor.py

@@ -30,7 +30,7 @@ class perform_site_check(difference_detection_processor):
     # Override to use PNG format for better image comparison (JPEG compression creates noise)
     screenshot_format = SCREENSHOT_FORMAT_PNG
 
-    def run_changedetection(self, watch, force_reprocess=False):
+    def run_changedetection(self, watch):
         """
         Perform screenshot comparison using OpenCV subprocess handler.
 
@@ -204,7 +204,7 @@ class perform_site_check(difference_detection_processor):
                 except Exception as e:
                     exception_container[0] = e
 
-            thread = threading.Thread(target=thread_target, daemon=True, name="ImageDiff-Processor")
+            thread = threading.Thread(target=thread_target)
             thread.start()
             thread.join(timeout=60)
 

changedetectionio/processors/magic.py

@@ -100,13 +100,7 @@ class guess_stream_type():
         if any(s in http_content_header for s in RSS_XML_CONTENT_TYPES):
             self.is_rss = True
         elif any(s in http_content_header for s in JSON_CONTENT_TYPES):
-            # JSONP detection: server claims application/json but content is actually JSONP (e.g. cb({...}))
-            # A JSONP response starts with an identifier followed by '(' - not valid JSON
-            if re.match(r'^\w[\w.]*\s*\(', test_content):
-                logger.warning(f"Content-Type header claims JSON but content looks like JSONP (starts with identifier+parenthesis) - treating as plaintext")
-                self.is_plaintext = True
-            else:
-                self.is_json = True
+            self.is_json = True
         elif 'pdf' in magic_content_header:
             self.is_pdf = True
         # magic will call a rss document 'xml'

changedetectionio/processors/restock_diff/__init__.py

@@ -1,19 +1,9 @@
 
 from babel.numbers import parse_decimal
 from changedetectionio.model.Watch import model as BaseWatch
-from decimal import Decimal, InvalidOperation
 from typing import Union
 import re
 
-# Processor capabilities
-supports_visual_selector = True
-supports_browser_steps = True
-supports_text_filters_and_triggers = True
-supports_text_filters_and_triggers_elements = True
-supports_request_type = True
-_price_re = re.compile(r"Price:\s*(\d+(?:\.\d+)?)", re.IGNORECASE)
-
-
 class Restock(dict):
 
     def parse_currency(self, raw_value: str) -> Union[float, None]:
@@ -34,7 +24,6 @@ class Restock(dict):
 
         if standardized_value:
             # Convert to float
-            # @todo locale needs to be the locale of the webpage
             return float(parse_decimal(standardized_value, locale='en'))
 
         return None
@@ -66,22 +55,15 @@ class Restock(dict):
 
         super().__setitem__(key, value)
 
-def get_price_from_history_str(history_str):
-    m = _price_re.search(history_str)
-    if not m:
-        return None
-
-    try:
-        return str(Decimal(m.group(1)))
-    except InvalidOperation:
-        return None
-
-
 class Watch(BaseWatch):
     def __init__(self, *arg, **kw):
         super().__init__(*arg, **kw)
         self['restock'] = Restock(kw['default']['restock']) if kw.get('default') and kw['default'].get('restock') else Restock()
 
+        self['restock_settings'] = kw['default']['restock_settings'] if kw.get('default',{}).get('restock_settings') else {
+            'follow_price_changes': True,
+            'in_stock_processing' : 'in_stock_only'
+        } #@todo update
 
     def clear_watch(self):
         super().clear_watch()
@@ -90,27 +72,13 @@ class Watch(BaseWatch):
     def extra_notification_token_values(self):
         values = super().extra_notification_token_values()
         values['restock'] = self.get('restock', {})
-
-        values['restock']['previous_price'] = None
-        if self.history_n >= 2:
-            history = self.history
-            if history and len(history) >=2:
-                """Unfortunately for now timestamp is stored as string key"""
-                sorted_keys = sorted(list(history), key=lambda x: int(x))
-                sorted_keys.reverse()
-
-                price_str = self.get_history_snapshot(timestamp=sorted_keys[-1])
-                if price_str:
-                    values['restock']['previous_price'] = get_price_from_history_str(price_str)
         return values
 
     def extra_notification_token_placeholder_info(self):
         values = super().extra_notification_token_placeholder_info()
 
         values.append(('restock.price', "Price detected"))
-        values.append(('restock.in_stock', "In stock status"))
         values.append(('restock.original_price', "Original price at first check"))
-        values.append(('restock.previous_price', "Previous price in history"))
 
         return values
 

changedetectionio/processors/restock_diff/api.yaml

@@ -1,149 +0,0 @@
-components:
-  schemas:
-    processor_config_restock_diff:
-      type: object
-      description: Configuration for the restock_diff processor (restock and price tracking)
-      properties:
-        in_stock_processing:
-          type: string
-          enum: [in_stock_only, all_changes, 'off']
-          default: in_stock_only
-          description: |
-            When to trigger on stock changes:
-            - `in_stock_only`: Only trigger on Out Of Stock -> In Stock transitions
-            - `all_changes`: Trigger on any availability change
-            - `off`: Disable stock/availability tracking
-        follow_price_changes:
-          type: boolean
-          default: true
-          description: Monitor and track price changes
-        price_change_min:
-          type: [number, 'null']
-          description: Trigger a notification when the price drops below this value
-        price_change_max:
-          type: [number, 'null']
-          description: Trigger a notification when the price rises above this value
-        price_change_threshold_percent:
-          type: [number, 'null']
-          minimum: 0
-          maximum: 100
-          description: Minimum price change percentage since the original price to trigger a notification
-
-paths:
-  /watch:
-    post:
-      x-code-samples:
-        - lang: 'curl'
-          label: 'Restock & price tracking'
-          source: |
-            curl -X POST "http://localhost:5000/api/v1/watch" \
-              -H "x-api-key: YOUR_API_KEY" \
-              -H "Content-Type: application/json" \
-              -d '{
-                "url": "https://example.com/product",
-                "processor": "restock_diff",
-                "processor_config_restock_diff": {
-                  "in_stock_processing": "in_stock_only",
-                  "follow_price_changes": true,
-                  "price_change_threshold_percent": 5
-                }
-              }'
-        - lang: 'Python'
-          label: 'Restock & price tracking'
-          source: |
-            import requests
-
-            headers = {
-                'x-api-key': 'YOUR_API_KEY',
-                'Content-Type': 'application/json'
-            }
-            data = {
-                'url': 'https://example.com/product',
-                'processor': 'restock_diff',
-                'processor_config_restock_diff': {
-                    'in_stock_processing': 'in_stock_only',
-                    'follow_price_changes': True,
-                    'price_change_threshold_percent': 5,
-                }
-            }
-            response = requests.post('http://localhost:5000/api/v1/watch',
-                                     headers=headers, json=data)
-            print(response.json())
-
-  /watch/{uuid}:
-    put:
-      x-code-samples:
-        - lang: 'curl'
-          label: 'Update restock config'
-          source: |
-            curl -X PUT "http://localhost:5000/api/v1/watch/YOUR-UUID" \
-              -H "x-api-key: YOUR_API_KEY" \
-              -H "Content-Type: application/json" \
-              -d '{
-                "processor_config_restock_diff": {
-                  "in_stock_processing": "all_changes",
-                  "follow_price_changes": true,
-                  "price_change_min": 10.00,
-                  "price_change_max": 500.00
-                }
-              }'
-        - lang: 'Python'
-          label: 'Update restock config'
-          source: |
-            import requests
-
-            headers = {
-                'x-api-key': 'YOUR_API_KEY',
-                'Content-Type': 'application/json'
-            }
-            uuid = 'YOUR-UUID'
-            data = {
-                'processor_config_restock_diff': {
-                    'in_stock_processing': 'all_changes',
-                    'follow_price_changes': True,
-                    'price_change_min': 10.00,
-                    'price_change_max': 500.00,
-                }
-            }
-            response = requests.put(f'http://localhost:5000/api/v1/watch/{uuid}',
-                                    headers=headers, json=data)
-            print(response.text)
-
-  /tag/{uuid}:
-    put:
-      x-code-samples:
-        - lang: 'curl'
-          label: 'Set restock config on group/tag'
-          source: |
-            curl -X PUT "http://localhost:5000/api/v1/tag/YOUR-TAG-UUID" \
-              -H "x-api-key: YOUR_API_KEY" \
-              -H "Content-Type: application/json" \
-              -d '{
-                "overrides_watch": true,
-                "processor_config_restock_diff": {
-                  "in_stock_processing": "in_stock_only",
-                  "follow_price_changes": true,
-                  "price_change_threshold_percent": 10
-                }
-              }'
-        - lang: 'Python'
-          label: 'Set restock config on group/tag'
-          source: |
-            import requests
-
-            headers = {
-                'x-api-key': 'YOUR_API_KEY',
-                'Content-Type': 'application/json'
-            }
-            tag_uuid = 'YOUR-TAG-UUID'
-            data = {
-                'overrides_watch': True,
-                'processor_config_restock_diff': {
-                    'in_stock_processing': 'in_stock_only',
-                    'follow_price_changes': True,
-                    'price_change_threshold_percent': 10,
-                }
-            }
-            response = requests.put(f'http://localhost:5000/api/v1/tag/{tag_uuid}',
-                                    headers=headers, json=data)
-            print(response.text)