tweaks

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

@@ -395,29 +395,6 @@ jobs:
           cd changedetectionio
           ./run_custom_browser_url_tests.sh
 
-  processor-plugin-tests:
-    runs-on: ubuntu-latest
-    needs: build
-    timeout-minutes: 20
-    env:
-      PYTHON_VERSION: ${{ inputs.python-version }}
-    steps:
-      - uses: actions/checkout@v6
-
-      - name: Download Docker image artifact
-        uses: actions/download-artifact@v7
-        with:
-          name: test-changedetectionio-${{ 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

Dockerfile

@@ -138,15 +138,6 @@ 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"]
 
 

changedetectionio/api/Watch.py

@@ -169,18 +169,58 @@ class Watch(Resource):
 
         # 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)
+        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.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
 
@@ -440,16 +480,6 @@ class CreateWatch(Resource):
 #            worker_pool.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

changedetectionio/blueprint/backups/templates/overview.html

@@ -3,10 +3,10 @@
     {% from '_helpers.html' import render_simple_field, render_field %}
     <div class="edit-form">
         <div class="box-wrap inner">
-            <h2>{{ _('Backups') }}</h2>
+            <h4>{{ _('Backups') }}</h4>
             {% if backup_running %}
                 <p>
-                    <span class="spinner"></span>&nbsp;<strong>{{ _('A backup is running!') }}</strong>
+                    <strong>{{ _('A backup is running!') }}</strong>
                 </p>
             {% endif %}
             <p>

changedetectionio/blueprint/imports/__init__.py

@@ -26,9 +26,8 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             # 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()))
+                importer_handler.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', 'text_json_diff'))
                 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:

changedetectionio/blueprint/settings/templates/settings.html

@@ -25,7 +25,7 @@
             <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.index') }}">{{ _('Backups') }}</a></li>
+            <li class="tab"><a href="{{ url_for('backups.index') }}" class="pure-menu-link">{{ _('Backups') }}</a></li>
             <li class="tab"><a href="#timedate">{{ _('Time & Date') }}</a></li>
             <li class="tab"><a href="#proxies">{{ _('CAPTCHA & Proxies') }}</a></li>
             {% if plugin_tabs %}
@@ -59,14 +59,6 @@
                         {{ _('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 %}

changedetectionio/blueprint/ui/diff.py

@@ -100,21 +100,23 @@ 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
@@ -154,21 +156,23 @@ 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
@@ -208,22 +212,24 @@ 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
@@ -273,33 +279,38 @@ 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

@@ -71,13 +71,8 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
         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])
 
@@ -154,10 +149,58 @@ 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
@@ -197,7 +240,7 @@ 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.data, default=datastore.data['watching'][uuid])
+            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
@@ -267,13 +310,6 @@ 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')}"]

changedetectionio/blueprint/ui/preview.py

@@ -38,21 +38,24 @@ 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 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 = []
@@ -157,33 +160,39 @@ 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/edit.html

@@ -45,19 +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 %}
@@ -115,20 +110,12 @@
                          {{ _('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">
                         {{ render_field(form.fetch_backend, class="fetch-backend") }}
@@ -216,7 +203,6 @@ Math: {{ 1 + 1 }}") }}
                     </div>
             </fieldset>
             </div>
-            {% endif %}
 
             <div class="tab-pane-inner" id="browser-steps">
             {% if capabilities.supports_browser_steps %}
@@ -297,7 +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)}}";
@@ -316,9 +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>
@@ -329,8 +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>
@@ -389,7 +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">
 
@@ -401,7 +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;">

changedetectionio/blueprint/ui/views.py

@@ -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:
@@ -39,4 +38,4 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
         return redirect(url_for('watchlist.index', tag=request.args.get('tag','')))
 
-    return views_blueprint
+    return views_blueprint

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>
@@ -73,9 +69,7 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
             </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">
@@ -211,24 +205,23 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
                         </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>
+                        <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>
                             {%- endfor -%}

changedetectionio/content_fetchers/playwright.py

@@ -1,4 +1,3 @@
-import asyncio
 import gc
 import json
 import os
@@ -350,7 +349,12 @@ class fetcher(Fetcher):
 
             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)
-                # Finally block will handle cleanup
+                # Cleanup before raising to prevent memory leak
+                await self.page.close()
+                await context.close()
+                await browser.close()
+                # Force garbage collection to release Playwright resources immediately
+                gc.collect()
                 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:
@@ -366,7 +370,12 @@ class fetcher(Fetcher):
                     try:
                         await self.iterate_browser_steps(start_url=url)
                     except BrowserStepsStepException:
-                        # Finally block will handle cleanup
+                        try:
+                            await context.close()
+                            await browser.close()
+                        except Exception as e:
+                            # Fine, could be messy situation
+                            pass
                         raise
 
                     await self.page.wait_for_timeout(extra_wait * 1000)
@@ -415,40 +424,35 @@ class fetcher(Fetcher):
                 raise ScreenshotUnavailable(url=url, status_code=self.status_code)
 
             finally:
-                # Clean up resources properly with timeouts to prevent hanging
+                # Request garbage collection one more time before closing
                 try:
-                    if hasattr(self, 'page') and self.page:
-                        await self.page.request_gc()
-                        await asyncio.wait_for(self.page.close(), timeout=5.0)
-                        logger.debug(f"Successfully closed page for {url}")
-                except asyncio.TimeoutError:
-                    logger.warning(f"Timed out closing page for {url} (5s)")
-                except Exception as e:
-                    logger.warning(f"Error closing page for {url}: {e}")
-                finally:
-                    self.page = None
+                    await self.page.request_gc()
+                except:
+                    pass
+                
+                # Clean up resources properly
+                try:
+                    await self.page.request_gc()
+                except:
+                    pass
 
                 try:
-                    if context:
-                        await asyncio.wait_for(context.close(), timeout=5.0)
-                        logger.debug(f"Successfully closed context for {url}")
-                except asyncio.TimeoutError:
-                    logger.warning(f"Timed out closing context for {url} (5s)")
-                except Exception as e:
-                    logger.warning(f"Error closing context for {url}: {e}")
-                finally:
-                    context = None
+                    await self.page.close()
+                except:
+                    pass
+                self.page = None
 
                 try:
-                    if browser:
-                        await asyncio.wait_for(browser.close(), timeout=5.0)
-                        logger.debug(f"Successfully closed browser connection for {url}")
-                except asyncio.TimeoutError:
-                    logger.warning(f"Timed out closing browser connection for {url} (5s)")
-                except Exception as e:
-                    logger.warning(f"Error closing browser for {url}: {e}")
-                finally:
-                    browser = None
+                    await context.close()
+                except:
+                    pass
+                context = None
+
+                try:
+                    await browser.close()
+                except:
+                    pass
+                browser = None
 
                 # Force Python GC to release Playwright resources immediately
                 # Playwright objects can have circular references that delay cleanup

changedetectionio/content_fetchers/puppeteer.py

@@ -1,5 +1,4 @@
 import asyncio
-import gc
 import json
 import os
 import websockets.exceptions
@@ -222,36 +221,19 @@ 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,
@@ -281,11 +263,9 @@ 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:
@@ -294,18 +274,7 @@ 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}")
-            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}"))
@@ -374,12 +343,6 @@ class fetcher(Fetcher):
             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!")
@@ -405,9 +368,7 @@ class fetcher(Fetcher):
             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')
+            await self.page._client.send('Page.stopLoading')
 
             if response:
                 break
@@ -476,9 +437,15 @@ class fetcher(Fetcher):
         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
+        # Force aggressive memory cleanup - pyppeteer base64 decode creates temporary buffers
         import gc
         gc.collect()
+        # Release C-level memory from base64 decode back to OS
+        try:
+            import ctypes
+            ctypes.CDLL('libc.so.6').malloc_trim(0)
+        except Exception:
+            pass
         self.xpath_data = await self.page.evaluate(XPATH_ELEMENT_JS, {
             "visualselector_xpath_selectors": visualselector_xpath_selectors,
             "max_height": MAX_TOTAL_HEIGHT

changedetectionio/forms.py

@@ -730,7 +730,7 @@ class quickWatchForm(Form):
     url = fields.URLField(_l('URL'), validators=[validateURL()])
     tags = StringTagUUID(_l('Group tag'), validators=[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"})
 
 
@@ -749,7 +749,7 @@ class commonSettingsForm(Form):
     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"))])
 
@@ -763,7 +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')})
@@ -837,8 +837,6 @@ 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
 
@@ -1036,8 +1034,6 @@ 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/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/model/App.py

@@ -46,7 +46,6 @@ class model(dict):
                     '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

changedetectionio/model/Watch.py

@@ -1,6 +1,3 @@
-import gc
-from copy import copy
-
 from blinker import signal
 from changedetectionio.validate_url import is_safe_valid_url
 
@@ -16,7 +13,7 @@ from .. import jinja2_custom as safe_jinja
 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))
+BROTLI_COMPRESS_SIZE_THRESHOLD = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
 
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3))
 mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
@@ -112,15 +109,8 @@ class model(watch_base):
         self.__datastore_path = kw.get('datastore_path')
         if kw.get('datastore_path'):
             del kw['datastore_path']
-
-        self.__datastore = kw.get('__datastore')
-        if not self.__datastore:
-            raise ValueError("Watch object requires '__datastore' reference - cannot access global settings without it")
-        if kw.get('__datastore'):
-            del kw['__datastore']
-
+            
         super(model, self).__init__(*arg, **kw)
-
         if kw.get('default'):
             self.update(kw['default'])
             del kw['default']
@@ -433,49 +423,16 @@ class model(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.watch_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
-
-        # 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.watch_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()
@@ -484,6 +441,7 @@ class model(watch_base):
         logger.trace(f"{self.get('uuid')} - Updating {self.history_index_filename} with timestamp {timestamp}")
 
         self.ensure_data_dir_exists()
+
         skip_brotli = strtobool(os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False'))
 
         # Binary data - detect file type and save without compression
@@ -543,15 +501,6 @@ class model(watch_base):
         self.__newest_history_key = timestamp
         self.__history_n += 1
 
-
-        maxlen = (
-                self.get('history_snapshot_max_length')
-                or (self.__datastore and self.__datastore['settings']['application'].get('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
 
@@ -664,11 +613,6 @@ class model(watch_base):
                 try:
                     with open(fname, 'wb') as f:
                         f.write(decoded)
-
-                    # Invalidate favicon filename cache
-                    if hasattr(self, '_favicon_filename_cache'):
-                        delattr(self, '_favicon_filename_cache')
-
                     # A signal that could trigger the socket server to update the browser also
                     watch_check_update = signal('watch_favicon_bump')
                     if watch_check_update:
@@ -685,32 +629,20 @@ class model(watch_base):
         Find any favicon.* file in the current working directory
         and return the contents of the newest one.
 
-        MEMORY LEAK FIX: Cache the result to avoid repeated glob.glob() operations.
-        glob.glob() causes millions of fnmatch allocations when called for every watch on page load.
-
         Returns:
-            str: Basename of the newest favicon file, or None if not found.
+            bytes: Contents of the newest favicon file, or None if not found.
         """
-        # Check cache first (prevents 26M+ allocations from repeated glob operations)
-        cache_key = '_favicon_filename_cache'
-        if hasattr(self, cache_key):
-            return getattr(self, cache_key)
-
         import glob
 
         # Search for all favicon.* files
         files = glob.glob(os.path.join(self.watch_data_dir, "favicon.*"))
 
         if not files:
-            result = None
-        else:
-            # Find the newest by modification time
-            newest_file = max(files, key=os.path.getmtime)
-            result = os.path.basename(newest_file)
+            return None
 
-        # Cache the result
-        setattr(self, cache_key, result)
-        return result
+        # 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.

changedetectionio/model/__init__.py

@@ -32,7 +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,

changedetectionio/pluggy_interface.py

@@ -105,30 +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
-
 
 # Set up Plugin Manager
 plugin_manager = pluggy.PluginManager(PLUGIN_NAMESPACE)

changedetectionio/processors/__init__.py

@@ -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
 
 
@@ -116,137 +97,54 @@ def find_processor_module(processor_name):
     return None
 
 
-def get_processor_module(processor_name):
-    """
-    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
-    """
-    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
-
-
 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).
+    Can be filtered via ALLOWED_PROCESSORS environment variable (comma-separated list).
     :return: A list :)
     """
 
     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))
 
@@ -257,20 +155,6 @@ def available_processors():
     return [(name, desc) for name, desc, weight in available]
 
 
-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():
     """
     Get a dictionary mapping processor names to their list_badge_text values.
@@ -395,76 +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/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/restock_diff/__init__.py

@@ -4,13 +4,6 @@ from changedetectionio.model.Watch import model as BaseWatch
 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
-
 class Restock(dict):
 
     def parse_currency(self, raw_value: str) -> Union[float, None]:

changedetectionio/processors/restock_diff/processor.py

@@ -193,17 +193,18 @@ class perform_site_check(difference_detection_processor):
 
 
         itemprop_availability = {}
-        multiple_prices_found = False
 
         # Try built-in extraction first, this will scan metadata in the HTML
         try:
             itemprop_availability = get_itemprop_availability(self.fetcher.content)
         except MoreThanOnePriceFound as e:
-            # Don't raise immediately - let plugins try to handle this case
-            # Plugins might be able to determine which price is correct
-            logger.warning(f"Built-in detection found multiple prices on {watch.get('url')}, will try plugin override")
-            multiple_prices_found = True
-            itemprop_availability = {}
+            # Add the real data
+            raise ProcessorException(message="Cannot run, more than one price detected, this plugin is only for product pages with ONE product, try the content-change detection mode.",
+                                     url=watch.get('url'),
+                                     status_code=self.fetcher.get_last_status_code(),
+                                     screenshot=self.fetcher.screenshot,
+                                     xpath_data=self.fetcher.xpath_data
+                                     )
 
         # If built-in extraction didn't get both price AND availability, try plugin override
         # Only check plugin if this watch is using a fetcher that might provide better data
@@ -215,21 +216,9 @@ class perform_site_check(difference_detection_processor):
             from changedetectionio.pluggy_interface import get_itemprop_availability_from_plugin
             fetcher_name = watch.get('fetch_backend', 'html_requests')
 
-            # Resolve 'system' to the actual fetcher being used
-            # This allows plugins to work even when watch uses "system settings default"
-            if fetcher_name == 'system':
-                # Get the actual fetcher that was used (from self.fetcher)
-                # Fetcher class name gives us the actual backend (e.g., 'html_requests', 'html_webdriver')
-                actual_fetcher = type(self.fetcher).__name__
-                if 'html_requests' in actual_fetcher.lower():
-                    fetcher_name = 'html_requests'
-                elif 'webdriver' in actual_fetcher.lower() or 'playwright' in actual_fetcher.lower():
-                    fetcher_name = 'html_webdriver'
-                logger.debug(f"Resolved 'system' fetcher to actual fetcher: {fetcher_name}")
-
-            # Try plugin override - plugins can decide if they support this fetcher
-            if fetcher_name:
-                logger.debug(f"Calling extra plugins for getting item price/availability (fetcher: {fetcher_name})")
+            # Only try plugin override if not using system default (which might be anything)
+            if fetcher_name and fetcher_name != 'system':
+                logger.debug("Calling extra plugins for getting item price/availability")
                 plugin_availability = get_itemprop_availability_from_plugin(self.fetcher.content, fetcher_name, self.fetcher, watch.link)
 
                 if plugin_availability:
@@ -244,16 +233,6 @@ class perform_site_check(difference_detection_processor):
                 if not plugin_availability:
                     logger.debug("No item price/availability from plugins")
 
-        # If we had multiple prices and plugins also failed, NOW raise the exception
-        if multiple_prices_found and not itemprop_availability.get('price'):
-            raise ProcessorException(
-                message="Cannot run, more than one price detected, this plugin is only for product pages with ONE product, try the content-change detection mode.",
-                url=watch.get('url'),
-                status_code=self.fetcher.get_last_status_code(),
-                screenshot=self.fetcher.screenshot,
-                xpath_data=self.fetcher.xpath_data
-            )
-
         # Something valid in get_itemprop_availability() by scraping metadata ?
         if itemprop_availability.get('price') or itemprop_availability.get('availability'):
             # Store for other usage

changedetectionio/processors/text_json_diff/__init__.py

@@ -1,11 +1,5 @@
-from loguru import logger
 
-# 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
+from loguru import logger
 
 
 
@@ -64,7 +58,7 @@ def prepare_filter_prevew(datastore, watch_uuid, form_data):
         # Only update vars that came in via the AJAX post
         p = {k: v for k, v in form.data.items() if k in form_data.keys()}
         tmp_watch.update(p)
-        blank_watch_no_filters = watch_model(datastore_path=datastore.datastore_path, __datastore=datastore.data)
+        blank_watch_no_filters = watch_model()
         blank_watch_no_filters['url'] = tmp_watch.get('url')
 
         latest_filename = next(reversed(tmp_watch.history))

changedetectionio/run_basic_tests.sh

@@ -67,7 +67,7 @@ echo "-------------------- Running rest of tests in parallel -------------------
 # REMOVE_REQUESTS_OLD_SCREENSHOTS disabled so that we can write a screenshot and send it in test_notifications.py without a real browser
 FETCH_WORKERS=2 REMOVE_REQUESTS_OLD_SCREENSHOTS=false \
 pytest tests/test_*.py \
-  -n 8 \
+  -n 18 \
   --dist=load \
   -vvv \
   -s \

changedetectionio/store/__init__.py

@@ -9,14 +9,18 @@ from flask import (
 )
 from flask_babel import gettext
 
-from ..model import App, Watch
-from copy import deepcopy
+from ..blueprint.rss import RSS_CONTENT_FORMAT_DEFAULT
+from ..html_tools import TRANSLATE_WHITESPACE_TABLE
+from ..model import App, Watch, USE_SYSTEM_DEFAULT_NOTIFICATION_FORMAT_FOR_WATCH
+from copy import deepcopy, copy
 from os import path, unlink
+from threading import Lock
 import json
 import os
 import re
 import secrets
 import sys
+import threading
 import time
 import uuid as uuid_builder
 from loguru import logger
@@ -31,6 +35,7 @@ except ImportError:
     HAS_ORJSON = False
 
 from ..processors import get_custom_watch_obj_for_processor
+from ..processors.restock_diff import Restock
 
 # Import the base class and helpers
 from .file_saving_datastore import FileSavingDataStore, load_all_watches, save_watch_atomic, save_json_atomic
@@ -132,19 +137,6 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
             )
             logger.info(f"Tag: {uuid} {tag['title']}")
 
-    def _rehydrate_watches(self):
-        """Rehydrate watch entities from stored data (converts dicts to Watch objects)."""
-        watch_count = len(self.__data.get('watching', {}))
-        if watch_count == 0:
-            return
-
-        logger.info(f"Rehydrating {watch_count} watches...")
-        watching_rehydrated = {}
-        for uuid, watch_dict in self.__data.get('watching', {}).items():
-            watching_rehydrated[uuid] = self.rehydrate_entity(uuid, watch_dict)
-        self.__data['watching'] = watching_rehydrated
-        logger.success(f"Rehydrated {watch_count} watches into Watch objects")
-
 
     def _load_state(self):
         """
@@ -182,7 +174,7 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
         self.json_store_path = os.path.join(self.datastore_path, "changedetection.json")
 
         # Base definition for all watchers (deepcopy part of #569)
-        self.generic_definition = deepcopy(Watch.model(datastore_path=datastore_path, __datastore=self.__data, default={}))
+        self.generic_definition = deepcopy(Watch.model(datastore_path=datastore_path, default={}))
 
         # Load build SHA if available (Docker deployments)
         if path.isfile('changedetectionio/source.txt'):
@@ -226,29 +218,23 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
                 logger.critical(f"Legacy datastore detected at {self.datastore_path}/url-watches.json")
                 logger.critical("Migration will be triggered via update_26")
 
-                # Load the legacy datastore
+                # Load the legacy datastore to get its schema_version
                 from .legacy_loader import load_legacy_format
                 legacy_path = os.path.join(self.datastore_path, "url-watches.json")
-                legacy_data = load_legacy_format(legacy_path)
+                with open(legacy_path) as f:
+                    self.__data = json.load(f)
 
-                if not legacy_data:
+                if not self.__data:
                     raise Exception("Failed to load legacy datastore from url-watches.json")
 
-                # Store the loaded data
-                self.__data = legacy_data
-
-                # CRITICAL: Rehydrate watches from dicts into Watch objects
-                # This ensures watches have their methods available during migration
-                self._rehydrate_watches()
-
-                # update_26 will save watches to individual files and create changedetection.json
-                # Next startup will load from new format normally
+                # update_26 will load the legacy data again and migrate to new format
+                # Only run updates AFTER the legacy schema version (e.g., if legacy is at 25, only run 26+)
                 self.run_updates()
 
 
             else:
                 # Fresh install - create new datastore
-                logger.warning(f"No datastore found, creating new datastore at {self.datastore_path}")
+                logger.critical(f"No datastore found, creating new datastore at {self.datastore_path}")
 
                 # Set schema version to latest (no updates needed)
                 updates_available = self.get_updates_available()
@@ -322,7 +308,7 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
         if entity.get('processor') != 'text_json_diff':
             logger.trace(f"Loading Watch object '{watch_class.__module__}.{watch_class.__name__}' for UUID {uuid}")
 
-        entity = watch_class(datastore_path=self.datastore_path, __datastore=self.__data, default=entity)
+        entity = watch_class(datastore_path=self.datastore_path, default=entity)
         return entity
 
     # ============================================================================
@@ -621,19 +607,6 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
 
             return None
 
-        # Check PAGE_WATCH_LIMIT if set
-        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.__data['watching'])
-                if current_watch_count >= page_watch_limit:
-                    logger.error(f"Watch limit reached: {current_watch_count}/{page_watch_limit} watches. Cannot add {url}")
-                    flash(gettext("Watch limit reached ({}/{} watches). Cannot add more watches.").format(current_watch_count, page_watch_limit), 'error')
-                    return None
-            except ValueError:
-                logger.warning(f"Invalid PAGE_WATCH_LIMIT value: {page_watch_limit}, ignoring limit check")
-
         if tag and type(tag) == str:
             # Then it's probably a string of the actual tag by name, split and add it
             for t in tag.split(','):
@@ -653,7 +626,7 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
 
         # If the processor also has its own Watch implementation
         watch_class = get_custom_watch_obj_for_processor(apply_extras.get('processor'))
-        new_watch = watch_class(datastore_path=self.datastore_path, __datastore=self.__data, url=url)
+        new_watch = watch_class(datastore_path=self.datastore_path, url=url)
 
         new_uuid = new_watch.get('uuid')
 

changedetectionio/tests/plugins/test_processor.py

@@ -1,41 +0,0 @@
-import time
-
-from flask import url_for
-
-from changedetectionio.tests.util import wait_for_all_checks
-
-
-def test_check_plugin_processor(client, live_server, measure_memory_usage, datastore_path):
-    # requires os-int intelligence plugin installed (first basic one we test with)
-
-    res = client.get(url_for("watchlist.index"))
-    assert b'OSINT Reconnaissance' in res.data, "Must have the OSINT plugin installed at test time"
-    assert b'<input checked id="processor-0" name="processor" type="radio" value="text_json_diff">' in res.data, "But the first text_json_diff processor should always be selected by default in quick watch form"
-
-    res = client.post(
-        url_for("ui.ui_views.form_quick_watch_add"),
-        data={"url": 'http://127.0.0.1', "tags": '', 'processor': 'osint_recon'},
-        follow_redirects=True
-    )
-    assert b"Watch added" in res.data
-    client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
-
-    wait_for_all_checks(client)
-
-    res = client.get(
-        url_for("ui.ui_preview.preview_page", uuid="first"),
-        follow_redirects=True
-    )
-
-    assert b'Target: http://127.0.0.1' in res.data
-    assert b'DNSKEY Records' in res.data
-    wait_for_all_checks(client)
-
-
-    # Now change it to something that doesnt exist
-    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
-    live_server.app.config['DATASTORE'].data['watching'][uuid]['processor'] = "now_missing"
-    client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
-    wait_for_all_checks(client)
-    res = client.get(url_for("watchlist.index"))
-    assert b"Exception: Processor module" in res.data and b'now_missing' in res.data, f'Should register that the plugin is missing for {uuid}'

changedetectionio/tests/test_history_consistency.py

@@ -182,86 +182,3 @@ def test_check_text_history_view(client, live_server, measure_memory_usage, data
     assert b'test-one' not in res.data
 
     delete_all_watches(client)
-
-
-def test_history_trim_global_only(client, live_server, measure_memory_usage, datastore_path):
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
-    uuid = None
-    limit = 3
-
-    for i in range(0, 10):
-        with open(os.path.join(datastore_path, "endpoint-content.txt"), "w") as f:
-            f.write(f"<html>test {i}</html>")
-        if not uuid:
-            uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
-        client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
-        wait_for_all_checks(client)
-
-        if i ==8:
-            watch = live_server.app.config['DATASTORE'].data['watching'][uuid]
-            history_n = len(list(watch.history.keys()))
-            logger.debug(f"History length should be at limit {limit} and it is {history_n}")
-            assert history_n == limit
-
-        if i == 6:
-            res = client.post(
-                url_for("settings.settings_page"),
-                data={"application-history_snapshot_max_length": limit},
-                follow_redirects=True
-            )
-            # It will need to detect one more change to start trimming it, which is really at 'start of 7'
-            assert b'Settings updated' in res.data
-
-    delete_all_watches(client)
-
-
-def test_history_trim_global_override_in_watch(client, live_server, measure_memory_usage, datastore_path):
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
-    uuid = None
-    limit = 3
-    res = client.post(
-        url_for("settings.settings_page"),
-        data={"application-history_snapshot_max_length": 10000},
-        follow_redirects=True
-    )
-    # It will need to detect one more change to start trimming it, which is really at 'start of 7'
-    assert b'Settings updated' in res.data
-
-
-    for i in range(0, 10):
-        with open(os.path.join(datastore_path, "endpoint-content.txt"), "w") as f:
-            f.write(f"<html>test {i}</html>")
-        if not uuid:
-            uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
-            res = client.post(
-                url_for("ui.ui_edit.edit_page", uuid="first"),
-                data={"include_filters": "", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests",
-                      "time_between_check_use_default": "y", "history_snapshot_max_length": str(limit)},
-                follow_redirects=True
-            )
-            assert b"Updated watch." in res.data
-
-            wait_for_all_checks(client)
-
-        client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
-        wait_for_all_checks(client)
-
-        if i == 8:
-            watch = live_server.app.config['DATASTORE'].data['watching'][uuid]
-            history_n = len(list(watch.history.keys()))
-            logger.debug(f"History length should be at limit {limit} and it is {history_n}")
-            assert history_n == limit
-
-        if i == 6:
-            res = client.post(
-                url_for("settings.settings_page"),
-                data={"application-history_snapshot_max_length": limit},
-                follow_redirects=True
-            )
-            # It will need to detect one more change to start trimming it, which is really at 'start of 7'
-            assert b'Settings updated' in res.data
-
-    delete_all_watches(client)
-

changedetectionio/tests/unit/test_watch_model.py

@@ -13,14 +13,7 @@ class TestDiffBuilder(unittest.TestCase):
 
     def test_watch_get_suggested_from_diff_timestamp(self):
         import uuid as uuid_builder
-        # Create minimal mock datastore for tests
-        mock_datastore = {
-            'settings': {
-                'application': {}
-            },
-            'watching': {}
-        }
-        watch = Watch.model(datastore_path='/tmp', __datastore=mock_datastore, default={})
+        watch = Watch.model(datastore_path='/tmp', default={})
         watch.ensure_data_dir_exists()
 
 
@@ -56,7 +49,7 @@ class TestDiffBuilder(unittest.TestCase):
         assert p == "109", "Correct when its the same time"
 
         # new empty one
-        watch = Watch.model(datastore_path='/tmp', __datastore=mock_datastore, default={})
+        watch = Watch.model(datastore_path='/tmp', default={})
         p = watch.get_from_version_based_on_last_viewed
         assert p == None, "None when no history available"
 

changedetectionio/worker.py

@@ -142,14 +142,11 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                     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)
@@ -368,9 +365,8 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                     logger.error(f"Exception (BrowserStepsInUnsupportedFetcher) reached processing watch UUID: {uuid}")
 
                 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
 
@@ -389,8 +385,8 @@ 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:
                         datastore.update_watch(uuid=uuid, update_obj=update_obj)
 
@@ -434,62 +430,64 @@ 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
-                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}'")
-                                datastore.update_watch(uuid=uuid, update_obj={'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)}")
 
-                    # Record server header
+                # 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:
-                        server_header = update_handler.fetcher.headers.get('server', '').strip().lower()[:255]
-                        datastore.update_watch(uuid=uuid, update_obj={'remote_server_reply': server_header})
+                        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:
-                        pass
+                        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')
-                                           )
+                # Record server header
+                try:
+                    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:
+                    pass
 
-                    datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - fetch_start_time, 3),
-                                                                   'check_count': count})
+                # 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')
+                                       )
 
-                    # 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}")
+                datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - fetch_start_time, 3),
+                                                               'check_count': count})
 
-                    # Explicitly delete update_handler to free all references
-                    if update_handler:
-                        del update_handler
-                        update_handler = None
+                # 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}")
 
-                # Force garbage collection
+                # Explicitly delete update_handler to free all references
+                if update_handler:
+                    del update_handler
+                    update_handler = None
+
+                # Force aggressive memory cleanup after clearing
                 import gc
                 gc.collect()
+                try:
+                    import ctypes
+                    ctypes.CDLL('libc.so.6').malloc_trim(0)
+                except Exception:
+                    pass
 
         except Exception as 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)}"})
@@ -497,43 +495,49 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
         finally:
             # Always cleanup - this runs whether there was an exception or not
             if uuid:
-                # 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:")
-
                 try:
                     # Release UUID from processing (thread-safe)
                     worker_pool.release_uuid_from_processing(uuid, worker_id=worker_id)
-
+                    
                     # 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'])
 
-                    # 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:")
 
             del(uuid)
 

docker-compose.yml

@@ -16,13 +16,6 @@ services:
   #        Log output levels: TRACE, DEBUG(default), INFO, SUCCESS, WARNING, ERROR, CRITICAL
   #      - LOGGER_LEVEL=TRACE
   #
-  #        Plugins! See https://changedetection.io/plugins for more plugins.
-  #        Install additional Python packages (processor plugins, etc.)
-  #        Example: Install the OSINT reconnaissance processor plugin
-  #      - EXTRA_PACKAGES=changedetection.io-osint-processor
-  #        Multiple packages can be installed by separating with spaces:
-  #      - EXTRA_PACKAGES=changedetection.io-osint-processor another-plugin
-  #
   #
   #       Uncomment below and the "sockpuppetbrowser" to use a real Chrome browser (It uses the "playwright" protocol)
   #      - PLAYWRIGHT_DRIVER_URL=ws://browser-sockpuppet-chrome:3000

docker-entrypoint.sh

@@ -1,28 +0,0 @@
-#!/bin/bash
-set -e
-
-# Install additional packages from EXTRA_PACKAGES env var
-# Uses a marker file to avoid reinstalling on every container restart
-INSTALLED_MARKER="/datastore/.extra_packages_installed"
-CURRENT_PACKAGES="$EXTRA_PACKAGES"
-
-if [ -n "$EXTRA_PACKAGES" ]; then
-    # Check if we need to install/update packages
-    if [ ! -f "$INSTALLED_MARKER" ] || [ "$(cat $INSTALLED_MARKER 2>/dev/null)" != "$CURRENT_PACKAGES" ]; then
-        echo "Installing extra packages: $EXTRA_PACKAGES"
-        pip3 install --no-cache-dir $EXTRA_PACKAGES
-
-        if [ $? -eq 0 ]; then
-            echo "$CURRENT_PACKAGES" > "$INSTALLED_MARKER"
-            echo "Extra packages installed successfully"
-        else
-            echo "ERROR: Failed to install extra packages"
-            exit 1
-        fi
-    else
-        echo "Extra packages already installed: $EXTRA_PACKAGES"
-    fi
-fi
-
-# Execute the main command
-exec "$@"

requirements.txt

@@ -51,9 +51,9 @@ linkify-it-py
 
 # - Needed for apprise/spush, and maybe others? hopefully doesnt trigger a rust compile.
 # - Requires extra wheel for rPi, adds build time for arm/v8 which is not in piwheels
-# Pinned to 44.x for ARM compatibility and sslyze compatibility (sslyze requires <45) and (45.x may not have pre-built ARM wheels)
+# Pinned to 43.0.1 for ARM compatibility (45.x may not have pre-built ARM wheels)
 # Also pinned because dependabot wants specific versions
-cryptography==44.0.0
+cryptography==46.0.3
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 # use any version other than 2.0.x due to https://github.com/eclipse/paho.mqtt.python/issues/814
@@ -70,7 +70,7 @@ lxml >=4.8.0,!=5.2.0,!=5.2.1,<7
 
 # XPath 2.0-3.1 support - 4.2.0 had issues, 4.1.5 stable
 # Consider updating to latest stable version periodically
-elementpath==5.1.1
+elementpath==5.1.0
 
 # For fast image comparison in screenshot change detection
 # opencv-python-headless is OPTIONAL (excluded from requirements.txt)