Price tracker - Use a more memory efficient price scraper, use subprocess on linux for cleaner memory management. (#3864)

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

@@ -103,7 +103,7 @@ jobs:
           docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_watch_model'
           docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_jinja2_security'
           docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_semver'
-          docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_html_to_text'
+          docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_html_to_text'         
 
   # Basic pytest tests with ancillary services
   basic-tests:
@@ -516,3 +516,142 @@ jobs:
             exit 1
           fi
           docker rm sig-test
+
+  # Upgrade path test
+  upgrade-path-test:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 25
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          fetch-depth: 0  # Fetch all history and tags for upgrade testing
+
+      - name: Set up Python ${{ env.PYTHON_VERSION }}
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Check upgrade works without error
+        run: |
+          echo "=== Testing upgrade path from 0.49.1 to ${{ github.ref_name }} (${{ github.sha }}) ==="
+
+          # Checkout old version and create datastore
+          git checkout 0.49.1
+          python3 -m venv .venv
+          source .venv/bin/activate
+          pip install -r requirements.txt
+          pip install 'pyOpenSSL>=23.2.0'
+
+          echo "=== Running version 0.49.1 to create datastore ==="
+          python3 ./changedetection.py -C -d /tmp/data &
+          APP_PID=$!
+
+          # Wait for app to be ready
+          echo "Waiting for 0.49.1 to be ready..."
+          sleep 6
+
+          # Extract API key from datastore (0.49.1 uses url-watches.json)
+          API_KEY=$(jq -r '.settings.application.api_access_token // empty' /tmp/data/url-watches.json)
+          echo "API Key: ${API_KEY:0:8}..."
+
+          # Create a watch with tag "github-group-test" via API
+          echo "Creating test watch with tag via API..."
+          curl -X POST "http://127.0.0.1:5000/api/v1/watch" \
+            -H "x-api-key: ${API_KEY}" \
+            -H "Content-Type: application/json" \
+            --show-error --fail \
+            --retry 6 --retry-delay 1 --retry-connrefused \
+            -d '{
+              "url": "https://example.com/upgrade-test",
+              "tag": "github-group-test"
+            }'
+
+          echo "✓ Created watch with tag 'github-group-test'"
+
+          # Create a specific test URL watch
+          echo "Creating test URL watch via API..."
+          curl -X POST "http://127.0.0.1:5000/api/v1/watch" \
+            -H "x-api-key: ${API_KEY}" \
+            -H "Content-Type: application/json" \
+            --show-error --fail \
+            -d '{
+              "url": "http://localhost/test.txt"
+            }'
+
+          echo "✓ Created watch for 'http://localhost/test.txt' in version 0.49.1"
+
+          # Stop the old version gracefully
+          kill $APP_PID
+          wait $APP_PID || true
+          echo "✓ Version 0.49.1 stopped"
+
+          # Upgrade to current version (use commit SHA since we're in detached HEAD)
+          echo "Upgrading to commit ${{ github.sha }}"
+          git checkout ${{ github.sha }}
+          pip install -r requirements.txt
+
+          echo "=== Running current version (commit ${{ github.sha }}) with old datastore (testing mode) ==="
+          TESTING_SHUTDOWN_AFTER_DATASTORE_LOAD=1 python3 ./changedetection.py -d /tmp/data > /tmp/upgrade-test.log 2>&1
+
+          echo "=== Upgrade test output ==="
+          cat /tmp/upgrade-test.log
+          echo "✓ Datastore upgraded successfully"
+
+          # Now start the current version normally to verify the tag survived
+          echo "=== Starting current version to verify tag exists after upgrade ==="
+          timeout 20 python3 ./changedetection.py -d /tmp/data > /tmp/ui-test.log 2>&1 &
+          APP_PID=$!
+
+          # Wait for app to be ready and fetch UI
+          echo "Waiting for current version to be ready..."
+          sleep 5
+          curl --retry 6 --retry-delay 1 --retry-connrefused --silent http://127.0.0.1:5000 > /tmp/ui-output.html
+
+          # Verify tag exists in UI
+          if grep -q "github-group-test" /tmp/ui-output.html; then
+            echo "✓ Tag 'github-group-test' found in UI after upgrade"
+          else
+            echo "ERROR: Tag 'github-group-test' not found in UI after upgrade"
+            echo "=== UI Output ==="
+            cat /tmp/ui-output.html
+            echo "=== App Log ==="
+            cat /tmp/ui-test.log
+            kill $APP_PID || true
+            exit 1
+          fi
+
+          # Verify test URL exists in UI
+          if grep -q "http://localhost/test.txt" /tmp/ui-output.html; then
+            echo "✓ Watch URL 'http://localhost/test.txt' found in UI after upgrade"
+          else
+            echo "ERROR: Watch URL 'http://localhost/test.txt' not found in UI after upgrade"
+            echo "=== UI Output ==="
+            cat /tmp/ui-output.html
+            echo "=== App Log ==="
+            cat /tmp/ui-test.log
+            kill $APP_PID || true
+            exit 1
+          fi
+
+          # Cleanup
+          kill $APP_PID || true
+          wait $APP_PID || true
+
+          echo ""
+          echo "✓✓✓ Upgrade test passed: 0.49.1 → ${{ github.ref_name }} ✓✓✓"
+          echo "    - Commit: ${{ github.sha }}"
+          echo "    - Datastore migrated successfully"
+          echo "    - Tag 'github-group-test' survived upgrade"
+          echo "    - Watch URL 'http://localhost/test.txt' survived upgrade"
+
+          echo "✓ Upgrade test passed: 0.49.1 → ${{ github.ref_name }}"
+
+      - name: Upload upgrade test logs
+        if: always()
+        uses: actions/upload-artifact@v6
+        with:
+          name: upgrade-test-logs-py${{ env.PYTHON_VERSION }}
+          path: /tmp/upgrade-test.log

changedetectionio/__init__.py

@@ -371,7 +371,15 @@ def main():
         # Dont' start if the JSON DB looks corrupt
         logger.critical(f"ERROR: JSON DB or Proxy List JSON at '{app_config['datastore_path']}' appears to be corrupt, aborting.")
         logger.critical(str(e))
-        return
+        sys.exit(1)
+
+    # Testing mode: Exit cleanly after datastore initialization (for CI/CD upgrade tests)
+    if os.environ.get('TESTING_SHUTDOWN_AFTER_DATASTORE_LOAD'):
+        logger.success(f"TESTING MODE: Datastore loaded successfully from {app_config['datastore_path']}")
+        logger.success(f"TESTING MODE: Schema version: {datastore.data['settings']['application'].get('schema_version', 'unknown')}")
+        logger.success(f"TESTING MODE: Loaded {len(datastore.data['watching'])} watches")
+        logger.success("TESTING MODE: Exiting cleanly (TESTING_SHUTDOWN_AFTER_DATASTORE_LOAD is set)")
+        sys.exit(0)
 
     # Apply all_paused setting if specified via CLI
     if all_paused is not None:

changedetectionio/api/Import.py

@@ -2,8 +2,12 @@ from changedetectionio.strtobool import strtobool
 from flask_restful import abort, Resource
 from flask import request
 from functools import wraps
-from . import auth, validate_openapi_request
+from . import auth, validate_openapi_request, schema_create_watch
 from ..validate_url import is_safe_valid_url
+import json
+
+# Number of URLs above which import switches to background processing
+IMPORT_SWITCH_TO_BACKGROUND_THRESHOLD = 20
 
 
 def default_content_type(content_type='text/plain'):
@@ -19,6 +23,62 @@ def default_content_type(content_type='text/plain'):
     return decorator
 
 
+def convert_query_param_to_type(value, schema_property):
+    """
+    Convert a query parameter string to the appropriate type based on schema definition.
+
+    Args:
+        value: String value from query parameter
+        schema_property: Schema property definition with 'type' or 'anyOf' field
+
+    Returns:
+        Converted value in the appropriate type
+    """
+    # Handle anyOf schemas (extract the first type)
+    if 'anyOf' in schema_property:
+        # Use the first non-null type from anyOf
+        for option in schema_property['anyOf']:
+            if option.get('type') and option.get('type') != 'null':
+                prop_type = option.get('type')
+                break
+        else:
+            prop_type = None
+    else:
+        prop_type = schema_property.get('type')
+
+    # Handle array type (e.g., notification_urls)
+    if prop_type == 'array':
+        # Support both comma-separated and JSON array format
+        if value.startswith('['):
+            try:
+                return json.loads(value)
+            except json.JSONDecodeError:
+                return [v.strip() for v in value.split(',')]
+        return [v.strip() for v in value.split(',')]
+
+    # Handle object type (e.g., time_between_check, headers)
+    elif prop_type == 'object':
+        try:
+            return json.loads(value)
+        except json.JSONDecodeError:
+            raise ValueError(f"Invalid JSON object for field: {value}")
+
+    # Handle boolean type
+    elif prop_type == 'boolean':
+        return strtobool(value)
+
+    # Handle integer type
+    elif prop_type == 'integer':
+        return int(value)
+
+    # Handle number type (float)
+    elif prop_type == 'number':
+        return float(value)
+
+    # Default: return as string
+    return value
+
+
 class Import(Resource):
     def __init__(self, **kwargs):
         # datastore is a black box dependency
@@ -28,40 +88,127 @@ class Import(Resource):
     @default_content_type('text/plain') #3547 #3542
     @validate_openapi_request('importWatches')
     def post(self):
-        """Import a list of watched URLs."""
+        """Import a list of watched URLs with optional watch configuration."""
+
+        # Special parameters that are NOT watch configuration
+        special_params = {'tag', 'tag_uuids', 'dedupe', 'proxy'}
 
         extras = {}
 
+        # Handle special 'proxy' parameter
         if request.args.get('proxy'):
             plist = self.datastore.proxy_list
             if not request.args.get('proxy') in plist:
-                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
+                proxy_list_str = ', '.join(plist) if plist else 'none configured'
+                return f"Invalid proxy choice, currently supported proxies are '{proxy_list_str}'", 400
             else:
                 extras['proxy'] = request.args.get('proxy')
 
+        # Handle special 'dedupe' parameter
         dedupe = strtobool(request.args.get('dedupe', 'true'))
 
+        # Handle special 'tag' and 'tag_uuids' parameters
         tags = request.args.get('tag')
         tag_uuids = request.args.get('tag_uuids')
 
         if tag_uuids:
             tag_uuids = tag_uuids.split(',')
 
+        # Extract ALL other query parameters as watch configuration
+        schema_properties = schema_create_watch.get('properties', {})
+        for param_name, param_value in request.args.items():
+            # Skip special parameters
+            if param_name in special_params:
+                continue
+
+            # Skip if not in schema (unknown parameter)
+            if param_name not in schema_properties:
+                return f"Unknown watch configuration parameter: {param_name}", 400
+
+            # Convert to appropriate type based on schema
+            try:
+                converted_value = convert_query_param_to_type(param_value, schema_properties[param_name])
+                extras[param_name] = converted_value
+            except (ValueError, json.JSONDecodeError) as e:
+                return f"Invalid value for parameter '{param_name}': {str(e)}", 400
+
+        # Validate processor if provided
+        if 'processor' in extras:
+            from changedetectionio.processors import available_processors
+            available = [p[0] for p in available_processors()]
+            if extras['processor'] not in available:
+                return f"Invalid processor '{extras['processor']}'. Available processors: {', '.join(available)}", 400
+
+        # Validate fetch_backend if provided
+        if 'fetch_backend' in extras:
+            from changedetectionio.content_fetchers import available_fetchers
+            available = [f[0] for f in available_fetchers()]
+            # Also allow 'system' and extra_browser_* patterns
+            is_valid = (
+                extras['fetch_backend'] == 'system' or
+                extras['fetch_backend'] in available or
+                extras['fetch_backend'].startswith('extra_browser_')
+            )
+            if not is_valid:
+                return f"Invalid fetch_backend '{extras['fetch_backend']}'. Available: system, {', '.join(available)}", 400
+
+        # Validate notification_urls if provided
+        if 'notification_urls' in extras:
+            from wtforms import ValidationError
+            from changedetectionio.api.Notifications import validate_notification_urls
+            try:
+                validate_notification_urls(extras['notification_urls'])
+            except ValidationError as e:
+                return f"Invalid notification_urls: {str(e)}", 400
+
         urls = request.get_data().decode('utf8').splitlines()
-        added = []
+        # Clean and validate URLs upfront
+        urls_to_import = []
         for url in urls:
             url = url.strip()
             if not len(url):
                 continue
 
-            # If hosts that only contain alphanumerics are allowed ("localhost" for example)
+            # Validate URL
             if not is_safe_valid_url(url):
                 return f"Invalid or unsupported URL - {url}", 400
 
+            # Check for duplicates if dedupe is enabled
             if dedupe and self.datastore.url_exists(url):
                 continue
 
-            new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags, tag_uuids=tag_uuids)
-            added.append(new_uuid)
+            urls_to_import.append(url)
 
-        return added
+        # For small imports, process synchronously for immediate feedback
+        if len(urls_to_import) < IMPORT_SWITCH_TO_BACKGROUND_THRESHOLD:
+            added = []
+            for url in urls_to_import:
+                new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags, tag_uuids=tag_uuids)
+                added.append(new_uuid)
+            return added, 200
+
+        # For large imports (>= 20), process in background thread
+        else:
+            import threading
+            from loguru import logger
+
+            def import_watches_background():
+                """Background thread to import watches - discarded after completion."""
+                try:
+                    added_count = 0
+                    for url in urls_to_import:
+                        try:
+                            self.datastore.add_watch(url=url, extras=extras, tag=tags, tag_uuids=tag_uuids)
+                            added_count += 1
+                        except Exception as e:
+                            logger.error(f"Error importing URL {url}: {e}")
+
+                    logger.info(f"Background import complete: {added_count} watches created")
+                except Exception as e:
+                    logger.error(f"Error in background import: {e}")
+
+            # Start background thread and return immediately
+            thread = threading.Thread(target=import_watches_background, daemon=True, name="ImportWatches-Background")
+            thread.start()
+
+            return {'status': f'Importing {len(urls_to_import)} URLs in background', 'count': len(urls_to_import)}, 202

changedetectionio/api/Watch.py

@@ -481,6 +481,7 @@ class CreateWatch(Resource):
                 'last_error': watch['last_error'],
                 'link': watch.link,
                 'page_title': watch['page_title'],
+                'tags': [*tags],  # Unpack dict keys to list (can't use list() since variable named 'list')
                 'title': watch['title'],
                 'url': watch['url'],
                 'viewed': watch.viewed

changedetectionio/model/Tag.py

@@ -20,11 +20,9 @@ See: Watch.py model docstring for full Pydantic architecture explanation
 See: processors/restock_diff/processor.py:184-192 for current manual implementation
 """
 
-import os
 from changedetectionio.model import watch_base
 from changedetectionio.model.persistence import EntityPersistenceMixin
 
-
 class model(EntityPersistenceMixin, watch_base):
     """
     Tag domain model - groups watches and can override their settings.

changedetectionio/model/__init__.py

@@ -2,7 +2,7 @@ import os
 import uuid
 
 from changedetectionio import strtobool
-from .persistence import EntityPersistenceMixin
+from .persistence import EntityPersistenceMixin, _determine_entity_type
 
 __all__ = ['EntityPersistenceMixin', 'watch_base']
 
@@ -511,10 +511,8 @@ class watch_base(dict):
         # Save to disk via subclass implementation
         try:
             # Determine entity type from module name (Watch.py -> watch, Tag.py -> tag)
-            from changedetectionio.model.persistence import _determine_entity_type
             entity_type = _determine_entity_type(self.__class__)
             filename = f"{entity_type}.json"
-
             self._save_to_disk(data_dict, uuid)
             logger.debug(f"Committed {entity_type} {uuid} to {uuid}/{filename}")
         except Exception as e:

changedetectionio/processors/restock_diff/processor.py

@@ -56,6 +56,259 @@ def _deduplicate_prices(data):
     return list(unique_data)
 
 
+# =============================================================================
+# MEMORY MANAGEMENT: Why We Use Multiprocessing (Linux Only)
+# =============================================================================
+#
+# The get_itemprop_availability() function uses 'extruct' to parse HTML metadata
+# (JSON-LD, microdata, OpenGraph, etc). Extruct internally uses lxml, which wraps
+# libxml2 - a C library that allocates memory at the C level.
+#
+# Memory Leak Problem:
+# --------------------
+# 1. lxml's document_fromstring() creates thousands of Python objects backed by
+#    C-level allocations (nodes, attributes, text content)
+# 2. Python's garbage collector can mark these objects as collectible, but
+#    cannot force the OS to reclaim the actual C-level memory
+# 3. malloc/free typically doesn't return memory to OS - it just marks it as
+#    "free in the process address space"
+# 4. With repeated parsing of large HTML (5MB+ pages), memory accumulates even
+#    after Python GC runs
+#
+# Why Multiprocessing Fixes This:
+# --------------------------------
+# When a subprocess exits, the OS forcibly reclaims ALL memory including C-level
+# allocations that Python GC couldn't release. This ensures clean memory state
+# after each extraction.
+#
+# Performance Impact:
+# -------------------
+# - Memray analysis showed 1.2M document_fromstring allocations per page
+# - Without subprocess: memory grows by ~50-500MB per parse and lingers
+# - With subprocess: ~35MB overhead but forces full cleanup after each run
+# - Trade-off: 35MB resource_tracker vs 500MB+ accumulated leak = much better at scale
+#
+# References:
+# -----------
+# - lxml memory issues: https://medium.com/devopss-hole/python-lxml-memory-leak-b8d0b1000dc7
+# - libxml2 caching behavior: https://www.mail-archive.com/lxml@python.org/msg00026.html
+# - GC limitations with C extensions: https://benbernardblog.com/tracking-down-a-freaky-python-memory-leak-part-2/
+#
+# Additional Context:
+# -------------------
+# - jsonpath_ng (used to query the parsed data) is pure Python and doesn't leak
+# - The leak is specifically from lxml's document parsing, not the JSONPath queries
+# - Linux-only because multiprocessing spawn is well-tested there; other platforms
+#   use direct call as fallback
+#
+# Alternative Solution (Future Optimization):
+# -------------------------------------------
+# This entire problem could be avoided by using regex to extract just the machine
+# data blocks (JSON-LD, microdata, OpenGraph tags) BEFORE parsing with lxml:
+#
+#   1. Use regex to extract <script type="application/ld+json">...</script> blocks
+#   2. Use regex to extract <meta property="og:*"> tags
+#   3. Use regex to find itemprop/itemtype attributes and their containing elements
+#   4. Parse ONLY those extracted snippets instead of the entire HTML document
+#
+# Benefits:
+#   - Avoids parsing 5MB of HTML when we only need a few KB of metadata
+#   - Eliminates the lxml memory leak entirely
+#   - Faster extraction (regex is much faster than DOM parsing)
+#   - No subprocess overhead needed
+#
+# Trade-offs:
+#   - Regex for HTML is brittle (comments, CDATA, edge cases)
+#   - Microdata extraction would be complex (need to track element boundaries)
+#   - Would need extensive testing to ensure we don't miss valid data
+#   - extruct is battle-tested; regex solution would need similar maturity
+#
+# For now, the subprocess approach is safer and leverages existing extruct code.
+# =============================================================================
+
+
+def _extract_itemprop_availability_worker(pipe_conn):
+    """
+    Subprocess worker for itemprop extraction (Linux memory management).
+
+    Uses spawn multiprocessing to isolate extruct/lxml memory allocations.
+    When the subprocess exits, the OS reclaims ALL memory including lxml's
+    C-level allocations that Python's GC cannot release.
+
+    Args:
+        pipe_conn: Pipe connection to receive HTML and send result
+    """
+    import json
+    import gc
+
+    html_content = None
+    result_data = None
+
+    try:
+        # Receive HTML as raw bytes (no pickle)
+        html_bytes = pipe_conn.recv_bytes()
+        html_content = html_bytes.decode('utf-8')
+
+        # Explicitly delete html_bytes to free memory
+        del html_bytes
+        gc.collect()
+
+        # Perform extraction in subprocess (uses extruct/lxml)
+        result_data = get_itemprop_availability(html_content)
+
+        # Convert Restock object to dict for JSON serialization
+        result = {
+            'success': True,
+            'data': dict(result_data) if result_data else {}
+        }
+        pipe_conn.send_bytes(json.dumps(result).encode('utf-8'))
+
+        # Clean up before exit
+        del result_data, html_content, result
+        gc.collect()
+
+    except MoreThanOnePriceFound:
+        # Serialize the specific exception type
+        result = {
+            'success': False,
+            'exception_type': 'MoreThanOnePriceFound'
+        }
+        pipe_conn.send_bytes(json.dumps(result).encode('utf-8'))
+
+    except Exception as e:
+        # Serialize other exceptions
+        result = {
+            'success': False,
+            'exception_type': type(e).__name__,
+            'exception_message': str(e)
+        }
+        pipe_conn.send_bytes(json.dumps(result).encode('utf-8'))
+
+    finally:
+        # Final cleanup before subprocess exits
+        # Variables may already be deleted in try block, so use try/except
+        try:
+            del html_content
+        except (NameError, UnboundLocalError):
+            pass
+        try:
+            del result_data
+        except (NameError, UnboundLocalError):
+            pass
+        gc.collect()
+        pipe_conn.close()
+
+
+def extract_itemprop_availability_safe(html_content) -> Restock:
+    """
+    Extract itemprop availability with hybrid approach for memory efficiency.
+
+    Strategy (fastest to slowest, least to most memory):
+    1. Try pure Python extraction (JSON-LD, OpenGraph, microdata) - covers 80%+ of cases
+    2. Fall back to extruct with subprocess isolation on Linux for complex cases
+
+    Args:
+        html_content: HTML string to parse
+
+    Returns:
+        Restock: Extracted availability data
+
+    Raises:
+        MoreThanOnePriceFound: When multiple prices detected
+        Other exceptions: From extruct/parsing
+    """
+    import platform
+
+    # Step 1: Try pure Python extraction first (fast, no lxml, no memory leak)
+    try:
+        from .pure_python_extractor import extract_metadata_pure_python, query_price_availability
+
+        logger.trace("Attempting pure Python metadata extraction (no lxml)")
+        extracted_data = extract_metadata_pure_python(html_content)
+        price_data = query_price_availability(extracted_data)
+
+        # If we got price AND availability, we're done!
+        if price_data.get('price') and price_data.get('availability'):
+            result = Restock(price_data)
+            logger.debug(f"Pure Python extraction successful: {dict(result)}")
+            return result
+
+        # If we got some data but not everything, still try extruct for completeness
+        if price_data.get('price') or price_data.get('availability'):
+            logger.debug(f"Pure Python extraction partial: {price_data}, will try extruct for completeness")
+
+    except Exception as e:
+        logger.debug(f"Pure Python extraction failed: {e}, falling back to extruct")
+
+    # Step 2: Fall back to extruct (uses lxml, needs subprocess on Linux)
+    logger.trace("Falling back to extruct (lxml-based) with subprocess isolation")
+
+    # Only use subprocess isolation on Linux
+    # Other platforms may have issues with spawn or don't need the aggressive memory management
+    if platform.system() == 'Linux':
+        import multiprocessing
+        import json
+        import gc
+
+        try:
+            ctx = multiprocessing.get_context('spawn')
+            parent_conn, child_conn = ctx.Pipe()
+            p = ctx.Process(target=_extract_itemprop_availability_worker, args=(child_conn,))
+            p.start()
+
+            # Send HTML as raw bytes (no pickle)
+            html_bytes = html_content.encode('utf-8')
+            parent_conn.send_bytes(html_bytes)
+
+            # Explicitly delete html_bytes copy immediately after sending
+            del html_bytes
+            gc.collect()
+
+            # Receive result as JSON
+            result_bytes = parent_conn.recv_bytes()
+            result = json.loads(result_bytes.decode('utf-8'))
+
+            # Wait for subprocess to complete
+            p.join()
+
+            # Close pipes
+            parent_conn.close()
+            child_conn.close()
+
+            # Clean up all subprocess-related objects
+            del p, parent_conn, child_conn, result_bytes
+            gc.collect()
+
+            # Handle result or re-raise exception
+            if result['success']:
+                # Reconstruct Restock object from dict
+                restock_obj = Restock(result['data'])
+                # Clean up result dict
+                del result
+                gc.collect()
+                return restock_obj
+            else:
+                # Re-raise the exception that occurred in subprocess
+                exception_type = result['exception_type']
+                exception_msg = result.get('exception_message', '')
+                del result
+                gc.collect()
+
+                if exception_type == 'MoreThanOnePriceFound':
+                    raise MoreThanOnePriceFound()
+                else:
+                    raise Exception(f"{exception_type}: {exception_msg}")
+
+        except Exception as e:
+            # If multiprocessing itself fails, log and fall back to direct call
+            logger.warning(f"Subprocess extraction failed: {e}, falling back to direct call")
+            gc.collect()
+            return get_itemprop_availability(html_content)
+    else:
+        # Non-Linux: direct call (no subprocess overhead needed)
+        return get_itemprop_availability(html_content)
+
+
 # should return Restock()
 # add casting?
 def get_itemprop_availability(html_content) -> Restock:
@@ -196,8 +449,9 @@ class perform_site_check(difference_detection_processor):
         multiple_prices_found = False
 
         # Try built-in extraction first, this will scan metadata in the HTML
+        # On Linux, this runs in a subprocess to prevent lxml/extruct memory leaks
         try:
-            itemprop_availability = get_itemprop_availability(self.fetcher.content)
+            itemprop_availability = extract_itemprop_availability_safe(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

changedetectionio/processors/restock_diff/pure_python_extractor.py

@@ -0,0 +1,286 @@
+"""
+Pure Python metadata extractor - no lxml, no memory leaks.
+
+This module provides a fast, memory-efficient alternative to extruct for common
+e-commerce metadata extraction. It handles:
+- JSON-LD (covers 80%+ of modern sites)
+- OpenGraph meta tags
+- Basic microdata attributes
+
+Uses Python's built-in html.parser instead of lxml/libxml2, avoiding C-level
+memory allocation issues. For edge cases, the main processor can fall back to
+extruct (with subprocess isolation on Linux).
+"""
+
+from html.parser import HTMLParser
+import json
+import re
+from loguru import logger
+
+
+class JSONLDExtractor(HTMLParser):
+    """
+    Extract JSON-LD structured data from HTML.
+
+    Finds all <script type="application/ld+json"> tags and parses their content.
+    Handles multiple JSON-LD blocks on the same page.
+    """
+
+    def __init__(self):
+        super().__init__()
+        self.in_jsonld = False
+        self.data = []  # List of all parsed JSON-LD objects
+        self.current_script = []
+
+    def handle_starttag(self, tag, attrs):
+        if tag == 'script':
+            # Check if this is a JSON-LD script tag
+            for attr, value in attrs:
+                if attr == 'type' and value == 'application/ld+json':
+                    self.in_jsonld = True
+                    self.current_script = []
+                    break
+
+    def handle_data(self, data):
+        if self.in_jsonld:
+            self.current_script.append(data)
+
+    def handle_endtag(self, tag):
+        if tag == 'script' and self.in_jsonld:
+            # Parse the accumulated script content
+            script_content = ''.join(self.current_script)
+            if script_content.strip():
+                try:
+                    # Parse JSON (handles both objects and arrays)
+                    parsed = json.loads(script_content)
+                    if isinstance(parsed, list):
+                        self.data.extend(parsed)
+                    else:
+                        self.data.append(parsed)
+                except json.JSONDecodeError as e:
+                    logger.debug(f"Failed to parse JSON-LD: {e}")
+                    pass
+
+            self.in_jsonld = False
+            self.current_script = []
+
+
+class OpenGraphExtractor(HTMLParser):
+    """
+    Extract OpenGraph meta tags from HTML.
+
+    Finds <meta property="og:*"> tags commonly used for social media sharing.
+    """
+
+    def __init__(self):
+        super().__init__()
+        self.og_data = {}
+
+    def handle_starttag(self, tag, attrs):
+        if tag == 'meta':
+            attrs_dict = dict(attrs)
+            prop = attrs_dict.get('property', '')
+
+            # Extract OpenGraph properties
+            if prop.startswith('og:'):
+                content = attrs_dict.get('content', '')
+                if content:
+                    self.og_data[prop] = content
+
+
+class MicrodataExtractor(HTMLParser):
+    """
+    Extract basic microdata attributes from HTML.
+
+    Finds elements with itemprop attributes. This is a simplified extractor
+    that doesn't handle nested itemscope/itemtype hierarchies - for complex
+    cases, use extruct as fallback.
+    """
+
+    def __init__(self):
+        super().__init__()
+        self.microdata = {}
+        self.current_itemprop = None
+
+    def handle_starttag(self, tag, attrs):
+        attrs_dict = dict(attrs)
+
+        if 'itemprop' in attrs_dict:
+            itemprop = attrs_dict['itemprop']
+
+            # Price/currency/availability can be in content/href attributes
+            if itemprop == 'price':
+                if 'content' in attrs_dict:
+                    self.microdata['price'] = attrs_dict['content']
+                else:
+                    self.current_itemprop = 'price'
+
+            elif itemprop == 'priceCurrency':
+                if 'content' in attrs_dict:
+                    self.microdata['currency'] = attrs_dict['content']
+                else:
+                    self.current_itemprop = 'priceCurrency'
+
+            elif itemprop == 'availability':
+                # Can be in href (link) or content (meta)
+                if 'href' in attrs_dict:
+                    self.microdata['availability'] = attrs_dict['href']
+                elif 'content' in attrs_dict:
+                    self.microdata['availability'] = attrs_dict['content']
+                else:
+                    self.current_itemprop = 'availability'
+
+    def handle_data(self, data):
+        # Capture text content for itemprop elements
+        if self.current_itemprop == 'price':
+            # Try to extract numeric price from text
+            try:
+                price_text = re.sub(r'[^\d.]', '', data.strip())
+                if price_text:
+                    self.microdata['price'] = float(price_text)
+            except ValueError:
+                pass
+        elif self.current_itemprop == 'priceCurrency':
+            currency = data.strip()
+            if currency:
+                self.microdata['currency'] = currency
+        elif self.current_itemprop == 'availability':
+            availability = data.strip()
+            if availability:
+                self.microdata['availability'] = availability
+
+    def handle_endtag(self, tag):
+        # Reset current itemprop after closing tag
+        self.current_itemprop = None
+
+
+def extract_metadata_pure_python(html_content):
+    """
+    Extract structured metadata from HTML using pure Python parsers.
+
+    Returns a dict with three keys:
+    - 'json-ld': List of parsed JSON-LD objects
+    - 'opengraph': Dict of OpenGraph properties
+    - 'microdata': Dict of microdata properties
+
+    Args:
+        html_content: HTML string to parse
+
+    Returns:
+        dict: Extracted metadata in three formats
+    """
+    result = {
+        'json-ld': [],
+        'opengraph': {},
+        'microdata': {}
+    }
+
+    # Extract JSON-LD
+    try:
+        jsonld_extractor = JSONLDExtractor()
+        jsonld_extractor.feed(html_content)
+        result['json-ld'] = jsonld_extractor.data
+        logger.trace(f"Pure Python: Found {len(jsonld_extractor.data)} JSON-LD blocks")
+    except Exception as e:
+        logger.debug(f"JSON-LD extraction failed: {e}")
+
+    # Extract OpenGraph
+    try:
+        og_extractor = OpenGraphExtractor()
+        og_extractor.feed(html_content)
+        result['opengraph'] = og_extractor.og_data
+        if result['opengraph']:
+            logger.trace(f"Pure Python: Found {len(og_extractor.og_data)} OpenGraph tags")
+    except Exception as e:
+        logger.debug(f"OpenGraph extraction failed: {e}")
+
+    # Extract Microdata
+    try:
+        microdata_extractor = MicrodataExtractor()
+        microdata_extractor.feed(html_content)
+        result['microdata'] = microdata_extractor.microdata
+        if result['microdata']:
+            logger.trace(f"Pure Python: Found microdata: {result['microdata']}")
+    except Exception as e:
+        logger.debug(f"Microdata extraction failed: {e}")
+
+    return result
+
+
+def query_price_availability(extracted_data):
+    """
+    Query extracted metadata for price and availability information.
+
+    Uses jsonpath_ng to query JSON-LD data (same approach as extruct).
+    Falls back to OpenGraph and microdata if JSON-LD doesn't have the data.
+
+    Args:
+        extracted_data: Dict from extract_metadata_pure_python()
+
+    Returns:
+        dict: {'price': float, 'currency': str, 'availability': str}
+    """
+    from jsonpath_ng import parse
+
+    result = {}
+
+    # 1. Try JSON-LD first (most reliable and common)
+    for data in extracted_data.get('json-ld', []):
+        try:
+            # Use jsonpath to find price/availability anywhere in the structure
+            price_parse = parse('$..(price|Price)')
+            availability_parse = parse('$..(availability|Availability)')
+            currency_parse = parse('$..(priceCurrency|currency|priceCurrency)')
+
+            price_results = [m.value for m in price_parse.find(data)]
+            if price_results and not result.get('price'):
+                # Handle various price formats
+                price_val = price_results[0]
+                if isinstance(price_val, (int, float)):
+                    result['price'] = float(price_val)
+                elif isinstance(price_val, str):
+                    # Extract numeric value from string
+                    try:
+                        result['price'] = float(re.sub(r'[^\d.]', '', price_val))
+                    except ValueError:
+                        pass
+
+            avail_results = [m.value for m in availability_parse.find(data)]
+            if avail_results and not result.get('availability'):
+                result['availability'] = str(avail_results[0])
+
+            curr_results = [m.value for m in currency_parse.find(data)]
+            if curr_results and not result.get('currency'):
+                result['currency'] = str(curr_results[0])
+
+            # If we found price, this JSON-LD block is good
+            if result.get('price'):
+                logger.debug(f"Pure Python: Found price data in JSON-LD: {result}")
+                break
+
+        except Exception as e:
+            logger.debug(f"Error querying JSON-LD: {e}")
+            continue
+
+    # 2. Try OpenGraph if JSON-LD didn't provide everything
+    og_data = extracted_data.get('opengraph', {})
+    if not result.get('price') and 'og:price:amount' in og_data:
+        try:
+            result['price'] = float(og_data['og:price:amount'])
+        except ValueError:
+            pass
+    if not result.get('currency') and 'og:price:currency' in og_data:
+        result['currency'] = og_data['og:price:currency']
+    if not result.get('availability') and 'og:availability' in og_data:
+        result['availability'] = og_data['og:availability']
+
+    # 3. Use microdata as last resort
+    microdata = extracted_data.get('microdata', {})
+    if not result.get('price') and 'price' in microdata:
+        result['price'] = microdata['price']
+    if not result.get('currency') and 'currency' in microdata:
+        result['currency'] = microdata['currency']
+    if not result.get('availability') and 'availability' in microdata:
+        result['availability'] = microdata['availability']
+
+    return result

changedetectionio/static/js/modal.js

@@ -184,7 +184,8 @@ $(document).ready(function() {
         }
         // If it's a button in a form, submit the form
         else if ($element.is('button')) {
-          $element.closest('form').submit();
+          // Use requestSubmit() to include the button's name/value in the form data
+          $element.closest('form')[0].requestSubmit($element[0]);
         }
       }
     };

changedetectionio/store/__init__.py

@@ -33,9 +33,8 @@ except ImportError:
 from ..processors import get_custom_watch_obj_for_processor
 
 # Import the base class and helpers
-from .file_saving_datastore import FileSavingDataStore, load_all_watches, load_all_tags, save_watch_atomic, save_tag_atomic, save_json_atomic
+from .file_saving_datastore import FileSavingDataStore, load_all_watches, load_all_tags, save_json_atomic
 from .updates import DatastoreUpdatesMixin
-from .legacy_loader import has_legacy_datastore
 
 # Because the server will run as a daemon and wont know the URL for notification links when firing off a notification
 BASE_URL_NOT_SET_TEXT = '("Base URL" not set - see settings - notifications)'
@@ -78,7 +77,7 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
             logger.info(f"Backing up changedetection.json due to new version to '{db_path_version_backup}'.")
             copyfile(db_path, db_path_version_backup)
 
-    def _load_settings(self):
+    def _load_settings(self, filename="changedetection.json"):
         """
         Load settings from storage.
 
@@ -87,7 +86,7 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
         Returns:
             dict: Settings data loaded from storage
         """
-        changedetection_json = os.path.join(self.datastore_path, "changedetection.json")
+        changedetection_json = os.path.join(self.datastore_path, filename)
 
         logger.info(f"Loading settings from {changedetection_json}")
 
@@ -122,6 +121,11 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
             if 'application' in settings_data['settings']:
                 self.__data['settings']['application'].update(settings_data['settings']['application'])
 
+        # More or less for the old format which had this data in the one url-watches.json
+        # cant hurt to leave it here,
+        if 'watching' in settings_data:
+            self.__data['watching'].update(settings_data['watching'])
+
     def _rehydrate_tags(self):
         """Rehydrate tag entities from stored data into Tag objects with restock_diff processor."""
         from ..model import Tag
@@ -146,23 +150,28 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
         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)
+            if isinstance(watch_dict, dict):
+                watching_rehydrated[uuid] = self.rehydrate_entity(uuid, watch_dict)
+            else:
+                logger.error(f"Watch UUID {uuid} already rehydrated")
+
         self.__data['watching'] = watching_rehydrated
         logger.success(f"Rehydrated {watch_count} watches into Watch objects")
 
 
-    def _load_state(self):
+    def _load_state(self, main_settings_filename="changedetection.json"):
         """
         Load complete datastore state from storage.
 
         Orchestrates loading of settings, watches, and tags using polymorphic methods.
         """
         # Load settings
-        settings_data = self._load_settings()
+        settings_data = self._load_settings(filename=main_settings_filename)
         self._apply_settings(settings_data)
 
-        # Load watches (polymorphic - parent class method)
+        # Load watches, scan them from the disk
         self._load_watches()
+        self._rehydrate_watches()
 
         # Load tags from individual tag.json files
         # These will override any tags in settings (migration path)
@@ -200,112 +209,73 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
 
         # Check if datastore already exists
         changedetection_json = os.path.join(self.datastore_path, "changedetection.json")
+        changedetection_json_old_schema = os.path.join(self.datastore_path, "url-watches.json")
 
         if os.path.exists(changedetection_json):
-            # Load existing datastore (changedetection.json + watch.json files)
-            logger.info("Loading existing datastore")
-            try:
-                self._load_state()
-            except Exception as e:
-                logger.critical(f"Failed to load datastore: {e}")
-                raise
-
             # Run schema updates if needed
             # Pass current schema version from loaded datastore (defaults to 0 if not set)
+            # Load existing datastore (changedetection.json + watch.json files)
+            logger.info("Loading existing datastore")
+            self._load_state()
+            current_schema = self.data['settings']['application'].get('schema_version', 0)
+            self.run_updates(current_schema_version=current_schema)
+
+        # Legacy datastore detected - trigger migration, even works if the schema is much before the migration step.
+        elif os.path.exists(changedetection_json_old_schema):
+
+            logger.critical(f"Legacy datastore detected at {changedetection_json_old_schema}, loading and running updates")
+            self._load_state(main_settings_filename="url-watches.json")
+            # update 26 will load the whole old config from disk to __data
             current_schema = self.__data['settings']['application'].get('schema_version', 0)
             self.run_updates(current_schema_version=current_schema)
+            # Probably tags were also shifted to disk and many other changes, so best to reload here.
+            self._load_state()
 
         else:
             # No datastore yet - check if this is a fresh install or legacy migration
-            # Generate app_guid FIRST (required for all operations)
-            if "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ:
-                self.__data['app_guid'] = "test-" + str(uuid_builder.uuid4())
-            else:
-                self.__data['app_guid'] = str(uuid_builder.uuid4())
+            self.init_fresh_install(include_default_watches=include_default_watches,
+                                    version_tag=version_tag)
 
-            # Generate RSS access token
-            self.__data['settings']['application']['rss_access_token'] = secrets.token_hex(16)
+    def init_fresh_install(self, include_default_watches, version_tag):
+      # Generate app_guid FIRST (required for all operations)
+        if "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ:
+            self.__data['app_guid'] = "test-" + str(uuid_builder.uuid4())
+        else:
+            self.__data['app_guid'] = str(uuid_builder.uuid4())
 
-            # Generate API access token
-            self.__data['settings']['application']['api_access_token'] = secrets.token_hex(16)
+        # Generate RSS access token
+        self.__data['settings']['application']['rss_access_token'] = secrets.token_hex(16)
 
-            # Check if legacy datastore exists (url-watches.json)
-            if has_legacy_datastore(self.datastore_path):
-                # Legacy datastore detected - trigger migration
-                logger.critical(f"Legacy datastore detected at {self.datastore_path}/url-watches.json")
-                logger.critical("Migration will be triggered via update_26")
+        # Generate API access token
+        self.__data['settings']['application']['api_access_token'] = secrets.token_hex(16)
+        logger.warning(f"No datastore found, creating new datastore at {self.datastore_path}")
 
-                # Load the legacy datastore
-                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)
+        # Set schema version to latest (no updates needed)
+        latest_update_available = self.get_updates_available().pop()
+        logger.info(f"Marking fresh install to schema version {latest_update_available}")
+        self.__data['settings']['application']['schema_version'] = latest_update_available
 
-                if not legacy_data:
-                    raise Exception("Failed to load legacy datastore from url-watches.json")
+        # Add default watches if requested
+        if include_default_watches:
+            self.add_watch(
+                url='https://news.ycombinator.com/',
+                tag='Tech news',
+                extras={'fetch_backend': 'html_requests'}
+            )
+            self.add_watch(
+                url='https://changedetection.io/CHANGELOG.txt',
+                tag='changedetection.io',
+                extras={'fetch_backend': 'html_requests'}
+            )
 
-                # Merge legacy data with base_config defaults (preserves new fields like 'ui')
-                # self.__data already has App.model() defaults from line 190
-                logger.info("Merging legacy data with base_config defaults...")
-
-                # Apply top-level fields from legacy data
-                if 'app_guid' in legacy_data:
-                    self.__data['app_guid'] = legacy_data['app_guid']
-                if 'build_sha' in legacy_data:
-                    self.__data['build_sha'] = legacy_data['build_sha']
-                if 'version_tag' in legacy_data:
-                    self.__data['version_tag'] = legacy_data['version_tag']
-
-                # Apply watching data (complete replacement as these are user's watches)
-                if 'watching' in legacy_data:
-                    self.__data['watching'] = legacy_data['watching']
-
-                # Merge settings sections (preserves base_config defaults for missing fields)
-                if 'settings' in legacy_data:
-                    if 'headers' in legacy_data['settings']:
-                        self.__data['settings']['headers'].update(legacy_data['settings']['headers'])
-                    if 'requests' in legacy_data['settings']:
-                        self.__data['settings']['requests'].update(legacy_data['settings']['requests'])
-                    if 'application' in legacy_data['settings']:
-                        # CRITICAL: Use .update() to merge, not replace
-                        # This preserves new fields like 'ui' that exist in base_config
-                        self.__data['settings']['application'].update(legacy_data['settings']['application'])
-
-                # 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
-                self.run_updates()
+        # Create changedetection.json immediately
+        try:
+            self._save_settings()
+            logger.info("Created changedetection.json for new datastore")
+        except Exception as e:
+            logger.error(f"Failed to create initial changedetection.json: {e}")
 
 
-            else:
-                # Fresh install - create new datastore
-                logger.warning(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()
-                self.__data['settings']['application']['schema_version'] = updates_available.pop() if updates_available else 26
-
-                # Add default watches if requested
-                if include_default_watches:
-                    self.add_watch(
-                        url='https://news.ycombinator.com/',
-                        tag='Tech news',
-                        extras={'fetch_backend': 'html_requests'}
-                    )
-                    self.add_watch(
-                        url='https://changedetection.io/CHANGELOG.txt',
-                        tag='changedetection.io',
-                        extras={'fetch_backend': 'html_requests'}
-                    )
-
-                # Create changedetection.json immediately
-                try:
-                    self._save_settings()
-                    logger.info("Created changedetection.json for new datastore")
-                except Exception as e:
-                    logger.error(f"Failed to create initial changedetection.json: {e}")
 
         # Set version tag
         self.__data['version_tag'] = version_tag
@@ -383,17 +353,9 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
         # Deep copy settings to avoid modifying the original
         settings_copy = copy.deepcopy(self.__data['settings'])
 
-        # Only exclude tags if we've already migrated them to individual files (schema >= 28)
-        # This ensures update_28 can migrate tags from settings
-        schema_version = self.__data['settings']['application'].get('schema_version', 0)
-        if schema_version >= 28:
-            # Tags are in individual tag.json files, don't save to settings
-            settings_copy['application']['tags'] = {}
-        # else: keep tags in settings for update_28 migration
-
         return {
             'note': 'Settings file - watches are in {uuid}/watch.json, tags are in {uuid}/tag.json',
-            'app_guid': self.__data['app_guid'],
+            'app_guid': self.__data.get('app_guid'),
             'settings': settings_copy,
             'build_sha': self.__data.get('build_sha'),
             'version_tag': self.__data.get('version_tag')
@@ -422,15 +384,14 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
         Implementation of abstract method from FileSavingDataStore.
         Delegates to helper function and stores results in internal data structure.
         """
-        watching = load_all_watches(
-            self.datastore_path,
-            self.rehydrate_entity
-        )
 
         # Store loaded data
-        self.__data['watching'] = watching
-
-        logger.debug(f"Loaded {len(watching)} watches")
+        # @note this will also work for the old legacy format because self.__data['watching'] should already have them loaded by this point.
+        self.__data['watching'].update(load_all_watches(
+            self.datastore_path,
+            self.rehydrate_entity
+        ))
+        logger.debug(f"Loaded {len(self.__data['watching'])} watches")
 
     def _load_tags(self):
         """

changedetectionio/store/file_saving_datastore.py

@@ -207,15 +207,6 @@ def save_watch_atomic(watch_dir, uuid, watch_dict):
     save_entity_atomic(watch_dir, uuid, watch_dict, "watch.json", "watch", max_size_mb=10)
 
 
-def save_tag_atomic(tag_dir, uuid, tag_dict):
-    """
-    Save a tag to disk using atomic write pattern.
-
-    Convenience wrapper around save_entity_atomic for tags.
-    Kept for backwards compatibility.
-    """
-    save_entity_atomic(tag_dir, uuid, tag_dict, "tag.json", "tag", max_size_mb=1)
-
 
 def load_watch_from_file(watch_json, uuid, rehydrate_entity_func):
     """

changedetectionio/store/legacy_loader.py

@@ -1,66 +0,0 @@
-"""
-Legacy format loader for url-watches.json.
-
-Provides functions to detect and load from the legacy monolithic JSON format.
-Used during migration (update_26) to transition to individual watch.json files.
-"""
-
-import os
-import json
-from loguru import logger
-
-# Try to import orjson for faster JSON serialization
-try:
-    import orjson
-    HAS_ORJSON = True
-except ImportError:
-    HAS_ORJSON = False
-
-
-def has_legacy_datastore(datastore_path):
-    """
-    Check if a legacy url-watches.json file exists.
-
-    This is used by update_26 to determine if migration is needed.
-
-    Args:
-        datastore_path: Path to datastore directory
-
-    Returns:
-        bool: True if url-watches.json exists
-    """
-    url_watches_json = os.path.join(datastore_path, "url-watches.json")
-    return os.path.exists(url_watches_json)
-
-
-def load_legacy_format(json_store_path):
-    """
-    Load datastore from legacy url-watches.json format.
-
-    Args:
-        json_store_path: Full path to url-watches.json file
-
-    Returns:
-        dict: Loaded datastore data with 'watching', 'settings', etc.
-        None: If file doesn't exist or loading failed
-    """
-    logger.info(f"Loading from legacy format: {json_store_path}")
-
-    if not os.path.isfile(json_store_path):
-        logger.warning(f"Legacy file not found: {json_store_path}")
-        return None
-
-    try:
-        if HAS_ORJSON:
-            with open(json_store_path, 'rb') as f:
-                data = orjson.loads(f.read())
-        else:
-            with open(json_store_path, 'r', encoding='utf-8') as f:
-                data = json.load(f)
-
-        logger.info(f"Loaded {len(data.get('watching', {}))} watches from legacy format")
-        return data
-
-    except Exception as e:
-        logger.error(f"Failed to load legacy format: {e}")
-        return None

changedetectionio/store/updates.py

@@ -16,12 +16,18 @@ import time
 from loguru import logger
 from copy import deepcopy
 
+
+# Try to import orjson for faster JSON serialization
+try:
+    import orjson
+    HAS_ORJSON = True
+except ImportError:
+    HAS_ORJSON = False
+
 from ..html_tools import TRANSLATE_WHITESPACE_TABLE
 from ..processors.restock_diff import Restock
 from ..blueprint.rss import RSS_CONTENT_FORMAT_DEFAULT
 from ..model import USE_SYSTEM_DEFAULT_NOTIFICATION_FORMAT_FOR_WATCH
-from .file_saving_datastore import save_watch_atomic
-
 
 def create_backup_tarball(datastore_path, update_number):
     """
@@ -97,7 +103,7 @@ def create_backup_tarball(datastore_path, update_number):
                     tar.add(tag_json, arcname=f"{entry}/tag.json")
                     tag_count += 1
 
-            logger.success(f"Backup created: {backup_filename} ({watch_count} watches, {tag_count} tags)")
+            logger.success(f"Backup created: {backup_filename} ({watch_count} watches from disk, {tag_count} tags from disk)")
             return backup_path
 
     except Exception as e:
@@ -137,6 +143,7 @@ class DatastoreUpdatesMixin:
         return updates_available
 
     def run_updates(self, current_schema_version=None):
+        import sys
         """
         Run all pending schema updates sequentially.
 
@@ -160,6 +167,23 @@ class DatastoreUpdatesMixin:
         4. All changes saved via individual .commit() calls
         """
         updates_available = self.get_updates_available()
+        if self.data.get('watching'):
+            test_watch = self.data['watching'].get(next(iter(self.data.get('watching', {}))))
+            from ..model.Watch import model
+
+            if not isinstance(test_watch, model):
+                import sys
+                logger.critical("Cannot run updates! Watch structure must be re-hydrated back to a Watch model object!")
+                sys.exit(1)
+
+        if self.data['settings']['application'].get('tags',{}):
+            test_tag = self.data['settings']['application'].get('tags',{}).get(next(iter(self.data['settings']['application'].get('tags',{}))))
+            from ..model.Tag import model as tag_model
+
+            if not isinstance(test_tag, tag_model):
+                import sys
+                logger.critical("Cannot run updates! Watch tag/group structure must be re-hydrated back to a Tag model object!")
+                sys.exit(1)
 
         # Determine current schema version
         if current_schema_version is None:
@@ -201,10 +225,9 @@ class DatastoreUpdatesMixin:
                 try:
                     update_method = getattr(self, f"update_{update_n}")()
                 except Exception as e:
-                    logger.error(f"Error while trying update_{update_n}")
-                    logger.error(e)
-                    # Don't run any more updates
-                    return
+                    logger.critical(f"Error while trying update_{update_n}")
+                    logger.exception(e)
+                    sys.exit(1)
                 else:
                     # Bump the version
                     self.data['settings']['application']['schema_version'] = update_n
@@ -555,27 +578,6 @@ class DatastoreUpdatesMixin:
         logger.critical("COPY-based migration: url-watches.json will remain intact for rollback")
         logger.critical("=" * 80)
 
-        # Check if already migrated
-        changedetection_json = os.path.join(self.datastore_path, "changedetection.json")
-        if os.path.exists(changedetection_json):
-            logger.info("Migration already completed (changedetection.json exists), skipping")
-            return
-
-        # Check if we need to load legacy data
-        from .legacy_loader import has_legacy_datastore, load_legacy_format
-
-        if not has_legacy_datastore(self.datastore_path):
-            logger.info("No legacy datastore found, nothing to migrate")
-            return
-
-        # Load legacy data from url-watches.json
-        logger.critical("Loading legacy datastore from url-watches.json...")
-        legacy_path = os.path.join(self.datastore_path, "url-watches.json")
-        legacy_data = load_legacy_format(legacy_path)
-
-        if not legacy_data:
-            raise Exception("Failed to load legacy datastore from url-watches.json")
-
         # Populate settings from legacy data
         logger.info("Populating settings from legacy data...")
         watch_count = len(self.data['watching'])
@@ -587,9 +589,7 @@ class DatastoreUpdatesMixin:
         saved_count = 0
         for uuid, watch in self.data['watching'].items():
             try:
-                watch_dict = dict(watch)
-                watch_dir = os.path.join(self.datastore_path, uuid)
-                save_watch_atomic(watch_dir, uuid, watch_dict)
+                watch.commit()
                 saved_count += 1
 
                 if saved_count % 100 == 0:
@@ -635,18 +635,19 @@ class DatastoreUpdatesMixin:
 
         # Phase 4: Verify settings file exists
         logger.critical("Phase 4/4: Verifying changedetection.json exists...")
+        changedetection_json_new_schema=os.path.join(self.datastore_path, "changedetection.json")
+        if not os.path.isfile(changedetection_json_new_schema):
+            import sys
+            logger.critical("Migration failed, changedetection.json not found after update ran!")
+            sys.exit(1)
 
-        if not os.path.isfile(changedetection_json):
-            raise Exception(
-                "Migration failed: changedetection.json not found after save. "
-                "url-watches.json remains intact, safe to retry."
-            )
 
         logger.critical("Phase 4 complete: Verified changedetection.json exists")
 
         # Success! Now reload from new format
         logger.critical("Reloading datastore from new format...")
-        self._load_state() # Includes load_watches
+        # write it to disk, it will be saved without ['watching'] in the JSON db because we find it from disk glob
+        self._save_settings()
         logger.success("Datastore reloaded from new format successfully")
         logger.critical("=" * 80)
         logger.critical("MIGRATION COMPLETED SUCCESSFULLY!")
@@ -681,9 +682,11 @@ class DatastoreUpdatesMixin:
         - Enables independent tag versioning/backup
         - Maintains backwards compatibility (tags stay in settings too)
         """
+        # Force save as tag.json (not watch.json) even if object is corrupted
+
         logger.critical("=" * 80)
         logger.critical("Running migration: Individual tag persistence (update_28)")
-        logger.critical("Creating individual tag.json files (tags remain in settings too)")
+        logger.critical("Creating individual tag.json files")
         logger.critical("=" * 80)
 
         tags = self.data['settings']['application'].get('tags', {})
@@ -700,27 +703,8 @@ class DatastoreUpdatesMixin:
 
         for uuid, tag_data in tags.items():
             try:
-                # Force save as tag.json (not watch.json) even if object is corrupted
-                from changedetectionio.store.file_saving_datastore import save_entity_atomic
-                import os
-
-                tag_dir = os.path.join(self.datastore_path, uuid)
-                os.makedirs(tag_dir, exist_ok=True)
-
-                # Convert to dict if it's an object
-                tag_dict = dict(tag_data) if hasattr(tag_data, '__iter__') else tag_data
-
-                # Save explicitly as tag.json
-                save_entity_atomic(
-                    tag_dir,
-                    uuid,
-                    tag_dict,
-                    filename='tag.json',
-                    entity_type='tag',
-                    max_size_mb=1
-                )
+                tag_data.commit()
                 saved_count += 1
-
                 if saved_count % 10 == 0:
                     logger.info(f"  Progress: {saved_count}/{tag_count} tags migrated...")
 
@@ -737,5 +721,5 @@ class DatastoreUpdatesMixin:
         # On next load, _load_tags() will read from tag.json files and merge with settings
         logger.info("Tags saved to both settings AND individual tag.json files")
         logger.info("Future tag edits will update both locations (dual storage)")
+        logger.critical("=" * 80)
 
-        logger.critical("=" * 80)

changedetectionio/tests/test_api.py

@@ -489,6 +489,7 @@ def test_api_import(client, live_server, measure_memory_usage, datastore_path):
 
     api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
 
+    # Test 1: Basic import with tag
     res = client.post(
         url_for("import") + "?tag=import-test",
         data='https://website1.com\r\nhttps://website2.com',
@@ -507,6 +508,209 @@ def test_api_import(client, live_server, measure_memory_usage, datastore_path):
     res = client.get(url_for('tags.tags_overview_page'))
     assert b'import-test' in res.data
 
+    # Test 2: Import with watch configuration fields (issue #3845)
+    # Test string field (include_filters), boolean (paused), and processor
+    import urllib.parse
+    params = urllib.parse.urlencode({
+        'tag': 'config-test',
+        'include_filters': 'div.content',
+        'paused': 'true',
+        'processor': 'text_json_diff',
+        'title': 'Imported with Config'
+    })
+
+    res = client.post(
+        url_for("import") + "?" + params,
+        data='https://website3.com',
+        headers={'x-api-key': api_key},
+        follow_redirects=True
+    )
+
+    assert res.status_code == 200
+    assert len(res.json) == 1
+    uuid = res.json[0]
+
+    # Verify the configuration was applied
+    watch = live_server.app.config['DATASTORE'].data['watching'][uuid]
+    assert watch['include_filters'] == ['div.content'], "include_filters should be set as array"
+    assert watch['paused'] == True, "paused should be True"
+    assert watch['processor'] == 'text_json_diff', "processor should be set"
+    assert watch['title'] == 'Imported with Config', "title should be set"
+
+    # Test 3: Import with array field (notification_urls) - using valid Apprise format
+    params = urllib.parse.urlencode({
+        'tag': 'notification-test',
+        'notification_urls': 'mailto://test@example.com,mailto://admin@example.com'
+    })
+
+    res = client.post(
+        url_for("import") + "?" + params,
+        data='https://website4.com',
+        headers={'x-api-key': api_key},
+        follow_redirects=True
+    )
+
+    assert res.status_code == 200
+    uuid = res.json[0]
+    watch = live_server.app.config['DATASTORE'].data['watching'][uuid]
+    assert 'mailto://test@example.com' in watch['notification_urls'], "notification_urls should contain first email"
+    assert 'mailto://admin@example.com' in watch['notification_urls'], "notification_urls should contain second email"
+
+    # Test 4: Import with object field (time_between_check)
+    import json
+    time_config = json.dumps({"hours": 2, "minutes": 30})
+    params = urllib.parse.urlencode({
+        'tag': 'schedule-test',
+        'time_between_check': time_config
+    })
+
+    res = client.post(
+        url_for("import") + "?" + params,
+        data='https://website5.com',
+        headers={'x-api-key': api_key},
+        follow_redirects=True
+    )
+
+    assert res.status_code == 200
+    uuid = res.json[0]
+    watch = live_server.app.config['DATASTORE'].data['watching'][uuid]
+    assert watch['time_between_check']['hours'] == 2, "time_between_check hours should be 2"
+    assert watch['time_between_check']['minutes'] == 30, "time_between_check minutes should be 30"
+
+    # Test 5: Import with invalid processor (should fail)
+    res = client.post(
+        url_for("import") + "?processor=invalid_processor",
+        data='https://website6.com',
+        headers={'x-api-key': api_key},
+        follow_redirects=True
+    )
+
+    assert res.status_code == 400, "Should reject invalid processor"
+    assert b"Invalid processor" in res.data, "Error message should mention invalid processor"
+
+    # Test 6: Import with invalid field (should fail)
+    res = client.post(
+        url_for("import") + "?unknown_field=value",
+        data='https://website7.com',
+        headers={'x-api-key': api_key},
+        follow_redirects=True
+    )
+
+    assert res.status_code == 400, "Should reject unknown field"
+    assert b"Unknown watch configuration parameter" in res.data, "Error message should mention unknown parameter"
+
+
+def test_api_import_small_synchronous(client, live_server, measure_memory_usage, datastore_path):
+    """Test that small imports (< threshold) are processed synchronously"""
+    from changedetectionio.api.Import import IMPORT_SWITCH_TO_BACKGROUND_THRESHOLD
+
+    api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
+
+    # Use local test endpoint to avoid network delays
+    test_url_base = url_for('test_endpoint', _external=True)
+
+    # Create URLs: threshold - 1 to stay under limit
+    num_urls = min(5, IMPORT_SWITCH_TO_BACKGROUND_THRESHOLD - 1)  # Use small number for faster test
+    urls = '\n'.join([f'{test_url_base}?id=small-{i}' for i in range(num_urls)])
+
+    # Import small batch
+    res = client.post(
+        url_for("import") + "?tag=small-test",
+        data=urls,
+        headers={'x-api-key': api_key},
+        follow_redirects=True
+    )
+
+    # Should return 200 OK with UUID list (synchronous)
+    assert res.status_code == 200, f"Should return 200 for small imports, got {res.status_code}"
+    assert isinstance(res.json, list), "Response should be a list of UUIDs"
+    assert len(res.json) == num_urls, f"Should return {num_urls} UUIDs, got {len(res.json)}"
+
+    # Verify all watches were created immediately
+    for uuid in res.json:
+        assert uuid in live_server.app.config['DATASTORE'].data['watching'], \
+            f"Watch {uuid} should exist immediately after synchronous import"
+
+    print(f"\n✓ Successfully created {num_urls} watches synchronously")
+
+
+def test_api_import_large_background(client, live_server, measure_memory_usage, datastore_path):
+    """Test that large imports (>= threshold) are processed in background thread"""
+    from changedetectionio.api.Import import IMPORT_SWITCH_TO_BACKGROUND_THRESHOLD
+    import time
+
+    api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
+
+    # Use local test endpoint to avoid network delays
+    test_url_base = url_for('test_endpoint', _external=True)
+
+    # Create URLs: threshold + 10 to trigger background processing
+    num_urls = IMPORT_SWITCH_TO_BACKGROUND_THRESHOLD + 10
+    urls = '\n'.join([f'{test_url_base}?id=bulk-{i}' for i in range(num_urls)])
+
+    # Import large batch
+    res = client.post(
+        url_for("import") + "?tag=bulk-test",
+        data=urls,
+        headers={'x-api-key': api_key},
+        follow_redirects=True
+    )
+
+    # Should return 202 Accepted (background processing)
+    assert res.status_code == 202, f"Should return 202 for large imports, got {res.status_code}"
+    assert b"background" in res.data.lower(), "Response should mention background processing"
+
+    # Extract expected count from response
+    response_json = res.json
+    assert 'count' in response_json, "Response should include count"
+    assert response_json['count'] == num_urls, f"Count should be {num_urls}, got {response_json['count']}"
+
+    # Wait for background thread to complete (with timeout)
+    max_wait = 10  # seconds
+    wait_interval = 0.5
+    elapsed = 0
+    watches_created = 0
+
+    while elapsed < max_wait:
+        time.sleep(wait_interval)
+        elapsed += wait_interval
+
+        # Count how many watches have been created
+        watches_created = len([
+            uuid for uuid, watch in live_server.app.config['DATASTORE'].data['watching'].items()
+            if 'id=bulk-' in watch['url']
+        ])
+
+        if watches_created == num_urls:
+            break
+
+    # Verify all watches were created
+    assert watches_created == num_urls, \
+        f"Expected {num_urls} watches to be created, but found {watches_created} after {elapsed}s"
+
+    # Verify watches have correct configuration
+    bulk_watches = [
+        watch for watch in live_server.app.config['DATASTORE'].data['watching'].values()
+        if 'id=bulk-' in watch['url']
+    ]
+
+    assert len(bulk_watches) == num_urls, "All bulk watches should exist"
+
+    # Check that they have the correct tag
+    datastore = live_server.app.config['DATASTORE']
+    # Get UUIDs of bulk watches by filtering the datastore keys
+    bulk_watch_uuids = [
+        uuid for uuid, watch in live_server.app.config['DATASTORE'].data['watching'].items()
+        if 'id=bulk-' in watch['url']
+    ]
+    for watch_uuid in bulk_watch_uuids:
+        tags = datastore.get_all_tags_for_watch(uuid=watch_uuid)
+        tag_names = [t['title'] for t in tags.values()]
+        assert 'bulk-test' in tag_names, f"Watch {watch_uuid} should have 'bulk-test' tag"
+
+    print(f"\n✓ Successfully created {num_urls} watches in background (took {elapsed}s)")
+
+
 def test_api_conflict_UI_password(client, live_server, measure_memory_usage, datastore_path):
 
 

changedetectionio/tests/test_api_tags.py

@@ -18,7 +18,7 @@ def test_api_tags_listing(client, live_server, measure_memory_usage, datastore_p
         url_for("tags"),
         headers={'x-api-key': api_key}
     )
-    assert res.text.strip() == "{}", "Should be empty list"
+    assert res.get_data(as_text=True).strip() == "{}", "Should be empty list"
     assert res.status_code == 200
 
     res = client.post(
@@ -36,7 +36,7 @@ def test_api_tags_listing(client, live_server, measure_memory_usage, datastore_p
         headers={'x-api-key': api_key}
     )
     assert res.status_code == 200
-    assert new_tag_uuid in res.text
+    assert new_tag_uuid in res.get_data(as_text=True)
     assert res.json[new_tag_uuid]['title'] == tag_title
     assert res.json[new_tag_uuid]['notification_muted'] == False
 
@@ -118,6 +118,16 @@ def test_api_tags_listing(client, live_server, measure_memory_usage, datastore_p
     assert res.status_code == 200
     assert new_tag_uuid in res.json.get('tags', [])
 
+    # Test that tags are returned when listing ALL watches (issue #3854)
+    res = client.get(
+        url_for("createwatch"),  # GET /api/v1/watch - list all watches
+        headers={'x-api-key': api_key}
+    )
+    assert res.status_code == 200
+    assert watch_uuid in res.json, "Watch should be in the list"
+    assert 'tags' in res.json[watch_uuid], "Tags field should be present in watch list"
+    assert new_tag_uuid in res.json[watch_uuid]['tags'], "Tag UUID should be in tags array"
+
     # Check recheck by tag
     before_check_time = live_server.app.config['DATASTORE'].data['watching'][watch_uuid].get('last_checked')
     time.sleep(1)
@@ -148,7 +158,7 @@ def test_api_tags_listing(client, live_server, measure_memory_usage, datastore_p
         headers={'x-api-key': api_key}
     )
     assert res.status_code == 200
-    assert new_tag_uuid not in res.text
+    assert new_tag_uuid not in res.get_data(as_text=True)
 
     # Verify tag was removed from watch
     res = client.get(

changedetectionio/tests/test_group.py

@@ -5,6 +5,8 @@ from flask import url_for
 from .util import live_server_setup, wait_for_all_checks, extract_rss_token_from_UI, get_UUID_for_tag_name, extract_UUID_from_client, delete_all_watches
 import os
 
+from ..store import ChangeDetectionStore
+
 
 # def test_setup(client, live_server, measure_memory_usage, datastore_path):
    #  live_server_setup(live_server) # Setup on conftest per function
@@ -487,7 +489,6 @@ def test_tag_json_persistence(client, live_server, measure_memory_usage, datasto
     - Tag deletion removes tag.json file
     """
     import json
-    from changedetectionio.store import ChangeDetectionStore
 
     datastore = client.application.config.get('DATASTORE')
 
@@ -569,9 +570,6 @@ def test_tag_json_migration_update_27(client, live_server, measure_memory_usage,
     This simulates a pre-update_27 datastore and verifies migration works.
     """
     import json
-    from changedetectionio.store import ChangeDetectionStore
-
-    datastore = client.application.config.get('DATASTORE')
 
     # 1. Create multiple tags
     tag_names = ['migration-tag-1', 'migration-tag-2', 'migration-tag-3']

docs/api-spec.yaml

@@ -28,7 +28,7 @@ info:
     
     For example: `x-api-key: YOUR_API_KEY`
     
-  version: 0.1.4
+  version: 0.1.5
   contact:
     name: ChangeDetection.io
     url: https://github.com/dgtlmoon/changedetection.io
@@ -1503,46 +1503,92 @@ paths:
     post:
       operationId: importWatches
       tags: [Import]
-      summary: Import watch URLs
-      description: Import a list of URLs to monitor. Accepts line-separated URLs in request body.
+      summary: Import watch URLs with configuration
+      description: |
+        Import a list of URLs to monitor with optional watch configuration. Accepts line-separated URLs in request body.
+
+        **Configuration via Query Parameters:**
+
+        You can pass ANY watch configuration field as query parameters to apply settings to all imported watches.
+        All parameters from the Watch schema are supported (processor, fetch_backend, notification_urls, etc.).
+
+        **Special Parameters:**
+        - `tag` / `tag_uuids` - Assign tags to imported watches
+        - `proxy` - Use specific proxy for imported watches
+        - `dedupe` - Skip duplicate URLs (default: true)
+
+        **Type Conversion:**
+        - Booleans: `true`, `false`, `1`, `0`, `yes`, `no`
+        - Arrays: Comma-separated or JSON format (`[item1,item2]`)
+        - Objects: JSON format (`{"key":"value"}`)
+        - Numbers: Parsed as int or float
       x-code-samples:
         - lang: 'curl'
           source: |
+            # Basic import
             curl -X POST "http://localhost:5000/api/v1/import" \
               -H "x-api-key: YOUR_API_KEY" \
               -H "Content-Type: text/plain" \
               -d $'https://example.com\nhttps://example.org\nhttps://example.net'
+
+            # Import with processor and fetch backend
+            curl -X POST "http://localhost:5000/api/v1/import?processor=restock_diff&fetch_backend=html_webdriver" \
+              -H "x-api-key: YOUR_API_KEY" \
+              -H "Content-Type: text/plain" \
+              -d $'https://example.com\nhttps://example.org'
+
+            # Import with multiple settings
+            curl -X POST "http://localhost:5000/api/v1/import?processor=restock_diff&paused=true&tag=production" \
+              -H "x-api-key: YOUR_API_KEY" \
+              -H "Content-Type: text/plain" \
+              -d $'https://example.com'
         - lang: 'Python'
           source: |
             import requests
-            
+
             headers = {
                 'x-api-key': 'YOUR_API_KEY',
                 'Content-Type': 'text/plain'
             }
+
+            # Basic import
             urls = 'https://example.com\nhttps://example.org\nhttps://example.net'
-            response = requests.post('http://localhost:5000/api/v1/import', 
+            response = requests.post('http://localhost:5000/api/v1/import',
                                    headers=headers, data=urls)
             print(response.json())
+
+            # Import with configuration
+            params = {
+                'processor': 'restock_diff',
+                'fetch_backend': 'html_webdriver',
+                'paused': 'false',
+                'tag': 'production'
+            }
+            response = requests.post('http://localhost:5000/api/v1/import',
+                                   headers=headers, params=params, data=urls)
+            print(response.json())
       parameters:
         - name: tag_uuids
           in: query
-          description: Tag UUID to apply to imported web page change monitors (watches)
+          description: Tag UUID(s) to apply to imported watches (comma-separated for multiple)
           schema:
             type: string
+          example: "550e8400-e29b-41d4-a716-446655440000"
         - name: tag
           in: query
-          description: Tag name to apply to imported web page change monitors (watches)
+          description: Tag name to apply to imported watches
           schema:
             type: string
+          example: "production"
         - name: proxy
           in: query
-          description: Proxy key to use for imported web page change monitors (watches)
+          description: Proxy key to use for imported watches
           schema:
             type: string
+          example: "proxy1"
         - name: dedupe
           in: query
-          description: Remove duplicate URLs (default true)
+          description: Skip duplicate URLs (default true)
           schema:
             type: boolean
             default: true