Possible RSS watch UUID bugfix

MANIFEST.in

@@ -11,7 +11,6 @@ recursive-include changedetectionio/realtime *
 recursive-include changedetectionio/static *
 recursive-include changedetectionio/templates *
 recursive-include changedetectionio/tests *
-recursive-include changedetectionio/translations *
 recursive-include changedetectionio/widgets *
 prune changedetectionio/static/package-lock.json
 prune changedetectionio/static/styles/node_modules

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 # Semver means never use .01, or 00. Should be .1.
-__version__ = '0.52.6'
+__version__ = '0.52.1'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError
@@ -41,10 +41,9 @@ from loguru import logger
 #
 # IMPLEMENTATION:
 #   1. Explicit contexts everywhere (primary protection):
+#      - Watch.py: ctx = multiprocessing.get_context('spawn')
 #      - playwright.py: ctx = multiprocessing.get_context('spawn')
 #      - puppeteer.py: ctx = multiprocessing.get_context('spawn')
-#      - isolated_opencv.py: ctx = multiprocessing.get_context('spawn')
-#      - isolated_libvips.py: ctx = multiprocessing.get_context('spawn')
 #
 #   2. Global default (defense-in-depth, below):
 #      - Safety net if future code forgets explicit context

changedetectionio/async_update_worker.py

@@ -1,4 +1,5 @@
 from blinker import signal
+
 from .processors.exceptions import ProcessorException
 import changedetectionio.content_fetchers.exceptions as content_fetchers_exceptions
 from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
@@ -8,6 +9,7 @@ from changedetectionio.flask_app import watch_check_update
 import asyncio
 import importlib
 import os
+import queue
 import time
 
 from loguru import logger

changedetectionio/blueprint/browser_steps/__init__.py

@@ -21,154 +21,31 @@ from changedetectionio.flask_app import login_optionally_required
 from loguru import logger
 
 browsersteps_sessions = {}
-browsersteps_watch_to_session = {}  # Maps watch_uuid -> browsersteps_session_id
 io_interface_context = None
 import json
 import hashlib
 from flask import Response
 import asyncio
 import threading
-import time
-
-# Dedicated event loop for ALL browser steps sessions
-_browser_steps_loop = None
-_browser_steps_thread = None
-_browser_steps_loop_lock = threading.Lock()
-
-def _start_browser_steps_loop():
-    """Start a dedicated event loop for browser steps in its own thread"""
-    global _browser_steps_loop
-
-    # Create and set the event loop for this thread
-    loop = asyncio.new_event_loop()
-    asyncio.set_event_loop(loop)
-    _browser_steps_loop = loop
-
-    logger.debug("Browser steps event loop started")
-
-    try:
-        # Run the loop forever - handles all browsersteps sessions
-        loop.run_forever()
-    except Exception as e:
-        logger.error(f"Browser steps event loop error: {e}")
-    finally:
-        try:
-            # Cancel all remaining tasks
-            pending = asyncio.all_tasks(loop)
-            for task in pending:
-                task.cancel()
-
-            # Wait for tasks to finish cancellation
-            if pending:
-                loop.run_until_complete(asyncio.gather(*pending, return_exceptions=True))
-        except Exception as e:
-            logger.debug(f"Error during browser steps loop cleanup: {e}")
-        finally:
-            loop.close()
-            logger.debug("Browser steps event loop closed")
-
-def _ensure_browser_steps_loop():
-    """Ensure the browser steps event loop is running"""
-    global _browser_steps_loop, _browser_steps_thread
-
-    with _browser_steps_loop_lock:
-        if _browser_steps_thread is None or not _browser_steps_thread.is_alive():
-            logger.debug("Starting browser steps event loop thread")
-            _browser_steps_thread = threading.Thread(
-                target=_start_browser_steps_loop,
-                daemon=True,
-                name="BrowserStepsEventLoop"
-            )
-            _browser_steps_thread.start()
-
-            # Wait for the loop to be ready
-            timeout = 5.0
-            start_time = time.time()
-            while _browser_steps_loop is None:
-                if time.time() - start_time > timeout:
-                    raise RuntimeError("Browser steps event loop failed to start")
-                time.sleep(0.01)
-
-            logger.debug("Browser steps event loop thread started and ready")
 
 def run_async_in_browser_loop(coro):
-    """Run async coroutine using the dedicated browser steps event loop"""
-    _ensure_browser_steps_loop()
-
-    if _browser_steps_loop and not _browser_steps_loop.is_closed():
-        logger.debug("Browser steps using dedicated event loop")
-        future = asyncio.run_coroutine_threadsafe(coro, _browser_steps_loop)
+    """Run async coroutine using the existing async worker event loop"""
+    from changedetectionio import worker_handler
+    
+    # Use the existing async worker event loop instead of creating a new one
+    if worker_handler.USE_ASYNC_WORKERS and worker_handler.async_loop and not worker_handler.async_loop.is_closed():
+        logger.debug("Browser steps using existing async worker event loop")
+        future = asyncio.run_coroutine_threadsafe(coro, worker_handler.async_loop)
         return future.result()
     else:
-        raise RuntimeError("Browser steps event loop is not available")
-
-def cleanup_expired_sessions():
-    """Remove expired browsersteps sessions and cleanup their resources"""
-    global browsersteps_sessions, browsersteps_watch_to_session
-
-    expired_session_ids = []
-
-    # Find expired sessions
-    for session_id, session_data in browsersteps_sessions.items():
-        browserstepper = session_data.get('browserstepper')
-        if browserstepper and browserstepper.has_expired:
-            expired_session_ids.append(session_id)
-
-    # Cleanup expired sessions
-    for session_id in expired_session_ids:
-        logger.debug(f"Cleaning up expired browsersteps session {session_id}")
-        session_data = browsersteps_sessions[session_id]
-
-        # Cleanup playwright resources asynchronously
-        browserstepper = session_data.get('browserstepper')
-        if browserstepper:
-            try:
-                run_async_in_browser_loop(browserstepper.cleanup())
-            except Exception as e:
-                logger.error(f"Error cleaning up session {session_id}: {e}")
-
-        # Remove from sessions dict
-        del browsersteps_sessions[session_id]
-
-        # Remove from watch mapping
-        for watch_uuid, mapped_session_id in list(browsersteps_watch_to_session.items()):
-            if mapped_session_id == session_id:
-                del browsersteps_watch_to_session[watch_uuid]
-                break
-
-    if expired_session_ids:
-        logger.info(f"Cleaned up {len(expired_session_ids)} expired browsersteps session(s)")
-
-def cleanup_session_for_watch(watch_uuid):
-    """Cleanup a specific browsersteps session for a watch UUID"""
-    global browsersteps_sessions, browsersteps_watch_to_session
-
-    session_id = browsersteps_watch_to_session.get(watch_uuid)
-    if not session_id:
-        logger.debug(f"No browsersteps session found for watch {watch_uuid}")
-        return
-
-    logger.debug(f"Cleaning up browsersteps session {session_id} for watch {watch_uuid}")
-
-    session_data = browsersteps_sessions.get(session_id)
-    if session_data:
-        browserstepper = session_data.get('browserstepper')
-        if browserstepper:
-            try:
-                run_async_in_browser_loop(browserstepper.cleanup())
-            except Exception as e:
-                logger.error(f"Error cleaning up session {session_id} for watch {watch_uuid}: {e}")
-
-        # Remove from sessions dict
-        del browsersteps_sessions[session_id]
-
-    # Remove from watch mapping
-    del browsersteps_watch_to_session[watch_uuid]
-
-    logger.debug(f"Cleaned up session for watch {watch_uuid}")
-
-    # Opportunistically cleanup any other expired sessions
-    cleanup_expired_sessions()
+        # Fallback: create a new event loop (for sync workers or if async loop not available)
+        logger.debug("Browser steps creating temporary event loop")
+        loop = asyncio.new_event_loop()
+        asyncio.set_event_loop(loop)
+        try:
+            return loop.run_until_complete(coro)
+        finally:
+            loop.close()
 
 def construct_blueprint(datastore: ChangeDetectionStore):
     browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
@@ -246,9 +123,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         if not watch_uuid:
             return make_response('No Watch UUID specified', 500)
 
-        # Cleanup any existing session for this watch
-        cleanup_session_for_watch(watch_uuid)
-
         logger.debug("Starting connection with playwright")
         logger.debug("browser_steps.py connecting")
 
@@ -257,10 +131,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             browsersteps_sessions[browsersteps_session_id] = run_async_in_browser_loop(
                 start_browsersteps_session(watch_uuid)
             )
-
-            # Store the mapping of watch_uuid -> browsersteps_session_id
-            browsersteps_watch_to_session[watch_uuid] = browsersteps_session_id
-
         except Exception as e:
             if 'ECONNREFUSED' in str(e):
                 return make_response('Unable to start the Playwright Browser session, is sockpuppetbrowser running? Network configuration is OK?', 401)

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

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

changedetectionio/blueprint/ui/edit.py

@@ -238,13 +238,6 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             datastore.data['watching'][uuid] = watch_class(datastore_path=datastore.datastore_path, default=datastore.data['watching'][uuid])
             flash(gettext("Updated watch - unpaused!") if request.args.get('unpause_on_save') else gettext("Updated watch."))
 
-            # Cleanup any browsersteps session for this watch
-            try:
-                from changedetectionio.blueprint.browser_steps import cleanup_session_for_watch
-                cleanup_session_for_watch(uuid)
-            except Exception as e:
-                logger.debug(f"Error cleaning up browsersteps session: {e}")
-
             # Re #286 - We wait for syncing new data to disk in another thread every 60 seconds
             # But in the case something is added we should save straight away
             datastore.needs_write_urgent = True
@@ -332,6 +325,8 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                     'url': url_for('rss.rss_single_watch', uuid=watch['uuid'], token=app_rss_token)
                 },
                 'settings_application': datastore.data['settings']['application'],
+                'system_has_playwright_configured': os.getenv('PLAYWRIGHT_DRIVER_URL'),
+                'system_has_webdriver_configured': os.getenv('WEBDRIVER_URL'),
                 'ui_edit_stats_extras': collect_ui_edit_stats_extras(watch),
                 'visual_selector_data_ready': datastore.visualselector_data_is_ready(watch_uuid=uuid),
                 'timezone_default_config': datastore.data['settings']['application'].get('scheduler_timezone_default'),

changedetectionio/blueprint/ui/templates/edit.html

@@ -206,7 +206,7 @@ Math: {{ 1 + 1 }}") }}
 
             <div class="tab-pane-inner" id="browser-steps">
             {% if capabilities.supports_browser_steps %}
-               {% if true %}
+               {% if visual_selector_data_ready %}
                 <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
                 <fieldset>
                     <div class="pure-control-group">

changedetectionio/blueprint/watchlist/__init__.py

@@ -2,6 +2,7 @@ import os
 import time
 
 from flask import Blueprint, request, make_response, render_template, redirect, url_for, flash, session
+from flask_login import current_user
 from flask_paginate import Pagination, get_page_parameter
 
 from changedetectionio import forms
@@ -84,7 +85,6 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             app_rss_token=datastore.data['settings']['application'].get('rss_access_token'),
             datastore=datastore,
             errored_count=errored_count,
-            extra_classes='has-queue' if len(update_q.queue) else '',
             form=form,
             generate_tag_colors=processors.generate_processor_badge_colors,
             guid=datastore.data['app_guid'],
@@ -92,10 +92,9 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             hosted_sticky=os.getenv("SALTED_PASS", False) == False,
             now_time_server=round(time.time()),
             pagination=pagination,
-            processor_badge_css=processors.get_processor_badge_css(),
             processor_badge_texts=processors.get_processor_badge_texts(),
             processor_descriptions=processors.get_processor_descriptions(),
-            queue_size=len(update_q.queue),
+            processor_badge_css=processors.get_processor_badge_css(),
             queued_uuids=[q_uuid.item['uuid'] for q_uuid in update_q.queue],
             search_q=request.args.get('q', '').strip(),
             sort_attribute=request.args.get('sort') if request.args.get('sort') else request.cookies.get('sort'),

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

@@ -99,14 +99,9 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
                        data-confirm-message="{{ _('<p>Are you sure you want to delete the selected watches?</strong></p><p>This action cannot be undone.</p>') }}"
                        data-confirm-button="{{ _('Delete') }}"><i data-feather="trash" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>{{ _('Delete') }}</button>
     </div>
-
-    <div id="stats_row">
-        <div class="left">{%- if watches|length >= pagination.per_page -%}{{ pagination.info }}{%- endif -%}</div>
-        <div class="right" >{{ _('Queued size') }}: <span id="queue-size-int">{{ queue_size }}</span></div>
-    </div>
-
-
-
+    {%- if watches|length >= pagination.per_page -%}
+        {{ pagination.info }}
+    {%- endif -%}
     {%- if search_q -%}<div id="search-result-info">{{ _('Searching') }} "<strong><i>{{search_q}}</i></strong>"</div>{%- endif -%}
     <div>
         <a href="{{url_for('watchlist.index')}}" class="pure-button button-tag {{'active' if not active_tag_uuid }}">{{ _('All') }}</a>

changedetectionio/content_fetchers/playwright.py

@@ -1,4 +1,3 @@
-import gc
 import json
 import os
 from urllib.parse import urlparse
@@ -186,33 +185,20 @@ class fetcher(Fetcher):
         super().screenshot_step(step_n=step_n)
         screenshot = await capture_full_page_async(page=self.page, screenshot_format=self.screenshot_format)
 
-        # Request GC immediately after screenshot to free memory
-        # Screenshots can be large and browser steps take many of them
-        await self.page.request_gc()
 
         if self.browser_steps_screenshot_path is not None:
             destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.jpeg'.format(step_n))
             logger.debug(f"Saving step screenshot to {destination}")
             with open(destination, 'wb') as f:
                 f.write(screenshot)
-            # Clear local reference to allow screenshot bytes to be collected
-            del screenshot
-            gc.collect()
 
     async def save_step_html(self, step_n):
         super().save_step_html(step_n=step_n)
         content = await self.page.content()
-
-        # Request GC after getting page content
-        await self.page.request_gc()
-
         destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.html'.format(step_n))
         logger.debug(f"Saving step HTML to {destination}")
         with open(destination, 'w', encoding='utf-8') as f:
             f.write(content)
-        # Clear local reference
-        del content
-        gc.collect()
 
     async def run(self,
                   fetch_favicon=True,
@@ -319,12 +305,6 @@ 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)
-                # 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:
@@ -333,52 +313,48 @@ class fetcher(Fetcher):
                 await browser.close()
                 raise EmptyReply(url=url, status_code=response.status)
 
-            # Wrap remaining operations in try/finally to ensure cleanup
+            # Run Browser Steps here
+            if self.browser_steps_get_valid_steps():
+                await self.iterate_browser_steps(start_url=url)
+
+            await self.page.wait_for_timeout(extra_wait * 1000)
+
+            now = time.time()
+            # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
+            if current_include_filters is not None:
+                await self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
+            else:
+                await self.page.evaluate("var include_filters=''")
+            await self.page.request_gc()
+
+            # request_gc before and after evaluate to free up memory
+            # @todo browsersteps etc
+            MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
+            self.xpath_data = await self.page.evaluate(XPATH_ELEMENT_JS, {
+                "visualselector_xpath_selectors": visualselector_xpath_selectors,
+                "max_height": MAX_TOTAL_HEIGHT
+            })
+            await self.page.request_gc()
+
+            self.instock_data = await self.page.evaluate(INSTOCK_DATA_JS)
+            await self.page.request_gc()
+
+            self.content = await self.page.content()
+            await self.page.request_gc()
+            logger.debug(f"Scrape xPath element data in browser done in {time.time() - now:.2f}s")
+
+
+            # Bug 3 in Playwright screenshot handling
+            # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
+            # JPEG is better here because the screenshots can be very very large
+
+            # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
+            # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
+            # acceptable screenshot quality here
             try:
-                # Run Browser Steps here
-                if self.browser_steps_get_valid_steps():
-                    await self.iterate_browser_steps(start_url=url)
-
-                    await self.page.wait_for_timeout(extra_wait * 1000)
-
-                now = time.time()
-                # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
-                if current_include_filters is not None:
-                    await self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
-                else:
-                    await self.page.evaluate("var include_filters=''")
-                await self.page.request_gc()
-
-                # request_gc before and after evaluate to free up memory
-                # @todo browsersteps etc
-                MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
-                self.xpath_data = await self.page.evaluate(XPATH_ELEMENT_JS, {
-                    "visualselector_xpath_selectors": visualselector_xpath_selectors,
-                    "max_height": MAX_TOTAL_HEIGHT
-                })
-                await self.page.request_gc()
-
-                self.instock_data = await self.page.evaluate(INSTOCK_DATA_JS)
-                await self.page.request_gc()
-
-                self.content = await self.page.content()
-                await self.page.request_gc()
-                logger.debug(f"Scrape xPath element data in browser done in {time.time() - now:.2f}s")
-
-
-                # Bug 3 in Playwright screenshot handling
-                # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
-                # JPEG is better here because the screenshots can be very very large
-
-                # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
-                # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
-                # acceptable screenshot quality here
                 # The actual screenshot - this always base64 and needs decoding! horrible! huge CPU usage
                 self.screenshot = await capture_full_page_async(page=self.page, screenshot_format=self.screenshot_format)
 
-            except ScreenshotUnavailable:
-                # Re-raise screenshot unavailable exceptions
-                raise
             except Exception as e:
                 # It's likely the screenshot was too long/big and something crashed
                 raise ScreenshotUnavailable(url=url, status_code=self.status_code)
@@ -413,10 +389,6 @@ class fetcher(Fetcher):
                     pass
                 browser = None
 
-                # Force Python GC to release Playwright resources immediately
-                # Playwright objects can have circular references that delay cleanup
-                gc.collect()
-
 
 # Plugin registration for built-in fetcher
 class PlaywrightFetcherPlugin:

changedetectionio/content_fetchers/webdriver_selenium.py

@@ -15,7 +15,7 @@ class fetcher(Fetcher):
     proxy_url = None
 
     # Capability flags
-    supports_browser_steps = False
+    supports_browser_steps = True
     supports_screenshots = True
     supports_xpath_element_data = True
 

changedetectionio/flask_app.py

@@ -9,7 +9,6 @@ import threading
 import time
 import timeago
 from blinker import signal
-from pathlib import Path
 
 from changedetectionio.strtobool import strtobool
 from threading import Event
@@ -85,10 +84,6 @@ app.config['NEW_VERSION_AVAILABLE'] = False
 if os.getenv('FLASK_SERVER_NAME'):
     app.config['SERVER_NAME'] = os.getenv('FLASK_SERVER_NAME')
 
-# Babel/i18n configuration
-app.config['BABEL_TRANSLATION_DIRECTORIES'] = str(Path(__file__).parent / 'translations')
-app.config['BABEL_DEFAULT_LOCALE'] = 'en_GB'
-
 #app.config["EXPLAIN_TEMPLATE_LOADING"] = True
 
 
@@ -400,9 +395,13 @@ def changedetection_app(config=None, datastore_o=None):
     def get_locale():
         # 1. Try to get locale from session (user explicitly selected)
         if 'locale' in session:
-            return session['locale']
+            locale = session['locale']
+            logger.trace(f"DEBUG: get_locale() returning from session: {locale}")
+            return locale
         # 2. Fall back to Accept-Language header
-        return request.accept_languages.best_match(language_codes)
+        locale = request.accept_languages.best_match(language_codes)
+        logger.trace(f"DEBUG: get_locale() returning from Accept-Language: {locale}")
+        return locale
 
     # Initialize Babel with locale selector
     babel = Babel(app, locale_selector=get_locale)
@@ -519,20 +518,9 @@ def changedetection_app(config=None, datastore_o=None):
     @app.route('/set-language/<locale>')
     def set_language(locale):
         """Set the user's preferred language in the session"""
-        if not request.cookies:
-            logger.error("Cannot set language without session cookie")
-            flash("Cannot set language without session cookie", 'error')
-            return redirect(url_for('watchlist.index'))
-
         # Validate the locale against available languages
         if locale in language_codes:
             session['locale'] = locale
-
-            # CRITICAL: Flask-Babel caches the locale in the request context (ctx.babel_locale)
-            # We must refresh to clear this cache so the new locale takes effect immediately
-            # This is especially important for tests where multiple requests happen rapidly
-            from flask_babel import refresh
-            refresh()
         else:
             logger.error(f"Invalid locale {locale}, available: {language_codes}")
 

changedetectionio/languages.py

@@ -29,9 +29,6 @@ def get_timeago_locale(flask_locale):
     """
     locale_map = {
         'zh': 'zh_CN',      # Chinese Simplified
-        # timeago library just hasn't been updated to use the more modern locale naming convention, before BCP 47 / RFC 5646.
-        'zh_TW': 'zh_TW',   # Chinese Traditional (timeago uses zh_TW)
-        'zh_Hant_TW': 'zh_TW',  # Flask-Babel normalizes zh_TW to zh_Hant_TW, map back to timeago's zh_TW
         'pt': 'pt_PT',      # Portuguese (Portugal)
         'sv': 'sv_SE',      # Swedish
         'no': 'nb_NO',      # Norwegian Bokmål
@@ -56,7 +53,7 @@ LANGUAGE_DATA = {
     'it': {'flag': 'fi fi-it fis', 'name': 'Italiano'},
     'ja': {'flag': 'fi fi-jp fis', 'name': '日本語'},
     'zh': {'flag': 'fi fi-cn fis', 'name': '中文 (简体)'},
-    'zh_Hant_TW': {'flag': 'fi fi-tw fis', 'name': '繁體中文'},
+    'zh_TW': {'flag': 'fi fi-tw fis', 'name': '繁體中文'},
     'ru': {'flag': 'fi fi-ru fis', 'name': 'Русский'},
     'pl': {'flag': 'fi fi-pl fis', 'name': 'Polski'},
     'nl': {'flag': 'fi fi-nl fis', 'name': 'Nederlands'},

changedetectionio/model/Watch.py

@@ -18,31 +18,21 @@ BROTLI_COMPRESS_SIZE_THRESHOLD = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRE
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3))
 mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
 
-def _brotli_save(contents, filepath, mode=None, fallback_uncompressed=False):
+def _brotli_compress_worker(conn, filepath, mode=None):
     """
-    Save compressed data using native brotli.
-    Testing shows no memory leak when using gc.collect() after compression.
+    Worker function to compress data with brotli in a separate process.
+    This isolates memory - when process exits, OS reclaims all memory.
 
     Args:
-        contents: data to compress (str or bytes)
+        conn: multiprocessing.Pipe connection to receive data
         filepath: destination file path
         mode: brotli compression mode (e.g., brotli.MODE_TEXT)
-        fallback_uncompressed: if True, save uncompressed on failure; if False, raise exception
-
-    Returns:
-        str: actual filepath saved (may differ from input if fallback used)
-
-    Raises:
-        Exception: if compression fails and fallback_uncompressed is False
     """
     import brotli
-    import gc
-
-    # Ensure contents are bytes
-    if isinstance(contents, str):
-        contents = contents.encode('utf-8')
 
     try:
+        # Receive data from parent process via pipe (avoids pickle overhead)
+        contents = conn.recv()
         logger.debug(f"Starting brotli compression of {len(contents)} bytes.")
 
         if mode is not None:
@@ -53,25 +43,111 @@ def _brotli_save(contents, filepath, mode=None, fallback_uncompressed=False):
         with open(filepath, 'wb') as f:
             f.write(compressed_data)
 
+        # Send success status back
+        conn.send(True)
         logger.debug(f"Finished brotli compression - From {len(contents)} to {len(compressed_data)} bytes.")
+        # No need for explicit cleanup - process exit frees all memory
+    except Exception as e:
+        logger.critical(f"Brotli compression worker failed: {e}")
+        conn.send(False)
+    finally:
+        conn.close()
 
-        # Force garbage collection to prevent memory buildup
-        gc.collect()
 
-        return filepath
+def _brotli_subprocess_save(contents, filepath, mode=None, timeout=30, fallback_uncompressed=False):
+    """
+    Save compressed data using subprocess to isolate memory.
+    Uses Pipe to avoid pickle overhead for large data.
+
+    Args:
+        contents: data to compress (str or bytes)
+        filepath: destination file path
+        mode: brotli compression mode (e.g., brotli.MODE_TEXT)
+        timeout: subprocess timeout in seconds
+        fallback_uncompressed: if True, save uncompressed on failure; if False, raise exception
+
+    Returns:
+        str: actual filepath saved (may differ from input if fallback used)
+
+    Raises:
+        Exception: if compression fails and fallback_uncompressed is False
+    """
+    import multiprocessing
+    import sys
+
+    # Ensure contents are bytes
+    if isinstance(contents, str):
+        contents = contents.encode('utf-8')
+
+    # Use explicit spawn context for thread safety (avoids fork() with multi-threaded parent)
+    # Always use spawn - consistent behavior in tests and production
+    ctx = multiprocessing.get_context('spawn')
+    parent_conn, child_conn = ctx.Pipe()
+
+    # Run compression in subprocess using spawn (not fork)
+    proc = ctx.Process(target=_brotli_compress_worker, args=(child_conn, filepath, mode))
+
+    # Windows-safe: Set daemon=False explicitly to avoid issues with process cleanup
+    proc.daemon = False
+    proc.start()
+
+    try:
+        # Send data to subprocess via pipe (avoids pickle)
+        parent_conn.send(contents)
+
+        # Wait for result with timeout
+        if parent_conn.poll(timeout):
+            success = parent_conn.recv()
+        else:
+            success = False
+            logger.warning(f"Brotli compression subprocess timed out after {timeout}s")
+            # Graceful termination with platform-aware cleanup
+            try:
+                proc.terminate()
+            except Exception as term_error:
+                logger.debug(f"Process termination issue (may be normal on Windows): {term_error}")
+
+        parent_conn.close()
+        proc.join(timeout=5)
+
+        # Force kill if still alive after graceful termination
+        if proc.is_alive():
+            try:
+                if sys.platform == 'win32':
+                    # Windows: use kill() which is more forceful
+                    proc.kill()
+                else:
+                    # Unix: terminate() already sent SIGTERM, now try SIGKILL
+                    proc.kill()
+                proc.join(timeout=2)
+            except Exception as kill_error:
+                logger.warning(f"Failed to kill brotli compression process: {kill_error}")
+
+        # Check if file was created successfully
+        if success and os.path.exists(filepath):
+            return filepath
 
     except Exception as e:
         logger.error(f"Brotli compression error: {e}")
+        try:
+            parent_conn.close()
+        except:
+            pass
+        try:
+            proc.terminate()
+            proc.join(timeout=2)
+        except:
+            pass
 
-        # Compression failed
-        if fallback_uncompressed:
-            logger.warning(f"Brotli compression failed for {filepath}, saving uncompressed")
-            fallback_path = filepath.replace('.br', '')
-            with open(fallback_path, 'wb') as f:
-                f.write(contents)
-            return fallback_path
-        else:
-            raise Exception(f"Brotli compression failed for {filepath}: {e}")
+    # Compression failed
+    if fallback_uncompressed:
+        logger.warning(f"Brotli compression failed for {filepath}, saving uncompressed")
+        fallback_path = filepath.replace('.br', '')
+        with open(fallback_path, 'wb') as f:
+            f.write(contents)
+        return fallback_path
+    else:
+        raise Exception(f"Brotli compression subprocess failed for {filepath}")
 
 
 class model(watch_base):
@@ -447,7 +523,7 @@ class model(watch_base):
 
                 if not os.path.exists(dest):
                     try:
-                        actual_dest = _brotli_save(contents, dest, mode=brotli.MODE_TEXT, fallback_uncompressed=True)
+                        actual_dest = _brotli_subprocess_save(contents, dest, mode=brotli.MODE_TEXT, fallback_uncompressed=True)
                         if actual_dest != dest:
                             snapshot_fname = os.path.basename(actual_dest)
                     except Exception as e:
@@ -873,13 +949,13 @@ class model(watch_base):
     def save_last_text_fetched_before_filters(self, contents):
         import brotli
         filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
-        _brotli_save(contents, filepath, mode=brotli.MODE_TEXT, fallback_uncompressed=False)
+        _brotli_subprocess_save(contents, filepath, mode=brotli.MODE_TEXT, fallback_uncompressed=False)
 
     def save_last_fetched_html(self, timestamp, contents):
         self.ensure_data_dir_exists()
         snapshot_fname = f"{timestamp}.html.br"
         filepath = os.path.join(self.watch_data_dir, snapshot_fname)
-        _brotli_save(contents, filepath, mode=None, fallback_uncompressed=True)
+        _brotli_subprocess_save(contents, filepath, mode=None, fallback_uncompressed=True)
         self._prune_last_fetched_html_snapshots()
 
     def get_fetched_html(self, timestamp):

changedetectionio/processors/image_ssim_diff/image_handler/isolated_libvips.py

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

changedetectionio/static/js/realtime.js

@@ -76,7 +76,7 @@ $(document).ready(function () {
 
     // Cache DOM elements for performance
     const queueBubble = document.getElementById('queue-bubble');
-    const queueSizePagerInfoText = document.getElementById('queue-size-int');
+
     // Only try to connect if authentication isn't required or user is authenticated
     // The 'is_authenticated' variable will be set in the template
     if (typeof is_authenticated !== 'undefined' ? is_authenticated : true) {
@@ -118,10 +118,6 @@ $(document).ready(function () {
 
             socket.on('queue_size', function (data) {
                 console.log(`${data.event_timestamp} - Queue size update: ${data.q_length}`);
-                if(queueSizePagerInfoText) {
-                    queueSizePagerInfoText.textContent = parseInt(data.q_length).toLocaleString() || 'None';
-                }
-                document.body.classList.toggle('has-queue', parseInt(data.q_length) > 0);
 
                 // Update queue bubble in action sidebar
                 //if (queueBubble) {

changedetectionio/static/styles/scss/parts/_pagination.scss

@@ -1,4 +1,6 @@
 .pagination-page-info {
+  color: #fff;
+  font-size: 0.85rem;
   text-transform: capitalize;
 }
 

changedetectionio/static/styles/scss/parts/_watch_table.scss

@@ -1,32 +1,4 @@
 /* table related */
-#stats_row {
-  display: flex;
-  align-items: center;
-  width: 100%;
-  color: #fff;
-  font-size: 0.85rem;
-  >* {
-    padding-bottom: 0.5rem;
-  }
-  .left {
-    text-align: left;
-  }
-
-  .right {
-    opacity: 0.5;
-    transition: opacity 0.6s ease;
-    margin-left: auto; /* pushes it to the far right */
-    text-align: right;
-  }
-}
-body.has-queue {
-  #stats_row {
-    .right {
-      opacity: 1.0;
-    }
-  }
-}
-
 .watch-table {
   width: 100%;
   font-size: 80%;

changedetectionio/templates/base.html

@@ -1,5 +1,5 @@
 <!DOCTYPE html>
-<html lang="{{ get_locale()|replace('_', '-') }}" data-darkmode="{{ get_darkmode_state() }}">
+<html lang="{{ get_locale() }}" data-darkmode="{{ get_darkmode_state() }}">
 
   <head>
     <meta charset="utf-8" >

changedetectionio/tests/test_i18n.py

@@ -1,71 +1,7 @@
 #!/usr/bin/env python3
 
 from flask import url_for
-from .util import live_server_setup, wait_for_all_checks
-
-
-def test_zh_TW(client, live_server, measure_memory_usage, datastore_path):
-    import time
-    test_url = url_for('test_endpoint', _external=True)
-
-    # Be sure we got a session cookie
-    res = client.get(url_for("watchlist.index"), follow_redirects=True)
-
-    res = client.get(
-        url_for("set_language", locale="zh_Hant_TW"), # Traditional
-        follow_redirects=True
-    )
-    # HTML follows BCP 47 language tag rules, not underscore-based locale formats.
-    assert b'<html lang="zh-Hant-TW"' in res.data
-    assert b'Cannot set language without session cookie' not in res.data
-    assert '選擇語言'.encode() in res.data
-
-    # Check second set works
-    res = client.get(
-        url_for("set_language", locale="en_GB"),
-        follow_redirects=True
-    )
-    assert b'Cannot set language without session cookie' not in res.data
-    res = client.get(url_for("watchlist.index"), follow_redirects=True)
-    assert b"Select Language" in res.data, "Second set of language worked"
-
-    # Check arbitration between zh_Hant_TW<->zh
-    res = client.get(
-        url_for("set_language", locale="zh"), # Simplified chinese
-        follow_redirects=True
-    )
-    res = client.get(url_for("watchlist.index"), follow_redirects=True)
-    assert "选择语言".encode() in res.data, "Simplified chinese worked and it means the flask-babel cache worked"
-
-
-# timeago library just hasn't been updated to use the more modern locale naming convention, before BCP 47 / RFC 5646.
-# The Python timeago library (https://github.com/hustcc/timeago) supports 48 locales but uses different naming conventions than Flask-Babel.
-def test_zh_Hant_TW_timeago_integration():
-    """Test that zh_Hant_TW mapping works and timeago renders Traditional Chinese correctly"""
-    import timeago
-    from datetime import datetime, timedelta
-    from changedetectionio.languages import get_timeago_locale
-
-    # 1. Test the mapping
-    mapped_locale = get_timeago_locale('zh_Hant_TW')
-    assert mapped_locale == 'zh_TW', "zh_Hant_TW should map to timeago's zh_TW"
-    assert get_timeago_locale('zh_TW') == 'zh_TW', "zh_TW should also map to zh_TW"
-
-    # 2. Test timeago library renders Traditional Chinese with the mapped locale
-    now = datetime.now()
-
-    # Test various time periods with Traditional Chinese strings
-    result_15s = timeago.format(now - timedelta(seconds=15), now, mapped_locale)
-    assert '秒前' in result_15s, f"Expected '秒前' in '{result_15s}'"
-
-    result_5m = timeago.format(now - timedelta(minutes=5), now, mapped_locale)
-    assert '分鐘前' in result_5m, f"Expected '分鐘前' in '{result_5m}'"
-
-    result_2h = timeago.format(now - timedelta(hours=2), now, mapped_locale)
-    assert '小時前' in result_2h, f"Expected '小時前' in '{result_2h}'"
-
-    result_3d = timeago.format(now - timedelta(days=3), now, mapped_locale)
-    assert '天前' in result_3d, f"Expected '天前' in '{result_3d}'"
+from .util import live_server_setup
 
 
 def test_language_switching(client, live_server, measure_memory_usage, datastore_path):
@@ -77,9 +13,6 @@ def test_language_switching(client, live_server, measure_memory_usage, datastore
     3. Switch back to English and verify English text appears
     """
 
-    # Establish session cookie
-    client.get(url_for("watchlist.index"), follow_redirects=True)
-
     # Step 1: Set the language to Italian using the /set-language endpoint
     res = client.get(
         url_for("set_language", locale="it"),
@@ -128,9 +61,6 @@ def test_invalid_locale(client, live_server, measure_memory_usage, datastore_pat
     The app should ignore invalid locales and continue working.
     """
 
-    # Establish session cookie
-    client.get(url_for("watchlist.index"), follow_redirects=True)
-
     # First set to English
     res = client.get(
         url_for("set_language", locale="en"),
@@ -163,9 +93,6 @@ def test_language_persistence_in_session(client, live_server, measure_memory_usa
     within the same session.
     """
 
-    # Establish session cookie
-    client.get(url_for("watchlist.index"), follow_redirects=True)
-
     # Set language to Italian
     res = client.get(
         url_for("set_language", locale="it"),
@@ -192,9 +119,6 @@ def test_set_language_with_redirect(client, live_server, measure_memory_usage, d
     """
     from flask import url_for
 
-    # Establish session cookie
-    client.get(url_for("watchlist.index"), follow_redirects=True)
-
     # Set language with a redirect parameter (simulating language change from /settings)
     res = client.get(
         url_for("set_language", locale="de", redirect="/settings"),

changedetectionio/tests/test_live_preview.py

@@ -25,13 +25,12 @@ def test_content_filter_live_preview(client, live_server, measure_memory_usage,
 
     test_url = url_for('test_endpoint', _external=True)
 
-
-    uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
-    res = client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
-    assert b'Queued 1 watch for rechecking.' in res.data
-   
-    wait_for_all_checks(client)
-
+    res = client.post(
+        url_for("ui.ui_views.form_quick_watch_add"),
+        data={"url": test_url, "tags": ''},
+        follow_redirects=True
+    )
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     res = client.post(
         url_for("ui.ui_edit.edit_page", uuid=uuid),
         data={

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -144,6 +144,7 @@ def test_basic_browserstep(client, live_server, measure_memory_usage, datastore_
 
 def test_non_200_errors_report_browsersteps(client, live_server, measure_memory_usage, datastore_path):
 
+
     four_o_four_url =  url_for('test_endpoint', status_code=404, _external=True)
     four_o_four_url = four_o_four_url.replace('localhost.localdomain', 'cdio')
     four_o_four_url = four_o_four_url.replace('localhost', 'cdio')
@@ -185,65 +186,3 @@ def test_non_200_errors_report_browsersteps(client, live_server, measure_memory_
         url_for("ui.form_delete", uuid="all"),
         follow_redirects=True
     )
-
-def test_browsersteps_edit_UI_startsession(client, live_server, measure_memory_usage, datastore_path):
-
-    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
-
-    # Add a watch first
-    test_url = url_for('test_interactive_html_endpoint', _external=True)
-    test_url = test_url.replace('localhost.localdomain', 'cdio')
-    test_url = test_url.replace('localhost', 'cdio')
-
-    uuid = client.application.config.get('DATASTORE').add_watch(url=test_url, extras={'fetch_backend': 'html_webdriver', 'paused': True})
-
-    # Test starting a browsersteps session
-    res = client.get(
-        url_for("browser_steps.browsersteps_start_session", uuid=uuid),
-        follow_redirects=True
-    )
-
-    assert res.status_code == 200
-    assert res.is_json
-    json_data = res.get_json()
-    assert 'browsersteps_session_id' in json_data
-    assert json_data['browsersteps_session_id']  # Not empty
-
-    browsersteps_session_id = json_data['browsersteps_session_id']
-
-    # Verify the session exists in browsersteps_sessions
-    from changedetectionio.blueprint.browser_steps import browsersteps_sessions, browsersteps_watch_to_session
-    assert browsersteps_session_id in browsersteps_sessions
-    assert uuid in browsersteps_watch_to_session
-    assert browsersteps_watch_to_session[uuid] == browsersteps_session_id
-
-    # Verify browsersteps UI shows up on edit page
-    res = client.get(url_for("ui.ui_edit.edit_page", uuid=uuid))
-    assert b'browsersteps-click-start' in res.data, "Browsersteps manual UI shows up"
-
-    # Session should still exist after GET (not cleaned up yet)
-    assert browsersteps_session_id in browsersteps_sessions
-    assert uuid in browsersteps_watch_to_session
-
-    # Test cleanup happens on save (POST)
-    res = client.post(
-        url_for("ui.ui_edit.edit_page", uuid=uuid),
-        data={
-            "url": test_url,
-            "tags": "",
-            'fetch_backend': "html_webdriver",
-            "time_between_check_use_default": "y",
-        },
-        follow_redirects=True
-    )
-    assert b"Updated watch" in res.data
-
-    # NOW verify the session was cleaned up after save
-    assert browsersteps_session_id not in browsersteps_sessions
-    assert uuid not in browsersteps_watch_to_session
-
-    # Cleanup
-    client.get(
-        url_for("ui.form_delete", uuid="all"),
-        follow_redirects=True
-    )

requirements.txt

@@ -91,7 +91,7 @@ jq~=1.3; python_version >= "3.8" and sys_platform == "linux"
 
 # playwright is installed at Dockerfile build time because it's not available on all platforms
 
-pyppeteer-ng==2.0.0rc11
+pyppeteer-ng==2.0.0rc10
 pyppeteerstealth>=0.0.4
 
 # Include pytest, so if theres a support issue we can ask them to run these tests on their setup
@@ -100,7 +100,7 @@ pytest-flask ~=1.3
 pytest-mock ~=3.15
 
 # Anything 4.0 and up but not 5.0
-jsonschema ~= 4.26
+jsonschema ~= 4.25
 
 # OpenAPI validation support
 openapi-core[flask] >= 0.19.0