Move Chrome default args to config.json CHROME_ARGS

- Add comprehensive default CHROME_ARGS in config.json with 55+ flags
  for deterministic rendering, security, performance, and UI suppression

- Update chrome_utils.js launchChromium() to read CHROME_ARGS and
  CHROME_ARGS_EXTRA from environment variables (set by get_config())

- Add getEnvArray() helper to parse JSON arrays or comma-separated
  strings from environment variables

- Separate args into three categories:
  1. baseArgs: Static flags from CHROME_ARGS config (configurable)
  2. dynamicArgs: Runtime-computed flags (port, sandbox, headless, etc.)
  3. extraArgs: User overrides from CHROME_ARGS_EXTRA

- Add CHROME_SANDBOX config option to control --no-sandbox flag

Args are now configurable via:
  - config.json defaults
  - ArchiveBox.conf file
  - Environment variables
  - Per-crawl/snapshot config overrides

archivebox/plugins/chrome/chrome_utils.js

@@ -56,6 +56,36 @@ function getEnvInt(name, defaultValue = 0) {
     return isNaN(val) ? defaultValue : val;
 }
 
+/**
+ * Get array environment variable (JSON array or comma-separated string).
+ * @param {string} name - Environment variable name
+ * @param {string[]} [defaultValue=[]] - Default value if not set
+ * @returns {string[]} - Array of strings
+ */
+function getEnvArray(name, defaultValue = []) {
+    const val = getEnv(name, '');
+    if (!val) return defaultValue;
+
+    // Try parsing as JSON array first
+    if (val.startsWith('[')) {
+        try {
+            const parsed = JSON.parse(val);
+            if (Array.isArray(parsed)) return parsed;
+        } catch (e) {
+            // Fall through to comma-separated parsing
+        }
+    }
+
+    // Parse as comma-separated (but be careful with args that contain commas)
+    // For Chrome args, we split on comma followed by '--' to be safe
+    if (val.includes(',--')) {
+        return val.split(/,(?=--)/).map(s => s.trim()).filter(Boolean);
+    }
+
+    // Simple comma-separated
+    return val.split(',').map(s => s.trim()).filter(Boolean);
+}
+
 /**
  * Parse resolution string into width/height.
  * @param {string} resolution - Resolution string like "1440,2000"
@@ -298,6 +328,7 @@ function killZombieChrome(dataDir = null) {
  * @param {string} [options.userDataDir] - Chrome user data directory for persistent sessions
  * @param {string} [options.resolution='1440,2000'] - Window resolution
  * @param {boolean} [options.headless=true] - Run in headless mode
+ * @param {boolean} [options.sandbox=true] - Enable Chrome sandbox
  * @param {boolean} [options.checkSsl=true] - Check SSL certificates
  * @param {string[]} [options.extensionPaths=[]] - Paths to unpacked extensions
  * @param {boolean} [options.killZombies=true] - Kill zombie processes first
@@ -310,6 +341,7 @@ async function launchChromium(options = {}) {
         userDataDir = getEnv('CHROME_USER_DATA_DIR'),
         resolution = getEnv('CHROME_RESOLUTION') || getEnv('RESOLUTION', '1440,2000'),
         headless = getEnvBool('CHROME_HEADLESS', true),
+        sandbox = getEnvBool('CHROME_SANDBOX', true),
         checkSsl = getEnvBool('CHROME_CHECK_SSL_VALIDITY', getEnvBool('CHECK_SSL_VALIDITY', true)),
         extensionPaths = [],
         killZombies = true,
@@ -353,38 +385,43 @@ async function launchChromium(options = {}) {
     const debugPort = await findFreePort();
     console.error(`[*] Using debug port: ${debugPort}`);
 
-    // Build Chrome arguments
-    const chromiumArgs = [
+    // Get base Chrome args from config (static flags from CHROME_ARGS env var)
+    // These come from config.json defaults, merged by get_config() in Python
+    const baseArgs = getEnvArray('CHROME_ARGS', []);
+
+    // Get extra user-provided args
+    const extraArgs = getEnvArray('CHROME_ARGS_EXTRA', []);
+
+    // Build dynamic Chrome arguments (these must be computed at runtime)
+    const dynamicArgs = [
+        // Remote debugging setup
         `--remote-debugging-port=${debugPort}`,
         '--remote-debugging-address=127.0.0.1',
-        '--no-sandbox',
-        '--disable-setuid-sandbox',
+
+        // Sandbox settings (disable in Docker)
+        ...(sandbox ? [] : ['--no-sandbox', '--disable-setuid-sandbox']),
+
+        // Docker-specific workarounds
         '--disable-dev-shm-usage',
         '--disable-gpu',
-        '--disable-sync',
-        '--no-first-run',
-        '--no-default-browser-check',
-        '--disable-default-apps',
-        '--disable-infobars',
-        '--disable-blink-features=AutomationControlled',
-        '--disable-component-update',
-        '--disable-domain-reliability',
-        '--disable-breakpad',
-        '--disable-background-networking',
-        '--disable-background-timer-throttling',
-        '--disable-backgrounding-occluded-windows',
-        '--disable-renderer-backgrounding',
-        '--disable-ipc-flooding-protection',
-        '--password-store=basic',
-        '--use-mock-keychain',
-        '--font-render-hinting=none',
-        '--force-color-profile=srgb',
+
+        // Window size
         `--window-size=${width},${height}`,
+
+        // User data directory (for persistent sessions with persona)
         ...(userDataDir ? [`--user-data-dir=${userDataDir}`] : []),
+
+        // Headless mode
         ...(headless ? ['--headless=new'] : []),
+
+        // SSL certificate checking
         ...(checkSsl ? [] : ['--ignore-certificate-errors']),
     ];
 
+    // Combine all args: base (from config) + dynamic (runtime) + extra (user overrides)
+    // Dynamic args come after base so they can override if needed
+    const chromiumArgs = [...baseArgs, ...dynamicArgs, ...extraArgs];
+
     // Add extension loading flags
     if (extensionPaths.length > 0) {
         const extPathsArg = extensionPaths.join(',');

archivebox/plugins/chrome/config.json

@@ -42,7 +42,7 @@
     "CHROME_USER_DATA_DIR": {
       "type": "string",
       "default": "",
-      "description": "Path to Chrome user data directory for persistent sessions"
+      "description": "Path to Chrome user data directory for persistent sessions (derived from ACTIVE_PERSONA if not set)"
     },
     "CHROME_USER_AGENT": {
       "type": "string",
@@ -53,16 +53,74 @@
     "CHROME_ARGS": {
       "type": "array",
       "items": {"type": "string"},
-      "default": [],
+      "default": [
+        "--no-first-run",
+        "--no-default-browser-check",
+        "--disable-default-apps",
+        "--disable-sync",
+        "--disable-infobars",
+        "--disable-blink-features=AutomationControlled",
+        "--disable-component-update",
+        "--disable-domain-reliability",
+        "--disable-breakpad",
+        "--disable-client-side-phishing-detection",
+        "--disable-hang-monitor",
+        "--disable-speech-synthesis-api",
+        "--disable-speech-api",
+        "--disable-print-preview",
+        "--disable-notifications",
+        "--disable-desktop-notifications",
+        "--disable-popup-blocking",
+        "--disable-prompt-on-repost",
+        "--disable-external-intent-requests",
+        "--disable-session-crashed-bubble",
+        "--disable-search-engine-choice-screen",
+        "--disable-datasaver-prompt",
+        "--ash-no-nudges",
+        "--hide-crash-restore-bubble",
+        "--suppress-message-center-popups",
+        "--noerrdialogs",
+        "--no-pings",
+        "--silent-debugger-extension-api",
+        "--deny-permission-prompts",
+        "--safebrowsing-disable-auto-update",
+        "--metrics-recording-only",
+        "--password-store=basic",
+        "--use-mock-keychain",
+        "--disable-cookie-encryption",
+        "--font-render-hinting=none",
+        "--force-color-profile=srgb",
+        "--disable-partial-raster",
+        "--disable-skia-runtime-opts",
+        "--disable-2d-canvas-clip-aa",
+        "--enable-webgl",
+        "--hide-scrollbars",
+        "--export-tagged-pdf",
+        "--generate-pdf-document-outline",
+        "--disable-lazy-loading",
+        "--disable-renderer-backgrounding",
+        "--disable-background-networking",
+        "--disable-background-timer-throttling",
+        "--disable-backgrounding-occluded-windows",
+        "--disable-ipc-flooding-protection",
+        "--disable-extensions-http-throttling",
+        "--disable-field-trial-config",
+        "--disable-back-forward-cache",
+        "--autoplay-policy=no-user-gesture-required",
+        "--disable-gesture-requirement-for-media-playback",
+        "--lang=en-US,en;q=0.9",
+        "--log-level=2",
+        "--enable-logging=stderr"
+      ],
       "x-aliases": ["CHROME_DEFAULT_ARGS"],
-      "description": "Default Chrome command-line arguments"
+      "description": "Default Chrome command-line arguments (static flags only, dynamic args like --user-data-dir are added at runtime)"
     },
     "CHROME_ARGS_EXTRA": {
       "type": "array",
       "items": {"type": "string"},
       "default": [],
       "x-aliases": ["CHROME_EXTRA_ARGS"],
-      "description": "Extra arguments to append to Chrome command"
+      "description": "Extra arguments to append to Chrome command (for user customization)"
     },
     "CHROME_PAGELOAD_TIMEOUT": {
       "type": "integer",