LEDMatrix/src/plugin_system/plugin_manager.py

"""
Plugin Manager

Manages plugin discovery, loading, and lifecycle for the LEDMatrix system.
Handles dynamic plugin loading from the plugins/ directory.

API Version: 1.0.0
"""

import json
import queue
import sys
import time
import threading
import types
from pathlib import Path
from typing import Dict, List, Optional, Any, Tuple
import logging
from src.exceptions import PluginError, ConfigError
from src.logging_config import get_logger
from src.plugin_system.plugin_loader import PluginLoader
from src.plugin_system.plugin_executor import PluginExecutor
from src.plugin_system.plugin_state import PluginStateManager, PluginState
from src.plugin_system.schema_manager import SchemaManager
from src.common.permission_utils import (
    ensure_directory_permissions,
    get_plugin_dir_mode
)


class PluginManager:
    """
    Manages plugin discovery, loading, and lifecycle.
    
    The PluginManager is responsible for:
    - Discovering plugins in the plugins/ directory
    - Loading plugin modules and instantiating plugin classes
    - Managing plugin lifecycle (load, unload, reload)
    - Providing access to loaded plugins
    - Maintaining plugin manifests
    
    Uses composition with specialized components:
    - PluginLoader: Handles module loading and dependency installation
    - PluginExecutor: Handles plugin execution with timeout and error isolation
    - PluginStateManager: Manages plugin state machine
    """
    
    def __init__(self, plugins_dir: str = "plugins", 
                 config_manager: Optional[Any] = None, 
                 display_manager: Optional[Any] = None, 
                 cache_manager: Optional[Any] = None, 
                 font_manager: Optional[Any] = None) -> None:
        """
        Initialize the Plugin Manager.
        
        Args:
            plugins_dir: Path to the plugins directory
            config_manager: Configuration manager instance
            display_manager: Display manager instance
            cache_manager: Cache manager instance
            font_manager: Font manager instance
        """
        self.plugins_dir: Path = Path(plugins_dir)
        self.config_manager: Optional[Any] = config_manager
        self.display_manager: Optional[Any] = display_manager
        self.cache_manager: Optional[Any] = cache_manager
        self.font_manager: Optional[Any] = font_manager
        self.logger: logging.Logger = get_logger(__name__)
        
        # Initialize plugin system components
        self.plugin_loader = PluginLoader(logger=self.logger)
        self.plugin_executor = PluginExecutor(default_timeout=30.0, logger=self.logger)
        self.state_manager = PluginStateManager(logger=self.logger)
        self.schema_manager = SchemaManager(plugins_dir=self.plugins_dir, logger=self.logger)
        
        # Lock protecting plugin_manifests and plugin_directories from
        # concurrent mutation (background reconciliation) and reads (requests).
        self._discovery_lock = threading.RLock()

        # Lock protecting plugin_last_update from concurrent mutation/iteration.
        # It's written from run_scheduled_updates()/update_all_plugins() (main
        # loop) and read/diffed by run_scheduled_updates_with_changes(), which
        # Vegas mode calls from its own background update-tick thread.
        self._plugin_last_update_lock = threading.RLock()

        # Active plugins
        self.plugins: Dict[str, Any] = {}
        self.plugin_manifests: Dict[str, Dict[str, Any]] = {}
        self.plugin_modules: Dict[str, Any] = {}
        self.plugin_last_update: Dict[str, float] = {}

        # Cached data-fetch intervals per plugin_id.
        # _get_plugin_update_interval falls back to config_manager.get_config()
        # (a full dict copy) when the manifest lacks an interval — caching avoids
        # that copy on every 30-fps tick.  Cleared on load/unload.
        self._update_interval_cache: Dict[str, Optional[float]] = {}

        # Health tracking (optional, set by display_controller if available)
        self.health_tracker = None
        self.resource_monitor = None

        # --- Asynchronous plugin updates -------------------------------
        # update() used to run inline in the render loop (execute_update's
        # internal thread.join(timeout=30) blocked it), so one slow plugin
        # HTTP fetch froze scrolling for the whole fetch. Scheduling still
        # happens on the render thread (run_scheduled_updates), but
        # execution moves to this single background worker. Per-plugin
        # locks keep a plugin's update() and display() mutually exclusive —
        # today's implicit guarantee, now explicit (and, unlike today,
        # also held across the post-timeout window).
        # Kill switch: plugin_system.synchronous_updates: true restores the
        # inline path.
        self._update_queue: "queue.Queue[Optional[Tuple[str, float]]]" = queue.Queue()
        self._pending_updates: set = set()
        self._pending_lock = threading.Lock()
        self._plugin_locks: Dict[str, threading.Lock] = {}
        self._plugin_locks_guard = threading.Lock()
        self._update_worker: Optional[threading.Thread] = None
        # Plugin ids whose update() has finished since the last time anyone
        # asked. Updates are dispatched to a worker thread, so a caller that
        # wants to know "whose data just changed" cannot learn it by diffing
        # plugin_last_update around run_scheduled_updates() -- that call only
        # enqueues, and the timestamp is stamped later, on the worker. See
        # run_scheduled_updates_with_changes().
        self._completed_updates: set = set()
        self._completed_updates_lock = threading.Lock()
        self._synchronous_updates = False
        if self.config_manager is not None:
            try:
                cfg = self.config_manager.get_config() or {}
            except (OSError, ValueError) as exc:
                self.logger.warning(
                    "Could not load config to check plugin_system.synchronous_updates "
                    "(%s: %s); defaulting to synchronous updates", type(exc).__name__, exc)
                self._synchronous_updates = True
            else:
                plugin_system_cfg = cfg.get('plugin_system', {})
                if not isinstance(plugin_system_cfg, dict):
                    self.logger.warning(
                        "config plugin_system must be a mapping, got %s; "
                        "defaulting to synchronous updates",
                        type(plugin_system_cfg).__name__)
                    self._synchronous_updates = True
                else:
                    sync_value = plugin_system_cfg.get('synchronous_updates', False)
                    if not isinstance(sync_value, bool):
                        self.logger.warning(
                            "config plugin_system.synchronous_updates must be a boolean, "
                            "got %r; defaulting to synchronous updates", sync_value)
                        self._synchronous_updates = True
                    else:
                        self._synchronous_updates = sync_value
        
        # Ensure plugins directory exists with proper permissions
        try:
            ensure_directory_permissions(self.plugins_dir, get_plugin_dir_mode())
        except (OSError, PermissionError) as e:
            self.logger.error("Could not create plugins directory %s: %s", self.plugins_dir, e, exc_info=True)
            raise PluginError(f"Could not create plugins directory: {self.plugins_dir}", context={'error': str(e)}) from e

    def _scan_directory_for_plugins(self, directory: Path) -> List[str]:
        """
        Scan a directory for plugins.

        Args:
            directory: Directory to scan

        Returns:
            List of plugin IDs found
        """
        plugin_ids = []

        if not directory.exists():
            return plugin_ids

        # Build new state locally before acquiring lock
        new_manifests: Dict[str, Dict[str, Any]] = {}
        new_directories: Dict[str, Path] = {}

        try:
            for item in directory.iterdir():
                if not item.is_dir():
                    continue
                # Skip backup directories so they don't overwrite live entries
                if '.standalone-backup-' in item.name:
                    continue

                manifest_path = item / "manifest.json"
                if manifest_path.exists():
                    try:
                        with open(manifest_path, 'r', encoding='utf-8') as f:
                            manifest = json.load(f)
                            plugin_id = manifest.get('id')
                            if plugin_id:
                                plugin_ids.append(plugin_id)
                                new_manifests[plugin_id] = manifest
                                new_directories[plugin_id] = item
                    except (json.JSONDecodeError, PermissionError, OSError) as e:
                        self.logger.warning("Error reading manifest from %s: %s", manifest_path, e, exc_info=True)
                        continue
        except (OSError, PermissionError) as e:
            self.logger.error("Error scanning directory %s: %s", directory, e, exc_info=True)

        # Replace shared state under lock so uninstalled plugins don't linger
        with self._discovery_lock:
            self.plugin_manifests.clear()
            self.plugin_manifests.update(new_manifests)
            if not hasattr(self, 'plugin_directories'):
                self.plugin_directories = {}
            else:
                self.plugin_directories.clear()
            self.plugin_directories.update(new_directories)

        return plugin_ids
    
    def discover_plugins(self) -> List[str]:
        """
        Discover all plugins in the plugins directory.

        Also checks for potential config key collisions and logs warnings.

        Returns:
            List of plugin IDs
        """
        self.logger.info("Discovering plugins in %s", self.plugins_dir)
        plugin_ids = self._scan_directory_for_plugins(self.plugins_dir)
        self.logger.info("Discovered %d plugin(s)", len(plugin_ids))

        # Check for config key collisions
        collisions = self.schema_manager.detect_config_key_collisions(plugin_ids)
        for collision in collisions:
            self.logger.warning(
                "Config collision detected: %s",
                collision.get('message', str(collision))
            )

        return plugin_ids

    def load_plugin(self, plugin_id: str) -> bool:
        """
        Load a plugin by ID.
        
        This method:
        1. Checks if plugin is already loaded
        2. Validates the manifest exists
        3. Uses PluginLoader to import module and instantiate plugin
        4. Validates the plugin configuration
        5. Stores the plugin instance
        6. Updates plugin state
        
        Args:
            plugin_id: Plugin identifier
            
        Returns:
            True if loaded successfully, False otherwise
        """
        if plugin_id in self.plugins:
            self.logger.warning("Plugin %s already loaded", plugin_id)
            return True
        
        manifest = self.plugin_manifests.get(plugin_id)
        if not manifest:
            self.logger.error("No manifest found for plugin: %s", plugin_id)
            self.state_manager.set_state(plugin_id, PluginState.ERROR)
            return False
        
        try:
            # Update state to LOADED
            self.state_manager.set_state(plugin_id, PluginState.LOADED)
            
            # Find plugin directory using PluginLoader
            plugin_directories = getattr(self, 'plugin_directories', None)
            plugin_dir = self.plugin_loader.find_plugin_directory(
                plugin_id,
                self.plugins_dir,
                plugin_directories
            )
            
            if plugin_dir is None:
                self.logger.error("Plugin directory not found: %s", plugin_id)
                self.logger.error("Searched in: %s", self.plugins_dir)
                self.state_manager.set_state(plugin_id, PluginState.ERROR)
                return False
            
            # Update mapping if found via search
            if plugin_directories is None or plugin_id not in plugin_directories:
                if not hasattr(self, 'plugin_directories'):
                    self.plugin_directories = {}
                self.plugin_directories[plugin_id] = plugin_dir
            
            # Get plugin config
            if self.config_manager:
                full_config = self.config_manager.load_config()
                config = full_config.get(plugin_id, {})
            else:
                config = {}
            
            # Check if plugin has a config schema
            schema_path = self.schema_manager.get_schema_path(plugin_id)
            if schema_path is None:
                # Schema file doesn't exist
                self.logger.warning(
                    f"Plugin '{plugin_id}' has no config_schema.json - configuration will not be validated. "
                    f"Consider adding a schema file for better error detection and user experience."
                )
            else:
                # Schema file exists, try to load it
                schema = self.schema_manager.load_schema(plugin_id)
                if schema is None:
                    # Schema exists but couldn't be loaded (likely invalid JSON or schema)
                    self.logger.warning(
                        f"Plugin '{plugin_id}' has a config_schema.json but it could not be loaded. "
                        f"The schema may be invalid. Please verify the schema file at: {schema_path}"
                    )

            # Merge config with schema defaults to ensure all defaults are applied
            try:
                defaults = self.schema_manager.generate_default_config(plugin_id, use_cache=True)
                config = self.schema_manager.merge_with_defaults(config, defaults)
                self.logger.debug(f"Merged config with schema defaults for {plugin_id}")
            except Exception as e:
                self.logger.warning(f"Could not apply schema defaults for {plugin_id}: {e}")
                # Continue with original config if defaults can't be applied
            
            # Use PluginLoader to load plugin
            plugin_instance, module = self.plugin_loader.load_plugin(
                plugin_id=plugin_id,
                manifest=manifest,
                plugin_dir=plugin_dir,
                config=config,
                display_manager=self.display_manager,
                cache_manager=self.cache_manager,
                plugin_manager=self,
                install_deps=True,
                plugins_dir=self.plugins_dir,
            )
            
            # Store module
            self.plugin_modules[plugin_id] = module

            # Register plugin-shipped fonts with the FontManager (if any).
            # Plugin manifests can declare a "fonts" block that ships custom
            # fonts with the plugin; FontManager.register_plugin_fonts handles
            # the actual loading. Wired here so manifest declarations take
            # effect without requiring plugin code changes.
            font_manifest = manifest.get('fonts')
            if font_manifest and self.font_manager is not None and hasattr(
                self.font_manager, 'register_plugin_fonts'
            ):
                try:
                    self.font_manager.register_plugin_fonts(plugin_id, font_manifest)
                except Exception as e:
                    self.logger.warning(
                        "Failed to register fonts for plugin %s: %s", plugin_id, e
                    )

            # Validate configuration
            if hasattr(plugin_instance, 'validate_config'):
                try:
                    if not plugin_instance.validate_config():
                        self.logger.error("Plugin %s configuration validation failed", plugin_id)
                        self.state_manager.set_state(plugin_id, PluginState.ERROR)
                        return False
                except Exception as e:
                    self.logger.error("Error validating plugin %s config: %s", plugin_id, e, exc_info=True)
                    self.state_manager.set_state(plugin_id, PluginState.ERROR, error=e)
                    return False

            # Schema validation (warn/degrade only — never blocks loading).
            # A config that violates the plugin's JSON schema is surfaced to the
            # user (log warning + degraded flag in the health tracker) but the
            # plugin still loads exactly as it does today. This deliberately does
            # NOT change load_plugin()'s pass/fail behaviour for any plugin that
            # loads under the current code.
            self._validate_config_schema_soft(plugin_id, config)

            # Store plugin instance
            self.plugins[plugin_id] = plugin_instance
            with self._plugin_last_update_lock:
                self.plugin_last_update[plugin_id] = 0.0
            # Invalidate cached interval so next tick re-derives it for this plugin
            self._update_interval_cache.pop(plugin_id, None)
            
            # Update state based on enabled status
            if config.get('enabled', True):
                self.state_manager.set_state(plugin_id, PluginState.ENABLED)
                # Call on_enable if plugin is enabled
                if hasattr(plugin_instance, 'on_enable'):
                    plugin_instance.on_enable()
            else:
                self.state_manager.set_state(plugin_id, PluginState.DISABLED)
            
            self.logger.info("Loaded plugin: %s", plugin_id)
            
            return True
            
        except PluginError as e:
            self.logger.error("Plugin error loading %s: %s", plugin_id, e, exc_info=True)
            self.state_manager.set_state(plugin_id, PluginState.ERROR, error=e)
            return False
        except Exception as e:
            self.logger.error("Unexpected error loading plugin %s: %s", plugin_id, e, exc_info=True)
            self.state_manager.set_state(plugin_id, PluginState.ERROR, error=e)
            return False
    
    #: Config keys the **core** reads out of a plugin's own config block. The
    #: plugin never declares them, so a schema with
    #: ``"additionalProperties": false`` — 37 of the 42 published ones — reports
    #: them as violations and the plugin gets flagged degraded in the web UI for
    #: using a documented core feature.
    #:
    #: Listed explicitly rather than matched on a ``vegas_`` prefix, because
    #: ``vegas_mode`` is the opposite case: plugins *do* declare that one, and a
    #: prefix rule would silently stop validating it.
    #:
    #: Read by: ``vegas_mode/plugin_adapter.py`` (``vegas_width_pct``,
    #: ``vegas_overflow``) and ``base_plugin.py`` (``vegas_max_width_screens``).
    CORE_OWNED_CONFIG_KEYS = frozenset({
        'vegas_width_pct',
        'vegas_overflow',
        'vegas_max_width_screens',
    })

    def _strip_core_owned_keys(self, config: Dict[str, Any]) -> Dict[str, Any]:
        """A shallow copy of ``config`` without the core's own tuning keys.

        Only the top level is touched, and only when such a key is present, so
        the common case allocates nothing extra.
        """
        if not isinstance(config, dict):
            return config
        if not self.CORE_OWNED_CONFIG_KEYS.intersection(config):
            return config
        return {k: v for k, v in config.items()
                if k not in self.CORE_OWNED_CONFIG_KEYS}

    def _validate_config_schema_soft(self, plugin_id: str, config: Dict[str, Any]) -> None:
        """Validate a plugin's config against its JSON schema — warn/degrade only.

        On a schema violation this logs a warning and marks the plugin degraded
        in the health tracker (when one is wired), so the problem is visible in
        the web UI. It never raises, never changes plugin state, and never
        affects whether the plugin loads. ``config`` here has already been
        merged with schema defaults by the caller, so fields that ship a default
        never appear "missing" — only genuinely user-supplied required fields
        (e.g. an API key) can trip the required-field check.
        """
        try:
            schema = self.schema_manager.load_schema(plugin_id)
        except Exception as e:  # pragma: no cover - defensive
            self.logger.debug("Could not load schema for %s: %s", plugin_id, e)
            return

        if not schema:
            # No schema shipped — nothing to validate. Clear any stale flag.
            self._set_degraded_safe(plugin_id, None)
            return

        try:
            is_valid, errors = self.schema_manager.validate_config_against_schema(
                self._strip_core_owned_keys(config), schema, plugin_id
            )
        except Exception as e:  # pragma: no cover - defensive
            # Validation machinery itself failed — do not penalise the plugin.
            self.logger.debug("Schema validation raised for %s: %s", plugin_id, e)
            return

        if is_valid or not errors:
            self._set_degraded_safe(plugin_id, None)
            return

        summary = "; ".join(errors[:5])
        if len(errors) > 5:
            summary += f" (+{len(errors) - 5} more)"
        self.logger.warning(
            "Plugin %s config does not match its schema (loading anyway): %s",
            plugin_id, summary,
        )
        self._set_degraded_safe(plugin_id, f"Config schema: {summary}")

    def _set_degraded_safe(self, plugin_id: str, reason: Optional[str]) -> None:
        """Best-effort ``health_tracker.set_degraded`` that never raises."""
        if not self.health_tracker:
            return
        try:
            self.health_tracker.set_degraded(plugin_id, reason)
        except Exception as e:  # pragma: no cover - defensive
            self.logger.debug("Could not set degraded flag for %s: %s", plugin_id, e)

    def unload_plugin(self, plugin_id: str) -> bool:
        """
        Unload a plugin by ID.
        
        Args:
            plugin_id: Plugin identifier
            
        Returns:
            True if unloaded successfully, False otherwise
        """
        if plugin_id not in self.plugins:
            self.logger.warning("Plugin %s not loaded", plugin_id)
            return False
        
        try:
            plugin = self.plugins[plugin_id]
            
            # Call cleanup if available
            if hasattr(plugin, 'cleanup'):
                try:
                    plugin.cleanup()
                except Exception as e:
                    self.logger.warning("Error during plugin cleanup: %s", e)
            
            # Call on_disable if available
            if hasattr(plugin, 'on_disable'):
                try:
                    plugin.on_disable()
                except Exception as e:
                    self.logger.warning("Error during plugin on_disable: %s", e)
            
            # Remove from active plugins
            del self.plugins[plugin_id]
            with self._plugin_last_update_lock:
                self.plugin_last_update.pop(plugin_id, None)
            self._update_interval_cache.pop(plugin_id, None)
            
            # Remove main module from sys.modules if present
            module_name = f"plugin_{plugin_id.replace('-', '_')}"
            sys.modules.pop(module_name, None)

            # Delegate sub-module and cached-module cleanup to the loader
            self.plugin_loader.unregister_plugin_modules(plugin_id)

            # Remove from plugin_modules
            self.plugin_modules.pop(plugin_id, None)
            
            # Update state
            self.state_manager.set_state(plugin_id, PluginState.UNLOADED)
            self.state_manager.clear_state(plugin_id)
            
            self.logger.info("Unloaded plugin: %s", plugin_id)
            return True
            
        except Exception as e:
            self.logger.error("Error unloading plugin %s: %s", plugin_id, e, exc_info=True)
            self.state_manager.set_state(plugin_id, PluginState.ERROR, error=e)
            return False
    
    def reload_plugin(self, plugin_id: str) -> bool:
        """
        Reload a plugin (unload and load).
        
        Args:
            plugin_id: Plugin identifier
            
        Returns:
            True if reloaded successfully, False otherwise
        """
        self.logger.info("Reloading plugin: %s", plugin_id)
        
        # Unload first
        if plugin_id in self.plugins:
            if not self.unload_plugin(plugin_id):
                return False
        
        # Re-discover to get updated manifest
        manifest_path = self.plugins_dir / plugin_id / "manifest.json"
        if manifest_path.exists():
            try:
                with open(manifest_path, 'r', encoding='utf-8') as f:
                    manifest = json.load(f)
                with self._discovery_lock:
                    self.plugin_manifests[plugin_id] = manifest
            except Exception as e:
                self.logger.error("Error reading manifest: %s", e, exc_info=True)
                return False
        
        return self.load_plugin(plugin_id)
    
    def get_plugin(self, plugin_id: str) -> Optional[Any]:
        """
        Get a loaded plugin instance by ID.
        
        Args:
            plugin_id: Plugin identifier
            
        Returns:
            Plugin instance or None if not loaded
        """
        return self.plugins.get(plugin_id)
    
    def get_all_plugins(self) -> Dict[str, Any]:
        """
        Get all loaded plugins.
        
        Returns:
            Dict of plugin_id: plugin_instance
        """
        return self.plugins.copy()
    
    def get_enabled_plugins(self) -> List[str]:
        """
        Get list of enabled plugin IDs.
        
        Returns:
            List of plugin IDs that are currently enabled
        """
        return [pid for pid, plugin in self.plugins.items() if plugin.enabled]
    
    def get_plugin_info(self, plugin_id: str) -> Optional[Dict[str, Any]]:
        """
        Get information about a plugin (manifest + runtime info).
        
        Args:
            plugin_id: Plugin identifier
            
        Returns:
            Dict with plugin information or None if not found
        """
        with self._discovery_lock:
            manifest = self.plugin_manifests.get(plugin_id)
        if not manifest:
            return None

        info = manifest.copy()
        
        # Add runtime information if plugin is loaded
        plugin = self.plugins.get(plugin_id)
        if plugin:
            info['loaded'] = True
            if hasattr(plugin, 'get_info'):
                info['runtime_info'] = plugin.get_info()
        else:
            info['loaded'] = False
        
        # Add state information
        info['state'] = self.state_manager.get_state_info(plugin_id)
        
        return info
    
    def get_all_plugin_info(self) -> List[Dict[str, Any]]:
        """
        Get information about all plugins.
        
        Returns:
            List of plugin info dictionaries
        """
        with self._discovery_lock:
            pids = list(self.plugin_manifests.keys())
        return [info for info in [self.get_plugin_info(pid) for pid in pids] if info]
    
    def get_plugin_directory(self, plugin_id: str) -> Optional[str]:
        """
        Get the directory path for a plugin.
        
        Args:
            plugin_id: Plugin identifier
            
        Returns:
            Directory path as string or None if not found
        """
        with self._discovery_lock:
            if hasattr(self, 'plugin_directories') and plugin_id in self.plugin_directories:
                return str(self.plugin_directories[plugin_id])
        
        plugin_dir = self.plugins_dir / plugin_id
        if plugin_dir.exists():
            return str(plugin_dir)
        
        plugin_dir = self.plugins_dir / f"ledmatrix-{plugin_id}"
        if plugin_dir.exists():
            return str(plugin_dir)
        
        return None
    
    def get_plugin_display_modes(self, plugin_id: str) -> List[str]:
        """
        Get display modes provided by a plugin.
        
        Args:
            plugin_id: Plugin identifier
            
        Returns:
            List of display mode names
        """
        with self._discovery_lock:
            manifest = self.plugin_manifests.get(plugin_id)
        if not manifest:
            return []

        display_modes = manifest.get('display_modes', [])
        if isinstance(display_modes, list):
            return display_modes
        return []
    
    def find_plugin_for_mode(self, mode: str) -> Optional[str]:
        """
        Find which plugin provides a given display mode.
        
        Args:
            mode: Display mode identifier
            
        Returns:
            Plugin identifier or None if not found.
        """
        normalized_mode = mode.strip().lower()
        with self._discovery_lock:
            manifests_snapshot = dict(self.plugin_manifests)
        for plugin_id, manifest in manifests_snapshot.items():
            display_modes = manifest.get('display_modes')
            if isinstance(display_modes, list) and display_modes:
                if any(m.lower() == normalized_mode for m in display_modes):
                    return plugin_id

        return None

    def _get_plugin_update_interval(self, plugin_id: str, plugin_instance: Any) -> Optional[float]:
        """
        Get the data-fetch interval for a plugin (seconds between update() calls).

        Result is cached per plugin_id after the first lookup to avoid calling
        config_manager.get_config() — which returns a full dict copy — on every
        tick of the 30-fps display loop.  The cache is invalidated when a plugin
        is loaded or unloaded.
        """
        if plugin_id in self._update_interval_cache:
            return self._update_interval_cache[plugin_id]

        interval: Optional[float] = None

        # 1. Manifest (immutable after load — preferred source)
        manifest = self.plugin_manifests.get(plugin_id, {})
        raw = manifest.get('update_interval')
        if raw is not None:
            try:
                interval = float(raw)
            except (ValueError, TypeError):
                pass

        # 2. Plugin config (mutable; only read once and then cached)
        if interval is None and self.config_manager:
            try:
                config = self.config_manager.get_config()
                raw = config.get(plugin_id, {}).get('update_interval')
                if raw is not None:
                    try:
                        interval = float(raw)
                    except (ValueError, TypeError):
                        pass
            except (ConfigError, OSError, ValueError, TypeError) as e:
                self.logger.debug("Could not get update interval from config: %s", e)

        # 3. Default
        if interval is None:
            interval = 60.0

        self._update_interval_cache[plugin_id] = interval
        return interval

    def _record_update_failure(
        self,
        plugin_id: str,
        exc: Optional[Exception] = None,
    ) -> None:
        """Apply the standard failure-recovery path for a plugin update.

        Stamps plugin_last_update with the actual failure time so the full
        configured interval elapses before the next retry, then transitions
        the plugin back to ENABLED (not ERROR) with structured error context
        so automatic recovery happens on the next scheduled cycle.

        Args:
            plugin_id: Plugin identifier
            exc: The exception that caused the failure, if any.  When None a
                 synthetic ExecutionFailure exception is constructed from the
                 timeout/executor-error path.
        """
        failure_time = time.time()
        if exc is not None:
            err: Exception = exc
            error_type = type(exc).__name__
        else:
            err = Exception(f"Plugin {plugin_id} execution failed (timeout or executor error)")
            error_type = 'ExecutionFailure'

        error_info = {
            'error': str(err),
            'error_type': error_type,
            'timestamp': failure_time,
            'recoverable': True,
        }
        self.logger.warning("Plugin %s update() failed; will retry after interval", plugin_id)
        with self._plugin_last_update_lock:
            self.plugin_last_update[plugin_id] = failure_time
        self.state_manager.set_state_with_error(plugin_id, PluginState.ENABLED, error_info, error=err)
        if self.health_tracker:
            self.health_tracker.record_failure(plugin_id, err)

    def run_scheduled_updates(self, current_time: Optional[float] = None) -> None:
        """
        Trigger plugin updates based on their defined update intervals.
        Includes health tracking and circuit breaker logic.
        Uses PluginExecutor for safe execution with timeout.
        """
        if current_time is None:
            current_time = time.time()

        for plugin_id, plugin_instance in list(self.plugins.items()):
            if not getattr(plugin_instance, "enabled", True):
                continue

            if not hasattr(plugin_instance, "update"):
                continue

            # Check circuit breaker before attempting update
            if self.health_tracker and self.health_tracker.should_skip_plugin(plugin_id):
                continue

            # Check if plugin can execute
            if not self.state_manager.can_execute(plugin_id):
                continue

            interval = self._get_plugin_update_interval(plugin_id, plugin_instance)
            if interval is None:
                continue

            with self._plugin_last_update_lock:
                last_update = self.plugin_last_update.get(plugin_id, 0.0)

            if last_update == 0.0 or (current_time - last_update) >= interval:
                if self._synchronous_updates:
                    # Kill-switch path: the original inline execution
                    # (blocks the caller until update() completes/times out)
                    self.state_manager.set_state(plugin_id, PluginState.RUNNING)
                    self._execute_update_now(plugin_id, plugin_instance, current_time)
                else:
                    self._enqueue_update(plugin_id, current_time)

    def get_plugin_lock(self, plugin_id: str) -> threading.Lock:
        """Per-plugin lock keeping update() and display() mutually exclusive.

        The update worker holds it for the duration of a plugin's update();
        the display side acquires it non-blocking and skips that frame's
        display() call when the plugin is mid-update.
        """
        with self._plugin_locks_guard:
            lock = self._plugin_locks.get(plugin_id)
            if lock is None:
                lock = threading.Lock()
                self._plugin_locks[plugin_id] = lock
            return lock

    def _enqueue_update(self, plugin_id: str, scheduled_time: float) -> None:
        """Queue a due update for the background worker (dedup while pending)."""
        with self._pending_lock:
            if plugin_id in self._pending_updates:
                return
            self._pending_updates.add(plugin_id)
        # RUNNING is set at enqueue time so can_execute() blocks re-entry and
        # the web UI shows the truthful state while the item waits its turn.
        self.state_manager.set_state(plugin_id, PluginState.RUNNING)
        self._ensure_update_worker()
        self._update_queue.put((plugin_id, scheduled_time))

    def _ensure_update_worker(self) -> None:
        if self._update_worker is not None and self._update_worker.is_alive():
            return
        self._update_worker = threading.Thread(
            target=self._update_worker_loop, name='plugin-update-worker',
            daemon=True)
        self._update_worker.start()

    def _update_worker_loop(self) -> None:
        """Single worker: dispatches queued updates off the render thread
        (matching the old inline behavior — no thundering herd of
        concurrent fetches).

        The plugin's lock is acquired here, before its instance is looked
        up, and the instance is re-fetched under the lock — a concurrent
        unload_plugin() can't leave this loop about to run update() on an
        instance that's already been torn down. The lock — and RUNNING/
        pending lifecycle state — is released by the update itself once the
        real update() call genuinely finishes (see _execute_update_now),
        which can be after this dispatch returns if PluginExecutor's own
        timeout elapses first.
        """
        while True:
            item = self._update_queue.get()
            if item is None:  # shutdown sentinel
                return
            plugin_id, scheduled_time = item
            lock = self.get_plugin_lock(plugin_id)
            lock.acquire()
            plugin_instance = self.plugins.get(plugin_id)
            if plugin_instance is None:  # unloaded while queued; its
                # lifecycle state was already cleared by unload_plugin —
                # leave it alone rather than resurrecting it to ENABLED
                lock.release()
                with self._pending_lock:
                    self._pending_updates.discard(plugin_id)
                continue
            try:
                self._execute_update_now(plugin_id, plugin_instance,
                                         scheduled_time, lock=lock)
            except Exception:  # pylint: disable=broad-except
                # _execute_update_now guarantees the lock/pending bookkeeping
                # is released via its own _finish() before returning or
                # raising; this is a last-resort log only.
                self.logger.exception("update worker: unexpected error for %s",
                                      plugin_id)

    def stop_update_worker(self, timeout: float = 5.0) -> None:
        """Signal the worker to exit (used by cleanup; thread is a daemon)."""
        if self._update_worker is not None and self._update_worker.is_alive():
            self._update_queue.put(None)
            self._update_worker.join(timeout=timeout)
            if self._update_worker.is_alive():
                self.logger.warning(
                    "Update worker did not stop within %.1fs; it is a daemon "
                    "thread and will be abandoned on shutdown", timeout)

    def _execute_update_now(self, plugin_id: str, plugin_instance: Any,
                            scheduled_time: float,
                            lock: Optional[threading.Lock] = None) -> None:
        """Execute a plugin's update() via PluginExecutor, then bookkeep.

        Caller is responsible for having set RUNNING state.

        On the synchronous path (``lock=None``) this is the original,
        unchanged inline behavior. On the async worker path, PluginExecutor's
        internal thread.join(timeout) blocks only the calling thread -- on
        timeout the lingering daemon update-thread keeps running the real
        plugin.update() call unkillable in the background. So that the
        plugin's lock (and its RUNNING/pending lifecycle state) stays held
        for that real duration rather than just this bounded wait, ownership
        of both is carried by the wrapped update callable itself, released
        from whichever thread actually finishes it -- see _finish() below.
        """
        finish_guard = threading.Lock()
        finished = {'done': False}

        def _finish(success: bool, exc: Optional[Exception] = None) -> None:
            with finish_guard:
                if finished['done']:
                    return
                finished['done'] = True
            try:
                if success:
                    with self._plugin_last_update_lock:
                        self.plugin_last_update[plugin_id] = scheduled_time
                    self._note_update_completed(plugin_id)
                    self.state_manager.record_update(plugin_id)
                    self.state_manager.set_state(plugin_id, PluginState.ENABLED)
                    if self.health_tracker:
                        self.health_tracker.record_success(plugin_id)
                else:
                    self._record_update_failure(plugin_id, exc=exc)
            finally:
                if lock is not None:
                    lock.release()
                    with self._pending_lock:
                        self._pending_updates.discard(plugin_id)

        if lock is None:
            # Synchronous / no-lock path: unchanged behavior.
            try:
                if self.resource_monitor:
                    def monitored_update():
                        self.resource_monitor.monitor_call(plugin_id, plugin_instance.update)
                    # SimpleNamespace stores `update` as an *instance*
                    # attribute, so attribute lookup returns the plain
                    # function object as-is. A dynamically-built class
                    # (`type(..., {'update': monitored_update})`) instead
                    # stores it as a *class* attribute, which the
                    # descriptor protocol turns into a bound method on
                    # access -- silently prepending the instance as an
                    # implicit first argument to a function that takes
                    # none, raising "monitored_update() takes 0
                    # positional arguments but 1 was given" on every call.
                    success = self.plugin_executor.execute_update(
                        types.SimpleNamespace(update=monitored_update),
                        plugin_id
                    )
                else:
                    success = self.plugin_executor.execute_update(plugin_instance, plugin_id)
                _finish(success)
            except Exception as exc:  # pylint: disable=broad-except
                self.logger.exception("Error updating plugin %s: %s", plugin_id, exc)
                _finish(False, exc=exc)
            return

        # Async worker path: the real update() call -- through the resource
        # monitor, if configured -- owns finishing the lock/lifecycle
        # bookkeeping, from whichever thread actually runs it to completion.
        def _target_update() -> None:
            try:
                if self.resource_monitor:
                    self.resource_monitor.monitor_call(plugin_id, plugin_instance.update)
                else:
                    plugin_instance.update()
            except Exception as exc:
                _finish(False, exc=exc)
                raise
            else:
                _finish(True)

        try:
            self.plugin_executor.execute_update(
                types.SimpleNamespace(update=_target_update), plugin_id)
        except Exception as exc:  # pragma: no cover - defensive; execute_update
            # catches everything internally, but guarantee _finish still
            # runs (releasing the lock) if something unexpected slips through.
            self.logger.exception("Unexpected error dispatching update for %s: %s", plugin_id, exc)
            _finish(False, exc=exc)

    def run_scheduled_updates_with_changes(self, current_time: Optional[float] = None) -> List[str]:
        """
        Like run_scheduled_updates(), but also reports which plugins have
        fresh data -- the ids whose update() has finished since the last
        call, not necessarily the ones enqueued by this one.

        That distinction is the whole point. This used to snapshot
        plugin_last_update, call run_scheduled_updates(), and diff. But
        run_scheduled_updates() only *enqueues*: the work runs on the
        update worker and the timestamp is stamped there, after this method
        has already returned. The two snapshots were therefore always
        identical and the result was always empty, so Vegas never learned
        that any plugin's data had changed and kept scrolling whatever a
        segment was first built from -- last night's live game still drawn
        as live the next morning. The only path that ever worked was the
        synchronous kill-switch, where update() runs inline.

        Reporting completions instead of enqueues costs a poll's worth of
        latency (the Vegas tick runs every ~4s) and is correct regardless of
        which side of the queue the work lands on.
        """
        self.run_scheduled_updates(current_time)
        return self.drain_completed_updates()

    def _note_update_completed(self, plugin_id: str) -> None:
        """Record that a plugin's update() finished, for the next poll."""
        with self._completed_updates_lock:
            self._completed_updates.add(plugin_id)

    def drain_completed_updates(self) -> List[str]:
        """Return and clear the plugin ids whose update() has since finished."""
        with self._completed_updates_lock:
            if not self._completed_updates:
                return []
            done = sorted(self._completed_updates)
            self._completed_updates.clear()
            return done

    def update_all_plugins(self) -> None:
        """
        Update all enabled plugins.
        Calls update() on each enabled plugin using PluginExecutor.
        """
        for plugin_id, plugin_instance in list(self.plugins.items()):
            if not getattr(plugin_instance, "enabled", True):
                continue
            
            if not hasattr(plugin_instance, "update"):
                continue
            
            # Check if plugin can execute
            if not self.state_manager.can_execute(plugin_id):
                continue
            
            # Update state to RUNNING
            self.state_manager.set_state(plugin_id, PluginState.RUNNING)
            
            try:
                success = self.plugin_executor.execute_update(plugin_instance, plugin_id)
                if success:
                    with self._plugin_last_update_lock:
                        self.plugin_last_update[plugin_id] = time.time()
                    self._note_update_completed(plugin_id)
                    self.state_manager.record_update(plugin_id)
                    self.state_manager.set_state(plugin_id, PluginState.ENABLED)
                else:
                    self._record_update_failure(plugin_id)
            except Exception as exc:  # pylint: disable=broad-except
                self.logger.exception("Error updating plugin %s: %s", plugin_id, exc)
                self._record_update_failure(plugin_id, exc=exc)
    
    def get_plugin_health_metrics(self) -> Dict[str, Any]:
        """
        Get health metrics for all plugins.
        
        Returns:
            Dictionary mapping plugin_id to health metrics
        """
        metrics = {}
        for plugin_id in self.plugins.keys():
            plugin_metrics = {}
            
            # Get state information
            state_info = self.state_manager.get_state_info(plugin_id)
            plugin_metrics.update(state_info)
            
            # Get health tracker metrics if available
            if self.health_tracker:
                health_info = self.health_tracker.get_health_summary(plugin_id)
                plugin_metrics['health'] = health_info
            else:
                plugin_metrics['health'] = {'status': 'unknown'}
            
            metrics[plugin_id] = plugin_metrics
        return metrics
    
    def get_plugin_resource_metrics(self) -> Dict[str, Any]:
        """
        Get resource usage metrics for all plugins.
        
        Returns:
            Dictionary mapping plugin_id to resource metrics
        """
        metrics = {}
        for plugin_id in self.plugins.keys():
            plugin_metrics = {}
            
            # Get state information
            state_info = self.state_manager.get_state_info(plugin_id)
            plugin_metrics.update(state_info)
            
            # Get resource monitor metrics if available
            if self.resource_monitor:
                resource_info = self.resource_monitor.get_metrics_summary(plugin_id)
                plugin_metrics['resources'] = resource_info
            else:
                plugin_metrics['resources'] = {'status': 'unknown'}
            
            metrics[plugin_id] = plugin_metrics
        return metrics
    
    def get_plugin_state(self, plugin_id: str) -> Dict[str, Any]:
        """
        Get comprehensive state information for a plugin.
        
        Args:
            plugin_id: Plugin identifier
            
        Returns:
            Dictionary with state information
        """
        return self.state_manager.get_state_info(plugin_id)