Add laborious

laborious/utils/repository/minio_manager.py

@@ -0,0 +1,32 @@
+from sientia_do.notifications.handlers import NotificationHandler
+from sientia_do.observability.logger import Logger
+from sientia_do.observability.metrics_controller import MetricsController
+from sientia_do.observability.sientia_monitoring import SientiaMonitoring
+from sientia_do.repository.minio_repository import MinioRepository
+
+
+class MinioManager(SientiaMonitoring):
+    minio_repository: MinioRepository | None = None
+
+    def __init__(
+        self,
+        minio_repository: MinioRepository | None = None,
+        logger: Logger | None = None,
+        notification_handler: NotificationHandler | None = None,
+        metrics_controller: MetricsController | None = None,
+    ):
+        if self.minio_repository is None:
+            self.minio_repository = minio_repository
+        SientiaMonitoring.__init__(self, logger, notification_handler, metrics_controller)
+
+    def close(self) -> None:
+        """
+        Close the MinioManager and clean up resources.
+        """
+        if self.minio_repository is not None:
+            try:
+                self.minio_repository.close()
+            finally:
+                self.minio_repository = None
+
+        SientiaMonitoring.shutdown(self)

laborious/utils/repository/opc_repository.py

@@ -0,0 +1,866 @@
+import asyncio
+import json
+import time
+import traceback
+from datetime import datetime
+from pathlib import Path
+from typing import Any
+
+from asyncua import Client
+from asyncua.crypto.security_policies import SecurityPolicyBasic256
+from asyncua.ua import DataValue, Variant, VariantType
+from asyncua.ua.uaerrors import UaStatusCodeError
+from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
+from sientia_do.notifications.models import NotificationLevel
+from sientia_do.observability.logger import Logger
+from sientia_do.observability.metrics_controller import MetricsController
+from sientia_do.observability.sientia_monitoring import SientiaMonitoring
+
+from laborious import metrics
+
+# Requested session and secure channel lifetime (ms) before server revision; 10 minutes.
+OPC_UA_SESSION_AND_CHANNEL_TIMEOUT_MS = 10 * 60 * 1000
+
+
+class OpcClientAlreadyExistsError(RuntimeError):
+    """Raised when _create_client is called while self.client is already set."""
+
+
+class OpcSessionAlreadyConnectedError(RuntimeError):
+    """Raised when _open_session is called while a UA session is already open."""
+
+
+class OpcClientNotInitializedError(RuntimeError):
+    """Raised when _open_session is called before _create_client."""
+
+
+RECONNECTABLE_OPC_BAD_NAMES: frozenset[str] = frozenset(
+    {
+        'BadSessionIdInvalid',
+        'BadSessionClosed',
+        'BadSessionNotActivated',
+        'BadSecureChannelIdInvalid',
+        'BadSecureChannelClosed',
+        'BadSecureChannelTokenUnknown',
+        'BadTcpSecureChannelUnknown',
+        'BadServerNotConnected',
+        'BadConnectionClosed',
+        'BadDisconnect',
+        'BadConnectionRejected',
+        'BadCommunicationError',
+        'BadRequestInterrupted',
+        'BadUnknownResponse',
+        'BadTimeout',
+        'BadRequestTimeout',
+        'BadSequenceNumberInvalid',
+        'BadSequenceNumberUnknown',
+        'BadSecurityModeInsufficient',
+        'BadRequestHeaderInvalid',
+        'BadInvalidState',
+    }
+)
+
+
+def _opc_authentication_token_str(client: Client | None) -> str:
+    """
+    Serialize the current OPC UA authentication token (session handle) for logging and metrics.
+
+    Return:
+        str: Token string, or "unknown" if unavailable.
+    """
+    if client is None:
+        return 'unknown'
+    try:
+        proto = client.uaclient.protocol
+        if proto is None:
+            return 'unknown'
+        tok = getattr(proto, 'authentication_token', None)
+        if tok is None:
+            return 'unknown'
+        return str(tok)
+    except Exception:
+        return 'unknown'
+
+
+def _opc_status_from_exception(exc: BaseException) -> str:
+    """
+    Resolve OPC UA status name from an exception, including chained UaStatusCodeError causes.
+
+    Args:
+        exc (BaseException): Raised error from asyncua.
+
+    Return:
+        str: Status class name or generic Python exception name.
+    """
+    current: BaseException | None = exc
+    while current is not None:
+        if isinstance(current, UaStatusCodeError):
+            return type(current).__name__
+        current = current.__cause__
+    return type(exc).__name__
+
+
+def is_reconnectable_opcua_bad(exc: BaseException) -> bool:
+    """
+    Return whether the exception is a Tier-1 OPC UA Bad* that should trigger reconnect.
+
+    Args:
+        exc (BaseException): Raised error from get_node or write_value.
+
+    Return:
+        bool: True if reconnect should be scheduled.
+    """
+    return _opc_status_from_exception(exc) in RECONNECTABLE_OPC_BAD_NAMES
+
+
+def _model_labels_from_write_metadata(metadata: dict[str, Any] | None) -> dict[str, str]:
+    """
+    Extract model_id and model_name from write metadata for Prometheus labels.
+
+    Args:
+        metadata (dict[str, Any] | None): Context passed into write_data; may omit keys.
+
+    Return:
+        dict[str, str]: Labels model_id and model_name, defaulting to "unknown".
+    """
+    if not metadata:
+        return {'model_id': 'unknown', 'model_name': 'unknown'}
+    return {
+        'model_id': str(metadata.get('model_id', 'unknown')),
+        'model_name': str(metadata.get('model_name', 'unknown')),
+    }
+
+
+data_type_map = {
+    'float': {
+        'converter': float,
+        'opc_type': VariantType.Float,
+    },
+    'double': {
+        'converter': float,
+        'opc_type': VariantType.Double,
+    },
+    'int': {
+        'converter': int,
+        'opc_type': VariantType.Int32,
+    },
+    'bool': {
+        'converter': bool,
+        'opc_type': VariantType.Boolean,
+    },
+    'str': {
+        'converter': str,
+        'opc_type': VariantType.String,
+    },
+}
+
+
+class OpcRepository(SientiaMonitoring):
+    def __init__(
+        self,
+        opc_id: str,
+        url: str,
+        server_name: str,
+        logger: Logger,
+        notification_handler: NotificationHandler,
+        metrics_controller: MetricsController,
+        reconnection_interval: int = 60,
+        server_uri: str | None = None,
+        cert_path: str | None = None,
+        private_key_path: str | None = None,
+        server_cert_path: str | None = None,
+    ):
+        self.url = url
+        self.id = opc_id
+        self.server_name = server_name
+        self.server_uri = server_uri
+        self.cert_path = cert_path
+        self.private_key_path = private_key_path
+        self.server_cert_path = server_cert_path
+        self.reconnection_interval = reconnection_interval
+        self.last_reconnection_time: None | datetime = None
+        self.disconnection_interval = 10.0
+        self.notification_handler = notification_handler
+        self.client: None | Client = None
+
+        SientiaMonitoring.__init__(self, logger, notification_handler, metrics_controller)
+
+        self.metadata = {
+            'model_name': '-',
+            'model_id': '-',
+            'workflow_name': 'opc_repository',
+            'schedule_name': '-',
+        }
+        self._last_write_mono: float | None = None
+        self._connection_lock = asyncio.Lock()
+        self._session_ready = asyncio.Event()
+        self._reconnect_task: asyncio.Task[None] | None = None
+        self._allow_reconnect = True
+
+    def _opc_debug_tags(self, session_id: str) -> dict[str, str]:
+        """
+        Build Prometheus/log label tags for OPC session-scoped metrics.
+
+        Args:
+            session_id (str): OPC UA session token string.
+
+        Return:
+            dict[str, str]: Labels pod_id, server_name, runtime, opc_server_id, session_id.
+        """
+        return {
+            'pod_id': str(getattr(self, 'pod_id', 'unknown')),
+            'server_name': self.server_name,
+            'runtime': str(getattr(self, 'runtime', 'unknown')),
+            'opc_server_id': self.id,
+            'session_id': session_id,
+        }
+
+    def _is_session_open(self) -> bool:
+        """
+        Return whether the asyncua client has an open transport session.
+
+        Return:
+            bool: True when protocol exists and is not closed.
+        """
+        if self.client is None:
+            return False
+        try:
+            proto = self.client.uaclient.protocol
+            return proto is not None and proto.state != 'closed'
+        except Exception:
+            return False
+
+    def _reconnection_window_elapsed(self) -> bool:
+        """
+        Return whether enough time has passed since the last reconnect attempt.
+
+        Return:
+            bool: True if a new reconnect is allowed.
+        """
+        if self.last_reconnection_time is None:
+            return True
+        return (
+            datetime.now() - self.last_reconnection_time
+        ).total_seconds() > self.reconnection_interval
+
+    def _not_connected_error(self) -> dict[str, Any]:
+        """
+        Build the standard error payload when validate_connection finds no open protocol.
+
+        Return:
+            dict[str, Any]: Notification fields for OPC_CONNECTION_NOT_READY.
+        """
+        return {
+            'notification_id': f'OPC_CONNECTION_NOT_READY_{self.id}',
+            'message': f'OPC server {self.id} is not connected',
+            'block': 'opc_repository',
+            'level': NotificationLevel.WARNING,
+        }
+
+    async def set_security(self) -> None:
+        """
+        Configure certificates and timeouts on the asyncua client.
+
+        Raises:
+            ValueError: If cert paths or client are missing.
+        """
+        if self.cert_path is None or self.private_key_path is None:
+            raise ValueError(
+                'Certificate and private key paths must be provided for secure connection.'
+            )
+
+        cert = Path(self.cert_path)
+        private_key = Path(self.private_key_path)
+        server_cert = Path(self.server_cert_path) if self.server_cert_path else None
+
+        if self.client is None:
+            raise ValueError('Client must be initialized before setting security')
+
+        self.client.application_uri = self.server_uri
+        self.info('Setting security...', self.metadata)
+        await self.client.set_security(
+            SecurityPolicyBasic256,
+            certificate=str(cert),
+            private_key=str(private_key),
+            server_certificate=str(server_cert) if server_cert else None,
+        )
+        self.client.secure_channel_timeout = OPC_UA_SESSION_AND_CHANNEL_TIMEOUT_MS
+        self.client.session_timeout = OPC_UA_SESSION_AND_CHANNEL_TIMEOUT_MS
+
+    async def _create_client(self) -> None:
+        """
+        Instantiate the asyncua Client and apply security when configured.
+
+        Caller must hold _connection_lock. Does not open a UA session.
+
+        Raises:
+            OpcClientAlreadyExistsError: If self.client is already set.
+        """
+        if self.client is not None:
+            raise OpcClientAlreadyExistsError(
+                f'OPC client already exists for server {self.id}; '
+                'call disconnect() before creating a new client'
+            )
+
+        self.client = Client(self.url, timeout=10, watchdog_intervall=50)  # type: ignore[attr-defined]
+        self.client.name = self.pod_id
+        self.client.application_name = self.pod_id
+        pod_uri = self.pod_id.replace('-', ':')
+        self.client.application_uri = pod_uri
+        self.client.product_uri = pod_uri
+        if self.cert_path:
+            await self.set_security()
+
+    async def _open_session(self) -> tuple[bool, dict[str, Any]]:
+        """
+        Open the OPC UA session on the existing client.
+
+        Caller must hold _connection_lock.
+
+        Raises:
+            OpcClientNotInitializedError: If self.client is None.
+            OpcSessionAlreadyConnectedError: If a session is already open.
+
+        Return:
+            tuple[bool, dict[str, Any]]: Success flag and error payload on connect failure.
+        """
+        if self.client is None:
+            raise OpcClientNotInitializedError(
+                f'OPC client is not initialized for server {self.id}; '
+                'call _create_client() before opening a session'
+            )
+        if self._is_session_open():
+            raise OpcSessionAlreadyConnectedError(
+                f'OPC session already connected for server {self.id}; '
+                'call disconnect() before connecting again'
+            )
+
+        tags = {
+            'pod_id': self.pod_id,
+            'server_name': self.server_name,
+        }
+        await self.emit_metric(metrics.OPC_CONNECTIONS_TOTAL, tags)
+
+        try:
+            await self.client.connect()
+
+            session_id = _opc_authentication_token_str(self.client)
+            revised_session_timeout_ms = int(self.client.session_timeout)
+            revised_secure_channel_timeout_ms = int(self.client.secure_channel_timeout)
+            self.info(
+                f'OPC new session connected opc_server_id={self.id} session_id={session_id} '
+                f'revised_session_timeout_ms={revised_session_timeout_ms} '
+                f'revised_secure_channel_timeout_ms={revised_secure_channel_timeout_ms}',
+                self.metadata,
+            )
+            await self.emit_metric(
+                metrics.OPC_SESSION_CREATED_TOTAL, self._opc_debug_tags(session_id)
+            )
+            await self.emit_metric(
+                metric_object=metrics.OPC_SESSION_REVISED_TIMEOUT_MS,
+                method='set',
+                tags=self._opc_debug_tags(session_id),
+                value=revised_session_timeout_ms,
+            )
+            await self.emit_metric(
+                metric_object=metrics.OPC_CONNECTION_STATUS,
+                method='set',
+                tags={**tags, 'server_url': self.url},
+                value=1,
+            )
+
+            self._last_write_mono = None
+            self._session_ready.set()
+            return True, {}
+
+        except Exception as e:
+            await self._disconnect_locked()
+            trace = traceback.format_exc()
+            self.error(trace, self.metadata)
+            await self.emit_metric(metrics.OPC_CONNECTIONS_FAILED, tags)
+            return False, {
+                'notification_id': f'OPC_CONNECTION_ERROR_{self.id}',
+                'message': f'Failed to connect to OPC server: {e}',
+                'block': 'opc_repository',
+                'level': NotificationLevel.ERROR,
+                'attachment_content': trace,
+            }
+
+    async def _connect_locked(self) -> tuple[bool, dict[str, Any]]:
+        """
+        Create the client when absent, then open a UA session.
+
+        Caller must hold _connection_lock.
+
+        Raises:
+            OpcSessionAlreadyConnectedError: If a session is already open.
+
+        Return:
+            tuple[bool, dict[str, Any]]: Result from _open_session on connect failure.
+        """
+        if self._is_session_open():
+            raise OpcSessionAlreadyConnectedError(
+                f'OPC session already connected for server {self.id}; '
+                'call disconnect() before connecting again'
+            )
+        if self.client is None:
+            await self._create_client()
+        return await self._open_session()
+
+    async def _disconnection_fallback(self) -> list[dict[str, Any]]:
+        """
+        Try up to five times to disconnect from the OPC UA server.
+        """
+        assert self.client is not None
+        error_stack: list[dict[str, Any]] = []
+        for i in range(5):
+            try:
+                self.info(
+                    f'Disconnecting from OPC UA server, attempt {i + 1} of 5',
+                    self.metadata,
+                )
+                await self.client.disconnect()
+                return []
+            except Exception as e:
+                self.error(
+                    f'Failed to disconnect from OPC UA server in attempt {i + 1} of 5: {e}',
+                    self.metadata,
+                )
+                error_stack.append(
+                    {
+                        'attempt': i + 1,
+                        'error': str(e),
+                        'traceback': traceback.format_exc(),
+                    }
+                )
+                await asyncio.sleep(self.disconnection_interval * i)
+        return error_stack
+
+    async def _disconnect_locked(self) -> None:
+        """
+        Tear down the current session and client.
+
+        Caller must hold _connection_lock.
+        """
+        self._last_write_mono = None
+        self._session_ready.clear()
+
+        if self.client is None:
+            return
+
+        session_id = _opc_authentication_token_str(self.client)
+        self.info(
+            f'OPC disconnecting opc_server_id={self.id} session_id={session_id}',
+            self.metadata,
+        )
+        await self.emit_metric(metrics.OPC_SESSION_CLOSED_TOTAL, self._opc_debug_tags(session_id))
+
+        errors = await self._disconnection_fallback()
+        if errors:
+            await self.send_notification_async(
+                metadata=self.metadata,
+                notification_id=f'OPC_DISCONNECTION_ERROR_{self.id}',
+                message='Failed to disconnect from OPC server in 5 attempts.',
+                block='opc_repository',
+                level=NotificationLevel.ERROR,
+                attachment_content=json.dumps(errors, indent=4),
+            )
+        else:
+            self.warning(f'Disconnected from OPC server {self.id} successfully', self.metadata)
+
+        await self.emit_metric(
+            metric_object=metrics.OPC_CONNECTION_STATUS,
+            method='set',
+            tags={
+                'pod_id': self.pod_id,
+                'server_name': self.server_name,
+                'server_url': self.url,
+            },
+            value=0,
+        )
+        self.client = None
+
+    async def _reconnect_locked(self) -> tuple[bool, dict[str, Any]]:
+        """
+        Close the current session and open a new one.
+
+        Caller must hold _connection_lock. Records last_reconnection_time for interval gating.
+
+        Return:
+            tuple[bool, dict[str, Any]]: Result from _connect_locked after teardown.
+        """
+        self.last_reconnection_time = datetime.now()
+        await self._disconnect_locked()
+        return await self._connect_locked()
+
+    async def connect(self) -> tuple[bool, dict[str, Any]]:
+        """
+        Open an OPC UA session under the connection lock (worker initialization).
+        """
+        async with self._connection_lock:
+            self.info(
+                f'Starting connection to OPC server {self.id}:{self.server_name}...',
+                self.metadata,
+            )
+            return await self._connect_locked()
+
+    async def disconnect(self) -> None:
+        """
+        Gracefully disconnect from the OPC server under the connection lock.
+
+        Disables background reconnect so late writes during worker shutdown do not
+        respawn sessions.
+        """
+        async with self._connection_lock:
+            self._allow_reconnect = False
+            await self._disconnect_locked()
+
+    async def validate_connection(self) -> tuple[bool, dict[str, Any]]:
+        """
+        Read-only check that the asyncua protocol is open.
+
+        Caller must ensure _session_ready before writing. Does not connect or reconnect.
+
+        Return:
+            tuple[bool, dict[str, Any]]: (True, {}) when open, otherwise (False, error).
+        """
+        if self._is_session_open():
+            return True, {}
+        self.error(f'OPC server {self.id} is not connected', self.metadata)
+        return False, self._not_connected_error()
+
+    def _reconnect_task_in_progress(self) -> bool:
+        """
+        Return whether a background reconnect task is currently running.
+
+        Return:
+            bool: True when a reconnect task exists and has not finished.
+        """
+        return self._reconnect_task is not None and not self._reconnect_task.done()
+
+    async def _start_reconnect(self, reason: str, session_id: str) -> None:
+        """
+        Schedule a background reconnect when allowed by interval and task state.
+
+        Clears _session_ready before starting the task. No-op when _allow_reconnect is
+        False, the reconnection window has not elapsed, or a reconnect is already running.
+
+        Args:
+            reason (str): Trigger for reconnect (OPC status name or synthetic reason).
+            session_id (str): Session token before failure.
+        """
+        if not self._allow_reconnect:
+            return
+        if not self._reconnection_window_elapsed():
+            self.warning(
+                f'OPC reconnect skipped reason=reconnection_window opc_server_id={self.id} '
+                f'reconnect_reason={reason}',
+                self.metadata,
+            )
+            return
+        if self._reconnect_task_in_progress():
+            self.warning(
+                f'OPC reconnect skipped reason=in_progress opc_server_id={self.id} '
+                f'reconnect_reason={reason}',
+                self.metadata,
+            )
+            return
+
+        self._session_ready.clear()
+        self.info(
+            f'OPC reconnect scheduled reconnect_reason={reason} opc_server_id={self.id} '
+            f'old_session_id={session_id}',
+            self.metadata,
+        )
+        self._reconnect_task = asyncio.create_task(self._run_reconnect(reason, session_id))
+
+    async def _run_reconnect(self, reason: str, session_id: str) -> None:
+        """
+        Background task that tears down and re-establishes the OPC UA session.
+
+        Args:
+            reason (str): Trigger for reconnect (OPC status or ProtocolClosed).
+            session_id (str): Previous session token string for logging.
+        """
+        try:
+            async with self._connection_lock:
+                self.info(
+                    f'OPC reconnect started reconnect_reason={reason} opc_server_id={self.id} '
+                    f'old_session_id={session_id}',
+                    self.metadata,
+                )
+                success, error = await self._reconnect_locked()
+            if not success:
+                self.error(
+                    f'OPC reconnect failed reconnect_reason={reason} opc_server_id={self.id}',
+                    self.metadata,
+                )
+                if error:
+                    self.error(error.get('message', ''), self.metadata)
+        except Exception:
+            self.error(
+                f'OPC reconnect task failed opc_server_id={self.id} reconnect_reason={reason}',
+                self.metadata,
+            )
+            self.error(traceback.format_exc(), self.metadata)
+
+    async def _log_write_inter_arrival(self, session_id: str, node: str) -> None:
+        """
+        Log elapsed wall time since the previous successful OPC write on this repository.
+
+        Args:
+            session_id (str): Current OPC UA session token string.
+            node (str): Node id written in this operation.
+        """
+        now = time.monotonic()
+        if self._last_write_mono is not None:
+            delta_s = now - self._last_write_mono
+            self.info(
+                f'OPC write inter-arrival_s={delta_s:.6f} opc_server_id={self.id} '
+                f'session_id={session_id} node={node}',
+                self.metadata,
+            )
+            if self.client is not None:
+                session_timeout_ms = float(self.client.session_timeout)
+                if session_timeout_ms > 0 and delta_s > (session_timeout_ms / 1000.0):
+                    await self.emit_metric(
+                        metrics.OPC_WRITE_INTER_ARRIVAL_OVER_SESSION_TIMEOUT_TOTAL,
+                        self._opc_debug_tags(session_id),
+                    )
+        self._last_write_mono = now
+
+    async def _emit_opc_write_metric(
+        self, session_id: str, result: str, metadata: dict[str, Any] | None
+    ) -> None:
+        """
+        Emit opc_write_attempts_total for a single write attempt outcome.
+
+        Args:
+            session_id (str): OPC UA session token string, or "unknown".
+            result (str): Outcome label (OK, OPC status name, ProtocolClosed, etc.).
+            metadata (dict[str, Any] | None): Write context for model_id/model_name labels.
+        """
+        await self.emit_metric(
+            metrics.OPC_WRITE_ATTEMPTS_TOTAL,
+            {
+                **self._opc_debug_tags(session_id),
+                **_model_labels_from_write_metadata(metadata),
+                'result': result,
+            },
+        )
+
+    def _write_failure_payload(
+        self,
+        notification_id: str,
+        message: str,
+        level: NotificationLevel = NotificationLevel.ERROR,
+        attachment_content: str | None = None,
+        opc_error_kind: str | None = None,
+        opc_status: str | None = None,
+    ) -> dict[str, Any]:
+        """
+        Build a structured error dict returned from failed write_data paths.
+
+        Args:
+            notification_id (str): Stable notification identifier.
+            message (str): Human-readable failure message.
+            level (NotificationLevel): Severity for downstream notifications.
+            attachment_content (str | None): Optional traceback or diagnostic text.
+            opc_error_kind (str | None): Classifier (session_bad, connection_lost, etc.).
+            opc_status (str | None): OPC UA status name or synthetic reason.
+
+        Return:
+            dict[str, Any]: Error payload consumed by the OPC activity layer.
+        """
+        payload: dict[str, Any] = {
+            'notification_id': notification_id,
+            'message': message,
+            'block': 'opc_repository',
+            'level': level,
+        }
+        if attachment_content is not None:
+            payload['attachment_content'] = attachment_content
+        if opc_error_kind is not None:
+            payload['opc_error_kind'] = opc_error_kind
+        if opc_status is not None:
+            payload['opc_status'] = opc_status
+        return payload
+
+    async def _handle_tier1_bad(
+        self,
+        exc: BaseException,
+        session_id: str,
+        node: str,
+        metadata: dict[str, Any],
+        phase: str,
+    ) -> tuple[bool, dict[str, Any]]:
+        """
+        Record metrics/logs and schedule reconnect after a Tier-1 Bad* error.
+
+        Args:
+            exc (BaseException): Tier-1 OPC UA error.
+            session_id (str): Session token at failure time.
+            node (str): Node id being written.
+            metadata (dict[str, Any]): Write context.
+            phase (str): get_node or write_value.
+
+        Return:
+            tuple[bool, dict[str, Any]]: Always (False, error payload).
+        """
+        opc_status = _opc_status_from_exception(exc)
+        trace = traceback.format_exc()
+        self.error(trace, metadata)
+        await self._emit_opc_write_metric(session_id, opc_status, metadata)
+        self.error(
+            f'OPC write failed opc_status={opc_status} opc_server_id={self.id} '
+            f'session_id={session_id} model_id={metadata.get("model_id", "unknown")} '
+            f'model_name={metadata.get("model_name", "unknown")} node={node} phase={phase}',
+            metadata,
+        )
+        await self._start_reconnect(opc_status, session_id)
+        return False, self._write_failure_payload(
+            notification_id=f'OPC_WRITE_DATA_ERROR_{self.id}',
+            message=f'Failed to {phase} on OPC server: {exc} | metadata: {metadata}',
+            attachment_content=trace,
+            opc_error_kind='session_bad',
+            opc_status=opc_status,
+        )
+
+    async def _write_reconnect_in_progress(
+        self, metadata: dict[str, Any]
+    ) -> tuple[bool, dict[str, Any]]:
+        """
+        Fail a write because a background reconnect task is already running.
+
+        Args:
+            metadata (dict[str, Any]): Write context passed through to the activity.
+
+        Return:
+            tuple[bool, dict[str, Any]]: (False, error info with opc_error_kind reconnect_in_progress).
+        """
+        await self._emit_opc_write_metric('unknown', 'ReconnectInProgress', metadata)
+        self.warning(
+            f'OPC write rejected reconnect_in_progress opc_server_id={self.id} '
+            f'model_id={metadata.get("model_id", "unknown")} '
+            f'model_name={metadata.get("model_name", "unknown")}',
+            metadata,
+        )
+        return False, {
+            'notification_id': f'OPC_WRITE_RECONNECT_IN_PROGRESS_{self.id}',
+            'message': f'OPC write skipped: reconnect in progress | metadata: {metadata}',
+            'block': 'opc_repository',
+            'level': NotificationLevel.WARNING,
+            'opc_error_kind': 'reconnect_in_progress',
+        }
+
+    async def _write_connection_lost(
+        self, metadata: dict[str, Any], opc_status: str
+    ) -> tuple[bool, dict[str, Any]]:
+        """
+        Fail a write after scheduling reconnect for a closed or stale session.
+
+        Args:
+            metadata (dict[str, Any]): Write context passed through to the activity.
+            opc_status (str): Synthetic reason (ProtocolClosed, SessionNotReady).
+
+        Return:
+            tuple[bool, dict[str, Any]]: (False, error info with opc_error_kind connection_lost).
+        """
+        await self._emit_opc_write_metric('unknown', opc_status, metadata)
+        return False, self._write_failure_payload(
+            notification_id=f'OPC_WRITE_CONNECTION_LOST_{self.id}',
+            message=f'OPC write skipped: connection lost ({opc_status}) | metadata: {metadata}',
+            level=NotificationLevel.WARNING,
+            opc_error_kind='connection_lost',
+            opc_status=opc_status,
+        )
+
+    async def write_data(
+        self, node: str, value: Any, data_type: str, metadata: dict[str, Any]
+    ) -> tuple[bool, dict[str, Any]]:
+        """
+        Write data to OPC server with a single attempt and background reconnect scheduling.
+
+        Reconnect is scheduled on Tier-1 Bad*, closed protocol, or stale session readiness.
+        There is no retry within the same call.
+
+        Args:
+            node (str): OPC UA node id to write.
+            value (Any): Value to convert and send.
+            data_type (str): Logical type key (float, int, bool, str, double).
+            metadata (dict[str, Any]): Activity context (model_id, model_name, etc.).
+
+        Return:
+            tuple[bool, dict[str, Any]]: (True, {response_time}) on success, or
+                (False, structured error info) on failure.
+        """
+        if self._reconnect_task_in_progress():
+            return await self._write_reconnect_in_progress(metadata)
+
+        if not self._session_ready.is_set():
+            session_id = _opc_authentication_token_str(self.client)
+            await self._start_reconnect('SessionNotReady', session_id)
+            if self._reconnect_task_in_progress():
+                return await self._write_reconnect_in_progress(metadata)
+            return await self._write_connection_lost(metadata, 'SessionNotReady')
+
+        is_connected, _error = await self.validate_connection()
+        if not is_connected:
+            session_id = _opc_authentication_token_str(self.client)
+            await self._start_reconnect('ProtocolClosed', session_id)
+            return await self._write_connection_lost(metadata, 'ProtocolClosed')
+
+        start_time = time.time()
+        session_id = _opc_authentication_token_str(self.client)
+
+        try:
+            node_obj = self.client.get_node(node)  # type: ignore[union-attr]
+        except Exception as e:
+            if is_reconnectable_opcua_bad(e):
+                return await self._handle_tier1_bad(e, session_id, node, metadata, 'get_node')
+            trace = traceback.format_exc()
+            self.error(trace, metadata)
+            await self._emit_opc_write_metric(
+                session_id, f'GetNodeError:{type(e).__name__}', metadata
+            )
+            return False, self._write_failure_payload(
+                notification_id=f'OPC_WRITE_GET_NODE_ERROR_{self.id}',
+                message=f'Failed to get node from OPC server: {e} | metadata: {metadata}',
+                attachment_content=trace,
+            )
+
+        if data_type not in data_type_map:
+            await self._emit_opc_write_metric(session_id, 'UnsupportedDataType', metadata)
+            return False, self._write_failure_payload(
+                notification_id=f'OPC_WRITE_DATA_TYPE_ERROR_{self.id}',
+                message=f'Unsupported data type: {data_type} | metadata: {metadata}',
+            )
+
+        data = data_type_map[data_type]['converter'](value)
+        self.info(f'Writing {data} - {type(data)} to {node}', metadata)
+        ua_data = DataValue(
+            Variant(data, data_type_map[data_type]['opc_type']),
+        )
+
+        try:
+            await node_obj.write_value(ua_data)
+            end_time = time.time()
+            response_time = end_time - start_time
+        except Exception as e:
+            if is_reconnectable_opcua_bad(e):
+                return await self._handle_tier1_bad(e, session_id, node, metadata, 'write_value')
+            trace = traceback.format_exc()
+            self.error(trace, metadata)
+            await self._emit_opc_write_metric(session_id, type(e).__name__, metadata)
+            return False, self._write_failure_payload(
+                notification_id=f'OPC_WRITE_DATA_ERROR_{self.id}',
+                message=f'Failed to write data to OPC server: {e} | metadata: {metadata}',
+                attachment_content=trace,
+            )
+
+        await self._emit_opc_write_metric(session_id, 'OK', metadata)
+        await self._log_write_inter_arrival(session_id, node)
+
+        return True, {
+            'response_time': response_time,
+        }