SIENTIAPDE-1811

Enhance OPC UA communication and metrics tracking

- Updated README.md to include new OPC UA Communication section and detailed metrics for session and write diagnostics.
- Added new metrics in laborious/metrics.py for tracking OPC UA session states and write attempts.
- Refactored OPC activity in laborious/activities/opc.py to handle session errors and improve error reporting.
- Updated e2e tests to cover new scenarios for OPC session/channel errors and reconnect handling.
- Modified .gitignore to include relatorio files and mlruns directory.
- Added ipykernel to requirements-dev.txt for Jupyter notebook support.

tests/laborious/utils/repository/test_opc_repository.py

@@ -253,6 +253,7 @@ def test_disconnect(opc_repository, mock_client):
 
     opc_repository._disconnection_fallback.assert_called_once()
     assert opc_repository.client is None
+    assert opc_repository._allow_reconnect is False
 
 
 def test_disconnect_no_client(opc_repository):
@@ -323,12 +324,19 @@ def test_write_data_validate_connection_do_nothing(opc_repository):
 def test_write_data_validate_connection_failed(opc_repository):
     opc_repository.validate_connection = MagicMock(return_value=(False, {}))
     opc_repository.client = MagicMock()
+    opc_repository._start_reconnect = MagicMock()
 
-    result = opc_repository.write_data('ns=2;s=TestNode', 42.0, 'float', metadata['metadata'])
+    is_success, error_data = opc_repository.write_data(
+        'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
+    )
 
     opc_repository.validate_connection.assert_called_once()
     opc_repository.client.get_node.assert_not_called()
-    assert result == (False, {})
+    opc_repository._start_reconnect.assert_called_once()
+    assert opc_repository._start_reconnect.call_args.args[0] == 'ProtocolClosed'
+    assert is_success is False
+    assert error_data['opc_error_kind'] == 'connection_lost'
+    assert error_data['opc_status'] == 'ProtocolClosed'
 
 
 def test_write_data_get_node_failed(opc_repository):
@@ -424,7 +432,7 @@ def test_is_reconnectable_opcua_bad():
 def test_write_data_bad_session_id_invalid_schedules_reconnect(opc_repository, mock_client):
     opc_repository.validate_connection = MagicMock(return_value=(True, {}))
     opc_repository.client = mock_client
-    opc_repository._start_reconnect_on_bad = MagicMock()
+    opc_repository._start_reconnect = MagicMock()
     mock_node = MagicMock()
     mock_client.get_node = MagicMock(return_value=mock_node)
     mock_node.write_value.side_effect = BadSessionIdInvalid()
@@ -434,7 +442,7 @@ def test_write_data_bad_session_id_invalid_schedules_reconnect(opc_repository, m
     )
 
     mock_node.write_value.assert_called_once()
-    opc_repository._start_reconnect_on_bad.assert_called_once()
+    opc_repository._start_reconnect.assert_called_once()
     assert is_success is False
     assert error_data['opc_error_kind'] == 'session_bad'
     assert error_data['opc_status'] == 'BadSessionIdInvalid'
@@ -455,15 +463,83 @@ def test_write_data_reconnect_in_progress_immediate(opc_repository):
     assert error_data['opc_error_kind'] == 'reconnect_in_progress'
 
 
-def test_start_reconnect_on_bad_skips_within_interval(opc_repository):
+def test_start_reconnect_skips_within_interval(opc_repository):
     opc_repository.last_reconnection_time = datetime.now()
     opc_repository.reconnection_interval = 3600
 
-    opc_repository._start_reconnect_on_bad('BadSessionIdInvalid', 'tok')
+    opc_repository._start_reconnect('BadSessionIdInvalid', 'tok')
 
     assert opc_repository._reconnect_thread is None
 
 
+def test_write_data_protocol_closed_schedules_reconnect(opc_repository):
+    opc_repository.client = MagicMock()
+    opc_repository.client.aio_obj.uaclient.protocol = MagicMock(state='closed')
+    opc_repository._start_reconnect = MagicMock()
+
+    is_success, error_data = opc_repository.write_data(
+        'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
+    )
+
+    opc_repository._start_reconnect.assert_called_once()
+    assert opc_repository._start_reconnect.call_args.args[0] == 'ProtocolClosed'
+    assert is_success is False
+    assert error_data['opc_error_kind'] == 'connection_lost'
+    assert error_data['opc_status'] == 'ProtocolClosed'
+
+
+def test_write_data_protocol_closed_skips_reconnect_within_interval(opc_repository):
+    opc_repository.client = MagicMock()
+    opc_repository.client.aio_obj.uaclient.protocol = MagicMock(state='closed')
+    opc_repository.last_reconnection_time = datetime.now()
+    opc_repository.reconnection_interval = 3600
+
+    is_success, error_data = opc_repository.write_data(
+        'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
+    )
+
+    assert opc_repository._reconnect_thread is None
+    assert is_success is False
+    assert error_data['opc_error_kind'] == 'connection_lost'
+
+
+def test_write_data_after_failed_reconnect_schedules_again(opc_repository):
+    opc_repository._session_ready.clear()
+    opc_repository.reconnection_interval = 0
+    opc_repository.last_reconnection_time = None
+    opc_repository._reconnect_locked = MagicMock(
+        return_value=(False, {'message': 'connect failed'})
+    )
+
+    opc_repository.write_data('ns=2;s=TestNode', 42.0, 'float', metadata['metadata'])
+    if opc_repository._reconnect_thread is not None:
+        opc_repository._reconnect_thread.join(timeout=2)
+    assert opc_repository._reconnect_locked.call_count == 1
+    assert not opc_repository._reconnect_thread_in_progress()
+
+    opc_repository.write_data('ns=2;s=TestNode', 42.0, 'float', metadata['metadata'])
+    if opc_repository._reconnect_thread is not None:
+        opc_repository._reconnect_thread.join(timeout=2)
+    assert opc_repository._reconnect_locked.call_count == 2
+
+
+def test_write_data_after_disconnect_does_not_schedule_reconnect(opc_repository, mock_client):
+    opc_repository.client = mock_client
+    proto = MagicMock()
+    proto.state = 'closed'
+    mock_client.aio_obj.uaclient.protocol = proto
+    opc_repository._disconnection_fallback = MagicMock(return_value=[])
+    opc_repository.disconnect()
+
+    is_success, error_data = opc_repository.write_data(
+        'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
+    )
+
+    assert opc_repository._reconnect_thread is None
+    assert is_success is False
+    assert error_data['opc_error_kind'] == 'connection_lost'
+
+
 def test_parallel_bad_writes_single_reconnect_task(opc_repository, mock_client):
     opc_repository.validate_connection = MagicMock(return_value=(True, {}))
     opc_repository.client = mock_client
@@ -472,7 +548,7 @@ def test_parallel_bad_writes_single_reconnect_task(opc_repository, mock_client):
     mock_node = MagicMock()
     mock_client.get_node = MagicMock(return_value=mock_node)
     mock_node.write_value.side_effect = BadSessionIdInvalid()
-    opc_repository._start_reconnect_on_bad = MagicMock()
+    opc_repository._start_reconnect = MagicMock()
 
     with concurrent.futures.ThreadPoolExecutor(max_workers=2) as executor:
         futures = [
@@ -487,7 +563,7 @@ def test_parallel_bad_writes_single_reconnect_task(opc_repository, mock_client):
         ]
         results = [future.result() for future in futures]
 
-    assert 1 <= opc_repository._start_reconnect_on_bad.call_count <= 2
+    assert 1 <= opc_repository._start_reconnect.call_count <= 2
     assert mock_node.write_value.call_count == 2
     error_kinds = [r[1].get('opc_error_kind') for r in results]
     assert error_kinds.count('session_bad') >= 1