SIENTIAPDE-2013: cap load_latest_data's Mongo fetch at a configurable batch size

A cold start or notification storm had no backstop: load_latest_data
fetched the entire matching backlog in one query. Confirmed live during
SIENTIAPDE-2012's cluster verification -- an empty Redis cursor plus a
real recurring error let a single run's query exceed Temporal's 4MB
message limit and get stuck retrying forever.

Threads a new notification_queue_batch_size config (env var
NOTIFICATION_QUEUE_BATCH_SIZE, default 5000) through to the repository's
find(), hard cap per run, no drain loop -- the incremental
last_data_timestamp cursor picks up any remainder next run, per the
parent ticket's design decision. Sorts by timestamp ascending so a
capped run always returns the oldest pending documents first; without
that, a capped batch has no guarantee of hitting the oldest documents,
and the cursor would advance past whatever it skipped.

Requires sientia_do>=1.13.0 (adds limit/sort params to
MongoDBRepository.find in both the sync and async client) -- bumped the
pin here per the parent ticket's decision to do it in the same PR.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

tests/orchestrator/activities/test_activities.py

@@ -27,6 +27,7 @@ def test___init__(
         'connection_string': 'mongodb://localhost:27017',
         'database_name': 'test_db',
         'ttl_index_seconds': 3600,
+        'notification_queue_batch_size': 5000,
     }
 
     redis_config = {'host': 'localhost', 'port': 6379, 'username': 'admin', 'password': 'password'}
@@ -89,6 +90,7 @@ def test___init__(
         connection_string='mongodb://localhost:27017',
         database_name='test_db',
         ttl_index_seconds=3600,
+        notification_queue_batch_size=5000,
         logger=logger,
         notification_handler=notification_handler,
         metrics_controller=mock_metrics_controller.return_value,

tests/orchestrator/activities/test_mongo_db.py

@@ -31,13 +31,14 @@ def test___init__(mongo_mock):
     notification_handler = MagicMock()
     metrics_controller = AsyncMock()
 
-    MongoDB(
+    mongo = MongoDB(
         connection_string='mongodb://localhost:27017',
         database_name='test_db',
         ttl_index_seconds=3600,
         logger=logger,
         notification_handler=notification_handler,
         metrics_controller=metrics_controller,
+        notification_queue_batch_size=5000,
     )
 
     mongo_mock.assert_called_once_with(
@@ -47,6 +48,22 @@ def test___init__(mongo_mock):
         notification_handler=notification_handler,
         metrics_controller=metrics_controller,
     )
+    assert mongo.notification_queue_batch_size == 5000
+
+
+@patch('orchestrator.activities.mongo_db.MongoDBRepository')
+def test___init___notification_queue_batch_size_defaults_to_zero(mongo_mock):
+    """0 means no limit, matching the underlying find()'s own convention."""
+    mongo = MongoDB(
+        connection_string='mongodb://localhost:27017',
+        database_name='test_db',
+        ttl_index_seconds=3600,
+        logger=MagicMock(),
+        notification_handler=MagicMock(),
+        metrics_controller=AsyncMock(),
+    )
+
+    assert mongo.notification_queue_batch_size == 0
 
 
 @patch('orchestrator.activities.mongo_db.SientiaMonitoring')
@@ -480,6 +497,8 @@ def test_load_latest_data_none_last_data_timestamp(mongo_db):
         'test_collection',
         {'level': 'ERROR'},
         {'workflow_name': 'test_pipeline', 'schedule_name': 'test_schedule'},
+        limit=0,
+        sort=[('timestamp', 1)],
     )
 
     assert result == [
@@ -487,6 +506,29 @@ def test_load_latest_data_none_last_data_timestamp(mongo_db):
     ]
 
 
+def test_load_latest_data_passes_configured_batch_size_as_limit(mongo_db):
+    """SIENTIAPDE-2013: the configured notification_queue_batch_size caps the query."""
+    mongo_db.notification_queue_batch_size = 100
+    mongo_db.mongo_db_repository.find = MagicMock(return_value=[])
+
+    mongo_db.load_latest_data(
+        {
+            'metadata': {'workflow_name': 'test_pipeline', 'schedule_name': 'test_schedule'},
+            'collection_name': 'test_collection',
+            'last_data_timestamp': None,
+            'base_data_filter': {'level': 'ERROR'},
+        }
+    )
+
+    mongo_db.mongo_db_repository.find.assert_called_once_with(
+        'test_collection',
+        {'level': 'ERROR'},
+        {'workflow_name': 'test_pipeline', 'schedule_name': 'test_schedule'},
+        limit=100,
+        sort=[('timestamp', 1)],
+    )
+
+
 def test_load_latest_data_not_none_last_data_timestamp(mongo_db):
     """Test load_latest_data compares native datetime against native datetime in $gt"""
 
@@ -516,6 +558,8 @@ def test_load_latest_data_not_none_last_data_timestamp(mongo_db):
             'timestamp': {'$gt': datetime(2023, 1, 1, 12, 0, 0, tzinfo=UTC)},
         },
         {'workflow_name': 'test_pipeline', 'schedule_name': 'test_schedule'},
+        limit=0,
+        sort=[('timestamp', 1)],
     )
 
     assert result == [
@@ -529,7 +573,7 @@ def test_load_latest_data_run_boundary_no_skip_or_duplicate(mongo_db):
 
     boundary_timestamp = datetime(2023, 1, 1, 12, 0, 0, tzinfo=UTC)
 
-    def fake_find(collection_name, data_filter, metadata):
+    def fake_find(collection_name, data_filter, metadata, limit=0, sort=None):
         gt = data_filter.get('timestamp', {}).get('$gt')
         all_docs = [
             {

tests/orchestrator/utils/test_connectors_config.py

@@ -64,10 +64,12 @@ def test_build_mongo_db_config_with_env_vars():
     environ['MONGODB_URL'] = 'localhost:27018'
     environ['MONGODB_DATABASE_NAME'] = 'test_db'
     environ['MONGODB_TTL_INDEX_HOURS'] = '2'
+    environ['NOTIFICATION_QUEUE_BATCH_SIZE'] = '2000'
     assert build_mongodb_config() == {
         'connection_string': 'mongodb://sientia1:sientia1@localhost:27018',
         'database_name': 'test_db',
         'ttl_index_seconds': 7200,
+        'notification_queue_batch_size': 2000,
     }
 
 
@@ -77,10 +79,12 @@ def test_build_mongo_db_config_with_defaults():
     environ.pop('MONGODB_DATABASE_NAME', None)
     environ.pop('MONGODB_URL', None)
     environ.pop('MONGODB_TTL_INDEX_HOURS', None)
+    environ.pop('NOTIFICATION_QUEUE_BATCH_SIZE', None)
     assert build_mongodb_config() == {
         'connection_string': 'mongodb://root:wKZDbMNU1c@localhost:27018',
         'database_name': 'sientia',
         'ttl_index_seconds': 3600,
+        'notification_queue_batch_size': 5000,
     }