fix(ingestion): silence basedpyright McpConnection union narrowing flake (#27834)

The static-checks job intermittently fails with ~35
reportAttributeAccessIssue errors of the form "Cannot access attribute X
for class McpConnection" (or CustomDriveConnection). Root cause:
basedpyright's --baselinemode=discard matches baseline entries by
per-file diagnostic stream order with no line numbers, so any schema
regen that shifts a Union arm's narrowing cascade-misaligns downstream
baseline matches and surfaces them as new errors.

Defer the architectural fix and silence the flake at source:

* Pin basedpyright to ==1.39.3 (was ~=1.39.0) so CI no longer pulls a
  different patch version with a different typeshed bundle on each run.
* Add # pyright: ignore[reportAttributeAccessIssue] on the 35 access /
  assign sites surfaced by the failing CI run. Inline ignores delete
  the diagnostic from the per-file stream entirely, so they're immune
  to ordering shifts.

reportUnnecessaryTypeIgnoreComment is already disabled in pyproject.toml,
so the ignores are inert on platforms where the union narrowing collapses
differently and the errors don't fire (macOS arm64).

Tableau pipeline client.py library-export errors deferred to that PR's
owner; unrelated to this flake.

Author: IceS2

ingestion/setup.py

@@ -401,7 +401,7 @@
     "mypy-boto3-glue",
     "nox",
     "pre-commit",
-    "basedpyright~=1.39.0",
+    "basedpyright==1.39.3",
     # For publishing
     "twine",
     "build",

ingestion/src/metadata/automations/runner.py

@@ -58,7 +58,7 @@ def _(
 
         host_port_type = type(request.connection.config.hostPort)
         docker_host_port_str = host_port_str.replace("localhost", "host.docker.internal")
-        request.connection.config.hostPort = host_port_type(docker_host_port_str)
+        request.connection.config.hostPort = host_port_type(docker_host_port_str)  # pyright: ignore[reportAttributeAccessIssue]
 
         _ = _test_connection(metadata, request.connection.config, automation_workflow)
 

ingestion/src/metadata/ingestion/source/api/rest/metadata.py

@@ -210,15 +210,15 @@ def _prepare_endpoint_data(self, path, method_type, info, collection) -> Optiona
 
     def _get_fallback_url(self) -> Optional[AnyUrl]:  # noqa: UP045
         """Return openAPISchemaURL if available, otherwise None."""
-        schema_conn = self.config.serviceConnection.root.config.openAPISchemaConnection
+        schema_conn = self.config.serviceConnection.root.config.openAPISchemaConnection  # pyright: ignore[reportAttributeAccessIssue]
         if isinstance(schema_conn, OpenAPISchemaURL):
             return schema_conn.openAPISchemaURL
         return None
 
     def _generate_collection_url(self, collection_name: str) -> Optional[AnyUrl]:  # noqa: UP045
         """generate collection url"""
         try:
-            base_url = self.config.serviceConnection.root.config.docURL
+            base_url = self.config.serviceConnection.root.config.docURL  # pyright: ignore[reportAttributeAccessIssue]
             if not base_url:
                 logger.debug(f"Could not generate collection url for {collection_name} because docURL is not present")
                 return self._get_fallback_url()

ingestion/src/metadata/ingestion/source/dashboard/mode/metadata.py

@@ -62,8 +62,8 @@ def __init__(
         metadata: OpenMetadata,
     ):
         super().__init__(config, metadata)
-        self.workspace_name = config.serviceConnection.root.config.workspaceName
-        self.filter_query_param = config.serviceConnection.root.config.filterQueryParam
+        self.workspace_name = config.serviceConnection.root.config.workspaceName  # pyright: ignore[reportAttributeAccessIssue]
+        self.filter_query_param = config.serviceConnection.root.config.filterQueryParam  # pyright: ignore[reportAttributeAccessIssue]
         self.data_sources = self.client.get_all_data_sources(self.workspace_name)
 
     @classmethod

ingestion/src/metadata/ingestion/source/dashboard/quicksight/metadata.py

@@ -91,7 +91,7 @@ def __init__(self, config: WorkflowSource, metadata: OpenMetadata):
         super().__init__(config, metadata)
         self.aws_account_id = self.service_connection.awsAccountId
         self.dashboard_url = None
-        self.aws_region = self.config.serviceConnection.root.config.awsConfig.awsRegion
+        self.aws_region = self.config.serviceConnection.root.config.awsConfig.awsRegion  # pyright: ignore[reportAttributeAccessIssue]
         self.default_args = {
             "AwsAccountId": self.aws_account_id,
             "MaxResults": QUICKSIGHT_MAX_RESULTS,

ingestion/src/metadata/ingestion/source/dashboard/tableau/metadata.py

@@ -1117,6 +1117,6 @@ def get_base_url(self) -> str:
         """
         Get the proxy url for the tableau server
         """
-        if self.config.serviceConnection.root.config.proxyURL:
-            return str(self.config.serviceConnection.root.config.proxyURL)
+        if self.config.serviceConnection.root.config.proxyURL:  # pyright: ignore[reportAttributeAccessIssue]
+            return str(self.config.serviceConnection.root.config.proxyURL)  # pyright: ignore[reportAttributeAccessIssue]
         return str(self.config.serviceConnection.root.config.hostPort)

ingestion/src/metadata/ingestion/source/database/azuresql/metadata.py

@@ -75,8 +75,8 @@ def get_database_names_raw(self) -> Iterable[str]:
         yield from self._execute_database_query(AZURE_SQL_GET_DATABASES)
 
     def get_database_names(self) -> Iterable[str]:
-        if not self.config.serviceConnection.root.config.ingestAllDatabases:
-            configured_db = self.config.serviceConnection.root.config.database
+        if not self.config.serviceConnection.root.config.ingestAllDatabases:  # pyright: ignore[reportAttributeAccessIssue]
+            configured_db = self.config.serviceConnection.root.config.database  # pyright: ignore[reportAttributeAccessIssue]
             self.set_inspector(database_name=configured_db)
             yield configured_db
         else:

ingestion/src/metadata/ingestion/source/database/cockroach/metadata.py

@@ -186,8 +186,8 @@ def get_database_names_raw(self) -> Iterable[str]:
         yield from self._execute_database_query(COCKROACH_GET_DB_NAMES)
 
     def get_database_names(self) -> Iterable[str]:
-        if not self.config.serviceConnection.root.config.ingestAllDatabases:
-            configured_db = self.config.serviceConnection.root.config.database
+        if not self.config.serviceConnection.root.config.ingestAllDatabases:  # pyright: ignore[reportAttributeAccessIssue]
+            configured_db = self.config.serviceConnection.root.config.database  # pyright: ignore[reportAttributeAccessIssue]
             self.set_inspector(database_name=configured_db)
             self.set_schema_description_map()
             yield configured_db

ingestion/src/metadata/ingestion/source/database/greenplum/metadata.py

@@ -128,8 +128,8 @@ def get_database_names_raw(self) -> Iterable[str]:
         yield from self._execute_database_query(GREENPLUM_GET_DB_NAMES)
 
     def get_database_names(self) -> Iterable[str]:
-        if not self.config.serviceConnection.root.config.ingestAllDatabases:
-            configured_db = self.config.serviceConnection.root.config.database
+        if not self.config.serviceConnection.root.config.ingestAllDatabases:  # pyright: ignore[reportAttributeAccessIssue]
+            configured_db = self.config.serviceConnection.root.config.database  # pyright: ignore[reportAttributeAccessIssue]
             self.set_inspector(database_name=configured_db)
             yield configured_db
         else:

ingestion/src/metadata/ingestion/source/database/microsoftfabric/metadata.py

@@ -123,8 +123,8 @@ def get_database_names(self) -> Iterable[str]:
 
         In Microsoft Fabric, each Warehouse and Lakehouse appears as a database.
         """
-        if not self.config.serviceConnection.root.config.ingestAllDatabases:
-            configured_db = self.config.serviceConnection.root.config.database
+        if not self.config.serviceConnection.root.config.ingestAllDatabases:  # pyright: ignore[reportAttributeAccessIssue]
+            configured_db = self.config.serviceConnection.root.config.database  # pyright: ignore[reportAttributeAccessIssue]
             self.set_inspector(database_name=configured_db)
             yield configured_db
         else: