fix: un-break local mode on FrameworkProcessor

Make Processors default to overriding LocalSession config
local_code=False, since local_code is not (yet) supported for local
mode processing. Fix corresponding integration test and add a unit
test for the defaulting behavior. Clarify the error message.

Author: athewsey

src/sagemaker/local/local_session.py

@@ -475,10 +475,30 @@ def invoke_endpoint(
 
 
 class LocalSession(Session):
-    """A LocalSession class definition."""
+    """A SageMaker ``Session`` class for Local Mode.
 
-    def __init__(self, boto_session=None, s3_endpoint_url=None):
+    This class provides alternative Local Mode implementations for the functionality of
+    :class:`~sagemaker.session.Session`.
+    """
+
+    def __init__(self, boto_session=None, s3_endpoint_url=None, disable_local_code=False):
+        """Create a Local SageMaker Session.
+
+        Args:
+            boto_session (boto3.session.Session): The underlying Boto3 session which AWS service
+                calls are delegated to (default: None). If not provided, one is created with
+                default AWS configuration chain.
+            s3_endpoint_url (str): Override the default endpoint URL for Amazon S3, if set
+                (default: None).
+            disable_local_code (bool): Set ``True`` to override the default AWS configuration
+                chain to disable the ``local.local_code`` setting, which may not be supported for
+                some SDK features (default: False).
+        """
         self.s3_endpoint_url = s3_endpoint_url
+        # We use this local variable to avoid disrupting the __init__->_initialize API of the
+        # parent class... But overwriting it after constructor won't do anything, so prefix _ to
+        # discourage external use:
+        self._disable_local_code = disable_local_code
 
         super(LocalSession, self).__init__(boto_session)
 
@@ -530,6 +550,8 @@ def _initialize(
                 raise e
 
             self.config = yaml.load(open(sagemaker_config_file, "r"))
+            if self._disable_local_code and "local" in self.config:
+                self.config["local"]["local_code"] = False
 
     def logs_for_job(self, job_name, wait=False, poll=5, log_type="All"):
         """A no-op method meant to override the sagemaker client.

src/sagemaker/processing.py

@@ -128,7 +128,8 @@ def __init__(
 
         if self.instance_type in ("local", "local_gpu"):
             if not isinstance(sagemaker_session, LocalSession):
-                sagemaker_session = LocalSession()
+                # Until Local Mode Processing supports local code, we need to disable it:
+                sagemaker_session = LocalSession(disable_local_code=True)
 
         self.sagemaker_session = sagemaker_session or Session()
 
@@ -1568,10 +1569,11 @@ def _pack_and_upload_code(self, code, source_dir, dependencies, git_config, job_
 
         local_code = get_config_value("local.local_code", self.sagemaker_session.config)
         if self.sagemaker_session.local_mode and local_code:
-            # TODO: Can we be more prescriptive about how to not trigger this error?
-            # How can user or us force a local mode `Estimator` to run with `local_code=False`?
             raise RuntimeError(
-                "Local *code* is not currently supported for SageMaker Processing in Local Mode"
+                "SageMaker Processing Local Mode does not currently support 'local code' mode. "
+                "Please use a LocalSession created with disable_local_code=True, or leave "
+                "sagemaker_session unspecified when creating your Processor to have one set up "
+                "automatically."
             )
 
         # Upload the bootstrapping code as s3://.../jobname/source/runproc.sh.

tests/integ/test_local_mode.py

@@ -58,6 +58,11 @@ def _initialize(self, boto_session, sagemaker_client, sagemaker_runtime_client,
         self.local_mode = True
 
 
+@pytest.fixture(scope="module")
+def sagemaker_local_session_no_local_code(boto_session):
+    return LocalSession(boto_session=boto_session, disable_local_code=True)
+
+
 @pytest.fixture(scope="module")
 def sklearn_image_uri(
     sklearn_latest_version,
@@ -322,7 +327,7 @@ def test_local_transform_mxnet(
 
 
 @pytest.mark.local_mode
-def test_local_processing_sklearn(sagemaker_local_session, sklearn_latest_version):
+def test_local_processing_sklearn(sagemaker_local_session_no_local_code, sklearn_latest_version):
     script_path = os.path.join(DATA_DIR, "dummy_script.py")
     input_file_path = os.path.join(DATA_DIR, "dummy_input.txt")
 
@@ -332,7 +337,7 @@ def test_local_processing_sklearn(sagemaker_local_session, sklearn_latest_versio
         instance_type="local",
         instance_count=1,
         command=["python3"],
-        sagemaker_session=sagemaker_local_session,
+        sagemaker_session=sagemaker_local_session_no_local_code,
     )
 
     sklearn_processor.run(
@@ -344,12 +349,12 @@ def test_local_processing_sklearn(sagemaker_local_session, sklearn_latest_versio
 
     job_description = sklearn_processor.latest_job.describe()
 
-    assert len(job_description["ProcessingInputs"]) == 2
+    assert len(job_description["ProcessingInputs"]) == 3
     assert job_description["ProcessingResources"]["ClusterConfig"]["InstanceCount"] == 1
     assert job_description["ProcessingResources"]["ClusterConfig"]["InstanceType"] == "local"
     assert job_description["AppSpecification"]["ContainerEntrypoint"] == [
-        "python3",
-        "/opt/ml/processing/input/code/dummy_script.py",
+        "/bin/bash",
+        "/opt/ml/processing/input/entrypoint/runproc.sh",
     ]
     assert job_description["RoleArn"] == "<no_role>"
 

tests/unit/test_processing.py

@@ -31,6 +31,7 @@
 )
 from sagemaker.sklearn.processing import SKLearnProcessor
 from sagemaker.pytorch.processing import PyTorchProcessor
+from sagemaker.utils import get_config_value
 from sagemaker.xgboost.processing import XGBoostEstimator
 from sagemaker.network import NetworkConfig
 from sagemaker.processing import FeatureStoreOutput
@@ -161,6 +162,20 @@ def test_sklearn_with_all_parameters(
     sagemaker_session.process.assert_called_with(**expected_args)
 
 
+
+def test_local_mode_disables_local_code_by_default(sklearn_latest_version):
+    processor = SKLearnProcessor(
+        framework_version=sklearn_latest_version,
+        role=ROLE,
+        instance_count=1,
+        instance_type="local",
+    )
+
+    # Most tests use a fixture for sagemaker_session for consistent behaviour, so this unit test
+    # checks that the default initialization disables unsupported 'local_code' mode:
+    assert not get_config_value("local.local_code", processor.sagemaker_session.config)
+
+
 @patch("sagemaker.utils._botocore_resolver")
 @patch("os.path.exists", return_value=True)
 @patch("os.path.isfile", return_value=True)