test(train): Stop MTRL training integ tests churning fixture MPG

sagemaker-train/tests/integ/train/test_mtrl_evaluator_3p_agent.py

@@ -316,8 +316,10 @@ def test_evaluate_with_attached_trainer(self, lambda_agent_arn, test_config):
         """Test evaluating a fine-tuned model by attaching to an existing training job."""
         from sagemaker.train.multi_turn_rl_trainer import MultiTurnRLTrainer
 
+        # Fixture job whose output package is pinned via the `pysdk-ci-protected=true`
+        # tag. Keep in sync with test_mtrl_trainer_integration.py.
         attached_job = MultiTurnRLTrainer.attach(
-            "mock-oss-test-mtrl-20260910094327", session=boto3.Session(region_name=_REGION)
+            "mock-oss-test-mtrl-20260929124814", session=boto3.Session(region_name=_REGION)
         )
 
         evaluator = MultiTurnRLEvaluator(

sagemaker-train/tests/integ/train/test_mtrl_trainer_integration.py

@@ -53,8 +53,10 @@ def _get_account_id():
     # PROD — Main account (729646638167)
     "729646638167": {
         "env_name": "PROD",
-        # "existing_job_name": "mock-oss-test-mtrl-20260611170946",
-        "existing_job_name": "mock-oss-test-mtrl-20260910094327",
+        # Fixture job; its output package (mock-oss-test-mtrl-mpg/219) is pinned via the
+        # `pysdk-ci-protected=true` tag so the CI resource cleaner keeps it.
+        # Keep in sync with test_mtrl_evaluator_3p_agent.py.
+        "existing_job_name": "mock-oss-test-mtrl-20260929124814",
         "base_model": "mock-oss-test",
         "agent_core_arn": "arn:aws:bedrock-agentcore:us-west-2:729646638167:runtime/"
         "sagemaker_rft_prod_gsm8k_streaming-Yk6O377mUS",

sagemaker-train/tests/integ/train/test_multi_turn_rl_trainer_integration.py

@@ -21,6 +21,7 @@
 import time
 
 import boto3
+import botocore.exceptions
 import pytest
 from sagemaker.core.helper.session_helper import Session
 from sagemaker.train.multi_turn_rl_trainer import MultiTurnRLTrainer
@@ -44,6 +45,13 @@ def _get_account_id():
 BASE_MODEL = "mock-oss-test"
 EXISTING_JOB_NAME = "mock-oss-test-mtrl-20260616153024"
 
+# Training jobs in this module register their output into a dedicated scratch group.
+# Without it they fall back to the SDK default ``{BASE_MODEL}-mtrl-mpg``
+# (``mock-oss-test-mtrl-mpg``), which also holds the fixed fixture package that the
+# MTRL evaluator integ tests attach to. Every new version there made the resource
+# cleaner trim (delete) that fixture package.
+TRAIN_OUTPUT_MODEL_PACKAGE_GROUP = f"{BASE_MODEL}-mtrl-train-mpg"
+
 
 @pytest.fixture(scope="module")
 def sagemaker_session():
@@ -52,6 +60,33 @@ def sagemaker_session():
     yield session
 
 
+@pytest.fixture(scope="module")
+def train_output_model_package_group(sagemaker_session):
+    """Get-or-create the scratch output ModelPackageGroup and return its name.
+
+    ``MultiTurnRLTrainer`` only validates an explicitly passed group, so it must
+    exist before the trainer is constructed. Race-safe for concurrent runs: losing
+    the create race ("already exists") is treated as success.
+    """
+    sm_client = sagemaker_session.boto_session.client("sagemaker")
+    try:
+        sm_client.describe_model_package_group(
+            ModelPackageGroupName=TRAIN_OUTPUT_MODEL_PACKAGE_GROUP
+        )
+    except botocore.exceptions.ClientError:
+        try:
+            sm_client.create_model_package_group(
+                ModelPackageGroupName=TRAIN_OUTPUT_MODEL_PACKAGE_GROUP,
+                ModelPackageGroupDescription=(
+                    "Scratch output group for MTRL trainer integ tests (sagemaker-train)"
+                ),
+            )
+        except botocore.exceptions.ClientError as e:
+            if "already exists" not in str(e):
+                raise
+    return TRAIN_OUTPUT_MODEL_PACKAGE_GROUP
+
+
 @pytest.fixture(scope="module")
 def test_resources():
     """Resolve account-specific resource ARNs lazily."""
@@ -69,12 +104,15 @@ def test_resources():
 class TestMultiTurnRLTrainerBedrockAgent:
     """Test MTRL training with Bedrock AgentCore runtime."""
 
-    def test_train_and_wait(self, sagemaker_session, test_resources):
+    def test_train_and_wait(
+        self, sagemaker_session, test_resources, train_output_model_package_group
+    ):
         """Test complete MTRL workflow with Bedrock AgentCore agent."""
         trainer = MultiTurnRLTrainer(
             model=BASE_MODEL,
             agent_env=AGENT_RUNTIME_ID,
             training_dataset=test_resources["s3_input_path"],
+            output_model_package_group=train_output_model_package_group,
             mlflow_app_arn=test_resources["mlflow_arn"],
             s3_output_path=test_resources["s3_output_path"],
             accept_eula=True,
@@ -93,12 +131,15 @@ def test_train_and_wait(self, sagemaker_session, test_resources):
         assert job.output_model_package_arn is not None
         assert job.s3_output_path is not None
 
-    def test_train_and_stop(self, sagemaker_session, test_resources):
+    def test_train_and_stop(
+        self, sagemaker_session, test_resources, train_output_model_package_group
+    ):
         """Test creating and stopping an MTRL job."""
         trainer = MultiTurnRLTrainer(
             model=BASE_MODEL,
             agent_env=AGENT_RUNTIME_ID,
             training_dataset=test_resources["s3_input_path"],
+            output_model_package_group=train_output_model_package_group,
             mlflow_app_arn=test_resources["mlflow_arn"],
             accept_eula=True,
             sagemaker_session=sagemaker_session,
@@ -121,12 +162,15 @@ def test_train_and_stop(self, sagemaker_session, test_resources):
 class TestMultiTurnRLTrainerLambdaAgent:
     """Test MTRL training with Lambda agent."""
 
-    def test_train_with_lambda_arn(self, sagemaker_session, test_resources):
+    def test_train_with_lambda_arn(
+        self, sagemaker_session, test_resources, train_output_model_package_group
+    ):
         """Test MTRL workflow using an existing Lambda ARN as agent."""
         trainer = MultiTurnRLTrainer(
             model=BASE_MODEL,
             agent_env=test_resources["lambda_arn"],
             training_dataset=test_resources["s3_input_path"],
+            output_model_package_group=train_output_model_package_group,
             mlflow_app_arn=test_resources["mlflow_arn"],
             s3_output_path=test_resources["s3_output_path"],
             accept_eula=True,