feat(train): add the interactive Training Sessions client surface (#6452)

Adds the interactive Training Sessions client surface to sagemaker-train.

* ServiceClient / TrainingClient / SamplingClient, exposed lazily from
  sagemaker.train
* Typed request and result models, futures, and exception hierarchy
* Session lifecycle management with refcounted handles and idempotent stop
* Reference docs for the new modules under docs/api/sagemaker_train.rst
* A "tokenizer" extra for the optional transformers dependency that
  get_tokenizer() needs

The clients call the Training Sessions control plane and runtime through
boto3, both of which are available in the public botocore release, so no
vendored service models ship in the wheel.

Co-authored-by: Xichao Wang <xichao@amazon.com>

Author: 992X

docs/api/sagemaker_train.rst

@@ -39,6 +39,44 @@ Multi-Turn RL Training
    :undoc-members:
    :show-inheritance:
 
+Interactive Training Sessions
+-----------------------------
+
+.. automodule:: sagemaker.train.training_session
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+.. automodule:: sagemaker.train.training_session.service_client
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+.. automodule:: sagemaker.train.training_session.training_client
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+.. automodule:: sagemaker.train.training_session.sampling_client
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+.. automodule:: sagemaker.train.training_session.types
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+.. automodule:: sagemaker.train.training_session.futures
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+.. automodule:: sagemaker.train.training_session.exceptions
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
 Model Evaluation
 ----------------
 

sagemaker-train/pyproject.toml

@@ -53,6 +53,7 @@ Homepage = "https://github.com/aws/sagemaker-python-sdk"
 [project.optional-dependencies]
 rft-strands = ["strands-agents"]
 rft-langchain = ["httpx>=0.24.0"]
+tokenizer = ["transformers"]
 test = [
     "pytest",
     "pytest-cov",
@@ -63,7 +64,8 @@ test = [
     "scipy",
     "omegaconf",
     "graphene",
-    "IPython"
+    "IPython",
+    "transformers",
 ]
 notebook = [
     "ipywidgets>=8.0.0",

sagemaker-train/src/sagemaker/train/__init__.py

@@ -158,4 +158,16 @@ def __getattr__(name):
         from sagemaker.train.common_utils.finetune_utils import list_hyperparameters
 
         return list_hyperparameters
+    elif name == "ServiceClient":
+        from sagemaker.train.training_session import ServiceClient
+
+        return ServiceClient
+    elif name == "TrainingClient":
+        from sagemaker.train.training_session import TrainingClient
+
+        return TrainingClient
+    elif name == "SamplingClient":
+        from sagemaker.train.training_session import SamplingClient
+
+        return SamplingClient
     raise AttributeError(f"module '{__name__}' has no attribute '{name}'")