Revert AWS services toolset for common AI provider

dev/breeze/doc/images/output_release-management_classify-provider-changes.txt

@@ -1 +1 @@
-3d2a0b7552829f49477890b293207a4c
+4cac13b21eee8b732a46c5a15aec7a4b

dev/breeze/doc/images/output_release-management_generate-issue-content-providers.txt

@@ -1 +1 @@
-abd6c12fe888796a153522495b802278
+bd80bf2dd63a27111b8c5745df5dfb86

dev/breeze/doc/images/output_release-management_generate-providers-metadata.txt

@@ -1 +1 @@
-010c3a7215ff699933b21bf4e5787fcb
+5865810f5a4b12c9199267b7dd6459b3

dev/breeze/doc/images/output_release-management_prepare-provider-distributions.txt

@@ -1 +1 @@
-e8af9b706de3926a3297a6c1114d7e5c
+a27c1726f5902e5fdb501ecdee226476

dev/breeze/doc/images/output_release-management_prepare-provider-documentation.txt

@@ -1 +1 @@
-33f340084282725cf473d84c59e2d63f
+c33a2f6d00a3a8dbec8b56c1c2d88d54

dev/breeze/tests/test_selective_checks.py

@@ -1121,7 +1121,7 @@ def assert_outputs_are_printed(expected_outputs: dict[str, str], stderr: str):
         pytest.param(
             ("providers/amazon/src/airflow/providers/amazon/provider.yaml",),
             {
-                "selected-providers-list-as-string": "amazon apache.hive cncf.kubernetes common.ai "
+                "selected-providers-list-as-string": "amazon apache.hive cncf.kubernetes "
                 "common.compat common.messaging common.sql databricks exasol ftp google http imap microsoft.azure "
                 "mongo mysql openlineage postgres salesforce ssh teradata",
                 "all-python-versions": f"['{DEFAULT_PYTHON_MAJOR_MINOR_VERSION}']",
@@ -1148,9 +1148,9 @@ def assert_outputs_are_printed(expected_outputs: dict[str, str], stderr: str):
                         {
                             "description": "amazon...google",
                             "test_types": "Providers[amazon] Providers[apache.hive,cncf.kubernetes,"
-                            "common.ai,common.compat,common.messaging,common.sql,databricks,exasol,ftp,"
-                            "http,imap,microsoft.azure,mongo,mysql,openlineage,postgres,salesforce,ssh,"
-                            "teradata] Providers[google]",
+                            "common.compat,common.messaging,common.sql,databricks,exasol,ftp,http,imap,"
+                            "microsoft.azure,mongo,mysql,openlineage,postgres,salesforce,ssh,teradata] "
+                            "Providers[google]",
                         }
                     ]
                 ),
@@ -1193,7 +1193,7 @@ def assert_outputs_are_printed(expected_outputs: dict[str, str], stderr: str):
         pytest.param(
             ("providers/amazon/src/airflow/providers/amazon/file.py",),
             {
-                "selected-providers-list-as-string": "amazon apache.hive cncf.kubernetes common.ai "
+                "selected-providers-list-as-string": "amazon apache.hive cncf.kubernetes "
                 "common.compat common.messaging common.sql databricks exasol ftp google http imap microsoft.azure "
                 "mongo mysql openlineage postgres salesforce ssh teradata",
                 "all-python-versions": f"['{DEFAULT_PYTHON_MAJOR_MINOR_VERSION}']",
@@ -1217,9 +1217,9 @@ def assert_outputs_are_printed(expected_outputs: dict[str, str], stderr: str):
                         {
                             "description": "amazon...google",
                             "test_types": "Providers[amazon] Providers[apache.hive,cncf.kubernetes,"
-                            "common.ai,common.compat,common.messaging,common.sql,databricks,exasol,ftp,"
-                            "http,imap,microsoft.azure,mongo,mysql,openlineage,postgres,salesforce,ssh,"
-                            "teradata] Providers[google]",
+                            "common.compat,common.messaging,common.sql,databricks,exasol,ftp,http,imap,"
+                            "microsoft.azure,mongo,mysql,openlineage,postgres,salesforce,ssh,teradata] "
+                            "Providers[google]",
                         }
                     ]
                 ),

providers/common/ai/docs/examples.rst

@@ -69,9 +69,7 @@ Agents & tools
        `example_agent_capabilities.py <https://github.com/apache/airflow/blob/providers-common-ai/|version|/providers/common/ai/src/airflow/providers/common/ai/example_dags/example_agent_capabilities.py>`__).
    * - :ref:`Toolsets <howto/toolsets>`
      - Loading ``SKILL.md`` Agent Skills
-       (`example_agent_skills.py <https://github.com/apache/airflow/blob/providers-common-ai/|version|/providers/common/ai/src/airflow/providers/common/ai/example_dags/example_agent_skills.py>`__),
-       allow-listed AWS API access via ``AWSToolset``
-       (`example_aws_toolset.py <https://github.com/apache/airflow/blob/providers-common-ai/|version|/providers/common/ai/src/airflow/providers/common/ai/example_dags/example_aws_toolset.py>`__),
+       (`example_agent_skills.py <https://github.com/apache/airflow/blob/providers-common-ai/|version|/providers/common/ai/src/airflow/providers/common/ai/example_dags/example_agent_skills.py>`__)
        and exposing an Airflow toolset to a LangChain agent, the reverse bridge
        (`example_langchain_toolset_bridge.py <https://github.com/apache/airflow/blob/providers-common-ai/|version|/providers/common/ai/src/airflow/providers/common/ai/example_dags/example_langchain_toolset_bridge.py>`__).
    * - :doc:`connections/mcp`

providers/common/ai/docs/index.rst

@@ -217,13 +217,12 @@ You can install such cross-provider dependencies when installing from PyPI. For
 
 .. code-block:: bash
 
-    pip install apache-airflow-providers-common-ai[amazon]
+    pip install apache-airflow-providers-common-ai[common.sql]
 
 
 ============================================================================================================  ==============
 Dependent package                                                                                             Extra
 ============================================================================================================  ==============
-`apache-airflow-providers-amazon <https://airflow.apache.org/docs/apache-airflow-providers-amazon>`_          ``amazon``
 `apache-airflow-providers-common-sql <https://airflow.apache.org/docs/apache-airflow-providers-common-sql>`_  ``common.sql``
 `apache-airflow-providers-git <https://airflow.apache.org/docs/apache-airflow-providers-git>`_                ``git``
 ============================================================================================================  ==============
@@ -253,14 +252,12 @@ Extra           Dependencies
 ``avro``        ``fastavro>=1.10.0; python_version < "3.14"``, ``fastavro>=1.12.1; python_version >= "3.14"``
 ``parquet``     ``pyarrow>=18.0.0; python_version < '3.14'``, ``pyarrow>=22.0.0; python_version >= '3.14'``
 ``sql``         ``apache-airflow-providers-common-sql>=1.33.0``, ``sqlglot>=30.0.0``
-``aws``         ``apache-airflow-providers-amazon>=9.0.0``
 ``common.sql``  ``apache-airflow-providers-common-sql>=1.33.0``
 ``langchain``   ``langchain>=1.0.0``
 ``llamaindex``  ``dataclasses-json>=0.6.7``, ``llama-index-core>=0.13.0``, ``llama-index-embeddings-openai>=0.6.0``, ``llama-index-llms-openai>=0.6.0``
 ``pdf``         ``pypdf>=4.0.0``
 ``docx``        ``python-docx>=1.0.0``
 ``git``         ``apache-airflow-providers-git``
-``amazon``      ``apache-airflow-providers-amazon``
 ==============  =======================================================================================================================================
 
 Downloading official packages

providers/common/ai/docs/toolsets.rst

@@ -24,20 +24,17 @@ Airflow's 350+ provider hooks already have typed methods, rich docstrings,
 and managed credentials. Toolsets expose them as pydantic-ai tools so that
 LLM agents can call them during multi-turn reasoning.
 
-Four toolsets are included:
+Three toolsets are included:
 
-- :class:`~airflow.providers.common.ai.toolsets.aws.AWSToolset` — configured
-  AWS services toolset for agent access to AWS APIs through Airflow-managed
-  AWS connections.
 - :class:`~airflow.providers.common.ai.toolsets.hook.HookToolset` — generic
   adapter for any Airflow Hook.
+- :class:`~airflow.providers.common.ai.toolsets.sql.SQLToolset` — curated
+  4-tool database toolset.
 - :class:`~airflow.providers.common.ai.toolsets.mcp.MCPToolset` — connect to
   `MCP servers <https://modelcontextprotocol.io/>`__ configured via Airflow
   connections.
-- :class:`~airflow.providers.common.ai.toolsets.sql.SQLToolset` — curated
-  4-tool database toolset.
 
-All four implement pydantic-ai's
+All three implement pydantic-ai's
 `AbstractToolset <https://ai.pydantic.dev/toolsets/>`__ interface and can be
 passed to any pydantic-ai ``Agent``, including via
 :class:`~airflow.providers.common.ai.operators.agent.AgentOperator`.
@@ -271,69 +268,6 @@ Parameters
   support DDL for in-memory tables; this guard blocks those by default.
 - ``max_rows``: Maximum rows returned from the ``query`` tool. Default ``50``.
 
-``AWSToolset``
---------------
-
-Curated toolset that gives an agent allow-listed access to AWS APIs with
-three tools:
-
-.. list-table::
-   :header-rows: 1
-   :widths: 20 50
-
-   * - Tool
-     - Description
-   * - ``list_aws_operations``
-     - Lists the operations the toolset allows, grouped by service
-   * - ``describe_aws_operation``
-     - Returns an operation's parameter and response shapes (from the
-       botocore service model), so the agent can check what a call expects
-       before making it
-   * - ``call_aws``
-     - Executes an allowed operation and returns the response as JSON,
-       aggregating paginated results
-
-Credentials, region, and session configuration come from the Airflow
-connection (``aws_conn_id``) via the amazon provider — the model cannot
-override them through tool arguments. Requires the ``aws`` extra::
-
-    pip install "apache-airflow-providers-common-ai[aws]"
-
-.. exampleinclude:: /../../ai/src/airflow/providers/common/ai/example_dags/example_aws_toolset.py
-    :language: python
-    :start-after: [START howto_operator_agent_aws]
-    :end-before: [END howto_operator_agent_aws]
-
-Access is deny-by-default: ``allowed_actions`` is required and supports ``*``
-wildcards in the operation part only (``"athena:*"``, ``"s3:List*"``).
-Operations that return credentials or decrypted secrets — ``sts:AssumeRole``,
-``secretsmanager:GetSecretValue``, ``kms:Decrypt``, and similar — are never
-matched by a wildcard and must be listed verbatim to be callable.
-
-.. warning::
-    ``allowed_actions`` bounds what the agent can ask for, not what the
-    credentials can do. Point ``aws_conn_id`` at a least-privilege IAM role
-    scoped to the same operations.
-
-Parameters
-^^^^^^^^^^
-
-- ``aws_conn_id``: Airflow connection ID for AWS credentials. Default
-  ``aws_default``.
-- ``allowed_actions``: Operations the agent may call, in
-  ``"<service>:<Operation>"`` form using boto3 service names and API
-  operation names. Required — there is no auto-discovery. Matching is case-
-  and underscore-insensitive, so ``"s3:list_buckets"`` equals
-  ``"s3:ListBuckets"``. Validated against botocore's bundled service
-  definitions at instantiation time (local metadata only — no network, no
-  credentials).
-- ``region_name``: AWS region for API calls. Default ``None`` — use the
-  region configured on the connection.
-- ``max_items``: Upper bound on items aggregated from paginated operations.
-  Default ``1000``.
-- ``max_output_bytes``: Upper bound on the serialized response returned to
-  the agent; larger payloads are clipped and flagged. Default ``65536``.
-
 ``LoggingToolset``
 ------------------
 

providers/common/ai/provider.yaml

@@ -21,7 +21,7 @@ name: Common AI
 description: |
   AI/LLM hooks and operators for Airflow pipelines using `pydantic-ai <https://ai.pydantic.dev/>`__.
 
-state: not-ready
+state: ready
 lifecycle: incubation
 source-date-epoch: 1784746595
 build-system: hatchling
@@ -455,7 +455,6 @@ operators:
 toolsets:
   - integration-name: Common AI
     python-modules:
-      - airflow.providers.common.ai.toolsets.aws
       - airflow.providers.common.ai.toolsets.hook
       - airflow.providers.common.ai.toolsets.sql
       - airflow.providers.common.ai.toolsets.datafusion

providers/common/ai/pyproject.toml

@@ -108,11 +108,6 @@ dependencies = [
     "apache-airflow-providers-common-sql>=1.33.0",
     "sqlglot>=30.0.0",
 ]
-# AWSToolset: allow-listed AWS API access for agents. The amazon provider
-# supplies credential resolution (AwsBaseHook) and brings boto3/botocore.
-"aws" = [
-    "apache-airflow-providers-amazon>=9.0.0",
-]
 "common.sql" = [
     "apache-airflow-providers-common-sql>=1.33.0"
 ]
@@ -130,16 +125,12 @@ dependencies = [
 "git" = [
     "apache-airflow-providers-git"
 ]
-"amazon" = [
-    "apache-airflow-providers-amazon"
-]
 
 [dependency-groups]
 dev = [
     "apache-airflow",
     "apache-airflow-task-sdk",
     "apache-airflow-devel-common",
-    "apache-airflow-providers-amazon",
     "apache-airflow-providers-common-compat",
     "apache-airflow-providers-common-sql",
     "apache-airflow-providers-git",

providers/common/ai/src/airflow/providers/common/ai/toolsets/__init__.py

@@ -20,7 +20,7 @@
 
 from airflow.providers.common.ai.toolsets.hook import HookToolset
 
-__all__ = ["AWSToolset", "HookToolset", "MCPToolset", "SQLToolset", "airflow_toolset_to_langchain_tools"]
+__all__ = ["HookToolset", "MCPToolset", "SQLToolset", "airflow_toolset_to_langchain_tools"]
 
 
 def __getattr__(name: str):
@@ -46,12 +46,4 @@ def __getattr__(name: str):
 
             raise AirflowOptionalProviderFeatureException(e)
         return MCPToolset
-    if name == "AWSToolset":
-        try:
-            from airflow.providers.common.ai.toolsets.aws import AWSToolset
-        except ImportError as e:
-            from airflow.providers.common.compat.sdk import AirflowOptionalProviderFeatureException
-
-            raise AirflowOptionalProviderFeatureException() from e
-        return AWSToolset
     raise AttributeError(f"module {__name__!r} has no attribute {name!r}")