gopidesupavan opened a new pull request, #70087:
URL: https://github.com/apache/airflow/pull/70087
This PR adds an `AWSToolset` for `common.ai` agents.
AWS has a very large API surface, so this is intentionally not implemented
as one toolset per AWS service. Instead, the toolset uses botocore’s local
service models to provide a scalable AWS services interface with configured
operation access.
The toolset exposes three agent tools:
- `list_aws_operations` lists the AWS operations configured for this agent.
- `describe_aws_operation` shows the input and output shape for an operation
before the agent calls it.
- `call_aws` executes a configured operation and returns a bounded JSON
response.
Dag authors configure the exact operations the agent may call through
`allowed_actions`, for example:
```python
AWSToolset(
aws_conn_id="aws_default",
allowed_actions=[
"s3:ListBuckets",
"s3:ListObjectsV2",
"athena:StartQueryExecution",
"athena:GetQueryResults",
],
)
```
Credentials, region, and AWS session configuration come from Airflow’s AWS
connection via the Amazon provider. They are not model-controlled tool
arguments.
The toolset also avoids matching credential- or secret-returning APIs
through wildcards. Those operations must be listed explicitly, and
least-privilege IAM on the AWS connection remains the real security boundary.
<!-- SPDX-License-Identifier: Apache-2.0
https://www.apache.org/licenses/LICENSE-2.0 -->
<!--
Thank you for contributing!
Please provide above a brief description of the changes made in this pull
request.
Write a good git commit message following this guide:
http://chris.beams.io/posts/git-commit/
Please make sure that your code changes are covered with tests.
And in case of new features or big changes remember to adjust the
documentation.
For user-facing UI changes, please attach before/after screenshots (or a
short
screen recording) so reviewers can assess the visual impact.
Feel free to ping (in general) for the review if you do not see reaction for
a few days
(72 Hours is the minimum reaction time you can expect from volunteers) - we
sometimes miss notifications.
In case of an existing issue, reference it using one of the following:
* closes: #ISSUE
* related: #ISSUE
-->
---
##### Was generative AI tooling used to co-author this PR?
<!--
If generative AI tooling has been used in the process of authoring this PR,
please
change below checkbox to `[X]` followed by the name of the tool, uncomment
the "Generated-by".
-->
- [ ] Yes (please specify the tool below)
<!--
Generated-by: [Tool Name] following [the
guidelines](https://github.com/apache/airflow/blob/main/contributing-docs/05_pull_requests.rst#gen-ai-assisted-contributions)
-->
---
* Read the **[Pull Request
Guidelines](https://github.com/apache/airflow/blob/main/contributing-docs/05_pull_requests.rst#pull-request-guidelines)**
for more information. Note: commit author/co-author name and email in commits
become permanently public when merged.
* For fundamental code changes, an Airflow Improvement Proposal
([AIP](https://cwiki.apache.org/confluence/display/AIRFLOW/Airflow+Improvement+Proposals))
is needed.
* When adding dependency, check compliance with the [ASF 3rd Party License
Policy](https://www.apache.org/legal/resolved.html#category-x).
* For significant user-facing changes create newsfragment:
`{pr_number}.significant.rst`, in
[airflow-core/newsfragments](https://github.com/apache/airflow/tree/main/airflow-core/newsfragments).
You can add this file in a follow-up commit after the PR is created so you
know the PR number.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
