mirror of https://github.com/microsoft/semantic-kernel.git synced 2026-10-12 02:19:06 +00:00

Files

T

History

SergeyMenshykhandCopilot 58f4a66858 Python: Improve function call invocation parameter consistency (#14014 )

## Description

This PR improves the consistency of how the function_behavior parameter
is passed through internal invoke_function_call callsites.

### Changes

- Thread function_behavior parameter through all internal
invoke_function_call callsites for consistent parameter handling:
  - Realtime connector (_open_ai_realtime.py)
  - Responses agent (responses_agent_thread_actions.py)
  - Assistant agent (assistant_thread_actions.py)
  - Azure AI agent (agent_thread_actions.py)
  - Bedrock agent (bedrock_agent.py)
- Add defensive logging in kernel.py when function_behavior is not
provided
- Add unit tests covering parameter handling scenarios

### Testing

- All existing tests pass (678 passed, 0 failed)
- 5 new tests added covering the updated parameter handling

Co-authored-by: Copilot <[email protected]>

2026-05-18 09:55:00 +00:00

models

Python: Introduce feature decorator to allow for experimental and release candidate decorator usage (#10691 )

2025-02-27 00:17:54 +00:00

__init__.py

Python: Bedrock agent (#10307 )

2025-01-31 19:44:39 +00:00

action_group_utils.py

Python: Bedrock agent (#10307 )

2025-01-31 19:44:39 +00:00

bedrock_agent_base.py

Python: Update Agent invoke abstraction parameters (#11192 )

2025-03-25 23:16:34 +00:00

bedrock_agent_settings.py

Python: Move to a thinner wrap for Bedrock Agent in Python (#10740 )

2025-03-03 22:07:41 +00:00

bedrock_agent.py

Python: Improve function call invocation parameter consistency (#14014 )

2026-05-18 09:55:00 +00:00

README.md

Python: Bedrock agent (#10307 )

2025-01-31 19:44:39 +00:00

README.md

Amazon Bedrock AI Agents in Semantic Kernel

Overview

AWS Bedrock Agents is a managed service that allows users to stand up and run AI agents in the AWS cloud quickly.

Tools/Functions

Bedrock Agents allow the use of tools via action groups.

The integration of Bedrock Agents with Semantic Kernel allows users to register kernel functions as tools in Bedrock Agents.

Enable code interpretation

Bedrock Agents can write and execute code via a feature known as code interpretation similar to what OpenAI also offers.

Enable user input

Bedrock Agents can request user input in case of missing information to invoke a tool. When this is enabled, the agent will prompt the user for the missing information. When this is disabled, the agent will guess the missing information.

Knowledge base

Bedrock Agents can leverage data saved on AWS to perform RAG tasks, this is referred to as the knowledge base in AWS.

Multi-agent

Bedrock Agents support multi-agent workflows for more complex tasks. However, it employs a different pattern than what we have in Semantic Kernel, thus this is not supported in the current integration.