Python: Handle agent user input request in AgentExecutor

[TaoChenOSU]

Motivation and Context

Closes: #1799

Description

This PR adds the following:

1. Allow agent executor to surface requests from the underlying agent to the workflow
2. Add a sample to demonstrate
3. Add unit tests

Contribution Checklist

• The code builds clean without any errors or warnings
• The PR follows the Contribution Guidelines
• All unit tests pass, and I have added new tests where possible
• Is this a breaking change? If yes, add "[BREAKING]" prefix to the title of the PR.

[Copilot]

Pull Request Overview

This PR adds support for function approval requests in agent workflows, allowing AI functions to require human approval before execution. The implementation includes both streaming and non-streaming modes with proper state checkpointing.

Key changes:

• Extended AgentExecutor to handle function approval requests from agents and pause execution until approvals are received
• Added checkpoint/restore support for pending approval requests and responses
• Implemented comprehensive test coverage for approval workflows in both streaming and non-streaming modes

Reviewed Changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 4 comments.

File	Description
python/packages/core/agent_framework/_workflows/_agent_executor.py	Added response handler for function approvals, checkpoint support for pending requests/responses, and refactored agent execution to handle user input requests
python/packages/core/tests/workflow/test_agent_executor_tool_calls.py	Added 4 new tests covering approval workflows in streaming/non-streaming modes with single and parallel tool calls
python/packages/core/tests/workflow/test_agent_executor.py	Added assertion to verify checkpoint includes pending agent requests and responses
python/samples/getting_started/workflows/human-in-the-loop/agents_with_approval_requests.py	Added comprehensive sample demonstrating email workflow with approval requests for reading historical data and sending emails

[markwallace-microsoft]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
packages/core/agent_framework/_workflows
_agent_executor.py	146	26	82%	86, 98–100, 125–126, 128–129, 144–145, 195–196, 198, 202, 232–234, 244–246, 248, 252, 256, 260–261, 281
TOTAL	13075	1923	85%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
1744	107 💤	0 ❌	0 🔥	35.140s ⏱️