feat: Add A2A Multi-Agent Demo Notebook with Setup Modifications

[kevincogan]

Description

This Pull Request introduces a new Agent-to-Agent (A2A) Multi-Agent Notebook Demo. This notebook guides users through setting up, launching, and interacting with a multi-agent system using Llama Stack.

Key changes include:

• New Multi-Agent Demo Notebook: Added a Jupyter notebook (A2A_Multi_Agent.ipynb) that demonstrates A2A protocol communication between an orchestrator, custom tool agents, and a composition agent.
• Added A2A Agent Server Code: Replaced and added new A2A server implementations for the planner, custom tools, and composer agents, enabling the multi-agent demo functionality. These updates include configuration via environment variables for remote instances and inference models.
• Dependency and Prerequisite Updates: Modified required installations to include packages like llama_stack_client, and dotenv, ensuring the notebook runs smoothly out of the box. The Python version requirement has also been updated in the documentation to python_requires >= 3.13.

How Has This Been Tested?

The new A2A_Multi_Agent.ipynb notebook was executed end-to-end in a local environment.

• Verified that all required packages installed successfully.
• Confirmed that the A2A orchestrator and skill agents (custom tools, composer) launched correctly and were reachable.
• Validated the multi-agent task flow (planning, execution, and composition) by running example queries within the notebook and inspecting the generated responses.
• Ensured that agent communication and tool execution functioned as expected.

Merge criteria:

• The commits are squashed in a cohesive manner and have meaningful messages.
• Testing instructions have been added in the PR body (for PRs involving changes that are not immediately obvious).
• The developer has manually tested the changes and verified that the changes work