feat: add configurable allow_parallel_tool_calls to FunctionAgent

[yarikama]

Description

This PR adds a configurable allow_parallel_tool_calls parameter to the FunctionAgent class. Previously, parallel tool calls were always enabled (hardcoded to True), which could cause issues in certain scenarios. This change allows users to disable parallel tool calls when needed while maintaining backward compatibility.

Motivation

When allow_parallel_tool_calls is always set to True, it can cause unexpected behavior or errors in some use cases, such as:

• When tools have dependencies on each other's execution order
• When the LLM model doesn't properly handle parallel tool calls
• When debugging tool execution flow

By making this parameter configurable, users can choose the appropriate behavior for their specific use case.

Changes

• Add allow_parallel_tool_calls parameter to FunctionAgent class with Pydantic Field
• Default to True for backward compatibility
• Update astream_chat_with_tools call to use instance parameter
• Add descriptive documentation for the parameter

New Package?

Did I fill in the tool.llamahub section in the pyproject.toml and provide a detailed README.md for my new integration or package?

• Yes
• No

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

• Yes
• No (core package)

Type of Change

Please delete options that are not relevant.

• New feature (non-breaking change which adds functionality)

How Has This Been Tested?

Your pull-request will likely not be merged unless it is covered by some form of impactful unit testing.

• I added new unit tests to cover this change
• I believe this change is already covered by existing unit tests

Usage Example

# Default behavior (parallel tool calls enabled)
agent = FunctionAgent(
    name="my_agent",
    llm=llm,
    tools=tools
)

# Disable parallel tool calls
agent = FunctionAgent(
    name="my_agent",
    llm=llm,
    tools=tools,
    allow_parallel_tool_calls=False
)

Suggested Checklist:

• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added Google Colab support for the newly added notebooks.
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I ran uv run make format; uv run make lint to appease the lint gods