Parse tool usage in Bedrock Anthropic streaming

[nathaniellombardi-toast]

Updates how Bedrock Anthropic responses are parsed to include tool usage. It reuses the logic from the Anthropic LLM client. As a result, this PR also has a couple of additional effects:

• Enforcing snake case for properties in Bedrock Anthropic responses
• Changes how other non-Anthropic Bedrock providers are handled

One thing I noticed is that the Bedrock Anthropic implementation uses a mix of data classes from its own implementation and from prompt-executor-anthropic-client for requests and responses. As a follow-up, another pass on what needs to be separate and what can be re-used from the Anthropic module should be done.

This should resolve KG-627.

Motivation and Context

Tool usage is missing when using Anthropic models with streaming in Bedrock.

Breaking Changes

---

Type of the changes

• New feature (non-breaking change which adds functionality)
• Bug fix (non-breaking change which fixes an issue)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update
• Tests improvement
• Refactoring

Checklist

• The pull request has a description of the proposed change
• I read the Contributing Guidelines before opening the pull request
• The pull request uses develop as the base branch
• Tests for the changes have been added
• All new and existing tests passed

Additional steps for pull requests adding a new feature

• An issue describing the proposed change exists
• The pull request includes a link to the issue
• The change was discussed and approved in the issue
• Docs have been added / updated