Add support for Anthropic Claude models via Google Vertex AI

[SrikarMannepalli]

Why are these changes needed?

This PR adds support for Anthropic Claude models via Google Vertex AI by introducing AnthropicVertexChatCompletionClient.

Background

While AutoGen already supports Anthropic Claude models through:

• Direct API (AnthropicChatCompletionClient)
• AWS Bedrock (AnthropicBedrockChatCompletionClient)

This PR add support for accessing Claude models through Vertex AI.

Changes Made

1. New Client Class: AnthropicVertexChatCompletionClient following the same pattern as the existing Bedrock client
2. Configuration Types: Added VertexInfo and related config models for GCP project/region configuration
3. Tests: Added 11 comprehensive test cases covering initialization, serialization, config conversion, and mocked API calls
4. Documentation: Added docstrings with usage examples and configuration loading patterns

Implementation Details

• Uses Anthropic's official AsyncAnthropicVertex client
• Requires project_id and region via VertexInfo configuration
• Maintains consistency with existing AutoGen model client patterns
• Supports all standard Claude model capabilities (vision, function calling, streaming)

Usage Example

from autogen_ext.models.anthropic import AnthropicVertexChatCompletionClient, VertexInfo

client = AnthropicVertexChatCompletionClient(
    model="claude-3-sonnet-20240229",
    vertex_info=VertexInfo(
        project_id="your-gcp-project-id",
        region="us-east5"
    )
)

Checks

• I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 81.30%. Comparing base (13e144e) to head (dc93a88).

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #7097      +/-   ##
==========================================
+ Coverage   81.22%   81.30%   +0.07%     
==========================================
  Files         244      244              
  Lines       18512    18564      +52     
==========================================
+ Hits        15036    15093      +57     
+ Misses       3476     3471       -5     

Flag	Coverage Δ
unittests	81.30% <100.00%> (+0.07%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[SrikarMannepalli]

Hi @ekzhu,
This change introduces support for Anthropic Claude models via Google Vertex AI along with tests.
I kindly request you to review the PR whenever you get a chance. Please let me know if there are any additional adjustments or clarifications you’d like.
Thanks so much for your time 🙏