feat: add Azure AI Foundry support to Anthropic provider

[roomote-v0]

This PR attempts to address Issue #9940. Feedback and guidance are welcome!

Summary

This PR adds first-class Azure AI Foundry support to the Anthropic provider, allowing users to use Claude models deployed on Azure AI Foundry with custom deployment names.

Changes

• Added new configuration options to ProviderSettings:

  • anthropicUseAzureFoundry: Enable Azure AI Foundry mode
  • anthropicAzureDeploymentName: Override model ID with Azure deployment name

• Updated AnthropicHandler to:

  • Use the Azure deployment name as the model ID when Azure Foundry mode is enabled
  • Maintain model capabilities and pricing info while using custom deployment names
  • Support both regular Anthropic API and Azure Foundry endpoints

• Added comprehensive tests for Azure Foundry functionality

How it works

When Azure Foundry mode is enabled and a deployment name is provided:

1. The handler uses the deployment name as the model ID in API requests
2. Model capabilities (context window, max tokens, etc.) are preserved from the selected model
3. The existing anthropicBaseUrl and anthropicUseAuthToken options handle the Azure endpoint and authentication

Example configuration

For Azure AI Foundry with Claude Opus 4.5:

• Provider: Anthropic
• ✅ Use custom base URL: https://my-resource.services.ai.azure.com/anthropic
• ✅ Use Azure AI Foundry: enabled
• ✅ Use auth token for API key: enabled (sends as x-api-key)
• API key: [Azure Foundry API key]
• Azure Deployment Name: claude-opus-4-5
• Model: Select any Claude model (will be overridden by deployment name)

Testing

• All existing Anthropic provider tests pass
• Added new test suite specifically for Azure Foundry functionality
• Tests cover deployment name override, auth token usage, and various model configurations

Fixes #9940

[roomote-v0]

Rooviewer   See task on Roo Cloud

Review complete. No issues found.

• Provider settings schema changes
• AnthropicHandler Azure Foundry logic
• Test coverage

_{Mention @roomote in a comment to request specific changes to this pull request or fix all unresolved issues.}