Added new multi model prompt executor for azure multi-models workflows

[kchojnackiAllegro]

I created multi-model executor for Azure purposes.
Azure Service has different strategy than other ai providers. You deploy some model and use it. Below is example base-uri for deployment:
https://<your-project>.openai.azure.com/openai/deployments/gpt-4o/
The llm model parameter is ignored and response is always from deployed model.

Motivation and Context

I want to use 2 different models in my strategy/action e.g 4.1-mini for small and simple actions and gpt-4o for summarize and return to user.

I can create subgraph with small model 41-mini parameter but on azure provider this model from request is ignored. I can use only model which I put to base-uri in client. So I have to deploy multiple OpenAI clients on azure and create multiple AIClients in koog.

Breaking Changes

There is no breaking changes. I added new executor for specific cases.
Created new multi-model prompt executor - similar to MulitLLMPrompExecutor. With key in map LLMModel not LLMProvider.

---

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
• CI/CD changes
• Dependencies update

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