Add token usage tracking

[ali-sedaghatbaf]

Description

This pull request enhances the LLM response handling across all supported providers by adding token usage tracking. The LLMResponse objects returned by each LLM now include an optional usage field that provides detailed token counts for requests and responses. This enables better monitoring and analysis of LLM costs and performance.

• Introduced the LLMUsage type and updated imports and __all__ in src/neo4j_graphrag/llm/__init__.py to expose it across the package.
• Updated all LLM provider modules (anthropic_llm.py, bedrock_llm.py, cohere_llm.py, mistralai_llm.py, ollama_llm.py, openai_llm.py) to extract token usage information from their respective API responses and include it in the LLMResponse via the new usage parameter.
• Ensured that all synchronous and asynchronous invocation methods for each provider now consistently attach usage data to the response, or None if unavailable, paving the way for uniform downstream handling and analytics.

Type of Change

• New feature
• Bug fix
• Breaking change
• Documentation update
• Project configuration change

Complexity

Complexity: low

How Has This Been Tested?

• Unit tests
• E2E tests
• Manual tests

Checklist

The following requirements should have been met (depending on the changes in the branch):

• Documentation has been updated
• Unit tests have been updated
• E2E tests have been updated
• Examples have been updated
• New files have copyright header
• CLA (https://neo4j.com/developer/cla/) has been signed
• CHANGELOG.md updated if appropriate

[serengil-neo4j]

LGTM