feat(runnable-rails): implement AIMessage metadata parity in RunnableRails

[Pouyanpi]

Ensure AIMessage responses from RunnableRails contain the same metadata fields (response_metadata, usage_metadata, additional_kwargs, id) as direct LLM calls, enabling consistent LangChain integration behavior.

[Copilot]

Pull Request Overview

This PR implements AIMessage metadata parity in RunnableRails by ensuring that LLM metadata (response_metadata, usage_metadata, additional_kwargs, id) from the underlying LLM is preserved and passed through to the final AIMessage responses. This enables consistent behavior when using RunnableRails within LangChain chains.

• Adds metadata preservation infrastructure to capture and store LLM response metadata
• Updates RunnableRails output formatting to include preserved metadata in AIMessage responses
• Adds comprehensive test coverage for metadata preservation scenarios

Reviewed Changes

Copilot reviewed 7 out of 7 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
tests/runnable_rails/test_runnable_rails.py	Adds integration test to verify metadata preservation through RunnableRails
tests/runnable_rails/test_metadata.py	Comprehensive test suite for metadata preservation with various input/output formats
nemoguardrails/rails/llm/options.py	Adds llm_metadata field to GenerationResponse to store LLM metadata
nemoguardrails/rails/llm/llmrails.py	Updates to include llm_metadata in generation responses
nemoguardrails/integrations/langchain/runnable_rails.py	Updates output formatting methods to include metadata in AIMessage creation
nemoguardrails/context.py	Adds context variable for storing LLM response metadata
nemoguardrails/actions/llm/utils.py	Adds function to store and retrieve LLM response metadata

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}