feat(meta-llama): add timeout and max_retries to chat generator

[Keyur-S-Patel]

Related Issues

• partially addresses #9309

Proposed Changes:

• Added timeout and max_retries to MetaLlamaChatGenerator.__init__.
• Forwarded both fields to OpenAIChatGenerator via super().__init__(..., timeout=..., max_retries=...).
• Included the new fields in to_dict serialization.
• Updated unit tests to reflect actual default behavior and serde output:
  • default timeout/max_retries are None
  • explicit values are preserved when provided.

How did you test it?

• Targeted tests:
  • test_init_default
  • test_to_dict_default
  • test_from_dict_fail_wo_env_var
• Full file:
  • hatch run test:unit tests/test_llama_chat_generator.py

All selected tests passed on this branch.

Notes for the reviewer

• Defaults are intentionally None in this integration path, and tests were adjusted accordingly.
• The change is minimal and relies on existing OpenAI generator retry/timeout handling.

Checklist

• I have read the contributors guidelines and the code of conduct
• I have updated the related issue with new insights and changes
• I added unit tests and updated the docstrings
• I've used one of the conventional commit types for my PR title: fix:, feat:, build:, chore:, ci:, docs:, style:, refactor:, perf:, test:.

[CLAassistant]

All committers have signed the CLA.

[anakin87]

Thank you!

I also tested it locally and it works correctly.