Fix tool calling for Llama 3

[aleroot]

Proposed changes

Support multiple parallel tool calls and buffering for Llama 3

Llama 3 natively supports tool calling through an ipython environment which
generates arrays for multiple parallel tool invocations. Depending on the
model size and prompt, it generates either a JSON list of function objects
or a python-style array of function calls.

• Sets startTag to <|python_tag|> to ensure ToolCallProcessor
  correctly buffers tool output without leaking it to the streaming UI.
• Upgrades Llama3ToolCallParser to parse multiple parallel tool calls
  from JSON array payloads [{"name": ...}] during parseEOS.
• Upgrades PythonicToolCallParser to extract multiple sequential
  pythonic function calls [func1(), func2()] via parseEOS.
• Refactors PythonicToolCallParser to use modern high-performance
  Swift 5.7+ Regex literals instead of legacy NSRegularExpression.
• Add integration unit tests for both parsers to verify multi-call arrays.

Checklist

Put an x in the boxes that apply.

• I have read the CONTRIBUTING document
• I have run pre-commit run --all-files to format my code / installed pre-commit prior to committing changes
• I have added tests that prove my fix is effective or that my feature works
• I have updated the necessary documentation (if needed)

[davidkoski]

Sorry for the long turnaround here -- the PythonicToolCallParser has a conflict with #152. Can you resolve that or let me know and I will resolve it. Thanks!

[aleroot]

Sorry for the long turnaround here -- the PythonicToolCallParser has a conflict with #152. Can you resolve that or let me know and I will resolve it. Thanks!

it should be fixed now.
@davidkoski I know it is off topic but I am looking for the equivalent of this project in C++, but I cannot find the mlx-cpp-lm and it looks like the mlx-lm is in python? I would like to embed MLX into my new in development coding agent in addition to llama.cpp, but I can't find this lm project in C++, do you know if it exists and where can I find it? Thank you very much.