Linked Issue

Closes #207

Description

This PR imports the Python-based generation benchmark suite into the repository.

Placed the files in a dedicated benchmarks/generation directory to keep the Python environment isolated from the main TS project. This benchmark allows for running the token efficiency and accuracy tests documented in the generation/readme.md update.

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Refactoring (no functional changes)
• Performance improvement
• Test coverage improvement

Changes Made

• Created benchmarks/generation/ directory.
• Added Python source code (src/), Pydantic models, and prompt templates.
• Added Gold Standard datasets (data/*.gold.json and *.toon).
• Added runs results in *.csv
• Added requirements.txt and a dedicated README.md with setup benchmark description and instructions for the Python environment.

SPEC Compliance

• This PR implements/fixes spec compliance
• Spec section(s) affected: N/A (Tooling only)
• Spec version: N/A

Testing

• All existing tests pass
• Added new tests for changes
• Tests cover edge cases and spec compliance

Pre-submission Checklist

• My code follows the project's coding standards
• I have run code formatting/linting tools
• I have added tests that prove my fix/feature works
• New and existing tests pass locally
• I have updated documentation if needed
• I have reviewed the TOON specification for relevant sections

Breaking Changes

• No breaking changes
• Breaking changes (describe migration path below)

Additional Context

This benchmark suite is self-contained and does not affect the core TypeScript build process. It requires an API key (e.g., Nebius, OpenAI) to run.