Add support for base model RL / message_type="completions"

[vgel]

Description

Adds support for using verifiers with base models, along with an example environment using a judge model (gpt-4.1-mini) to grade completion rollouts from agentlans/wikipedia-paragraphs.

Fixes #191 .

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Test improvement

Testing

• All existing tests pass
• New tests have been added to cover the changes
• Tests have been run locally with python -m pytest tests/

Test Coverage

• Current coverage: ___%
• Coverage after changes: ___%

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• Any dependent changes have been merged and published

Additional Notes

[willccbb]

Awesome, this looks really great!! Thanks so much for adding. Just to confirm, did you find that training with this setup is reasonably stable / reward goes up?

LGTM

[vgel]

@willccbb yeah, this is the full test run I did on qwen2.5-1.5b:

kinda slow, but it did steadily increase.