[FEATURE] Add Image Support to Moderation

[decaffeinatedio]

Scope check

• This is core LLM communication (not application logic)
• This benefits most users (not just my use case)
• This can't be solved in application code with current RubyLLM
• I read the Contributing Guide

Due diligence

• I searched existing issues
• I checked the documentation

What problem does this solve?

The moderation endpoint only supports passing text, although the backing OpenAI model is multi-modal.

Proposed solution

Add new image keyword argument to the RubyLLM.moderate endpoint to allow a user to call moderation on an image, text, or both. The call will remain backwards-compatible with enabling all features available on the backend.

See draft PR here: #723

Why this belongs in RubyLLM

Image checks are a core moderation use case and this feature is well-supported by the underlying OpenAI API.