Judge Provider

judge resolves which provider grades the output, in this order:

1. An explicit provider: (and optional model:) kwarg passed to judge.

2. OmniAgent.configuration.eval_judge_provider / eval_judge_model, set once globally:

   OmniAgent.configure do |config|
     config.eval_judge_provider = :openai
     config.eval_judge_model = "gpt-4o-mini"
   end

3. Falls back to the same provider/model the agent under test already uses — no judge setup required to get started.

The judge sends a fixed grading prompt asking for {"score": 0-1, "reason": "..."} and compares score against threshold from the judge call (see Generating and Running Evals).