agentops eval init currently relies on a static baseline evaluator set unless evaluators are explicitly configured. It should inspect the configured agent and dataset shape, reuse the evaluator recommendation logic from agentops eval run, and pass the recommended built-in evaluators to azd while still respecting explicit evaluator overrides.
agentops eval init currently relies on a static baseline evaluator set unless evaluators are explicitly configured. It should inspect the configured agent and dataset shape, reuse the evaluator recommendation logic from agentops eval run, and pass the recommended built-in evaluators to azd while still respecting explicit evaluator overrides.