Start a run-until-done goal loop. Records the completion condition; the agent should then work toward it and call check_goal at the end of every turn until the goal is met.

Evaluate whether the active goal is fully met. Call at the end of every turn with a concrete summary of the work just done. Returns done=true when finished, or done=false plus the specific gap to address next.

Inspect the current goal session: condition, turn count, elapsed time, and last evaluation.

End a goal session. Pass completed=true when the goal was verifiably met (used by the self-check fallback); otherwise the session is abandoned.