Function metrics_from_jsonl 

pub fn metrics_from_jsonl(
    jsonl: &str,
    root: &Path,
    id: &str,
    gt_files: &[String],
) -> AgentTaskResult

Score an in-process JSONL tool stream the same way [run_task] scores an agent. Event index is used as first_correct_ms so deterministic pack-consumers have a stable ordinal (not wall-clock noise).