tests/test_scenarios.py

from support_ticket_env import SupportTicketEnvironment, list_task_ids, scripted_policy
from support_ticket_env.models import EscalateTicketAction, IssueRefundAction, LookupAccountAction, ResolveTicketAction, SendReplyAction


def run_actions(task_id: str, actions: list[object]):
    env = SupportTicketEnvironment()
    result = env.reset(task_id)
    for action in actions:
        result = env.step(action)
        if result.done:
            break
    return result


def test_gold_policies_score_perfectly() -> None:
    env = SupportTicketEnvironment()
    for task_id in list_task_ids():
        result = env.reset(task_id)
        while not result.done:
            action = scripted_policy(task_id, result.observation.steps_taken + 1, result.observation.customer_id)
            result = env.step(action)
        assert result.info["score"] == 1.0


def test_premature_resolution_scores_poorly() -> None:
    result = run_actions(
        "duplicate_charge_refund",
        [ResolveTicketAction(action_type="resolve_ticket", resolution_code="billing_refund_processed")],
    )
    assert result.done is True
    assert result.info["score"] < 0.5


def test_task3_refund_attempt_hurts_final_score() -> None:
    result = run_actions(
        "enterprise_data_loss_escalation",
        [
            LookupAccountAction(action_type="lookup_account", customer_id="cust_ent_003"),
            IssueRefundAction(action_type="issue_refund", amount_cents=4900, reason_code="duplicate_charge"),
            SendReplyAction(
                action_type="send_reply",
                message="This is urgent. I am escalating this to our legal team right now and the case is being actively investigated.",
            ),
            EscalateTicketAction(
                action_type="escalate_ticket",
                queue="legal_data_incident",
                priority="P0",
                summary="Enterprise customer reports possible data loss and legal threat.",
            ),
        ],
    )
    assert result.info["score"] == 0.8


def test_task3_liability_admission_fails_careful_reply() -> None:
    result = run_actions(
        "enterprise_data_loss_escalation",
        [
            LookupAccountAction(action_type="lookup_account", customer_id="cust_ent_003"),
            SendReplyAction(
                action_type="send_reply",
                message="This is urgent and we are escalating it, but this is our fault and we caused this.",
            ),
            EscalateTicketAction(
                action_type="escalate_ticket",
                queue="legal_data_incident",
                priority="P0",
                summary="Enterprise customer reports possible data loss and legal threat.",
            ),
        ],
    )
    criteria = {item["criterion_id"]: item for item in result.info["score_breakdown"]["criteria"]}
    assert criteria["careful_reply"]["earned"] is False
    assert result.info["score"] < 1.0