tests/test_env.py

import pytest

from support_ticket_env import SupportTicketEnvironment
from support_ticket_env.models import LookupAccountAction, SearchKBAction, SendReplyAction


def test_search_returns_expected_article_and_progress_reward() -> None:
    env = SupportTicketEnvironment()
    env.reset("password_reset_guidance")
    result = env.step(SearchKBAction(action_type="search_kb", query="password reset email not arriving"))
    assert result.observation.last_tool_result.tool_name == "search_kb"
    assert result.observation.last_tool_result.article_ids[0] == "KB-PW-RESET"
    assert result.reward == pytest.approx(0.19)


def test_lookup_populates_account_facts() -> None:
    env = SupportTicketEnvironment()
    env.reset("duplicate_charge_refund")
    result = env.step(LookupAccountAction(action_type="lookup_account", customer_id="cust_bill_002"))
    account = result.observation.known_facts["account"]
    assert account["plan"] == "Business"
    assert account["duplicate_charge_amount_cents"] == 4900


def test_redundant_search_is_penalized() -> None:
    env = SupportTicketEnvironment()
    env.reset("password_reset_guidance")
    env.step(SearchKBAction(action_type="search_kb", query="password reset email not arriving"))
    result = env.step(SearchKBAction(action_type="search_kb", query="password reset email not arriving"))
    assert result.reward == pytest.approx(-0.03)
    assert result.info["redundancy_penalty"] == pytest.approx(0.02)


def test_refund_before_lookup_is_invalid() -> None:
    env = SupportTicketEnvironment()
    env.reset("duplicate_charge_refund")
    result = env.step({"action_type": "issue_refund", "amount_cents": 4900, "reason_code": "duplicate_charge"})
    assert result.observation.last_action_error == "lookup_required_before_refund"
    assert result.reward == pytest.approx(-0.11)


def test_reset_clears_previous_state() -> None:
    env = SupportTicketEnvironment()
    env.reset("password_reset_guidance")
    env.step(SearchKBAction(action_type="search_kb", query="password reset email not arriving"))
    result = env.reset("password_reset_guidance")
    assert result.observation.steps_taken == 0
    assert result.observation.known_facts == {}
    assert len(result.observation.conversation_history) == 1


def test_max_steps_timeout_is_deterministic() -> None:
    env = SupportTicketEnvironment()
    result = env.reset("password_reset_guidance")
    for _ in range(8):
        result = env.step(SendReplyAction(action_type="send_reply", message="Still investigating."))
    assert result.done is True
    assert result.info["terminal_reason"] == "max_steps_exceeded"