tests/test_supportdesk.py

"""Smoke tests for the SupportDesk environment."""

import pytest

try:
    from fastapi.testclient import TestClient
except RuntimeError:
    TestClient = None  # type: ignore[assignment]

from supportdesk_env.graders import grade_case
from supportdesk_env.models import SupportDeskAction
from supportdesk_env.server.supportdesk_environment import SupportDeskEnvironment
from supportdesk_env.tasks import get_task, list_task_ids


def test_all_tasks_are_registered():
    assert list_task_ids() == [
        "billing_refund_easy",
        "account_takeover_medium",
        "api_incident_hard",
    ]


def test_environment_reset_and_state():
    env = SupportDeskEnvironment(task_id="billing_refund_easy")
    observation = env.reset()
    assert observation.task_id == "billing_refund_easy"
    assert env.state.step_count == 0
    assert env.state.current_score == 0.15


def test_perfect_solution_grades_full_score():
    task = get_task("billing_refund_easy")
    env = SupportDeskEnvironment(task_id=task.task_id)
    env.reset()
    env.step(
        SupportDeskAction(
            operation="classify",
            queue=task.gold_queue,
            priority=task.gold_priority,
            issue_type=task.gold_issue_type,
        )
    )
    env.step(
        SupportDeskAction(
            operation="draft_reply",
            reply="Refund approved for the duplicate charge and it should arrive within 5-7 business days.",
        )
    )
    env.step(
        SupportDeskAction(
            operation="add_internal_note",
            internal_note="Duplicate charge verified and refund approved.",
        )
    )
    env.step(
        SupportDeskAction(
            operation="submit",
            status=task.gold_status,
            resolution_code=task.gold_resolution_code,
        )
    )

    breakdown = grade_case(task, env.state.case)
    assert breakdown.total_score == 1.0


def test_max_steps_ends_episode():
    env = SupportDeskEnvironment(task_id="billing_refund_easy")
    observation = env.reset()
    for _ in range(6):
        observation = env.step(SupportDeskAction(operation="classify"))
    assert observation.done is True
    assert env.state.step_count == 6


def test_grade_is_bounded_between_zero_and_one():
    task = get_task("api_incident_hard")
    env = SupportDeskEnvironment(task_id=task.task_id)
    env.reset()
    breakdown = grade_case(task, env.state.case)
    assert 0.0 <= breakdown.total_score <= 1.0


def test_state_includes_episode_id_after_reset():
    env = SupportDeskEnvironment(task_id="billing_refund_easy")
    env.reset(episode_id="episode-123")
    assert env.state.episode_id == "episode-123"


@pytest.mark.skipif(TestClient is None, reason="httpx is not installed for FastAPI TestClient")
def test_http_reset_step_state_are_session_consistent():
    from supportdesk_env.server.app import app

    client = TestClient(app)

    reset_response = client.post("/reset", json={"episode_id": "http-episode"})
    assert reset_response.status_code == 200

    step_response = client.post(
        "/step",
        json={
            "action": {
                "operation": "classify",
                "queue": "billing_ops",
                "priority": "high",
                "issue_type": "duplicate_charge",
                "status": "new",
                "requested_fields": [],
                "reply": "",
                "internal_note": "",
            }
        },
    )
    assert step_response.status_code == 200

    state_response = client.get("/state")
    assert state_response.status_code == 200
    state_payload = state_response.json()

    assert state_payload["episode_id"] == "http-episode"
    assert state_payload["step_count"] == 1
    assert state_payload["case"]["queue"] == "billing_ops"
    assert state_payload["case"]["priority"] == "high"
    assert state_payload["case"]["issue_type"] == "duplicate_charge"