MobilityOps/backend/tests/test_seed.py

from datetime import UTC, datetime

from sqlalchemy import func, select

from app.core.db import SessionLocal
from app.models.audit import AuditEvent
from app.models.booking import Booking
from app.models.customer import Customer
from app.models.data_quality import DataQualityIssue
from app.models.outbox import DEMO_SCENARIO_ERROR_CODE, OutboxEvent
from app.models.user import User
from app.models.vehicle import Vehicle
from app.seed_loader import SEED_AUTHORED_ANCHOR, reset_and_seed


def test_seed_counts_match_deterministic_dataset():
    # Other test modules mutate shared demo state (returns, resets), so this test
    # re-seeds immediately before asserting counts rather than trusting whatever
    # order pytest happened to run modules in.
    db = SessionLocal()
    try:
        reset_and_seed(db)
        assert db.scalar(select(func.count()).select_from(Vehicle)) == 50
        assert db.scalar(select(func.count()).select_from(Customer)) == 180
        # 246 original plus 8 (BK-T-001..008) added so "Today's movements" reads as a
        # real day of traffic rather than the same fixed 4 rows on every reset.
        assert db.scalar(select(func.count()).select_from(Booking)) == 254
        # 21 from the CSV (15 original + 6 giving every unexplained blocked vehicle a
        # real open issue) plus a deterministic set discovered by the post-seed scan. The
        # shared vehicle-status evaluator (app.services.vehicle_status) also catches
        # MO-024: an active/return-pending booking (BK-DEMO-RETURN) on a vehicle that has
        # already crossed its service-due odometer threshold -- a genuine conflict the
        # previous hand-rolled scanner never checked for.
        assert db.scalar(select(func.count()).select_from(DataQualityIssue)) == 33
        assert db.scalar(select(func.count()).select_from(OutboxEvent)) == 20
        assert db.scalar(select(func.count()).select_from(User)) == 2
    finally:
        db.close()


def test_seed_demo_scenarios_present():
    db = SessionLocal()
    try:
        reset_and_seed(db)

        booking = db.scalar(select(Booking).where(Booking.public_ref == "BK-DEMO-RETURN"))
        assert booking is not None
        assert booking.status == "active"

        duplicate_customer = db.scalar(select(Customer).where(Customer.public_ref == "CUS-0178"))
        assert duplicate_customer is not None

        duplicate_issue = db.scalar(
            select(DataQualityIssue).where(DataQualityIssue.public_ref == "DQ-DEMO-DUPLICATE")
        )
        assert duplicate_issue is not None
        assert duplicate_issue.rule_type == "possible_duplicate_customer"

        failed_run = db.scalar(
            select(OutboxEvent).where(OutboxEvent.delivery_status == "failed")
        )
        assert failed_run is not None
    finally:
        db.close()


def _by_ref(db, model, ref):
    return db.scalar(select(model).where(model.public_ref == ref))


def test_seed_scenario_s1_odometer_regression_return():
    """S1: BK-DEMO-RETURN on MO-024 is an active booking ready for a return with a
    below-canonical odometer reading, using the vehicle's own current odometer."""
    db = SessionLocal()
    try:
        reset_and_seed(db)
        booking = _by_ref(db, Booking, "BK-DEMO-RETURN")
        vehicle = _by_ref(db, Vehicle, "MO-024")
        assert booking is not None and vehicle is not None
        assert booking.vehicle_id == vehicle.id
        assert booking.status == "active"
        assert booking.end_odometer_km is None
        # A demo return reading must sit below the vehicle's canonical odometer to
        # reproduce the odometer-regression anomaly deterministically.
        assert vehicle.odometer_km > 0
    finally:
        db.close()


def test_seed_scenario_s2_duplicate_customer_pair():
    """S2: CUS-0012/CUS-0178 form a possible-duplicate pair with a matching open issue."""
    db = SessionLocal()
    try:
        reset_and_seed(db)
        primary = _by_ref(db, Customer, "CUS-0012")
        duplicate = _by_ref(db, Customer, "CUS-0178")
        assert primary is not None and duplicate is not None
        assert primary.email == duplicate.email
        assert duplicate.merged_into_customer_id is None

        issue = _by_ref(db, DataQualityIssue, "DQ-DEMO-DUPLICATE")
        assert issue is not None
        assert issue.rule_type == "possible_duplicate_customer"
        assert issue.status == "open"
        related = issue.evidence_json.get("related_refs", [])
        assert "CUS-0012" in related or "CUS-0178" in related
    finally:
        db.close()


def test_seed_scenario_s4_booking_overlap():
    """S4: MO-016 carries two overlapping reservations plus a matching open issue."""
    db = SessionLocal()
    try:
        reset_and_seed(db)
        vehicle = _by_ref(db, Vehicle, "MO-016")
        booking_a = _by_ref(db, Booking, "BK-DEMO-OVERLAP-A")
        booking_b = _by_ref(db, Booking, "BK-DEMO-OVERLAP-B")
        assert vehicle is not None and booking_a is not None and booking_b is not None
        assert booking_a.vehicle_id == vehicle.id
        assert booking_b.vehicle_id == vehicle.id
        assert booking_a.starts_at < booking_b.ends_at
        assert booking_b.starts_at < booking_a.ends_at

        issue = _by_ref(db, DataQualityIssue, "DQ-DEMO-OVERLAP")
        assert issue is not None
        assert issue.rule_type == "booking_overlap"
        assert issue.status == "open"
    finally:
        db.close()


def test_seed_scenario_s5_failed_workflow_run():
    """S5: one seeded outbox event is durably 'failed' (terminal, retryable), not merely
    pending, so the background dispatcher never silently auto-heals it away."""
    db = SessionLocal()
    try:
        reset_and_seed(db)
        failed = db.scalar(
            select(OutboxEvent).where(
                OutboxEvent.event_id == "00000000-0000-4000-8000-000000000020"
            )
        )
        assert failed is not None
        assert failed.delivery_status == "failed"
        assert failed.attempts >= 1
        assert failed.last_error
        # Coded as a prepared demo scenario, not as a real connectionError: the whole
        # point of this row is to demonstrate retry and audit, so nothing downstream
        # may read it as evidence that the n8n integration is unhealthy.
        assert failed.last_error_code == DEMO_SCENARIO_ERROR_CODE
    finally:
        db.close()


def test_seed_dates_are_anchored_to_reset_moment():
    """Every reset shifts seeded dates by (real today - authored anchor), so scenario
    bookings stay 'today'/'near-future' relative to whenever the reset actually ran,
    instead of decaying back to the fixed 2026-08-01 authoring date."""
    db = SessionLocal()
    try:
        result = reset_and_seed(db)
        today = datetime.now(UTC).date()
        assert result.anchor_date == today

        shift = today - SEED_AUTHORED_ANCHOR
        booking = _by_ref(db, Booking, "BK-DEMO-RETURN")
        assert booking is not None
        # Authored ends_at was 2026-08-01T09:00Z; after shifting it must land on the
        # real reset date, not the frozen authoring date (unless shift is exactly zero).
        assert booking.ends_at.date() == today or shift.days == 0

        marker = db.scalar(
            select(AuditEvent)
            .where(AuditEvent.action == "demo_data_seeded")
            .order_by(AuditEvent.occurred_at.desc())
        )
        assert marker is not None
        assert marker.metadata_json["anchor_date"] == today.isoformat()
        assert marker.metadata_json["seed_authored_anchor"] == SEED_AUTHORED_ANCHOR.isoformat()
    finally:
        db.close()


def test_seed_today_movements_are_a_credible_mix():
    """A fresh reset must not land on a thin, always-identical 'Today's movements'
    dashboard section: a real day of fleet traffic (>=5 departures, >=5 returns, across
    more than 4 distinct vehicles) should fall on the reset day, mirroring the same
    status/date rule the dashboard router uses to build the today list."""
    db = SessionLocal()
    try:
        reset_and_seed(db)
        today = datetime.now(UTC).date()
        bookings = db.scalars(select(Booking)).all()
        departures = [
            b
            for b in bookings
            if b.starts_at.date() == today and b.status in ("reserved", "active")
        ]
        returns = [
            b for b in bookings if b.ends_at.date() == today and b.status in ("active", "returned")
        ]
        assert len(departures) >= 5
        assert len(returns) >= 5
        vehicles_involved = {b.vehicle_id for b in departures} | {b.vehicle_id for b in returns}
        assert len(vehicles_involved) > 4
    finally:
        db.close()


def test_every_blocked_vehicle_has_a_real_open_issue():
    """A live reviewer found blocked vehicles with no explanation anywhere in the UI --
    5 with zero quality issues at all, one (MO-049) with only a resolved one. Every
    vehicle seeded as 'blocked' must now have at least one real, currently open
    DataQualityIssue an operator can click through to."""
    db = SessionLocal()
    try:
        reset_and_seed(db)
        blocked = db.scalars(select(Vehicle).where(Vehicle.operational_status == "blocked")).all()
        assert len(blocked) > 0
        for vehicle in blocked:
            open_issue = db.scalar(
                select(DataQualityIssue).where(
                    DataQualityIssue.entity_type == "vehicle",
                    DataQualityIssue.entity_id == vehicle.id,
                    DataQualityIssue.status == "open",
                )
            )
            assert open_issue is not None, f"{vehicle.public_ref} is blocked with no open issue"
    finally:
        db.close()


def test_seed_scenario_mo024_service_conflict_is_flagged():
    """Regression lock-in for the live-reported MO-024 defect: 'rented' with a real
    active booking (BK-DEMO-RETURN) yet already 14,820 km past its service threshold,
    with nothing surfacing the contradiction. The shared vehicle-status evaluator
    already catches this (a real conflict, not a fabricated third status) -- this test
    exists so a future change can't silently regress it back to unexplained."""
    db = SessionLocal()
    try:
        reset_and_seed(db)
        vehicle = _by_ref(db, Vehicle, "MO-024")
        assert vehicle is not None
        assert vehicle.operational_status == "rented"
        assert vehicle.odometer_km >= vehicle.next_service_km

        issue = db.scalar(
            select(DataQualityIssue).where(
                DataQualityIssue.entity_type == "vehicle",
                DataQualityIssue.entity_id == vehicle.id,
                DataQualityIssue.status == "open",
                DataQualityIssue.rule_type == "vehicle_status_conflict",
            )
        )
        assert issue is not None
        signals = issue.evidence_json.get("signals", [])
        assert any(s["code"] == "vehicle.manual_review_required" for s in signals)
    finally:
        db.close()


def test_seed_evidence_has_no_placeholder_summary():
    """Every seed-only data-quality issue used to carry the vacuous evidence
    'Synthetic deterministic seed issue' with no structured signal at all -- a visitor
    had no way to understand why it needed attention. Every issue must now carry a real
    summary and at least one localizable signal (code + params)."""
    db = SessionLocal()
    try:
        reset_and_seed(db)
        issues = db.scalars(select(DataQualityIssue)).all()
        assert len(issues) > 0
        for issue in issues:
            summary = issue.evidence_json.get("summary", "")
            assert summary != "Synthetic deterministic seed issue", (
                f"{issue.public_ref} still has the meaningless placeholder summary"
            )
            signals = issue.evidence_json.get("signals", [])
            assert len(signals) > 0, f"{issue.public_ref} has no structured evidence signal"
    finally:
        db.close()