Files
MobilityOps/backend/tests/test_data_quality.py
T
NuklearRabbitandClaude Sonnet 5 1fdd2b3ccf test: add targeted E2E coverage for branding, status flow, MO-016, and knowledge; fix two real bugs found along the way
New frontend/e2e/fleet-ops-correction.spec.ts covers section 12 of the brief:
branding (Fleet Ops visible, no MobilityOps/PoC leaks, in all 3 languages), the
language switcher persisting across reload, the full status-recommendation flow
(non-mutating preview, exact-status confirm button, manual review with no apply
button, stale-token rejection), MO-016 order independence at the browser level, the
knowledge base grounding the exact brief question in its own language, and localized
audit/automation content with raw codes only under "Technical details".

Writing these tests surfaced two real bugs:

- DataQualityIssueDetail.tsx conflated "no conflict" with "manual review required"
  because both carry safe_to_apply: false (a no_conflict recommendation has nothing to
  apply, so it's trivially "not safe to apply" without being unsafe). This showed a
  false "manual review required" panel for MO-016 after its overlap was resolved,
  instead of the correct "no change needed" state. Fixed by keying the branch on
  manual_review_required alone.
- test_mo_016_status_conflict_recommendation_is_order_independent never actually
  exercised MO-016: _first_open() returned whichever vehicle_status_conflict issue was
  most recently detected (there are ~14 open after a reset), not necessarily
  DQ-DEMO-STATUS, so the test's MO-016 assertions were trivially true regardless of
  what the code under test did. Added _first_open_for_vehicle() and rewrote the test
  to explicitly target MO-016, and to assert the behaviour order independence actually
  requires: resolving the overlap first must correctly leave nothing to apply (the
  vehicle already matches the facts), not literally the same end status as resolving
  the conflict first.

151 backend tests, Ruff, mypy green; full 108-test Playwright suite green (two
transient, non-reproducible flakes confirmed to pass in isolation and unrelated to
this change).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-03 22:53:55 +02:00

524 lines
21 KiB
Python

from sqlalchemy import select
from app.core.db import SessionLocal
from app.models.booking import Booking
from app.models.vehicle import Vehicle
def _activate_booking(vehicle_ref: str, start_odometer_km: int) -> str:
db = SessionLocal()
try:
vehicle = db.scalar(select(Vehicle).where(Vehicle.public_ref == vehicle_ref))
booking = db.scalar(
select(Booking).where(Booking.vehicle_id == vehicle.id, Booking.status == "returned")
)
booking.status = "active"
booking.start_odometer_km = start_odometer_km
booking.end_odometer_km = None
db.commit()
return booking.public_ref
finally:
db.close()
def test_list_includes_all_five_rule_types(ops_client):
response = ops_client.get("/api/v1/data-quality/issues")
assert response.status_code == 200
issues = response.json()
rule_types = {i["rule_type"] for i in issues}
assert rule_types == {
"possible_duplicate_customer",
"missing_required_field",
"odometer_regression",
"booking_overlap",
"vehicle_status_conflict",
}
def test_scan_is_idempotent_once_seeded(ops_client):
# The session fixture already ran a scan as part of seeding; running again
# must not create duplicate open issues for the same (rule_type, entity).
response = ops_client.post("/api/v1/data-quality/scan")
assert response.status_code == 200
assert response.json()["created"] == {}
def test_scan_requires_operations_manager(employee_client):
response = employee_client.post("/api/v1/data-quality/scan")
assert response.status_code == 403
def test_list_issues_requires_operations_manager(employee_client):
response = employee_client.get("/api/v1/data-quality/issues")
assert response.status_code == 403
def test_get_issue_requires_operations_manager(employee_client):
response = employee_client.get("/api/v1/data-quality/issues/DQ-DEMO-DUPLICATE")
assert response.status_code == 403
def test_defer_requires_operations_manager(employee_client):
response = employee_client.post("/api/v1/data-quality/issues/DQ-DEMO-OVERLAP/defer")
assert response.status_code == 403
def test_reject_requires_operations_manager(employee_client):
response = employee_client.post("/api/v1/data-quality/issues/DQ-DEMO-OVERLAP/reject")
assert response.status_code == 403
def test_s2_duplicate_customer_issue_detail(ops_client):
response = ops_client.get("/api/v1/data-quality/issues/DQ-DEMO-DUPLICATE")
assert response.status_code == 200
body = response.json()
assert body["entity_ref"] == "CUS-0012"
assert body["entity_snapshot"]["public_ref"] == "CUS-0012"
assert [s["public_ref"] for s in body["related_snapshots"]] == ["CUS-0178"]
def test_s4_booking_overlap_issue_detail(ops_client):
response = ops_client.get("/api/v1/data-quality/issues/DQ-DEMO-OVERLAP")
assert response.status_code == 200
body = response.json()
assert body["entity_ref"] == "MO-016"
assert set(body["evidence"]["related_refs"]) == {"BK-DEMO-OVERLAP-A", "BK-DEMO-OVERLAP-B"}
def test_defer_then_reject_are_rejected_on_closed_issue(ops_client):
issues = ops_client.get(
"/api/v1/data-quality/issues",
params={"rule_type": "missing_required_field", "status": "open"},
).json()
target = issues[0]["public_ref"]
deferred = ops_client.post(f"/api/v1/data-quality/issues/{target}/defer")
assert deferred.status_code == 200
assert deferred.json()["status"] == "deferred"
again = ops_client.post(f"/api/v1/data-quality/issues/{target}/reject")
assert again.status_code == 409
assert again.json()["error"]["code"] == "ISSUE_NOT_OPEN"
def test_merge_customers_requires_operations_manager(employee_client):
response = employee_client.post(
"/api/v1/data-quality/issues/DQ-DEMO-DUPLICATE/merge-customers",
json={"survivor_ref": "CUS-0012"},
)
assert response.status_code == 403
def test_merge_customers_rejects_unrelated_survivor(ops_client):
response = ops_client.post(
"/api/v1/data-quality/issues/DQ-DEMO-DUPLICATE/merge-customers",
json={"survivor_ref": "CUS-0099"},
)
assert response.status_code == 422
assert response.json()["error"]["code"] == "INVALID_SURVIVOR"
def test_merge_customers_s2_scenario_rewires_and_audits(ops_client):
before_bookings = ops_client.get(
"/api/v1/bookings", params={"vehicle_ref": "MO-001"}
) # warm the client session; irrelevant vehicle, just a cheap authenticated call
assert before_bookings.status_code == 200
response = ops_client.post(
"/api/v1/data-quality/issues/DQ-DEMO-DUPLICATE/merge-customers",
json={"survivor_ref": "CUS-0012", "field_overrides": {"city": "Turnhout"}},
)
assert response.status_code == 200
body = response.json()
assert body["survivor_ref"] == "CUS-0012"
assert body["loser_ref"] == "CUS-0178"
issue = ops_client.get("/api/v1/data-quality/issues/DQ-DEMO-DUPLICATE").json()
assert issue["status"] == "resolved"
audit_events = ops_client.get(
"/api/v1/audit", params={"action": "customer_merged"}
).json()
assert len(audit_events) >= 1
# Already-resolved issue cannot be merged again.
replay = ops_client.post(
"/api/v1/data-quality/issues/DQ-DEMO-DUPLICATE/merge-customers",
json={"survivor_ref": "CUS-0012"},
)
assert replay.status_code == 409
def test_overlap_related_snapshots_are_typed_as_bookings_not_vehicles(ops_client):
body = ops_client.get("/api/v1/data-quality/issues/DQ-DEMO-OVERLAP").json()
assert len(body["related_snapshots"]) == 2
for snap in body["related_snapshots"]:
assert snap["entity_type"] == "booking"
assert snap["public_ref"] in {"BK-DEMO-OVERLAP-A", "BK-DEMO-OVERLAP-B"}
assert "starts_at" in snap and "ends_at" in snap
def _first_open(ops_client, rule_type: str) -> dict:
issues = ops_client.get(
"/api/v1/data-quality/issues", params={"rule_type": rule_type, "status": "open"}
).json()
assert issues, f"expected at least one open {rule_type} issue"
return issues[0]
def test_provide_fields_requires_operations_manager(employee_client):
response = employee_client.post(
"/api/v1/data-quality/issues/DQ-DEMO-ATTENTION/provide-fields",
json={"fields": {"registration_number": "TST-001"}},
)
assert response.status_code == 403
def test_provide_fields_rejects_wrong_rule_type(ops_client):
response = ops_client.post(
"/api/v1/data-quality/issues/DQ-DEMO-OVERLAP/provide-fields",
json={"fields": {"make": "Test"}},
)
assert response.status_code == 409
assert response.json()["error"]["code"] == "NOT_A_MISSING_FIELD_ISSUE"
def test_provide_fields_rejects_disallowed_field(ops_client):
target = _first_open(ops_client, "missing_required_field")
detail = ops_client.get(f"/api/v1/data-quality/issues/{target['public_ref']}").json()
disallowed = "city" if detail["entity_type"] == "customer" else "next_service_km"
response = ops_client.post(
f"/api/v1/data-quality/issues/{target['public_ref']}/provide-fields",
json={"fields": {disallowed: "anything"}},
)
assert response.status_code == 422
assert response.json()["error"]["code"] == "INVALID_FIELD"
def test_provide_fields_resolves_a_vehicle_missing_field_issue(ops_client):
issues = ops_client.get(
"/api/v1/data-quality/issues",
params={"rule_type": "missing_required_field", "status": "open"},
).json()
target = next(i for i in issues if i["entity_type"] == "vehicle")
response = ops_client.post(
f"/api/v1/data-quality/issues/{target['public_ref']}/provide-fields",
json={
"fields": {
"registration_number": "TST-999",
"make": "TestMake",
"model": "TestModel",
"location": "Depot",
}
},
)
assert response.status_code == 200
assert response.json()["status"] == "resolved"
vehicle = ops_client.get(f"/api/v1/vehicles/{target['entity_ref']}").json()
assert vehicle["registration_number"] == "TST-999"
def test_resolve_overlap_requires_operations_manager(employee_client):
response = employee_client.post(
"/api/v1/data-quality/issues/DQ-DEMO-OVERLAP/resolve-overlap",
json={"booking_ref": "BK-DEMO-OVERLAP-A"},
)
assert response.status_code == 403
def test_resolve_overlap_rejects_unrelated_booking(ops_client):
response = ops_client.post(
"/api/v1/data-quality/issues/DQ-DEMO-OVERLAP/resolve-overlap",
json={"booking_ref": "BK-DEMO-RETURN"},
)
assert response.status_code == 422
assert response.json()["error"]["code"] == "INVALID_BOOKING_REFERENCE"
def test_resolve_overlap_blocks_one_booking_and_resolves(ops_client):
response = ops_client.post(
"/api/v1/data-quality/issues/DQ-DEMO-OVERLAP/resolve-overlap",
json={"booking_ref": "BK-DEMO-OVERLAP-A", "note": "Blocked the later commitment."},
)
assert response.status_code == 200
assert response.json()["status"] == "resolved"
booking = ops_client.get("/api/v1/bookings/BK-DEMO-OVERLAP-A").json()
assert booking["status"] == "blocked"
def test_status_recommendation_requires_operations_manager(employee_client):
response = employee_client.post(
"/api/v1/data-quality/issues/DQ-DEMO-STATUS/status-recommendation"
)
assert response.status_code == 403
def test_apply_recommended_status_requires_operations_manager(employee_client):
response = employee_client.post(
"/api/v1/data-quality/issues/DQ-DEMO-STATUS/apply-recommended-status",
json={"recommendation_token": "irrelevant"},
)
assert response.status_code == 403
def test_status_recommendation_preview_does_not_mutate_anything(ops_client):
target = _first_open(ops_client, "vehicle_status_conflict")
vehicle_before = ops_client.get(f"/api/v1/vehicles/{target['entity_ref']}").json()
preview_response = ops_client.post(
f"/api/v1/data-quality/issues/{target['public_ref']}/status-recommendation"
)
assert preview_response.status_code == 200
preview = preview_response.json()
assert preview["current_status"] == vehicle_before["operational_status"]
assert preview["recommendation_token"]
assert "facts" in preview
# Calling preview again (as the UI would on every open) must still not mutate.
ops_client.post(f"/api/v1/data-quality/issues/{target['public_ref']}/status-recommendation")
issue_after = ops_client.get(f"/api/v1/data-quality/issues/{target['public_ref']}").json()
vehicle_after = ops_client.get(f"/api/v1/vehicles/{target['entity_ref']}").json()
assert issue_after["status"] == "open"
assert vehicle_after["operational_status"] == vehicle_before["operational_status"]
def test_apply_recommended_status_resolves_conflict(ops_client):
target = _first_open(ops_client, "vehicle_status_conflict")
preview = ops_client.post(
f"/api/v1/data-quality/issues/{target['public_ref']}/status-recommendation"
).json()
assert preview["safe_to_apply"] is True
assert preview["manual_review_required"] is False
response = ops_client.post(
f"/api/v1/data-quality/issues/{target['public_ref']}/apply-recommended-status",
json={"recommendation_token": preview["recommendation_token"]},
)
assert response.status_code == 200
body = response.json()
assert body["issue"]["status"] == "resolved"
assert body["applied_status"] == preview["recommended_status"]
assert body["reason_code"] == preview["recommendation_code"]
vehicle = ops_client.get(f"/api/v1/vehicles/{target['entity_ref']}").json()
assert vehicle["operational_status"] == body["applied_status"]
def test_apply_recommended_status_rejects_stale_token(ops_client):
target = _first_open(ops_client, "vehicle_status_conflict")
response = ops_client.post(
f"/api/v1/data-quality/issues/{target['public_ref']}/apply-recommended-status",
json={"recommendation_token": "not-a-real-token"},
)
assert response.status_code == 409
assert response.json()["error"]["code"] == "RECOMMENDATION_STALE"
def test_resolve_odometer_regression_requires_operations_manager(employee_client):
response = employee_client.post(
"/api/v1/data-quality/issues/DQ-0007/resolve-odometer-regression",
json={"decision": "retain_canonical"},
)
assert response.status_code == 403
def test_resolve_odometer_regression_correction_below_canonical_is_rejected_then_retained(
ops_client,
):
target = _first_open(ops_client, "odometer_regression")
vehicle_before = ops_client.get(f"/api/v1/vehicles/{target['entity_ref']}").json()
too_low = ops_client.post(
f"/api/v1/data-quality/issues/{target['public_ref']}/resolve-odometer-regression",
json={
"decision": "correct_reading",
"booking_ref": "BK-DEMO-RETURN",
"corrected_odometer_km": max(vehicle_before["odometer_km"] - 100, 0),
},
)
assert too_low.status_code == 422
assert too_low.json()["error"]["code"] in (
"CORRECTION_BELOW_CANONICAL",
"INVALID_BOOKING_REFERENCE",
)
# The rejected attempt must not have resolved or mutated anything.
still_open = ops_client.get(f"/api/v1/data-quality/issues/{target['public_ref']}").json()
assert still_open["status"] == "open"
retained = ops_client.post(
f"/api/v1/data-quality/issues/{target['public_ref']}/resolve-odometer-regression",
json={"decision": "retain_canonical", "note": "Submitted reading treated as erroneous."},
)
assert retained.status_code == 200
assert retained.json()["status"] == "resolved"
vehicle_after = ops_client.get(f"/api/v1/vehicles/{target['entity_ref']}").json()
assert vehicle_after["odometer_km"] == vehicle_before["odometer_km"]
def test_resolve_odometer_regression_correct_reading_updates_canonical(ops_client):
# The seeded odometer_regression issues carry no related booking (CSV-only rows).
# Create a fresh one with a real related booking via a live regression return, so
# the "correct_reading" path has an actual booking_ref to target.
booking_ref = _activate_booking("MO-018", start_odometer_km=12000)
vehicle_before = ops_client.get("/api/v1/vehicles/MO-018").json()
low_reading = vehicle_before["odometer_km"] - 200
returned = ops_client.post(
f"/api/v1/bookings/{booking_ref}/return",
json={
"end_odometer_km": low_reading,
"fuel_level_percent": 50,
"cleanliness_ok": True,
"damage_reported": False,
"technical_warning": False,
},
headers={"Idempotency-Key": "test-dq-odometer-correct-001"},
)
assert returned.status_code == 201
issue_ref = returned.json()["quality_issue_ref"]
assert issue_ref is not None
corrected = vehicle_before["odometer_km"] + 500
response = ops_client.post(
f"/api/v1/data-quality/issues/{issue_ref}/resolve-odometer-regression",
json={
"decision": "correct_reading",
"booking_ref": booking_ref,
"corrected_odometer_km": corrected,
},
)
assert response.status_code == 200
assert response.json()["status"] == "resolved"
vehicle = ops_client.get("/api/v1/vehicles/MO-018").json()
assert vehicle["odometer_km"] == corrected
booking = ops_client.get(f"/api/v1/bookings/{booking_ref}").json()
assert booking["end_odometer_km"] == corrected
def test_manual_scan_records_audit_event(ops_client):
scan = ops_client.post("/api/v1/data-quality/scan")
assert scan.status_code == 200
events = ops_client.get(
"/api/v1/audit", params={"action": "data_quality_scan_run"}
).json()
assert len(events) >= 1
assert "created" in events[0]["metadata"]
def _reset_demo(ops_client) -> None:
# /api/v1/demo/reset deletes the session cookie (the reset recreates the users
# table, so the old session's user id no longer exists) -- the caller must log back
# in before making any further authenticated call with the same client.
response = ops_client.post("/api/v1/demo/reset")
assert response.status_code == 200, response.text
login_response = ops_client.post(
"/api/v1/demo/login", json={"role": "operations_manager"}
)
assert login_response.status_code == 200, login_response.text
def _resolve_overlap_issue(ops_client, *, booking_to_block: str) -> None:
overlap = _first_open(ops_client, "booking_overlap")
response = ops_client.post(
f"/api/v1/data-quality/issues/{overlap['public_ref']}/resolve-overlap",
json={"booking_ref": booking_to_block},
)
assert response.status_code == 200, response.text
assert response.json()["status"] == "resolved"
def _first_open_for_vehicle(ops_client, rule_type: str, vehicle_ref: str) -> dict:
issues = ops_client.get(
"/api/v1/data-quality/issues", params={"rule_type": rule_type, "status": "open"}
).json()
match = next((i for i in issues if i["entity_ref"] == vehicle_ref), None)
assert match, f"expected an open {rule_type} issue for {vehicle_ref}"
return match
def _apply_status_recommendation(ops_client, public_ref: str) -> dict:
preview = ops_client.post(
f"/api/v1/data-quality/issues/{public_ref}/status-recommendation"
).json()
apply_response = ops_client.post(
f"/api/v1/data-quality/issues/{public_ref}/apply-recommended-status",
json={"recommendation_token": preview["recommendation_token"]},
)
assert apply_response.status_code == 200, apply_response.text
return apply_response.json()
def test_mo_016_status_conflict_recommendation_is_order_independent(ops_client):
# MO-016 carries both a booking_overlap (DQ-DEMO-OVERLAP) and a vehicle_status_conflict
# (DQ-DEMO-STATUS) issue at once. Order independence does NOT mean "the same final
# vehicle status regardless of order" -- resolving the overlap first genuinely removes
# the conflict, so there is correctly nothing left to apply. What must hold in either
# order: the recommendation always reflects the real, current facts (never a stale
# "was some other issue open" proxy), and nothing unsafe is ever applied (never
# "rented", never a status change once the underlying condition has already resolved
# itself). See docs/fleet-ops-correction/current-gap-audit.md §6-7 and
# vehicle-status-decision-table.md.
# Order A: resolve the booking overlap first. The status-conflict issue's own
# recommendation must now correctly report that the conflict is gone -- nothing unsafe
# should be auto-applied, and the vehicle (never touched) stays exactly as it was.
_reset_demo(ops_client)
_resolve_overlap_issue(ops_client, booking_to_block="BK-DEMO-OVERLAP-B")
status_issue_a = _first_open_for_vehicle(ops_client, "vehicle_status_conflict", "MO-016")
preview_a = ops_client.post(
f"/api/v1/data-quality/issues/{status_issue_a['public_ref']}/status-recommendation"
).json()
assert preview_a["recommendation_code"] == "vehicle.no_conflict"
assert preview_a["recommended_status"] is None
assert preview_a["safe_to_apply"] is False
vehicle_a = ops_client.get("/api/v1/vehicles/MO-016").json()
assert vehicle_a["operational_status"] == "available"
# Order B: resolve the status conflict first, while the overlap is still open -- the
# conflict genuinely still exists, so the evaluator must still detect it and safely
# resolve it (never "rented").
_reset_demo(ops_client)
status_issue_b = _first_open_for_vehicle(ops_client, "vehicle_status_conflict", "MO-016")
result_b = _apply_status_recommendation(ops_client, status_issue_b["public_ref"])
assert result_b["applied_status"] != "rented"
vehicle_b_mid = ops_client.get("/api/v1/vehicles/MO-016").json()
assert vehicle_b_mid["operational_status"] == result_b["applied_status"]
# Resolving the now-redundant overlap afterwards must not itself change the vehicle's
# status as a side effect.
_resolve_overlap_issue(ops_client, booking_to_block="BK-DEMO-OVERLAP-B")
vehicle_b = ops_client.get("/api/v1/vehicles/MO-016").json()
assert vehicle_b["operational_status"] == result_b["applied_status"]
assert vehicle_b["operational_status"] != "rented"
_reset_demo(ops_client)
def test_rejected_issue_recurrence_links_to_prior_decision(ops_client):
# Reject an open vehicle_status_conflict issue without changing the vehicle, so the
# next scan re-detects the same unresolved condition -- it must not silently vanish
# or reopen the old row, but the new issue should stay linked to the rejection.
target = _first_open(ops_client, "vehicle_status_conflict")
rejected = ops_client.post(f"/api/v1/data-quality/issues/{target['public_ref']}/reject")
assert rejected.status_code == 200
rescan = ops_client.post("/api/v1/data-quality/scan")
assert rescan.status_code == 200
assert rescan.json()["created"].get("vehicle_status_conflict", 0) >= 1
reopened = ops_client.get(
"/api/v1/data-quality/issues",
params={"rule_type": "vehicle_status_conflict", "status": "open"},
).json()
match = next(
(i for i in reopened if i["evidence"].get("reopened_from") == target["public_ref"]), None
)
assert match is not None, "expected a new issue linked back to the rejected one"
assert match["evidence"]["previous_decision"] == "rejected"