Files
MobilityOps/backend/tests/test_seed.py
T
NuklearRabbitandClaude Sonnet 5 34df66d28c M8: GUI polish, n8n workflow-3 fixes, RAGcore retrieval root-cause and fix
GUI: dashboard Attention Queue presents a curated severity mix instead of pure
severity-sort (grouped Now/Today/Later headers); Today's Movements seed data
curated so a fresh reset shows a credible day (2+ departures, 2+ returns), with
a new seed-integrity test; About Demo restructured into a compact grid with
progressive disclosure for technical sections; Duplicate Merge shows match/conflict
counts, hides matching fields by default, and previews the final merged record
before confirmation.

Repo hygiene: removed a stray empty `backend;C` directory and an untracked 31MB
zip export; `.gitignore` now excludes future archive exports.

n8n: fixed invalid JSON (a missing `},` between two node objects) in the committed
`fleet-ops-vehicle-return.json` -- the file could not be parsed. Live-validated
workflow 3 (RAGcore Procedure Sync): found and fixed a real defect (three body
parameters had a stray trailing `}}`) and a missing Error Workflow wiring, both
via the safe `n8n import:workflow` CLI path; exported the corrected, still-
inactive workflow as the new source of truth and updated MANIFEST.md/check_drift.py.
Publishing it (starts real daily unattended runs) remains a separate decision.

RAGcore: root-caused and fixed (live, approved) the "zero retrieval candidates"
bug -- a filesystem permission bug (`embedding_profiles.json` unreadable by the
app's own runtime user) that broke every retrieval call before it reached Qdrant.
Every other suspect (grants, scope resolution, Qdrant filters, embeddings) was
verified healthy first. Found a second, deeper gap: the reranker adapter calls
an Ollama HTTP route that does not exist on the deployed Ollama version, so
`/v1/answers` still returns `not_answerable`. `KNOWLEDGE_PROVIDER` stays `demo`
until that is resolved on the RAGcore side. Evidence-based MCP Hub integration
status (real tool-call audit history, not just a boolean flag) replaces the old
`configured`/`not_configured` guess. Full findings in
`docs/final-integrations/current-state-audit.md`.

Backend: 172 tests passing, ruff clean, mypy clean (50 files). Frontend: tsc
clean, production build clean.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-05 13:05:02 +02:00

194 lines
7.7 KiB
Python

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 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
assert db.scalar(select(func.count()).select_from(Booking)) == 246
# 15 from the CSV plus a deterministic set discovered by the post-seed scan. The
# shared vehicle-status evaluator (app.services.vehicle_status) now 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)) == 27
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
assert failed.last_error_code == "connectionError"
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 dead 'Today's movements' dashboard section:
at least two departures and two returns 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) >= 2
assert len(returns) >= 2
finally:
db.close()