app.bettersight.io/backend/tests/test_api.py

"""
Integration tests for api.py routes, run against mock repositories
(USE_MOCK_REPOSITORIES=true, set in conftest.py before any import).
"""
from repositories.tenant_repository import tenant_repository
from repositories.seat_repository import seat_repository
from repositories.competitor_repository import competitor_repository


def _make_tenant(**overrides):
    data = {
        'name': 'G Adventures', 'email': 'pm@gadventures.com', 'domain': 'gadventures.com',
        'tier': 'analyse', 'status': 'active', 'max_seats': 5,
    }
    data.update(overrides)
    return tenant_repository.create(data)


def test_health_requires_no_auth(client):
    response = client.get('/health')
    assert response.status_code == 200
    assert response.json == {'status': 'ok', 'version': '0.1.0-phase1'}


def test_protected_route_rejects_missing_api_key(client):
    response = client.post('/validate-email', json={'email': 'pm@gadventures.com'})
    assert response.status_code == 401
    assert response.json['error'] is True
    assert response.json['code'] == 'unauthorized'


def test_protected_route_rejects_wrong_api_key(client):
    response = client.post(
        '/validate-email', json={'email': 'pm@gadventures.com'},
        headers={'X-API-Key': 'wrong-key'}
    )
    assert response.status_code == 401


def test_validate_email_happy_path(client, api_headers):
    _make_tenant()
    response = client.post('/validate-email', json={'email': 'pm@gadventures.com'}, headers=api_headers)
    assert response.status_code == 200
    assert response.json == {'valid': True, 'tier': 'analyse'}


def test_validate_email_missing_field_returns_structured_error(client, api_headers):
    response = client.post('/validate-email', json={}, headers=api_headers)
    assert response.status_code == 400
    assert response.json['error'] is True
    assert response.json['code'] == 'missing_field'


def test_add_seat_rejects_when_tenant_at_seat_limit(client, api_headers):
    tenant = _make_tenant(max_seats=1)
    seat_repository.create({'tenant_id': tenant['id'], 'email': 'first@gadventures.com', 'active': True})

    response = client.post(
        '/account/seats', json={'tenant_id': tenant['id'], 'email': 'second@gadventures.com'},
        headers=api_headers
    )

    assert response.status_code == 400
    assert response.json['code'] == 'seat_limit_reached'


def test_add_seat_succeeds_under_limit(client, api_headers):
    tenant = _make_tenant(max_seats=5)

    response = client.post(
        '/account/seats', json={'tenant_id': tenant['id'], 'email': 'newuser@gadventures.com'},
        headers=api_headers
    )

    assert response.status_code == 201
    assert seat_repository.count_active(tenant['id']) == 1


def test_remove_seat(client, api_headers):
    tenant = _make_tenant()
    seat = seat_repository.create({'tenant_id': tenant['id'], 'email': 'x@gadventures.com', 'active': True})

    response = client.delete(f'/account/seats/{seat["id"]}', headers=api_headers)

    assert response.status_code == 200
    assert seat_repository.count_active(tenant['id']) == 0


def test_get_competitors_resolves_tenant_by_email_header(client, api_headers):
    tenant = _make_tenant()
    competitor_repository.create({
        'tenant_id': tenant['id'], 'name': 'Intrepid Travel', 'website': 'https://intrepidtravel.com',
        'catalogue_url': 'https://intrepidtravel.com/adventures', 'primary_market': 'GB', 'active': True,
    })

    response = client.get('/competitors', headers={**api_headers, 'X-User-Email': 'pm@gadventures.com'})

    assert response.status_code == 200
    body = response.json
    assert len(body) == 1
    assert body[0]['name'] == 'Intrepid Travel'
    assert body[0]['status'] == 'stale'  # never scraped → stale


def test_get_competitors_unknown_email_returns_404(client, api_headers):
    response = client.get('/competitors', headers={**api_headers, 'X-User-Email': 'nobody@nowhere.com'})
    assert response.status_code == 404


def test_research_find_urls_requires_fields(client, api_headers):
    response = client.post('/research/find-urls', json={}, headers=api_headers)
    assert response.status_code == 400
    assert response.json['code'] == 'missing_field'


def test_research_find_urls_omits_own_trip_without_tenant_id(client, api_headers, monkeypatch):
    monkeypatch.setattr(
        'api.trip_finder_service.find_all_competitor_urls',
        lambda competitors, destination, duration, travel_style: [],
    )
    response = client.post('/research/find-urls', json={
        'destination': 'Peru', 'duration': 15, 'travel_style': 'Classic', 'competitor_ids': [],
    }, headers=api_headers)

    assert response.status_code == 200
    assert response.json['own_trip'] is None


def test_research_find_urls_omits_own_trip_when_tenant_has_no_website(client, api_headers, monkeypatch):
    tenant = _make_tenant()
    monkeypatch.setattr(
        'api.trip_finder_service.find_all_competitor_urls',
        lambda competitors, destination, duration, travel_style: [],
    )
    response = client.post('/research/find-urls', json={
        'tenant_id': tenant['id'], 'destination': 'Peru', 'duration': 15,
        'travel_style': 'Classic', 'competitor_ids': [],
    }, headers=api_headers)

    assert response.status_code == 200
    assert response.json['own_trip'] is None


def test_research_find_urls_includes_own_trip_when_tenant_has_website(client, api_headers, monkeypatch):
    tenant = _make_tenant(website='https://wildhorizons.com')
    monkeypatch.setattr(
        'api.trip_finder_service.find_all_competitor_urls',
        lambda competitors, destination, duration, travel_style: [],
    )
    monkeypatch.setattr(
        'api.trip_finder_service.find_own_trip_url',
        lambda website, destination, duration, travel_style: {'url': f'{website}/peru-classic', 'confidence': 0.9, 'found': True},
    )
    response = client.post('/research/find-urls', json={
        'tenant_id': tenant['id'], 'destination': 'Peru', 'duration': 15,
        'travel_style': 'Classic', 'competitor_ids': [],
    }, headers=api_headers)

    assert response.status_code == 200
    assert response.json['own_trip'] == {'url': 'https://wildhorizons.com/peru-classic', 'confidence': 0.9, 'found': True}


def test_research_enqueues_job_without_touching_real_redis(client, api_headers, monkeypatch):
    import jobs
    tenant = _make_tenant()
    captured = {}

    def _fake_enqueue(job_id, data):
        captured['job_id'] = job_id
        captured['data'] = data
        return job_id

    monkeypatch.setattr(jobs, 'enqueue_research_job', _fake_enqueue)

    response = client.post('/research', json={
        'tenant_id': tenant['id'], 'destination': 'Peru', 'duration': 15,
        'travel_style': 'Classic', 'tab_type': 'Standard', 'competitors': [],
    }, headers=api_headers)

    assert response.status_code == 200
    assert response.json['status'] == 'queued'
    assert captured['job_id'] == response.json['job_id']


def test_research_persists_created_by_email(client, api_headers, monkeypatch):
    import jobs
    from repositories.scrape_repository import scrape_repository
    tenant = _make_tenant()
    monkeypatch.setattr(jobs, 'enqueue_research_job', lambda job_id, data: job_id)

    response = client.post('/research', json={
        'tenant_id': tenant['id'], 'destination': 'Peru', 'duration': 15,
        'travel_style': 'Classic', 'tab_type': 'Standard', 'competitors': [],
        'email': 'pm@gadventures.com',
    }, headers=api_headers)

    run = scrape_repository.get_by_id(response.json['job_id'])
    assert run['created_by_email'] == 'pm@gadventures.com'


def test_research_persists_client_trip_from_trip_intent(client, api_headers, monkeypatch):
    from repositories.client_trips_repository import client_trips_repository
    import jobs
    tenant = _make_tenant()
    monkeypatch.setattr(jobs, 'enqueue_research_job', lambda job_id, data: job_id)

    client.post('/research', json={
        'tenant_id': tenant['id'], 'destination': 'Peru', 'duration': 15,
        'travel_style': 'Classic', 'tab_type': 'Standard', 'competitors': [],
        'productName': 'Inca Trail Classic',
    }, headers=api_headers)

    trips = client_trips_repository.list_for_tenant(tenant['id'])
    assert len(trips) == 1
    assert trips[0]['trip_name'] == 'Inca Trail Classic'
    assert trips[0]['destination'] == 'Peru'


def test_research_still_queues_job_when_client_trip_save_fails(client, api_headers, monkeypatch):
    import jobs
    tenant = _make_tenant()
    monkeypatch.setattr(jobs, 'enqueue_research_job', lambda job_id, data: job_id)
    monkeypatch.setattr(
        'services.embedding_service.save_client_trip',
        lambda *a, **k: (_ for _ in ()).throw(RuntimeError('pocketbase down'))
    )

    response = client.post('/research', json={
        'tenant_id': tenant['id'], 'destination': 'Peru', 'duration': 15,
        'travel_style': 'Classic', 'tab_type': 'Standard', 'competitors': [],
    }, headers=api_headers)

    assert response.status_code == 200  # side-effect failure never blocks the primary operation
    assert response.json['status'] == 'queued'


def test_bulk_import_rejects_more_than_fifty_rows(client, api_headers):
    tenant = _make_tenant()
    rows = [
        {'name': f'Comp {i}', 'website': f'https://comp{i}.com',
         'catalogue_url': f'https://comp{i}.com/trips', 'primary_market': 'GB'}
        for i in range(51)
    ]
    response = client.post(
        '/account/competitors/bulk', json={'tenant_id': tenant['id'], 'rows': rows}, headers=api_headers
    )
    assert response.status_code == 400
    assert response.json['code'] == 'too_many_rows'


def test_competitors_template_download(client, api_headers):
    response = client.get('/account/competitors/template', headers=api_headers)
    assert response.status_code == 200
    assert response.mimetype == 'text/csv'
    assert b'name,website,catalogue_url,primary_market' in response.data