Files
govoplan-workflow-engine/tests/test_dsar_provider.py
T

579 lines
20 KiB
Python

from __future__ import annotations
import json
import unittest
from datetime import UTC, datetime, timedelta
from sqlalchemy import create_engine
from sqlalchemy.orm import Session
from govoplan_core.core.dsar import (
DsarErasureActionRef,
DsarProvider,
DsarRecordRef,
DsarSubjectRef,
)
from govoplan_core.db.base import Base
from govoplan_core.privacy.dsar_workflow import (
create_data_subject_request,
search_data_subject_request,
)
from govoplan_workflow_engine.backend.db.models import (
WorkflowDefinition,
WorkflowDefinitionRevision,
WorkflowInstance,
WorkflowInstanceEvent,
WorkflowInstanceStep,
WorkflowTrigger,
WorkflowTriggerDelivery,
WorkflowWaitState,
)
from govoplan_workflow_engine.backend.dsar_provider import (
WORKFLOW_ENGINE_DSAR_CAPABILITY,
WorkflowEngineDsarProvider,
)
from govoplan_workflow_engine.backend.manifest import manifest
NOW = datetime(2026, 8, 21, 21, 0, tzinfo=UTC)
SECRET = "private-workflow-detail-do-not-export"
class _Registry:
def __init__(
self,
provider: WorkflowEngineDsarProvider,
*,
active: bool = True,
) -> None:
self.provider = provider
self.active = active
def capability_names(self):
return (WORKFLOW_ENGINE_DSAR_CAPABILITY,)
def capability_owner(self, name):
self._assert_capability(name)
return "workflow_engine"
def tenant_entitlement_resolver(self):
active = self.active
class _Resolver:
@staticmethod
def resolve(session, tenant_id):
del session, tenant_id
return type(
"State",
(),
{"effective_modules": ("workflow_engine",) if active else ()},
)()
return _Resolver()
def require_tenant_capability(self, name, session, **kwargs):
del session, kwargs
self._assert_capability(name)
return self.provider
def manifests(self):
return (type("Manifest", (), {"id": "workflow_engine"})(),)
@staticmethod
def _assert_capability(name: str) -> None:
if name != WORKFLOW_ENGINE_DSAR_CAPABILITY:
raise KeyError(name)
class WorkflowEngineDsarProviderTests(unittest.TestCase):
def setUp(self) -> None:
self.engine = create_engine("sqlite+pysqlite:///:memory:")
Base.metadata.create_all(self.engine)
self.session = Session(self.engine)
self.provider = WorkflowEngineDsarProvider()
self.assertIsInstance(self.provider, DsarProvider)
self._seed()
self.session.commit()
def tearDown(self) -> None:
self.session.close()
self.engine.dispose()
def _seed(self) -> None:
definition = WorkflowDefinition(
id="definition-1",
tenant_id="tenant-1",
scope_type="tenant",
scope_id="tenant-1",
scope_key="tenant:tenant-1",
definition_kind="flow",
definition_key="resident-permit",
name=SECRET,
description=SECRET,
status="active",
current_revision=1,
active_revision=1,
metadata_={"secret": SECRET},
derivation_provenance={"secret": SECRET},
created_by="account-1",
updated_by="account-1",
)
other = WorkflowDefinition(
id="definition-other",
tenant_id="tenant-2",
scope_type="tenant",
scope_id="tenant-2",
scope_key="tenant:tenant-2",
definition_kind="flow",
definition_key="other",
name=SECRET,
status="active",
current_revision=1,
created_by="account-1",
updated_by="account-1",
)
self.session.add_all((definition, other))
self.session.flush()
revision = WorkflowDefinitionRevision(
id="revision-1",
tenant_id="tenant-1",
definition_id=definition.id,
revision=1,
schema_version=1,
graph={"secret": SECRET},
content_hash="a" * 64,
library_id="bpmn",
library_version="1.0.0",
execution_mode="hybrid",
bpmn_xml=SECRET,
bpmn_hash="b" * 64,
bpmn_runtime_kind="native_graph",
bpmn_executable=True,
contribution_metadata={"secret": SECRET},
created_by="account-1",
)
self.session.add(revision)
self.session.flush()
instance = WorkflowInstance(
id="instance-1",
tenant_id="tenant-1",
definition_id=definition.id,
definition_revision_id=revision.id,
status="completed",
start_origin="service",
idempotency_key=SECRET,
correlation_id=SECRET,
input_={"secret": SECRET},
context_={"secret": SECRET},
output_={"secret": SECRET},
authorization_={
"account_id": "account-1",
"identity_id": "identity-1",
"membership_id": "membership-1",
"secret": SECRET,
},
started_at=NOW,
finished_at=NOW,
error=SECRET,
created_by="account-1",
)
self.session.add(instance)
self.session.flush()
step = WorkflowInstanceStep(
id="step-1",
tenant_id="tenant-1",
instance_id=instance.id,
sequence=1,
node_id="review",
node_type="human_task",
status="completed",
attempt=1,
idempotency_key=SECRET,
input_={"secret": SECRET},
output_={"secret": SECRET},
handoff={"secret": SECRET},
external_ref=SECRET,
started_at=NOW,
finished_at=NOW,
error=SECRET,
completed_by="account-1",
work_assignment_kind="membership",
work_assignment_id="membership-1",
work_assignment_label=SECRET,
work_due_at=NOW,
)
trigger = WorkflowTrigger(
id="trigger-1",
tenant_id="tenant-1",
definition_id=definition.id,
definition_revision_id=revision.id,
node_id="start-event",
kind="event",
status="active",
config_={"secret": SECRET},
event_type="permit.submitted",
next_fire_at=NOW + timedelta(hours=1),
last_error=SECRET,
authorization_subject_kind="delegated_user",
authorization_account_id="account-1",
authorization_membership_id="membership-1",
authorization_ref=SECRET,
grant_scopes=[SECRET],
created_by="account-1",
updated_by="account-1",
)
self.session.add_all((step, trigger))
self.session.flush()
self.session.add_all(
(
WorkflowInstanceEvent(
id="event-1",
tenant_id="tenant-1",
instance_id=instance.id,
step_id=step.id,
sequence=1,
kind="step.completed",
actor_id="account-1",
payload={"secret": SECRET},
created_at=NOW,
),
WorkflowTriggerDelivery(
id="delivery-1",
tenant_id="tenant-1",
trigger_id=trigger.id,
definition_id=definition.id,
definition_revision_id=revision.id,
source_key=SECRET,
invocation_kind="event",
status="succeeded",
scheduled_for=NOW,
event_={"secret": SECRET},
instance_id=instance.id,
attempts=1,
error=SECRET,
),
WorkflowWaitState(
id="wait-1",
tenant_id="tenant-1",
instance_id=instance.id,
step_id=step.id,
mode="event",
status="completed",
due_at=NOW,
event_type="permit.approved",
config_={"secret": SECRET},
source_event_id=SECRET,
event_={"secret": SECRET},
error=SECRET,
revision=1,
),
)
)
def test_canonical_selector_uses_structured_links_and_minimized_output(
self,
) -> None:
records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
account_id="account-1",
identity_id="identity-1",
membership_id="membership-1",
),
)
self.assertEqual(6, len(records))
categories = {record.resource_type: record.category for record in records}
self.assertEqual(
"workflow_automation_authority",
categories["workflow_trigger"],
)
self.assertEqual(
"workflow_subject_authorization",
categories["workflow_instance"],
)
self.assertEqual(
"workflow_subject_work_assignment",
categories["workflow_instance_step"],
)
exported = json.dumps([record.to_dict() for record in records])
self.assertNotIn(SECRET, exported)
self.assertNotIn("account-1", exported)
self.assertNotIn("identity-1", exported)
self.assertNotIn("membership-1", exported)
self.assertNotIn("definition-other", exported)
def test_exact_instance_and_definition_packages_are_review_only(self) -> None:
instance_records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
external_references={"workflow.instance": "instance:instance-1"}
),
)
definition_records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
external_references={"workflow.definition": "definition-1"}
),
)
self.assertEqual(4, len(instance_records))
self.assertEqual(8, len(definition_records))
self.assertNotIn(
SECRET,
json.dumps([record.to_dict() for record in definition_records]),
)
actions = self.provider.plan_erasure(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
external_references={"workflow.definition": "definition-1"}
),
records=definition_records,
)
self.assertEqual({"manual_review"}, {action.kind for action in actions})
def test_every_exact_reference_and_conflicts_fail_closed(self) -> None:
references = {
"workflow_engine.definition_revision": "revision-1",
"workflow_engine.step": "step-1",
"workflow_engine.event": "event-1",
"workflow_engine.trigger": "trigger-1",
"workflow_engine.trigger_delivery": "delivery-1",
"workflow_engine.wait_state": "wait-1",
}
for key, value in references.items():
with self.subTest(key=key):
records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(external_references={key: value}),
)
self.assertEqual(1, len(records))
mismatch = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
account_id="account-2",
external_references={"workflow.instance": "instance-1"},
),
)
wrong_tenant = self.provider.search_subject(
self.session,
tenant_id="tenant-2",
subject=DsarSubjectRef(
external_references={"workflow.instance": "instance-1"}
),
)
conflict = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=DsarSubjectRef(
external_references={
"workflow_engine.revision": "revision-1",
"workflow_engine.definition_revision": "different",
}
),
)
self.assertEqual((), mismatch)
self.assertEqual((), wrong_tenant)
self.assertEqual((), conflict)
def test_terminal_delivery_minimization_preserves_replay_identity(self) -> None:
subject = DsarSubjectRef(
external_references={"workflow_engine.delivery": "delivery-1"}
)
records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=subject,
)
actions = self.provider.plan_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
records=records,
)
self.assertEqual("anonymize", actions[0].kind)
first = self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
actions=actions,
request_id="dsar-1",
)
second = self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
actions=actions,
request_id="dsar-1-retry",
)
self.assertEqual("executed", first[0].status)
self.assertEqual("unchanged", second[0].status)
delivery = self.session.get(WorkflowTriggerDelivery, "delivery-1")
self.assertIsNone(delivery.event_)
self.assertIsNone(delivery.error)
self.assertEqual(SECRET, delivery.source_key)
def test_automation_authority_revocation_is_idempotent(self) -> None:
subject = DsarSubjectRef(
account_id="account-1",
membership_id="membership-1",
)
records = self.provider.search_subject(
self.session,
tenant_id="tenant-1",
subject=subject,
)
actions = self.provider.plan_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
records=records,
)
trigger_action = next(
action for action in actions if action.resource_type == "workflow_trigger"
)
self.assertEqual("revoke", trigger_action.kind)
first = self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
actions=(trigger_action,),
request_id="dsar-2",
)
second = self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
actions=(trigger_action,),
request_id="dsar-2-retry",
)
self.assertEqual("executed", first[0].status)
self.assertEqual("unchanged", second[0].status)
trigger = self.session.get(WorkflowTrigger, "trigger-1")
self.assertEqual("disabled", trigger.status)
self.assertIsNone(trigger.authorization_account_id)
self.assertIsNone(trigger.authorization_membership_id)
self.assertEqual([], trigger.grant_scopes)
self.assertEqual({}, trigger.config_)
def test_foreign_records_and_actions_are_rejected(self) -> None:
subject = DsarSubjectRef(account_id="account-1")
with self.assertRaisesRegex(ValueError, "foreign provider record"):
self.provider.plan_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
records=(
DsarRecordRef(
provider_id="cases",
module_id="cases",
resource_type="case",
resource_id="case-1",
category="case",
title="Case",
),
),
)
with self.assertRaisesRegex(ValueError, "foreign provider action"):
self.provider.execute_erasure(
self.session,
tenant_id="tenant-1",
subject=subject,
actions=(
DsarErasureActionRef(
action_id="cases:delete:case:case-1",
provider_id="cases",
module_id="cases",
kind="delete",
resource_type="case",
resource_id="case-1",
title="Delete case",
rationale="Foreign",
executable=True,
),
),
request_id="dsar-3",
)
def test_core_workflow_reports_active_and_inactive_provider(self) -> None:
row = create_data_subject_request(
self.session,
tenant_id="tenant-1",
reference="DSAR-WORKFLOW-1",
request_kind="access_and_erasure",
subject=DsarSubjectRef(account_id="account-1"),
purpose="Respond to a verified request.",
legal_basis="Article 15 and 17 GDPR",
due_at=None,
requested_by_account_id="privacy-officer",
)
self.session.commit()
search_data_subject_request(
self.session,
registry=_Registry(self.provider),
row=row,
expected_revision=1,
)
self.assertEqual(
[WORKFLOW_ENGINE_DSAR_CAPABILITY],
row.coverage["provider_capabilities"],
)
self.assertEqual(6, row.search_result["record_count"])
inactive = create_data_subject_request(
self.session,
tenant_id="tenant-1",
reference="DSAR-WORKFLOW-2",
request_kind="access",
subject=DsarSubjectRef(account_id="account-1"),
purpose="Respond to a verified request.",
legal_basis="Article 15 GDPR",
due_at=None,
requested_by_account_id="privacy-officer",
)
self.session.commit()
search_data_subject_request(
self.session,
registry=_Registry(self.provider, active=False),
row=inactive,
expected_revision=1,
)
self.assertEqual([], inactive.coverage["provider_capabilities"])
self.assertEqual(
[WORKFLOW_ENGINE_DSAR_CAPABILITY],
inactive.coverage["inactive_provider_capabilities"],
)
self.assertEqual(0, inactive.search_result["record_count"])
def test_manifest_registers_and_documents_capability(self) -> None:
self.assertIn(
WORKFLOW_ENGINE_DSAR_CAPABILITY,
manifest.capability_factories,
)
self.assertIn(
WORKFLOW_ENGINE_DSAR_CAPABILITY,
manifest.capability_documentation,
)
self.assertIn(
WORKFLOW_ENGINE_DSAR_CAPABILITY,
{item.name for item in manifest.provides_interfaces},
)
self.assertTrue(
any(
topic.id == "workflow.data-subject-requests"
and {"admin", "user"}.issubset(topic.documentation_types)
for topic in manifest.documentation
)
)
if __name__ == "__main__":
unittest.main()