fix(broker): cap outage backoff overflow and expand worker matrix coverage

Co-authored-by: genichin <4282227+genichin@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-09-13 06:40:06 +00:00
committed by GitHub
co-authored by genichin
parent 5eef76d59e
commit 8b3e7ac753
5 changed files with 275 additions and 6 deletions
@@ -5,6 +5,8 @@ from datetime import UTC, datetime, timedelta, timezone
from types import SimpleNamespace
from unittest.mock import MagicMock
import pytest
from trex_core.adapters.broker.paper import PaperBroker
from trex_core.adapters.portfolio.stub_read import StubPortfolioRead
from trex_core.application.alarm_emitter import AlarmEmitter
@@ -896,3 +898,172 @@ def test_run_forever_retries_due_worker_on_production_loop_path():
state = sched.balance_worker_health(stale_after_sec=86_400)
assert state["position_reconciliation"]["state"] == "ok"
assert state["position_reconciliation"]["consecutive_failures"] == 0
@pytest.mark.parametrize(
"error_code",
[
"timeout",
"http_5xx",
"authentication_failed",
"token_issuance_failed",
"malformed_response",
],
ids=["timeout", "http_5xx", "auth", "token", "pagination_middle_malformed"],
)
def test_position_worker_classification_matrix_is_fail_closed(error_code):
from trex_core.application.broker_port import BrokerBalanceError
from trex_core.domain.slot import SlotService
from trex_core.domain.slot.in_memory_repository import InMemorySlotRepository
class ReadOnce:
def whoami(self):
return "d-1"
def get_portfolios(self, _daemon_id):
return [PortfolioItem(portfolio_id="pf-X", symbol="X", cash_balance=100, asset_quantity=1)]
class RaiseOrListBroker:
def __init__(self, failure: str | None):
self.failure = failure
def get_balance(self):
if self.failure is not None:
raise BrokerBalanceError(self.failure)
return []
store = SnapshotStore()
slot_repo = InMemorySlotRepository()
slot_service = SlotService(slot_repo, instance_key="default")
slot_repo.reconcile_universe("default", {"pf-X": "X"})
store.swap([PortfolioItem(portfolio_id="pf-X", symbol="X", cash_balance=100, asset_quantity=1)])
store.set_warning("pf-X", True)
sched = SnapshotScheduler(
read_port=ReadOnce(),
store=store,
broker=RaiseOrListBroker(error_code),
core_holdings_broker=RaiseOrListBroker(None),
slot_repo=slot_repo,
slot_service=slot_service,
)
assert sched.run_once() is True
health = sched.balance_worker_health(stale_after_sec=86_400)
assert health["position_reconciliation"]["state"] == "unavailable"
assert health["position_reconciliation"]["failure_code"] == error_code
assert health["position_reconciliation"]["consecutive_failures"] == 1
assert health["core_holding_reconciliation"]["state"] == "ok"
# fail-closed on failure: warning clear path did not run.
assert store.get("pf-X").warning is True
def test_position_worker_validated_empty_success_does_not_create_failure_state():
from trex_core.domain.slot import SlotService
from trex_core.domain.slot.in_memory_repository import InMemorySlotRepository
class ReadOnce:
def whoami(self):
return "d-1"
def get_portfolios(self, _daemon_id):
return [PortfolioItem(portfolio_id="pf-X", symbol="X", cash_balance=100, asset_quantity=0)]
class EmptyBalanceBroker:
def get_balance(self):
return []
store = SnapshotStore()
slot_repo = InMemorySlotRepository()
slot_service = SlotService(slot_repo, instance_key="default")
slot_repo.reconcile_universe("default", {"pf-X": "X"})
sched = SnapshotScheduler(
read_port=ReadOnce(),
store=store,
broker=EmptyBalanceBroker(),
core_holdings_broker=EmptyBalanceBroker(),
slot_repo=slot_repo,
slot_service=slot_service,
)
assert sched.run_once() is True
health = sched.balance_worker_health(stale_after_sec=86_400)
assert health["position_reconciliation"]["state"] == "ok"
assert health["position_reconciliation"]["consecutive_failures"] == 0
assert health["position_reconciliation"]["failure_code"] is None
@pytest.mark.parametrize(
"error_code",
[
"timeout",
"http_5xx",
"authentication_failed",
"token_issuance_failed",
"malformed_response",
],
ids=["timeout", "http_5xx", "auth", "token", "pagination_middle_malformed"],
)
def test_core_worker_classification_matrix_is_fail_closed(error_code):
from trex_core.application.broker_port import BrokerBalanceError
from trex_core.domain.slot import SlotService, SlotState
from trex_core.domain.slot.in_memory_repository import InMemorySlotRepository
class ReadOnce:
def whoami(self):
return "d-1"
def get_portfolios(self, _daemon_id):
return [PortfolioItem(portfolio_id="pf-X", symbol="X", cash_balance=100, asset_quantity=0)]
class EmptyBalanceBroker:
def get_balance(self):
return []
class ErrorBroker:
def __init__(self, failure: str):
self.failure = failure
def get_balance(self):
raise BrokerBalanceError(self.failure)
slot_repo = InMemorySlotRepository()
slot_service = SlotService(slot_repo, instance_key="default")
slot_repo.reconcile_universe("default", {"pf-X": "X"})
slot = slot_repo.find_slot_by_portfolio("default", "pf-X")
pending = slot_service.transit_slot(
slot.slot_id,
SlotState.INACTIVE,
SlotState.PENDING_BUY,
reason="buy",
actor="test",
symbol="X",
)
slot_service.transit_slot(
pending.slot_id,
SlotState.PENDING_BUY,
SlotState.HOLDING,
reason="filled",
actor="test",
avg_price=100.0,
qty=1.0,
)
before = slot_repo.fetch_slot(slot.slot_id)
sched = SnapshotScheduler(
read_port=ReadOnce(),
store=SnapshotStore(),
broker=EmptyBalanceBroker(),
core_holdings_broker=ErrorBroker(error_code),
slot_repo=slot_repo,
slot_service=slot_service,
)
assert sched.run_once() is True
health = sched.balance_worker_health(stale_after_sec=86_400)
assert health["position_reconciliation"]["state"] == "ok"
assert health["core_holding_reconciliation"]["state"] == "unavailable"
assert health["core_holding_reconciliation"]["failure_code"] == error_code
assert health["core_holding_reconciliation"]["consecutive_failures"] == 1
# fail-closed on failure: no slot mutation on this failed core reconcile.
after = slot_repo.fetch_slot(slot.slot_id)
assert after.status is before.status
assert after.qty == before.qty