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:
co-authored by
genichin
parent
5eef76d59e
commit
8b3e7ac753
@@ -23,6 +23,28 @@ def test_long_outage_backoff_is_capped_and_status_stays_valid():
|
||||
assert state["failure_code"] == "http_5xx"
|
||||
|
||||
|
||||
def test_long_outage_over_1100_failures_never_overflows_and_stays_capped():
|
||||
now = {"t": datetime(2026, 9, 12, tzinfo=UTC)}
|
||||
tracker = BalanceHealthTracker(clock=lambda: now["t"], base_backoff_sec=15, max_backoff_sec=300)
|
||||
|
||||
last_lifecycle = None
|
||||
for i in range(1_100):
|
||||
lifecycle, backoff = tracker.record_failure("execution", code="http_5xx")
|
||||
last_lifecycle = lifecycle
|
||||
if i >= 5:
|
||||
assert backoff == 300.0
|
||||
else:
|
||||
assert backoff <= 300.0
|
||||
now["t"] += timedelta(seconds=301)
|
||||
|
||||
state = tracker.status("execution", stale_after_sec=600)
|
||||
assert state["state"] == "unavailable"
|
||||
assert state["consecutive_failures"] == 1_100
|
||||
assert state["failure_code"] == "http_5xx"
|
||||
assert state["next_retry_at"] is not None
|
||||
assert last_lifecycle in {None, "ongoing"}
|
||||
|
||||
|
||||
def test_restart_resets_process_local_health_and_re_emits_detected():
|
||||
now = {"t": datetime(2026, 9, 12, tzinfo=UTC)}
|
||||
before_restart = BalanceHealthTracker(clock=lambda: now["t"])
|
||||
|
||||
@@ -7,6 +7,8 @@ from __future__ import annotations
|
||||
|
||||
from datetime import UTC, datetime, timedelta
|
||||
|
||||
import pytest
|
||||
|
||||
from trex_core.adapters.broker.paper import PaperBroker
|
||||
from trex_core.adapters.persistence.in_memory_intent_store import InMemoryIntentStore
|
||||
from trex_core.application.account_snapshot import AccountSnapshotUnavailable
|
||||
@@ -303,6 +305,70 @@ def test_pending_sell_health_preserves_non_transient_snapshot_failure_code():
|
||||
assert health["failure_code"] == "authentication_failed"
|
||||
|
||||
|
||||
@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_execution_wrapper_classification_fail_closed_matrix(error_code):
|
||||
broker = PaperBroker(fill_after_polls=0)
|
||||
repo, svc, intents, _ = _wire(broker)
|
||||
sid = _buy(intents, qty=3).slot_id
|
||||
ExecutionService(svc, repo, broker, instance_key=INST).run_once()
|
||||
svc.sell(sid, actor="t", reason="full")
|
||||
|
||||
calls = {"n": 0}
|
||||
|
||||
def fail_reader():
|
||||
calls["n"] += 1
|
||||
raise AccountSnapshotUnavailable("live_read_failed", detail_code=error_code)
|
||||
|
||||
execution = ExecutionService(
|
||||
svc,
|
||||
repo,
|
||||
broker,
|
||||
instance_key=INST,
|
||||
balance_reader=fail_reader,
|
||||
)
|
||||
result = execution.run_once()
|
||||
assert result.dispatched == 0
|
||||
assert result.sell_skipped_no_balance == 1
|
||||
assert calls["n"] == 1
|
||||
health = execution.balance_worker_health(stale_after_sec=600)
|
||||
assert health["state"] == "unavailable"
|
||||
assert health["consecutive_failures"] == 1
|
||||
assert health["failure_code"] == error_code
|
||||
|
||||
|
||||
def test_execution_wrapper_treats_validated_empty_success_as_success_not_failure():
|
||||
broker = PaperBroker(fill_after_polls=0)
|
||||
repo, svc, intents, _ = _wire(broker)
|
||||
sid = _buy(intents, qty=3).slot_id
|
||||
ExecutionService(svc, repo, broker, instance_key=INST).run_once()
|
||||
svc.sell(sid, actor="t", reason="full")
|
||||
|
||||
execution = ExecutionService(
|
||||
svc,
|
||||
repo,
|
||||
broker,
|
||||
instance_key=INST,
|
||||
balance_reader=lambda: [],
|
||||
)
|
||||
result = execution.run_once()
|
||||
assert result.dispatched == 0
|
||||
assert result.sell_skipped_no_balance == 1 # broker flat is valid success
|
||||
health = execution.balance_worker_health(stale_after_sec=600)
|
||||
assert health["state"] == "ok"
|
||||
assert health["consecutive_failures"] == 0
|
||||
assert health["failure_code"] is None
|
||||
|
||||
|
||||
def test_partial_sell_qty_is_min_intent_broker():
|
||||
"""dcy-021/REQ-062 (D4): partial sell dispatches min(intent qty, broker);
|
||||
remainder stays holding (broker-authoritative qty), cost basis preserved."""
|
||||
|
||||
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user