piker/tests/test_ib_history.py

589 lines
15 KiB
Python

'''
IB historical-data request regressions.
'''
from datetime import (
UTC,
datetime,
)
from types import SimpleNamespace
from ib_async import RequestError
import numpy as np
from pendulum import (
datetime as pdatetime,
duration,
)
import pytest
import trio
from piker.brokers import DataUnavailable
from piker.brokers.ib import feed as ib_feed
from piker.brokers.ib.api import Client
from piker.brokers.ib.feed import get_bars
@pytest.mark.parametrize(
('end_dt', 'expected'),
[
(None, ''),
(
datetime(2026, 7, 28, 23, 30, tzinfo=UTC),
'20260728-23:30:00',
),
(
pdatetime(2026, 7, 28, 23, 30, tz='UTC'),
'20260728-23:30:00',
),
(
pdatetime(
2026,
7,
28,
23,
30,
tz='America/New_York',
),
'20260729-03:30:00',
),
],
)
def test_history_end_datetime_uses_ib_utc_format(
end_dt: datetime|None,
expected: str,
) -> None:
'''
Reverse history boundaries must use IB's explicit UTC syntax.
``ib_async`` adds a trailing ``UTC`` zone to aware datetimes.
The live IB gateway rejected that form with error 10314 while
filling an MNQ gap. Invoke ``Client.bars()`` with stdlib and
Pendulum boundaries, then capture the request kwargs.
Prove each becomes IB's UTC-dash form while latest requests stay
blank.
'''
request: dict = {}
class FakeIB:
async def reqHistoricalDataAsync(self, **kwargs) -> list:
request.update(kwargs)
return []
client = SimpleNamespace(ib=FakeIB())
async def find_contracts(fqme: str) -> list:
return [SimpleNamespace()]
client.find_contracts = find_contracts
async def main() -> None:
await Client.bars(
client,
fqme='mnq.cme.20260918',
sample_period_s=60,
end_dt=end_dt,
)
trio.run(main)
assert request['endDateTime'] == expected
def test_empty_history_frame_completes() -> None:
'''
A blank IB response must release the history request slot.
``get_bars()`` previously returned from its query task without
signalling the parent, which then reset the feed forever. That
kept serialized SHM repair from running. Return IB's empty
response and prove the request completes explicitly
with no result instead of relying on a reset timeout.
'''
class Proxy:
'''
Return one empty IB history response.
'''
async def bars(self, **kwargs):
'''
Model ``Client.bars()`` during a venue data gap.
'''
return (
[],
np.empty(0),
duration(seconds=2000),
)
async def main() -> None:
with trio.fail_after(0.1):
result, timedout = await get_bars(
Proxy(),
'qqq.nasdaq.ib',
1,
)
assert result is None
assert not timedout
trio.run(main)
def test_repeated_ib_cancellation_is_bounded() -> None:
'''
Repeated IB cancellation must not monopolize history forever.
IB can answer a historical request with error 162 cancellation.
The old retry loop had no limit, so reverse backfill could retain
the backend's sole request slot and prevent final null repair.
Always raise that response and prove the configured retry bound
terminates with ``DataUnavailable`` deterministically.
'''
class Proxy:
'''
Cancel every IB history request.
'''
async def bars(self, **kwargs):
'''
Raise IB's historical-query cancellation response.
'''
raise RequestError(
1,
162,
'API historical data query cancelled',
)
async def main() -> None:
with (
trio.fail_after(0.1),
pytest.raises(DataUnavailable),
):
await get_bars(
Proxy(),
'qqq.nasdaq.ib',
1,
max_failed_resets=2,
)
trio.run(main)
def test_query_error_cancels_stalled_reset(
monkeypatch: pytest.MonkeyPatch,
) -> None:
'''
Exceptional history exit must cancel its in-flight reset task.
A timed-out request acquires the reset lock before launching
IB's VNC reset task. If the query then raises while that task is
blocked, stale work must not retain the reset lock. Force that
ordering with explicit Trio checkpoints, then prove bounded query
failure cancels the reset task before propagating.
'''
reset_cancelled: list[bool] = []
class Proxy:
'''
Delay once, then return IB cancellation.
'''
async def bars(self, **kwargs):
'''
Let the parent acquire the reset lock before failing.
'''
await trio.sleep(0.02)
raise RequestError(
1,
162,
'API historical data query cancelled',
)
async def stalled_reset(
proxy,
reset_type='data',
task_status=trio.TASK_STATUS_IGNORED,
) -> bool:
'''
Publish reset state, then block until sibling failure.
'''
done = trio.Event()
result: list[bool] = []
with trio.CancelScope() as cs:
task_status.started((cs, done, result))
try:
await trio.sleep_forever()
finally:
reset_cancelled.append(True)
return False
monkeypatch.setattr(
ib_feed,
'wait_on_data_reset',
stalled_reset,
)
async def main() -> None:
with (
trio.fail_after(0.1),
pytest.raises(DataUnavailable),
):
await get_bars(
Proxy(),
'qqq.nasdaq.ib',
1,
feed_reset_timeout=0.001,
max_failed_resets=1,
)
trio.run(main)
assert reset_cancelled == [True]
def test_failed_pacing_resets_reach_retry_limit(
monkeypatch: pytest.MonkeyPatch,
) -> None:
'''
Failed pacing resets must increment the request's retry count.
The reset API returns an ``Event`` and result box. The old
code tested the always-truthy event and reset the failure counter
after each failure. Return immediate failures and prove two
pacing responses terminate instead of looping forever.
'''
reset_calls: list[bool] = []
class Proxy:
'''
Return a pacing violation for every request.
'''
_aio_ns = SimpleNamespace(
ib=SimpleNamespace(
client=SimpleNamespace(),
),
)
async def bars(self, **kwargs):
'''
Raise IB's pacing response.
'''
raise RequestError(
1,
162,
ib_feed._pacing,
)
async def failed_reset(
proxy,
reset_type='data',
task_status=trio.TASK_STATUS_IGNORED,
) -> bool:
'''
Publish one completed, unsuccessful reset.
'''
done = trio.Event()
result = [False]
reset_calls.append(True)
with trio.CancelScope() as cs:
task_status.started((cs, done, result))
done.set()
return False
monkeypatch.setattr(
ib_feed,
'wait_on_data_reset',
failed_reset,
)
async def main() -> None:
with (
trio.fail_after(0.1),
pytest.raises(DataUnavailable),
):
await get_bars(
Proxy(),
'qqq.nasdaq.ib',
1,
max_failed_resets=2,
)
trio.run(main)
assert reset_calls == [True, True]
def test_pacing_resets_are_serialized_across_requests(
monkeypatch: pytest.MonkeyPatch,
) -> None:
'''
Concurrent history requests must never reset IB farms together.
Pacing recovery bypassed reset ownership, allowing 1s and 60s
requests to launch the VNC hack concurrently. Start two pacing
failures in one nursery and hold each fake reset across a Trio
checkpoint. Active-count assertions prove the actor-global lock
serializes reset lifetimes without depending on scheduler timing.
'''
active: int = 0
max_active: int = 0
reset_calls: int = 0
class Proxy:
'''
Return a pacing violation for every request.
'''
_aio_ns = SimpleNamespace(
ib=SimpleNamespace(
client=SimpleNamespace(),
),
)
async def bars(self, **kwargs):
'''
Raise IB's pacing response.
'''
raise RequestError(
1,
162,
ib_feed._pacing,
)
async def failed_reset(
proxy,
reset_type='data',
task_status=trio.TASK_STATUS_IGNORED,
) -> bool:
'''
Hold one failed reset long enough to expose overlap.
'''
nonlocal active, max_active, reset_calls
done = trio.Event()
result: list[bool] = []
with trio.CancelScope() as cs:
task_status.started((cs, done, result))
active += 1
reset_calls += 1
max_active = max(max_active, active)
await trio.sleep(0.01)
active -= 1
result.append(False)
done.set()
return False
monkeypatch.setattr(
ib_feed,
'wait_on_data_reset',
failed_reset,
)
async def request() -> None:
'''
Run one independently bounded history request.
'''
with pytest.raises(DataUnavailable):
await get_bars(
Proxy(),
'qqq.nasdaq.ib',
1,
max_failed_resets=1,
)
async def main() -> None:
with trio.fail_after(0.1):
async with trio.open_nursery() as nursery:
nursery.start_soon(request)
nursery.start_soon(request)
trio.run(main)
assert reset_calls == 2
assert max_active == 1
def test_pacing_supersedes_timeout_reset_once(
monkeypatch: pytest.MonkeyPatch,
) -> None:
'''
Pacing handoff must not count cancellation as another failure.
A slow request can trigger timeout recovery immediately before IB
returns a pacing violation. Query-side recovery then deliberately
cancels that data reset and waits for the same actor-global lock.
Reproduce this with blocked first and failed second resets. A
one-attempt limit proves cancellation releases the lock
without aborting before the intended connection reset runs.
'''
reset_types: list[str] = []
class Proxy:
'''
Return pacing only after timeout recovery starts.
'''
_aio_ns = SimpleNamespace(
ib=SimpleNamespace(
client=SimpleNamespace(),
),
)
async def bars(self, **kwargs):
'''
Delay past the reset timeout, then report pacing.
'''
await trio.sleep(0.02)
raise RequestError(
1,
162,
ib_feed._pacing,
)
async def reset(
proxy,
reset_type='data',
task_status=trio.TASK_STATUS_IGNORED,
) -> bool:
'''
Block data reset and fail connection reset immediately.
'''
done = trio.Event()
result: list[bool] = []
reset_types.append(reset_type)
with trio.CancelScope() as cs:
task_status.started((cs, done, result))
if reset_type == 'data':
await trio.sleep_forever()
result.append(False)
done.set()
return False
monkeypatch.setattr(
ib_feed,
'wait_on_data_reset',
reset,
)
async def main() -> None:
with (
trio.fail_after(0.1),
pytest.raises(DataUnavailable),
):
await get_bars(
Proxy(),
'qqq.nasdaq.ib',
1,
feed_reset_timeout=0.001,
max_failed_resets=1,
)
trio.run(main)
assert reset_types == ['data', 'connection']
def test_completed_pacing_reset_restarts_timeout_wait(
monkeypatch: pytest.MonkeyPatch,
) -> None:
'''
A queued timeout waiter must consume completed pacing recovery.
While query-side pacing recovery holds the reset lock, the outer
timeout task can already queue behind it. Without a completion
handoff, that waiter launches a redundant data reset immediately.
Return a blank frame just after a successful connection reset and
prove no third reset runs before the restarted timeout observes
completion.
'''
reset_types: list[str] = []
class Proxy:
'''
Pace the first query and return blank data on retry.
'''
_aio_ns = SimpleNamespace(
ib=SimpleNamespace(
client=SimpleNamespace(),
),
)
def __init__(self) -> None:
self.calls: int = 0
async def bars(self, **kwargs):
'''
Control the pacing-to-success handoff ordering.
'''
self.calls += 1
if self.calls == 1:
await trio.sleep(0.02)
raise RequestError(
1,
162,
ib_feed._pacing,
)
await trio.sleep(0.0005)
return (
[],
np.empty(0),
duration(seconds=2000),
)
async def reset(
proxy,
reset_type='data',
task_status=trio.TASK_STATUS_IGNORED,
) -> bool:
'''
Cancel timeout recovery and complete pacing recovery.
'''
done = trio.Event()
result: list[bool] = []
reset_types.append(reset_type)
with trio.CancelScope() as cs:
task_status.started((cs, done, result))
if reset_type == 'data':
await trio.sleep_forever()
result.append(reset_type == 'connection')
done.set()
return result[0]
monkeypatch.setattr(
ib_feed,
'wait_on_data_reset',
reset,
)
async def main() -> None:
with trio.fail_after(0.1):
result, _ = await get_bars(
Proxy(),
'qqq.nasdaq.ib',
1,
feed_reset_timeout=0.001,
max_failed_resets=2,
)
assert result is None
trio.run(main)
assert reset_types == ['data', 'connection']