genichinandClaude Opus 4.8
2f57aad7b2
Wire the existing PaperBroker scenario knobs (fill_after_polls / qty_per_poll / reject_symbols) to daemon env so REQ-011 AC-2 e2e scenarios (delayed / partial / reject) can be reproduced by a daemon restart. Unset == prior PaperBroker() behaviour, byte-for-byte (no regression). - config.py: PaperBrokerConfig + from_env parsing (TREX_PAPER_*) - daemon.py: _build_broker injects config.paper into PaperBroker - .env.example: document the 3 paper tuning keys (paper-only, e2e) - tests: paper broker defaults + env tuning parsing SDLC: REQ-010 CHG-20260606-01 (AC-5 added) / -02 (Implemented); BAT-009 batch-lite release-candidate; REL-001 feedback handoff records pre-deployment e2e observations incl. event-publisher idle-drop and paper correlation_id collision (GitHub #4, #5). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
292 lines
11 KiB
Python
292 lines
11 KiB
Python
"""Slot-core daemon entrypoint (REQ-005, REQ-012/013/014, BAT-007).
|
|
|
|
Sync + threaded runtime. HTTP `/v1` API has been removed (REQ-025); all
|
|
strategy-facing communication runs over RabbitMQ (REQ-021/022/023).
|
|
|
|
Threads (started in `run()`):
|
|
- intent RPC consumer — `trex.intent.req`, prefetch=1, FIFO, dedup via intent_log
|
|
- snapshot RPC consumer — `trex.snapshot.req`
|
|
- execution loop — broker dispatch + poll + slot transitions + event emit
|
|
- ledger writer — ledger outbox drain (REQ-019)
|
|
|
|
Each consumer/publisher uses its OWN RabbitMQTransport instance because
|
|
pika BlockingConnection is not thread-safe across channels.
|
|
Console script: `trex-core-daemon`.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
import signal
|
|
import threading
|
|
from datetime import datetime, timezone
|
|
|
|
from datetime import time as time_cls
|
|
|
|
from trex_core.adapters.broker.paper import PaperBroker
|
|
from trex_core.adapters.ledger import InMemoryLedger, PortfolioHubLedger
|
|
from trex_core.adapters.messaging import (
|
|
InMemoryTransport,
|
|
RabbitMQTransport,
|
|
topology,
|
|
)
|
|
from trex_core.adapters.persistence.migrate import apply_migrations
|
|
from trex_core.adapters.persistence.postgresql import (
|
|
PostgreSQLIntentStore,
|
|
PostgreSQLLedgerOutbox,
|
|
PostgreSQLSlotRepository,
|
|
)
|
|
from trex_core.adapters.portfolio import (
|
|
PortfolioHubReadAdapter,
|
|
PostgreSQLPauseStore,
|
|
StubPortfolioRead,
|
|
)
|
|
from trex_core.application.broker_port import BrokerPort
|
|
from trex_core.application.execution import ExecutionService
|
|
from trex_core.application.intents import IntentService
|
|
from trex_core.application.ledger_outbox import LedgerWriter
|
|
from trex_core.application.ledger_port import LedgerPort
|
|
from trex_core.application.messaging import MessagingTransport
|
|
from trex_core.application.messaging_handlers import (
|
|
make_intent_rpc_handler,
|
|
make_pause_rpc_handler,
|
|
make_snapshot_rpc_handler,
|
|
slot_transition_event_payload,
|
|
)
|
|
from trex_core.application.portfolio import (
|
|
PortfolioHubReadPort,
|
|
SnapshotStore,
|
|
)
|
|
from trex_core.application.snapshot_scheduler import SnapshotScheduler
|
|
from trex_core.domain.slot import SlotService
|
|
from trex_core.runtime.config import DaemonConfig
|
|
|
|
_log = logging.getLogger(__name__)
|
|
|
|
|
|
def _build_broker(config: DaemonConfig) -> BrokerPort:
|
|
if config.broker == "kis":
|
|
from trex_core.adapters.broker.kis import KISBroker
|
|
|
|
k = config.kis
|
|
token_cache = None
|
|
if k.redis_url:
|
|
from trex_core.adapters.broker.token_cache import RedisTokenCache
|
|
|
|
token_cache = RedisTokenCache(k.redis_url)
|
|
return KISBroker(
|
|
k.account_ref, app_key=k.app_key, app_secret=k.app_secret,
|
|
base_url=k.base_url, timeout=k.timeout, allow_live=k.allow_live,
|
|
token_cache=token_cache,
|
|
)
|
|
return PaperBroker(
|
|
fill_after_polls=config.paper.fill_after_polls,
|
|
qty_per_poll=config.paper.qty_per_poll,
|
|
reject_symbols=set(config.paper.reject_symbols),
|
|
)
|
|
|
|
|
|
def _build_ledger(config: DaemonConfig) -> LedgerPort:
|
|
"""portfolio-hub when configured; otherwise in-memory stub (REQ-017)."""
|
|
pf = config.portfolio_hub
|
|
if pf is None:
|
|
return InMemoryLedger()
|
|
return PortfolioHubLedger(pf.base_url, token=pf.token or None, timeout=pf.timeout)
|
|
|
|
|
|
def _build_transport(config: DaemonConfig) -> MessagingTransport:
|
|
"""RabbitMQ when configured; otherwise in-memory stub (REQ-022)."""
|
|
mq = config.rabbitmq
|
|
if mq is None:
|
|
# Stub: lets the daemon boot in environments without a broker (CI,
|
|
# local dev). REQ-024 degrade policy still applies — call_rpc raises.
|
|
return InMemoryTransport()
|
|
return RabbitMQTransport(mq.url, timeout=mq.timeout)
|
|
|
|
|
|
def _build_portfolio_read(config: DaemonConfig) -> PortfolioHubReadPort:
|
|
"""portfolio-hub HTTP read adapter when configured; otherwise stub (REQ-027)."""
|
|
pf = config.portfolio_hub
|
|
if pf is None:
|
|
return StubPortfolioRead()
|
|
return PortfolioHubReadAdapter(
|
|
pf.base_url, token=pf.token or None, timeout=pf.timeout,
|
|
)
|
|
|
|
|
|
def _parse_kst_time(spec: str) -> time_cls:
|
|
parts = spec.split(":")
|
|
h = int(parts[0])
|
|
m = int(parts[1]) if len(parts) > 1 else 0
|
|
return time_cls(hour=h, minute=m)
|
|
|
|
|
|
class Daemon:
|
|
"""Thread-orchestrating daemon (no HTTP)."""
|
|
|
|
def __init__(self, config: DaemonConfig) -> None:
|
|
self.config = config
|
|
self.stop = threading.Event()
|
|
self._threads: list[threading.Thread] = []
|
|
self._transports: list[MessagingTransport] = []
|
|
|
|
# Persistence + services
|
|
self.slot_repo = PostgreSQLSlotRepository(config.dsn)
|
|
self.intent_store = PostgreSQLIntentStore(config.dsn)
|
|
self.slot_service = SlotService(self.slot_repo)
|
|
self.intent_service = IntentService(self.slot_service, self.slot_repo, self.intent_store)
|
|
self.broker = _build_broker(config)
|
|
self.outbox = PostgreSQLLedgerOutbox(config.dsn)
|
|
self.ledger_writer = LedgerWriter(self.outbox, _build_ledger(config))
|
|
|
|
# BAT-008: portfolio-hub read + snapshot store + durable pause + scheduler.
|
|
self.snapshot_store = SnapshotStore()
|
|
self.pause_store = PostgreSQLPauseStore(config.dsn)
|
|
self.portfolio_read = _build_portfolio_read(config)
|
|
self.snapshot_scheduler = SnapshotScheduler(
|
|
read_port=self.portfolio_read,
|
|
store=self.snapshot_store,
|
|
broker=self.broker,
|
|
schedule_kst=_parse_kst_time(config.snapshot_schedule.kst_time),
|
|
)
|
|
|
|
# Event publisher transport — one dedicated instance for the
|
|
# execution-loop thread (pika is not thread-safe).
|
|
self.event_publisher: MessagingTransport = _build_transport(config)
|
|
self._transports.append(self.event_publisher)
|
|
|
|
self.execution = ExecutionService(
|
|
self.slot_service, self.slot_repo, self.broker,
|
|
ledger_outbox=self.outbox,
|
|
event_emitter=self._make_event_emitter(),
|
|
)
|
|
|
|
# ------------------------------------------------------------ event hook
|
|
def _make_event_emitter(self):
|
|
def emit(event_type: str, slot) -> None:
|
|
payload = slot_transition_event_payload(slot, event_type=event_type)
|
|
rk = topology.event_routing_key(
|
|
event_type, slot.strategy_id or "_", slot.symbol or "_",
|
|
)
|
|
try:
|
|
self.event_publisher.publish_event(rk, payload)
|
|
except Exception: # noqa: BLE001 - publish failure must not roll back
|
|
_log.warning("event publish failed (rk=%s)", rk, exc_info=True)
|
|
return emit
|
|
|
|
# ------------------------------------------------------------ workers
|
|
def _execution_loop(self) -> None:
|
|
while not self.stop.wait(self.config.execution_interval_sec):
|
|
try:
|
|
self.execution.run_once()
|
|
except Exception: # noqa: BLE001 - loop must survive transient errors
|
|
continue
|
|
|
|
def _ledger_loop(self) -> None:
|
|
while not self.stop.wait(self.config.ledger_interval_sec):
|
|
try:
|
|
self.ledger_writer.run_once()
|
|
except Exception: # noqa: BLE001
|
|
continue
|
|
|
|
def _intent_rpc_loop(self) -> None:
|
|
transport = _build_transport(self.config)
|
|
self._transports.append(transport)
|
|
try:
|
|
transport.declare_topology()
|
|
except Exception: # noqa: BLE001
|
|
pass
|
|
handler = make_intent_rpc_handler(self.intent_service)
|
|
transport.consume_rpc_forever(topology.INTENT_REQ_QUEUE, handler, self.stop)
|
|
|
|
def _snapshot_rpc_loop(self) -> None:
|
|
transport = _build_transport(self.config)
|
|
self._transports.append(transport)
|
|
try:
|
|
transport.declare_topology()
|
|
except Exception: # noqa: BLE001
|
|
pass
|
|
handler = make_snapshot_rpc_handler(
|
|
self.slot_repo, self.slot_service,
|
|
snapshot_store=self.snapshot_store,
|
|
pause_store=self.pause_store,
|
|
default_total_slots=self.config.total_slots,
|
|
)
|
|
transport.consume_rpc_forever(topology.SNAPSHOT_REQ_QUEUE, handler, self.stop)
|
|
|
|
def _pause_rpc_loop(self) -> None:
|
|
transport = _build_transport(self.config)
|
|
self._transports.append(transport)
|
|
try:
|
|
transport.declare_topology()
|
|
except Exception: # noqa: BLE001
|
|
pass
|
|
handler = make_pause_rpc_handler(self.pause_store)
|
|
transport.consume_rpc_forever(topology.PAUSE_REQ_QUEUE, handler, self.stop)
|
|
|
|
def _snapshot_scheduler_loop(self) -> None:
|
|
try:
|
|
self.snapshot_scheduler.run_forever(
|
|
self.stop, tick_sec=self.config.snapshot_schedule.tick_sec,
|
|
)
|
|
except Exception: # noqa: BLE001
|
|
_log.exception("snapshot scheduler loop crashed")
|
|
|
|
# ------------------------------------------------------------ lifecycle
|
|
def setup(self) -> None:
|
|
apply_migrations(self.config.dsn)
|
|
self.slot_service.preallocate_daily_slots(
|
|
datetime.now(tz=timezone.utc).date(), self.config.total_slots
|
|
)
|
|
self.execution.reconcile() # REQ-014 restart recovery
|
|
try:
|
|
self.event_publisher.declare_topology()
|
|
except Exception: # noqa: BLE001
|
|
_log.warning("event publisher topology declare failed", exc_info=True)
|
|
|
|
def start(self) -> None:
|
|
workers = [
|
|
("trex-execution", self._execution_loop),
|
|
("trex-ledger", self._ledger_loop),
|
|
("trex-intent-rpc", self._intent_rpc_loop),
|
|
("trex-snapshot-rpc", self._snapshot_rpc_loop),
|
|
("trex-pause-rpc", self._pause_rpc_loop),
|
|
("trex-snapshot-scheduler", self._snapshot_scheduler_loop),
|
|
]
|
|
for name, target in workers:
|
|
t = threading.Thread(target=target, name=name, daemon=True)
|
|
t.start()
|
|
self._threads.append(t)
|
|
|
|
def shutdown(self) -> None:
|
|
self.stop.set()
|
|
for t in self._threads:
|
|
t.join(
|
|
timeout=max(self.config.execution_interval_sec, self.config.ledger_interval_sec) * 3
|
|
)
|
|
for tr in self._transports:
|
|
try:
|
|
tr.close()
|
|
except Exception: # noqa: BLE001
|
|
pass
|
|
|
|
def run(self) -> None: # pragma: no cover - process entrypoint
|
|
self.setup()
|
|
self.start()
|
|
signal.signal(signal.SIGINT, lambda *_: self.stop.set())
|
|
signal.signal(signal.SIGTERM, lambda *_: self.stop.set())
|
|
try:
|
|
while not self.stop.is_set():
|
|
self.stop.wait(1.0)
|
|
finally:
|
|
self.shutdown()
|
|
|
|
|
|
def main() -> None: # pragma: no cover - process entrypoint
|
|
logging.basicConfig(level=logging.INFO)
|
|
config = DaemonConfig.from_env()
|
|
Daemon(config).run()
|
|
|
|
|
|
if __name__ == "__main__": # pragma: no cover
|
|
main()
|