fix(ledger): dcy-015 outbox 영속 오류 분류 + 백오프/dead-letter (BAT-019)
portfolio-hub 404(미등록 포트폴리오)가 retryable 로 분류되어 백오프·상한 없이 초당 영구 재시도되던 버그(issue #13, 실측 930회) 정정. 거버넌스: 전부 change-req (신규 REQ 없음, dcy-015 OQ-3; 백오프 env 는 REQ-019 흡수). - REQ-017: 404/400/422 → LedgerPermanentError 분류 (409 conflict / 408·429·5xx· network retryable 불변). LedgerPort 에 permanent 타입 추가 - REQ-019: 영속 → 터미널 delivery_failed 즉시(재시도 0). retryable 지수 백오프 +jitter+next_retry_at, max_attempts 초과 시 dead-letter delivery_failed. list_pending 이 백오프 행 스킵(head-of-line 보호). 마이그레이션 007(status enum +next_retry_at). 백오프 env(base/cap/max-attempts) - REQ-018: 터미널/dead-letter WARN + WriterStats.delivery_failed 카운터 가시화 - REQ-020: runtime-flows/data-model/interface-contract 정합 단일 터미널 delivery_failed(permanent/dead-letter, last_outcome 로 사유 구분) — conflict_blocked 패턴과 동형. dead-letter 는 운영자 재처리 가능 상태. 검증: 단위 311 passed/34 skipped, 인프라 게이트(PG+RabbitMQ) 345 passed, ruff clean. 신규 test_ledger_outbox_backoff + adapter/PG 테스트, 기존 retryable 백오프 정합. BAT-019 release-candidate. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
@@ -5,6 +5,7 @@ import threading
|
||||
|
||||
from trex_core.application.ledger_port import (
|
||||
LedgerConflictError,
|
||||
LedgerPermanentError,
|
||||
LedgerRetryableError,
|
||||
LedgerTrade,
|
||||
LedgerWriteResult,
|
||||
@@ -21,6 +22,8 @@ class InMemoryLedger:
|
||||
then accept.
|
||||
conflict_executions -- execution_ids that raise LedgerConflictError
|
||||
(simulates portfolio-hub 409).
|
||||
permanent_executions -- execution_ids that raise LedgerPermanentError
|
||||
(simulates portfolio-hub 404/400/422, dcy-015).
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
@@ -28,12 +31,14 @@ class InMemoryLedger:
|
||||
*,
|
||||
fail_n_then_succeed: int = 0,
|
||||
conflict_executions: set[str] | None = None,
|
||||
permanent_executions: set[str] | None = None,
|
||||
) -> None:
|
||||
self._trades: dict[str, LedgerTrade] = {}
|
||||
self._order: list[LedgerTrade] = []
|
||||
self._lock = threading.Lock()
|
||||
self._fail_remaining = fail_n_then_succeed
|
||||
self._conflicts = set(conflict_executions or set())
|
||||
self._permanent = set(permanent_executions or set())
|
||||
|
||||
def record_trade(self, trade: LedgerTrade) -> LedgerWriteResult:
|
||||
with self._lock:
|
||||
@@ -41,6 +46,10 @@ class InMemoryLedger:
|
||||
raise LedgerConflictError(
|
||||
f"ledger conflict for execution_id={trade.execution_id}"
|
||||
)
|
||||
if trade.execution_id in self._permanent:
|
||||
raise LedgerPermanentError(
|
||||
f"ledger permanent error for execution_id={trade.execution_id}"
|
||||
)
|
||||
if self._fail_remaining > 0:
|
||||
self._fail_remaining -= 1
|
||||
raise LedgerRetryableError("simulated transient failure")
|
||||
|
||||
@@ -6,7 +6,9 @@ Live portfolio-hub contract (verified against openapi, REQ-017 CHG-04):
|
||||
execution_id, order_id
|
||||
- 2xx (201) => recorded (or duplicate accepted idempotently)
|
||||
- 409 => LedgerConflictError (operator resolution)
|
||||
- 4xx (other)/5xx => LedgerRetryableError (outbox retries)
|
||||
- 404/400/422 => LedgerPermanentError (dcy-015/REQ-017 — retry can't fix:
|
||||
portfolio not registered / malformed trade)
|
||||
- 4xx (other)/5xx => LedgerRetryableError (outbox backoff retries)
|
||||
- httpx error => LedgerRetryableError
|
||||
|
||||
`asset_id` on LedgerTrade carries the portfolio_id value (REQ-018:
|
||||
@@ -21,11 +23,15 @@ import httpx
|
||||
|
||||
from trex_core.application.ledger_port import (
|
||||
LedgerConflictError,
|
||||
LedgerPermanentError,
|
||||
LedgerRetryableError,
|
||||
LedgerTrade,
|
||||
LedgerWriteResult,
|
||||
)
|
||||
|
||||
# dcy-015 / REQ-017: client errors that retrying cannot resolve.
|
||||
_PERMANENT_STATUS = frozenset({400, 404, 422})
|
||||
|
||||
|
||||
class PortfolioHubLedger:
|
||||
"""portfolio-hub ledger adapter (single endpoint, single responsibility)."""
|
||||
@@ -91,6 +97,14 @@ class PortfolioHubLedger:
|
||||
f"portfolio-hub 409 conflict for execution_id={trade.execution_id}: "
|
||||
f"{resp.text[:200]}"
|
||||
)
|
||||
if resp.status_code in _PERMANENT_STATUS:
|
||||
# dcy-015 / REQ-017 (issue #13): 404/400/422 won't be fixed by
|
||||
# retrying — surface as permanent so the outbox terminates the row.
|
||||
raise LedgerPermanentError(
|
||||
f"portfolio-hub {resp.status_code} permanent error for "
|
||||
f"asset_id={trade.asset_id} execution_id={trade.execution_id}: "
|
||||
f"{resp.text[:200]}"
|
||||
)
|
||||
raise LedgerRetryableError(
|
||||
f"portfolio-hub {resp.status_code} response: {resp.text[:200]}"
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user