Retry a stuck payout automatically, and log every failure (B-26)

_trigger_payout used to run exactly once, from _close_and_draw. Any
failure after that point — no Electrum client, insufficient pool
UTXOs, a missing fee_address, a rejected broadcast — wedged the round
in paying_out forever, and every one of those early returns except the
generic exception handler logged nothing at all: /admin showed a
stalled round with no explanation. A process restart while paying_out
hit the same dead end.

_tick now handles status == "paying_out": it calls the new
_retry_payout_if_due, which re-invokes _trigger_payout unless the most
recent payout_failed audit entry for the round is younger than
_PAYOUT_RETRY_INTERVAL_SECONDS (60s) — throttled so a persistently
broken payout (e.g. no fee_address set yet) doesn't retry, and re-log
a failure, on every 5-second tick. Every early return in
_trigger_payout now calls _log_payout_failure with a reason string, so
that throttle always has something to check against and /admin always
shows why a round is stuck.

This is safe to fire on a restart too, because B-25 already made
_trigger_payout idempotent (it no-ops if a non-terminal payout
PendingTransaction already exists) and persists before broadcasting —
so a round found paying_out at startup, whatever state its payout was
actually in, gets retried the same way. That closes the paying_out
half of the "scheduler doesn't resume mid-flight rounds after a
restart" gap in CLAUDE.md; the drawing/block-wait half is untouched
(see BUGS.md B-36).

BUGS.md moves B-26 to "Previously fixed" with the fix description; the
suite grows from 143 to 148 tests.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
2026-07-27 09:29:14 +02:00
co-authored by Claude Sonnet 5
parent f13f6850b7
commit 50a43ae3ca
3 changed files with 223 additions and 45 deletions
+106
View File
@@ -247,3 +247,109 @@ async def test_reserved_payout_outpoints_excludes_utxos_claimed_by_a_stale_payou
reserved = await _reserved_payout_outpoints(session)
assert reserved == {(reserved_txid, 2)}
# --- B-26: a "paying_out" round must retry its payout automatically ---------------
async def test_trigger_payout_logs_a_failure_when_not_connected(payout_session_factory):
"""Before B-26, this early return logged nothing beyond a log line — invisible
in /admin and unusable as a signal for an automatic retry."""
await _seed_paying_out_round(payout_session_factory)
scheduler = RoundScheduler(payout_session_factory, FakePayoutListener(client=None))
await scheduler._trigger_payout(1)
async with payout_session_factory() as session:
entries = (await session.scalars(select(AuditLog).where(AuditLog.event_type == "payout_failed"))).all()
assert len(entries) == 1
assert entries[0].payload_json.count("electrum client not connected") == 1
async def test_trigger_payout_logs_a_failure_when_fee_address_missing(payout_session_factory):
winner_id = await _seed_paying_out_round(payout_session_factory)
async with payout_session_factory() as session:
config = (await session.scalars(select(RoundConfig))).one()
config.fee_address = ""
await session.commit()
entries = [{"tx_hash": "77" * 32, "tx_pos": 0, "height": 10, "value": _POOL_AMOUNT_SATS + 100_000}]
scheduler = RoundScheduler(payout_session_factory, FakePayoutListener(FakePayoutClient(entries)))
await scheduler._trigger_payout(1)
async with payout_session_factory() as session:
entry = (await session.scalars(select(AuditLog).where(AuditLog.event_type == "payout_failed"))).one()
assert "no fee_address configured" in entry.payload_json
assert entry.user_id == winner_id
async def test_tick_retries_a_stuck_paying_out_round_with_no_recent_failure(payout_session_factory):
"""The scenario B-26 exists for: a round stuck in "paying_out" (a prior failure,
or a process restart mid-payout) with no non-terminal PendingTransaction. A
fresh tick must retry rather than leaving it wedged forever."""
await _seed_paying_out_round(payout_session_factory)
entries = [{"tx_hash": "88" * 32, "tx_pos": 0, "height": 10, "value": _POOL_AMOUNT_SATS + 100_000}]
client = FakePayoutClient(entries)
scheduler = RoundScheduler(payout_session_factory, FakePayoutListener(client))
await scheduler._tick()
assert client.broadcasted
async with payout_session_factory() as session:
round_ = await session.get(Round, 1)
assert round_.payout_txid is not None
pending = (await session.scalars(select(PendingTransaction))).one()
assert pending.status == "pending"
async def test_tick_throttles_retry_after_a_recent_payout_failure(payout_session_factory):
"""A payout that just failed must not be retried on the very next tick, or a
persistently-broken payout (e.g. no fee_address) would spam a retry — and a
fresh payout_failed audit entry — every _TICK_INTERVAL_SECONDS."""
await _seed_paying_out_round(payout_session_factory)
async with payout_session_factory() as session:
session.add(
AuditLog(
event_type="payout_failed",
payload_json='{"round_id": 1, "reason": "insufficient pool UTXOs"}',
round_id=1,
created_at=datetime.now(timezone.utc),
)
)
await session.commit()
entries = [{"tx_hash": "99" * 32, "tx_pos": 0, "height": 10, "value": _POOL_AMOUNT_SATS + 100_000}]
client = FakePayoutClient(entries)
scheduler = RoundScheduler(payout_session_factory, FakePayoutListener(client))
await scheduler._tick()
assert not client.broadcasted
async with payout_session_factory() as session:
assert (await session.scalars(select(PendingTransaction))).all() == []
async def test_tick_retries_once_the_throttle_window_has_elapsed(payout_session_factory):
await _seed_paying_out_round(payout_session_factory)
async with payout_session_factory() as session:
session.add(
AuditLog(
event_type="payout_failed",
payload_json='{"round_id": 1, "reason": "insufficient pool UTXOs"}',
round_id=1,
created_at=datetime.now(timezone.utc) - timedelta(seconds=120),
)
)
await session.commit()
entries = [{"tx_hash": "aa" * 32, "tx_pos": 0, "height": 10, "value": _POOL_AMOUNT_SATS + 100_000}]
client = FakePayoutClient(entries)
scheduler = RoundScheduler(payout_session_factory, FakePayoutListener(client))
await scheduler._tick()
assert client.broadcasted
async with payout_session_factory() as session:
pending = (await session.scalars(select(PendingTransaction))).one()
assert pending.status == "pending"