The code treated a broadcast as final: money moved on-chain and the DB was updated on the assumption it would either confirm or be fee-bumped until it did. Neither is guaranteed, and every way that assumption broke was permanent (BUGS.md B-02, B-03, B-04, B-07, B-08, B-20, B-21). Persist before broadcasting. place_bet and request_withdrawal now write their rows in a "building" state and commit, then broadcast, then promote to broadcast/pending in a second commit. Before, a failure or crash between the broadcast and the commit left the coins irreversibly spent with no trace: no participant (so no entry in the draw), no pending row (so no RBF and no confirmation tracking), and the UTXOs not even marked spent, so the next bet would try to double-spend them. A refused broadcast now releases the reserved UTXOs, restores the balance, removes the participant (or marks the withdrawal failed), audit-logs it, and answers a translatable broadcast_failed — as 502, since the network refused it, not the caller, where it used to be an opaque 500. Reconcile what's in flight against the chain. New PendingTransactionReconciler (app/tx/reconcile.py, every 120s and once at startup) asks whether each non-terminal tx exists: present -> promote, gone -> mark failed with a reason, release the inputs, roll the domain row back, audit-log it. Grace periods differ by state (120s for "building", 6h for "pending", so the RBF bumper gets its attempts first). It is deliberately biased to inaction: only a server that positively doesn't know the tx counts as absent, and a transport failure never abandons anything, because releasing a UTXO whose tx is actually alive would invite a double-spend. Verified against the live server, which answers "No such mempool or blockchain transaction" for an unknown txid. Stop keying on a value that changes. An RBF bump changes the txid, and _on_bet_confirmed looked the participant up by bet_txid — so a bumped bet confirmed under a txid no participant carried, the row stayed "broadcast" forever, and the scheduler waited on it forever: the round could never close and the lottery stopped. Handlers now resolve by immutable ids (round_id/user_id, withdrawal_id), and bump_fee retargets every stored txid — bet_txid, Withdrawal.txid, Round.payout_txid and UtxoEvent.spent_txid — plus records the previous one in replaced_by_txid, which was never written at all. One bad row no longer blocks the rest. The confirmation poller's per-tx lookup is guarded: a txid the server can't resolve used to abort the whole pass, so nothing confirmed again until an operator intervened. It also selects plain columns instead of hydrating entities that outlive their session. Tests: 6 reconciler cases including "a broken connection must not release coins"; the bet-ordering test probes committed state from an independent session during the broadcast, and caught a real mistake in the first draft of this change (the _pending_transaction helper still hardcoded status="pending", so rows were born already-broadcast and would have got the 6-hour grace instead of 120s). Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
165 lines
6.4 KiB
Python
165 lines
6.4 KiB
Python
from datetime import datetime, timezone
|
|
|
|
from embit import script
|
|
from sqlalchemy import select
|
|
from sqlalchemy.ext.asyncio import AsyncSession
|
|
|
|
from app.api.errors import ApiError
|
|
from app.audit.log import write_audit_log
|
|
from app.db.models import PendingTransaction, RoundParticipant, User, UtxoEvent
|
|
from app.electrum.client import ElectrumClient
|
|
from app.rounds.config import get_round_config
|
|
from app.rounds.events import broadcaster
|
|
from app.rounds.service import open_new_round_if_needed, round_accepts_bets
|
|
from app.wallet.balance import recompute_balance
|
|
from app.wallet.hd import derive_pool_address, derive_user_key
|
|
from app.wallet.psbt_builder import BuiltTransaction, InsufficientFundsError, Utxo, build_signed_transaction
|
|
|
|
|
|
class BetError(ApiError):
|
|
pass
|
|
|
|
|
|
async def place_bet(session: AsyncSession, client: ElectrumClient, user: User) -> RoundParticipant:
|
|
round_ = await open_new_round_if_needed(session)
|
|
if round_ is None:
|
|
raise BetError("no_round_open", "no round open right now, please try again shortly")
|
|
|
|
config = await get_round_config(session)
|
|
if not round_accepts_bets(round_, config.round_duration_seconds):
|
|
raise BetError("round_closing", "the current round is closing, please try again shortly")
|
|
|
|
already_playing = await session.scalar(
|
|
select(RoundParticipant).where(
|
|
RoundParticipant.round_id == round_.id, RoundParticipant.user_id == user.id
|
|
)
|
|
)
|
|
if already_playing is not None:
|
|
raise BetError("already_betting", "you already have an active bet in the current round")
|
|
|
|
bet_amount = config.bet_amount_sats
|
|
|
|
unspent = (
|
|
await session.scalars(
|
|
select(UtxoEvent).where(UtxoEvent.user_id == user.id, UtxoEvent.spent_txid.is_(None))
|
|
)
|
|
).all()
|
|
if sum(u.amount_sats for u in unspent) < bet_amount:
|
|
raise BetError("insufficient_balance", "insufficient balance", required_sats=bet_amount)
|
|
|
|
user_key = derive_user_key(user.derivation_index)
|
|
from_script = script.p2wpkh(user_key.to_public())
|
|
utxos = [Utxo(u.txid, u.vout, u.amount_sats) for u in unspent]
|
|
|
|
try:
|
|
built = build_signed_transaction(
|
|
signing_key=user_key,
|
|
from_script=from_script,
|
|
utxos=utxos,
|
|
to_address=derive_pool_address(),
|
|
amount_sats=bet_amount,
|
|
change_address=user.address,
|
|
fee_rate_sat_vb=config.fee_rate_sat_vb,
|
|
)
|
|
except InsufficientFundsError as exc:
|
|
raise BetError(exc.code, str(exc)) from exc
|
|
|
|
# --- Phase 1: record the intent, *then* broadcast (B-08) --------------------
|
|
# Broadcasting first meant a failure (or a crash) between the broadcast and the
|
|
# commit left the coins irreversibly spent on-chain with no trace in the DB: no
|
|
# participant, so no entry in the draw; no pending row, so no RBF and no
|
|
# confirmation tracking; and the UTXOs not even marked spent, so the next bet
|
|
# would try to double-spend them. Writing "building" rows first means the worst
|
|
# case is a row the reconciler (app/tx/reconcile.py) can resolve either way by
|
|
# asking the chain whether the tx exists.
|
|
spent_by_key = {(u.txid, u.vout): u for u in unspent}
|
|
for spent in built.spent_utxos:
|
|
spent_by_key[(spent.txid, spent.vout)].spent_txid = built.txid
|
|
await recompute_balance(session, user.id)
|
|
|
|
broadcast_at = datetime.now(timezone.utc)
|
|
participant = RoundParticipant(
|
|
round_id=round_.id,
|
|
user_id=user.id,
|
|
bet_amount_sats=built.recipient_sats,
|
|
bet_txid=built.txid,
|
|
broadcast_at=broadcast_at,
|
|
status="building",
|
|
)
|
|
session.add(participant)
|
|
pending = _pending_transaction(round_.id, user.id, built, config.fee_rate_sat_vb)
|
|
session.add(pending)
|
|
await session.commit()
|
|
|
|
# --- Phase 2: broadcast, then promote both rows to their live state ---------
|
|
try:
|
|
await client.broadcast(built.raw_hex)
|
|
except Exception as exc:
|
|
# The node refused it (fee too low, dust, mempool conflict, or simply an
|
|
# unreachable server) — nothing is on-chain, so undo phase 1 completely and
|
|
# give the user a translatable failure instead of a bare 500 (B-07).
|
|
await _release_failed_bet(session, participant, pending, built, user.id, str(exc))
|
|
raise BetError("broadcast_failed", f"the network refused the transaction: {exc}") from exc
|
|
|
|
participant.status = "broadcast"
|
|
pending.status = "pending"
|
|
await write_audit_log(
|
|
session,
|
|
"bet_placed",
|
|
{"txid": built.txid, "amount_sats": built.recipient_sats},
|
|
user_id=user.id,
|
|
round_id=round_.id,
|
|
)
|
|
|
|
await session.commit()
|
|
await session.refresh(participant)
|
|
broadcaster.publish() # participant_count/jackpot changed — nudge every dashboard to refetch
|
|
return participant
|
|
|
|
|
|
async def _release_failed_bet(
|
|
session: AsyncSession,
|
|
participant: RoundParticipant,
|
|
pending: PendingTransaction,
|
|
built: BuiltTransaction,
|
|
user_id: int,
|
|
reason: str,
|
|
) -> None:
|
|
"""Undo phase 1 after a failed broadcast: free the UTXOs the build reserved, drop
|
|
the two rows, and restore the balance. Same shape as what the reconciler does for
|
|
a tx that turns out never to have made it onto the chain."""
|
|
for spent in built.spent_utxos:
|
|
row = await session.scalar(
|
|
select(UtxoEvent).where(UtxoEvent.txid == spent.txid, UtxoEvent.vout == spent.vout)
|
|
)
|
|
if row is not None:
|
|
row.spent_txid = None
|
|
await session.delete(participant)
|
|
await session.delete(pending)
|
|
await recompute_balance(session, user_id)
|
|
await write_audit_log(
|
|
session,
|
|
"bet_broadcast_failed",
|
|
{"txid": built.txid, "reason": reason[:200]},
|
|
user_id=user_id,
|
|
)
|
|
await session.commit()
|
|
|
|
|
|
def _pending_transaction(
|
|
round_id: int, user_id: int, built: BuiltTransaction, fee_rate_sat_vb: int
|
|
) -> PendingTransaction:
|
|
return PendingTransaction(
|
|
kind="bet",
|
|
round_id=round_id,
|
|
user_id=user_id,
|
|
current_txid=built.txid,
|
|
fee_rate_sat_vb=fee_rate_sat_vb,
|
|
raw_tx_hex=built.raw_hex,
|
|
# "building" until the broadcast succeeds — see place_bet's two phases. It
|
|
# matters which one this starts as: the reconciler gives a "building" row a
|
|
# short grace period (we may have died mid-broadcast) and a "pending" one a
|
|
# long one (a node accepted it once, so it deserves the RBF attempts first).
|
|
status="building",
|
|
)
|