Files
plm-lottery/app/main.py
T
davideandClaude Sonnet 5.5 a4b160e240 Abandon a transaction only on proof, and keep watching failed rows (B-78, TX-15, TX-17, TX-23, TX-26, ELC-28, DAT-33, DAT-36, DAT-69, DAT-72, AUD-11, AUD-12, AUD-31, AUD-39, API-32)
reconcile_once abandoned a row when the *active* server's history lacked its txid:
after 120s for `building` (which a restart onto a different server makes likely),
after 6h for `pending`, and all at once after a forward clock jump. It re-checked the
status but not the txid, so it raced the bumper, and a `failed` row was never looked at
again.

- The reconciler asks every server (ElectrumListener.get_histories, active + others) for
  the history of the row's address and looks for every txid of the row. Present on any
  server -> promoted (adopting the version found). Absent is only "no server of the
  quorum knows it" and needs the active server plus the quorum minimum of the others to
  have answered; even then nothing is released without proof:
  (a) an input spent in a block by a transaction that is none of the row's versions,
      agreed by a strict majority of a quorum of the other servers (confirmed_spender), or
  (b) a rebroadcast of the latest raw tx to every server (rebroadcast_everywhere)
      refused by all of them, explicitly, for missing/spent inputs.
  Accepted or "already known" by any server means alive; a fee refusal is not proof
  (`building` -> `pending` for the bumper, `pending` untouched); too few answers or
  anything else leaves the row alone. failure_reason names the proof.
- The write re-reads status *and* current_txid under begin_immediate (TX-26).
- pending_transactions.failed_at (set by _abandon and _release_failed_withdrawal) starts
  a 14-day watch: a failed row that a majority of the other servers (at least the quorum
  minimum) list in a block becomes `confirmed`, writes pending_tx_resurrected once and
  pauses the lottery with paused_reason `resurrected_tx`; linked rows are not corrected.
  The confirmation is by quorum of histories for now; merkle proofs come with B-83.
- round_config.paused_reason (migration b7d2e41c9a05, with the failed_at one): `operator`
  from POST /admin/pause (which accepts an optional `note` and never overwrites an
  automatic reason), cleared by resume, which logs the reason it lifted; exposed on
  /admin/config and GET /rounds/current. rounds/pause.py:pause_automatically is the
  system's way in.
- PendingTransactionReconciler takes the listener as `network`; with none it can promote
  but never abandon.

Tests changed because the spec changed: the three reconciler tests that expect an
abandonment (and the one in test_tx_versions) now supply a network that proves the
transaction is gone.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-14 15:07:09 +02:00

153 lines
6.0 KiB
Python

import asyncio
import logging
from contextlib import asynccontextmanager
from fastapi import FastAPI, Request, status
from fastapi.responses import FileResponse, JSONResponse
from fastapi.staticfiles import StaticFiles
from app.logging_config import setup_logging
setup_logging()
import app.bets.confirmation # noqa: F401 (registers the "bet" confirmation handler)
import app.rounds.confirmation # noqa: F401 (registers the "payout" confirmation handler)
import app.withdrawals.confirmation # noqa: F401 (registers the "withdrawal" confirmation handler)
from app.api.routes.admin import router as admin_router
from app.api.routes.bets import router as bets_router
from app.api.routes.bug_reports import router as bug_reports_router
from app.api.routes.qr import router as qr_router
from app.api.routes.rounds import router as rounds_router
from app.api.routes.users import router as users_router
from app.api.routes.withdrawals import router as withdrawals_router
from app.auth.routes import router as auth_router
from app.api.errors import ApiError
from app.config import settings, validate_quorum_servers, validate_runtime_secrets
from app.db.base import AsyncSessionLocal
from app.deposits.reconcile import DepositReconciler
from app.electrum.client import ElectrumClient, ElectrumEndpoint, parse_endpoints
from app.electrum.listener import ElectrumListener
from app.rounds.scheduler import RoundScheduler
from app.tx.broadcast import RbfBumper
from app.tx.confirmation import ConfirmationPoller
from app.tx.locks import UserLocks
from app.tx.reconcile import PendingTransactionReconciler
logger = logging.getLogger(__name__)
def _make_electrum_client(endpoint: ElectrumEndpoint) -> ElectrumClient:
return ElectrumClient(endpoint.host, endpoint.port, endpoint.use_ssl, endpoint.pin)
@asynccontextmanager
async def lifespan(app: FastAPI):
# Refuses to serve rather than starting up half-configured (B-15).
validate_runtime_secrets()
endpoints = parse_endpoints(
settings.electrum_host,
settings.electrum_port,
settings.electrum_use_ssl,
settings.electrum_fallback_servers,
settings.electrum_cert_pin,
)
validate_quorum_servers(endpoints) # B-84: refuses to serve without a usable quorum
logger.info("Electrum endpoints (in rotation order): %s", ", ".join(str(e) for e in endpoints))
listener = ElectrumListener(
_make_electrum_client, AsyncSessionLocal, endpoints, allow_no_quorum=settings.allow_no_quorum
)
app.state.electrum_listener = listener
app.state.user_locks = UserLocks()
scheduler = RoundScheduler(AsyncSessionLocal, listener)
poller = ConfirmationPoller(AsyncSessionLocal, lambda: listener.client)
bumper = RbfBumper(AsyncSessionLocal, lambda: listener.client, network=listener)
# Resolves in-flight transactions against the chain — the piece that lets the
# system recover on its own from a broadcast that never confirmed (B-04/B-08).
reconciler = PendingTransactionReconciler(AsyncSessionLocal, lambda: listener.client, network=listener)
# Periodic safety net for deposit crediting/external-spend detection,
# independent of scripthash-change notifications — catches a subscription
# silently lost on an otherwise healthy connection (B-30).
deposit_reconciler = DepositReconciler(AsyncSessionLocal, listener)
tasks = [
asyncio.create_task(listener.run()),
asyncio.create_task(scheduler.run()),
asyncio.create_task(poller.run()),
asyncio.create_task(bumper.run()),
asyncio.create_task(reconciler.run()),
asyncio.create_task(deposit_reconciler.run()),
]
try:
yield
finally:
for task in tasks:
task.cancel()
if listener.client is not None:
await listener.client.close()
# Swagger/ReDoc/the raw OpenAPI JSON enumerate the entire API surface, admin
# endpoints included, to anyone who requests them (B-42) — disabled unless
# ENABLE_API_DOCS is explicitly set, which should only happen in development.
app = FastAPI(
title="PLM Lottery",
lifespan=lifespan,
docs_url="/docs" if settings.enable_api_docs else None,
redoc_url="/redoc" if settings.enable_api_docs else None,
openapi_url="/openapi.json" if settings.enable_api_docs else None,
)
app.include_router(auth_router)
app.include_router(users_router)
app.include_router(bets_router)
app.include_router(withdrawals_router)
app.include_router(admin_router)
app.include_router(bug_reports_router)
app.include_router(qr_router)
app.include_router(rounds_router)
@app.exception_handler(Exception)
async def log_unhandled_exception(request: Request, exc: Exception) -> JSONResponse:
"""Answers with the same structured `detail` shape as every deliberate failure
(app/api/errors.py) so clients never have to special-case unexpected errors.
The exception itself stays in logs/app.log only — never in the response body."""
logger.exception("Unhandled error on %s %s", request.method, request.url.path)
return JSONResponse(
status_code=500,
content={"detail": ApiError("internal_error", "internal server error").as_detail()},
)
@app.get("/health")
async def health() -> dict[str, str]:
return {"status": "ok"}
_NO_STORE_HEADERS = {"Cache-Control": "no-store"}
@app.get("/", include_in_schema=False)
async def index_page() -> FileResponse:
return FileResponse("app/static/index.html", headers=_NO_STORE_HEADERS)
@app.get("/admin", include_in_schema=False)
async def admin_panel() -> FileResponse:
return FileResponse("app/static/admin.html", headers=_NO_STORE_HEADERS)
@app.get("/guida", include_in_schema=False)
async def user_guide() -> FileResponse:
return FileResponse("app/static/guida.html", headers=_NO_STORE_HEADERS)
@app.get("/report-bug", include_in_schema=False)
async def report_bug_page() -> FileResponse:
return FileResponse("app/static/report-bug.html", headers=_NO_STORE_HEADERS)
app.mount("/", StaticFiles(directory="app/static", html=True), name="static")