A dropped connection used to hang the whole platform permanently, and three defects composed to do it (BUGS.md B-01): The read loop's death was invisible. When the socket closed, _read_loop broke out and finished, but _run_once was blocked on gather() over two notification consumers waiting on queues nobody would ever fill again — it never returned and never raised, so the reconnect-with-backoff logic was unreachable. client.wait_closed() now resolves when the loop ends for any reason, and _run_once races it against the consumers and a keepalive with asyncio.wait(FIRST_COMPLETED). Nothing had a timeout. request() registered a future, wrote to a half-closed socket (drain() often doesn't raise) and awaited a reply that would never come. That hung a POST /bets *while holding the per-user lock*, and could stop the confirmation poller for good. Every request is now bounded at 15s, and a timeout tears the connection down rather than leaving a server that owes us a reply in rotation. There was no keepalive, so on a quiet instance the normal way this connection dies is an idle-timeout drop by the server (~10 minutes for many). A server.ping every 60s makes that observable within a minute. listener.client is also cleared before reconnecting, so callers stop treating a dead connection as live. On top of the finding, the listener now rotates over a list of servers: ELECTRUM_FALLBACK_SERVERS holds comma-separated host:port[:notls] extras, tried after the primary. Everything the platform does goes through this one connection — deposit credits, broadcasts, confirmations, the chain tip the draw waits on — which made a single hardcoded server its biggest point of failure. A failed or dropped session moves to the next server immediately and only sleeps on the backoff once every server has had a turn, so one dead server costs one attempt instead of an outage, while a genuinely offline network still backs off. A malformed entry fails at startup, not during the outage when the fallback is what you need. Also fixes B-19: header handling refuses a height below the current tip and applies height and hex together, since _wait_for_next_block waits for tip_height > tip_at_close (a regression silently added a block to the draw's wait) and that hex is the draw's entropy source, so a mismatched pair would be worse than a stale one. Verified in the live deployment: the log shows the endpoint list, then "Electrum connected to santantonio.sytes.net:50002", and the connection holds. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
141 lines
5.4 KiB
Python
141 lines
5.4 KiB
Python
import asyncio
|
|
import logging
|
|
from contextlib import asynccontextmanager
|
|
from pathlib import Path
|
|
|
|
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.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, http_error
|
|
from app.config import settings, validate_runtime_secrets
|
|
from app.db.base import AsyncSessionLocal
|
|
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)
|
|
|
|
|
|
@asynccontextmanager
|
|
async def lifespan(app: FastAPI):
|
|
# Refuses to serve rather than starting up half-configured — see B-15 in BUGS.md.
|
|
validate_runtime_secrets()
|
|
|
|
endpoints = parse_endpoints(
|
|
settings.electrum_host,
|
|
settings.electrum_port,
|
|
settings.electrum_use_ssl,
|
|
settings.electrum_fallback_servers,
|
|
)
|
|
logger.info("Electrum endpoints (in rotation order): %s", ", ".join(str(e) for e in endpoints))
|
|
|
|
listener = ElectrumListener(_make_electrum_client, AsyncSessionLocal, endpoints)
|
|
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)
|
|
# 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)
|
|
|
|
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()),
|
|
]
|
|
try:
|
|
yield
|
|
finally:
|
|
for task in tasks:
|
|
task.cancel()
|
|
if listener.client is not None:
|
|
await listener.client.close()
|
|
|
|
|
|
app = FastAPI(title="PLM Lottery", lifespan=lifespan)
|
|
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(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)
|
|
|
|
|
|
_USER_GUIDE_PATH = Path("docs/guida-utente.md")
|
|
|
|
|
|
@app.get("/guida", include_in_schema=False)
|
|
async def user_guide() -> FileResponse:
|
|
"""Serves docs/guida-utente.md as plain text so it opens inline in the
|
|
browser (no markdown rendering — keeps this simple), linked from the
|
|
navbar's help button in app/static/index.html.
|
|
|
|
The Dockerfile must COPY docs/ for this to exist inside the container (it
|
|
didn't, which made this a guaranteed 500 in every real deployment — B-16).
|
|
Answers a clean 404 if the file is missing rather than an unhandled error."""
|
|
if not _USER_GUIDE_PATH.is_file():
|
|
logger.error("user guide missing at %s (is docs/ shipped in the image?)", _USER_GUIDE_PATH)
|
|
raise http_error(status.HTTP_404_NOT_FOUND, "guide_unavailable", "user guide not available")
|
|
return FileResponse(_USER_GUIDE_PATH, media_type="text/plain; charset=utf-8")
|
|
|
|
|
|
app.mount("/", StaticFiles(directory="app/static", html=True), name="static")
|