Files
plm-lottery/app/api/routes/rounds.py
T
davide 702b37b319 Cap SSE subscribers per client IP instead of only globally (B-38)
GET /rounds/stream capped concurrent subscribers with one global
counter (MAX_SUBSCRIBERS=500): anyone opening 500 connections degraded
every other user to polling. The comment called it a defensive cap;
it was actually the vector, since nothing stopped a single source from
exhausting it alone.

RoundEventBroadcaster now also tracks subscribers per client IP,
capped much lower (MAX_SUBSCRIBERS_PER_IP=5). Past that cap, opening
one more stream evicts that same IP's own oldest connection (woken via
a new EVICTED sentinel so the SSE generator closes it promptly) rather
than refusing the new one or letting one abusive IP crowd out unrelated
clients under the old global-only cap. The global cap stays as a
backstop against overall resource exhaustion regardless of source.

Extracted client_ip() (X-Forwarded-For, since Caddy reverse-proxies
every request) out of auth/routes.py into app/api/client_ip.py so the
login/registration throttles (B-33) and this new per-IP cap share one
definition instead of two that could drift apart.

Not implemented: enforcing the connection cap at the Caddy layer
itself, which the proposed fix also suggested - the standard Caddy
image this project uses has no such directive without a third-party
module, and building a custom image felt like a bigger, separate change
than this fix warranted.

Suite grows from 201 to 211 tests. BUGS.md moves B-38 to Previously
fixed.
2026-07-27 14:44:15 +02:00

189 lines
8.3 KiB
Python

import asyncio
import json
from datetime import datetime, timedelta, timezone
from fastapi import APIRouter, Depends, Request
from fastapi.responses import JSONResponse, Response, StreamingResponse
from pydantic import BaseModel
from sqlalchemy import func, select
from sqlalchemy.ext.asyncio import AsyncSession
from app.api.client_ip import client_ip
from app.api.timeutil import isoformat_utc
from app.auth.dependencies import get_optional_user
from app.db.models import RoundParticipant, User
from app.db.session import get_session
from app.rounds.config import get_round_config
from app.rounds.events import EVICTED, RoundEventCapacityError, broadcaster
from app.rounds.service import get_active_round
router = APIRouter(prefix="/rounds", tags=["rounds"])
# How often request.is_disconnected() gets (re-)checked while idle — bounds
# how long a subscriber slot lingers after a client goes away without a clean
# TCP close (e.g. the network just vanishes). Kept short since the check
# itself is cheap; it does NOT control how often anything is sent on the wire.
_SSE_DISCONNECT_CHECK_SECONDS = 5
# How often to send an SSE keep-alive comment on an otherwise-idle connection —
# well under any reasonable reverse-proxy/load-balancer idle-connection timeout
# (Caddy's default is 5 minutes) so the stream isn't silently dropped. Expressed
# as a multiple of the disconnect-check interval above.
_SSE_KEEPALIVE_TICKS = 4 # 4 * 5s = 20s between keep-alive comments
@router.get("/stream")
async def round_stream(request: Request) -> Response:
"""Server-Sent Events channel: pushes a content-free "update" notification
the instant round/bet/balance state changes anywhere (see app/rounds/events.py
for the publish() call sites), instead of clients only finding out on their
next poll. No payload and no auth: it's a public "go refetch" signal, and
the actual data still comes from the normal per-user REST endpoints, which
is where authorization and personalization (e.g. user_played) already live.
Frontend polling (app/static/index.html) is left in place as a fallback —
this is purely additive, so a dropped/blocked SSE connection degrades to
the pre-existing polling behavior rather than losing updates outright.
That's also what happens past MAX_SUBSCRIBERS (app/rounds/events.py): this
returns 503 rather than opening a stream, and the browser's EventSource
just retries later while the frontend keeps working off polling meanwhile.
Concurrent streams are additionally capped per client IP (B-38): past
MAX_SUBSCRIBERS_PER_IP, opening one more evicts that IP's own oldest
connection rather than refusing the new one or letting a single source
exhaust the global cap and degrade every other user.
"""
try:
queue = broadcaster.subscribe(client_ip(request))
except RoundEventCapacityError:
return JSONResponse(status_code=503, content={"detail": "too many concurrent update streams"})
async def event_generator():
ticks_since_keepalive = 0
try:
while True:
if await request.is_disconnected():
break
try:
item = await asyncio.wait_for(queue.get(), timeout=_SSE_DISCONNECT_CHECK_SECONDS)
if item is EVICTED:
break # this IP opened another stream past its per-IP cap
yield "event: update\ndata: {}\n\n".format(json.dumps({}))
ticks_since_keepalive = 0
except asyncio.TimeoutError:
ticks_since_keepalive += 1
if ticks_since_keepalive >= _SSE_KEEPALIVE_TICKS:
yield ": keep-alive\n\n"
ticks_since_keepalive = 0
finally:
broadcaster.unsubscribe(queue)
return StreamingResponse(
event_generator(),
media_type="text/event-stream",
headers={"Cache-Control": "no-store", "X-Accel-Buffering": "no"},
)
class CurrentRoundResponse(BaseModel):
server_time: str
round_id: int | None = None
status: str | None = None
opened_at: str | None = None
closes_at: str | None = None
participant_count: int = 0
bet_amount_sats: int
jackpot_sats: int = 0
draw_animation_seconds: int
winner_user_id: int | None = None
winner_amount_sats: int | None = None
draw_block_height: int | None = None
draw_block_hash: str | None = None
# B-36: set only while status == "drawing", so the frontend can show "still
# waiting for a block" rather than a countdown implying a bounded wait — this
# phase has no timeout, only draw_animation_seconds' cosmetic minimum.
draw_waiting_since: str | None = None
chain_tip_height: int | None = None
lottery_paused: bool = False
user_played: bool = False
@router.get("/current", response_model=CurrentRoundResponse)
async def current_round(
request: Request,
session: AsyncSession = Depends(get_session),
user: User | None = Depends(get_optional_user),
) -> CurrentRoundResponse:
config = await get_round_config(session)
round_ = await get_active_round(session)
listener = request.app.state.electrum_listener
chain_tip_height = listener.tip_height or None
if round_ is None:
await session.commit()
return CurrentRoundResponse(
server_time=datetime.now(timezone.utc).isoformat(),
bet_amount_sats=config.bet_amount_sats,
draw_animation_seconds=config.draw_animation_seconds,
chain_tip_height=chain_tip_height,
lottery_paused=config.paused,
)
participant_count = await session.scalar(
select(func.count()).select_from(RoundParticipant).where(RoundParticipant.round_id == round_.id)
) or 0
# The pool is the sum of what the participants' bets actually paid into the pool
# address — each one is already net of that bet's network fee. Deriving it from
# participant_count * the *current* bet_amount_sats instead overstated it, and
# silently changed the advertised jackpot of a round in progress whenever an
# operator edited the bet amount (B-11).
pool_amount_sats = await session.scalar(
select(func.coalesce(func.sum(RoundParticipant.bet_amount_sats), 0)).where(
RoundParticipant.round_id == round_.id
)
) or 0
opened_at = round_.opened_at.replace(tzinfo=timezone.utc)
closes_at = opened_at + timedelta(seconds=config.round_duration_seconds)
# Lets the frontend show the personalized win/lose reveal only to players in
# this round — everyone else (not logged in, or logged in but didn't bet)
# just sees the generic phase progress instead of a "non hai vinto" that
# wouldn't mean anything to them.
user_played = False
if user is not None:
user_played = (
await session.scalar(
select(RoundParticipant).where(
RoundParticipant.round_id == round_.id, RoundParticipant.user_id == user.id
)
)
) is not None
await session.commit()
# Shown to players as "jackpot": the winner's 70% share of the pool (same split
# rounds/scheduler.py applies at payout time), not the full pool. It remains an
# upper bound by the payout tx's own fee, which is deducted from the winner's
# share and isn't knowable until the payout is built — a few hundred sat on a
# 1 sat/vB payout, i.e. invisible at PLM amounts, but it is not exact.
jackpot_sats = pool_amount_sats * 70 // 100
return CurrentRoundResponse(
server_time=datetime.now(timezone.utc).isoformat(),
round_id=round_.id,
status=round_.status,
opened_at=opened_at.isoformat(),
closes_at=closes_at.isoformat(),
participant_count=participant_count,
bet_amount_sats=config.bet_amount_sats,
jackpot_sats=jackpot_sats,
draw_animation_seconds=config.draw_animation_seconds,
winner_user_id=round_.winner_user_id,
winner_amount_sats=round_.winner_amount_sats,
draw_block_height=round_.draw_block_height,
draw_block_hash=round_.draw_block_hash,
draw_waiting_since=isoformat_utc(round_.drawing_started_at) if round_.status == "drawing" else None,
chain_tip_height=chain_tip_height,
lottery_paused=config.paused,
user_played=user_played,
)