Phase 5: Redis pub/sub for horizontal scaling

Splits the WebSocket layer into three pieces so one app instance and many
behave identically: ConnectionManager stays a purely local socket registry;
RoomBroadcaster publishes chat messages to a per-room Redis channel and
every instance (including the publisher) forwards received messages to its
own local sockets via a single psubscribe("room:*") listener started in
main.py's lifespan; Presence is a Redis-backed refcounted hash per room
tracking who's connected across all instances.

Presence replaces the old process-local connected_user_ids check that
Phase 4's offline-push logic used -- without it, a user connected on a
different instance would look offline and get a redundant push. Fixing
this was scoped in beyond the issue's literal ask (message fan-out only)
since it's a real correctness gap in a phase specifically about running
more than one instance; a known limitation (no heartbeat/TTL, so a hard
crash leaks a presence increment) is documented in the README instead of
solved here.

New tests/test_broadcast.py spins up two independent app instances sharing
one Postgres + Redis to prove delivery and presence both actually cross
the Redis boundary, not just work in-process. Manually verified the same
thing against two real uvicorn processes on different ports.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

backend/app/ws/broadcaster.py

@@ -0,0 +1,41 @@
+import json
+import uuid
+
+from redis.asyncio import Redis
+
+from app.ws.connection_manager import ConnectionManager
+
+ROOM_CHANNEL_PREFIX = "room:"
+
+
+class RoomBroadcaster:
+    """Cross-instance message fan-out (ARCHITECTURE.md phase 5).
+
+    Publishes to a per-room Redis channel; every app instance -- including
+    the one that published -- subscribes via a single pattern subscription
+    and forwards to its own locally connected WebSocket clients via
+    ConnectionManager. A single instance just talks to itself through Redis,
+    so there's no separate code path for the 1-instance vs N-instance case.
+    """
+
+    def __init__(self, redis: Redis, manager: ConnectionManager) -> None:
+        self._redis = redis
+        self._manager = manager
+
+    async def publish(self, room_id: uuid.UUID, payload: dict) -> None:
+        await self._redis.publish(f"{ROOM_CHANNEL_PREFIX}{room_id}", json.dumps(payload))
+
+    async def listen(self) -> None:
+        pubsub = self._redis.pubsub()
+        await pubsub.psubscribe(f"{ROOM_CHANNEL_PREFIX}*")
+        try:
+            async for message in pubsub.listen():
+                if message["type"] != "pmessage":
+                    continue
+                channel = message["channel"]
+                room_id = uuid.UUID(channel.removeprefix(ROOM_CHANNEL_PREFIX))
+                payload = json.loads(message["data"])
+                await self._manager.broadcast(room_id, payload)
+        finally:
+            await pubsub.punsubscribe(f"{ROOM_CHANNEL_PREFIX}*")
+            await pubsub.aclose()

backend/app/ws/chat.py

@@ -9,7 +9,7 @@ from app.database import get_db
 from app.models import Room, RoomMembership, User
 from app.services.message_service import create_message
 from app.services.push_service import send_push_to_user
-from app.ws.connection_manager import ConnectionManager
+from app.ws.presence import Presence
 
 router = APIRouter(tags=["ws"])
 
@@ -33,7 +33,7 @@ async def _is_room_member(db: AsyncSession, room_id: uuid.UUID, user_id: uuid.UU
 
 async def _notify_offline_members(
     db: AsyncSession,
-    manager: ConnectionManager,
+    presence: Presence,
     room_id: uuid.UUID,
     sender: User,
     content: str,
@@ -42,7 +42,7 @@ async def _notify_offline_members(
         select(RoomMembership.user_id).where(RoomMembership.room_id == room_id)
     )
     member_ids = {row[0] for row in result.all()}
-    offline_ids = member_ids - manager.connected_user_ids(room_id)
+    offline_ids = member_ids - await presence.connected_user_ids(room_id)
     if not offline_ids:
         return
 
@@ -70,6 +70,8 @@ async def chat_endpoint(websocket: WebSocket, db: AsyncSession = Depends(get_db)
 
     await websocket.accept()
     manager = websocket.app.state.connection_manager
+    presence: Presence = websocket.app.state.presence
+    broadcaster = websocket.app.state.broadcaster
     joined_rooms: set[uuid.UUID] = set()
 
     try:
@@ -90,7 +92,8 @@ async def chat_endpoint(websocket: WebSocket, db: AsyncSession = Depends(get_db)
                         {"type": "error", "detail": "Not a member of this room"}
                     )
                     continue
-                manager.join(envelope.room_id, websocket, user.id)
+                manager.join(envelope.room_id, websocket)
+                await presence.join(envelope.room_id, user.id)
                 joined_rooms.add(envelope.room_id)
                 await websocket.send_json({"type": "joined", "room_id": str(envelope.room_id)})
 
@@ -99,6 +102,7 @@ async def chat_endpoint(websocket: WebSocket, db: AsyncSession = Depends(get_db)
                     await websocket.send_json({"type": "error", "detail": "room_id required"})
                     continue
                 manager.leave(envelope.room_id, websocket)
+                await presence.leave(envelope.room_id, user.id)
                 joined_rooms.discard(envelope.room_id)
 
             elif envelope.type == "message":
@@ -115,7 +119,7 @@ async def chat_endpoint(websocket: WebSocket, db: AsyncSession = Depends(get_db)
                     )
                     continue
                 message = await create_message(db, envelope.room_id, user.id, envelope.content)
-                await manager.broadcast(
+                await broadcaster.publish(
                     envelope.room_id,
                     {
                         "type": "message",
@@ -128,7 +132,7 @@ async def chat_endpoint(websocket: WebSocket, db: AsyncSession = Depends(get_db)
                     },
                 )
                 await _notify_offline_members(
-                    db, manager, envelope.room_id, user, envelope.content
+                    db, presence, envelope.room_id, user, envelope.content
                 )
 
             else:
@@ -140,3 +144,5 @@ async def chat_endpoint(websocket: WebSocket, db: AsyncSession = Depends(get_db)
         pass
     finally:
         manager.leave_all(websocket)
+        for room_id in joined_rooms:
+            await presence.leave(room_id, user.id)

backend/app/ws/connection_manager.py

@@ -5,22 +5,19 @@ from fastapi import WebSocket
 
 
 class ConnectionManager:
-    """In-memory, single-process WebSocket registry.
+    """Local, single-process WebSocket socket registry.
 
-    Correct for a single app-server instance only; cross-instance fan-out via
-    Redis pub/sub is a later phase (ARCHITECTURE.md phase 5).
+    Purely about delivering to sockets connected to *this* process --
+    cross-instance fan-out lives in RoomBroadcaster, and cross-instance
+    "who's connected" for push lives in Presence, both backed by Redis
+    (ARCHITECTURE.md phase 5).
     """
 
     def __init__(self) -> None:
         self._rooms: dict[uuid.UUID, set[WebSocket]] = defaultdict(set)
-        # A single connection can be joined to multiple rooms at once (one
-        # `join` message per room over the same socket), so this is keyed on
-        # the socket alone, not per-room.
-        self._ws_user: dict[WebSocket, uuid.UUID] = {}
 
-    def join(self, room_id: uuid.UUID, websocket: WebSocket, user_id: uuid.UUID) -> None:
+    def join(self, room_id: uuid.UUID, websocket: WebSocket) -> None:
         self._rooms[room_id].add(websocket)
-        self._ws_user[websocket] = user_id
 
     def leave(self, room_id: uuid.UUID, websocket: WebSocket) -> None:
         self._rooms[room_id].discard(websocket)
@@ -30,15 +27,6 @@ class ConnectionManager:
     def leave_all(self, websocket: WebSocket) -> None:
         for room_id in list(self._rooms.keys()):
             self.leave(room_id, websocket)
-        self._ws_user.pop(websocket, None)
-
-    def connected_user_ids(self, room_id: uuid.UUID) -> set[uuid.UUID]:
-        """Users (not just sockets) with an active connection to this room --
-        used to skip push notifications for anyone already watching, per
-        ARCHITECTURE.md's "members with no active connection" push flow."""
-        return {
-            self._ws_user[ws] for ws in self._rooms.get(room_id, ()) if ws in self._ws_user
-        }
 
     async def broadcast(self, room_id: uuid.UUID, payload: dict) -> None:
         for websocket in list(self._rooms.get(room_id, ())):

backend/app/ws/presence.py

@@ -0,0 +1,39 @@
+import uuid
+
+from redis.asyncio import Redis
+
+
+class Presence:
+    """Cross-instance "who's connected to this room," backed by a Redis hash
+    per room (field = user_id, value = connection refcount).
+
+    Refcounted rather than a plain set so a user with two connections to the
+    same room -- two tabs, or one per app instance -- doesn't get marked
+    offline when only one of those connections closes.
+
+    Known limitation: a hard crash (not a clean disconnect) leaks that
+    connection's increment forever, since there's no heartbeat/TTL here to
+    reclaim it -- out of scope for this phase, same category of
+    simplification as the "no server-side session revocation" note in the
+    README.
+    """
+
+    def __init__(self, redis: Redis) -> None:
+        self._redis = redis
+
+    def _key(self, room_id: uuid.UUID) -> str:
+        return f"presence:{room_id}"
+
+    async def join(self, room_id: uuid.UUID, user_id: uuid.UUID) -> None:
+        await self._redis.hincrby(self._key(room_id), str(user_id), 1)
+
+    async def leave(self, room_id: uuid.UUID, user_id: uuid.UUID) -> None:
+        key = self._key(room_id)
+        field = str(user_id)
+        remaining = await self._redis.hincrby(key, field, -1)
+        if remaining <= 0:
+            await self._redis.hdel(key, field)
+
+    async def connected_user_ids(self, room_id: uuid.UUID) -> set[uuid.UUID]:
+        fields = await self._redis.hkeys(self._key(room_id))
+        return {uuid.UUID(f) for f in fields}