Merge pull request 'fix(voice-limit-guard): two simultaneous joins can no longer both pass a full room (#25)' (#33) from fix/voice-limit-race into main

The limit was checked against participants LiveKit already had, so
tokens issued but not yet connected were not counted: two users
pressing Join together could both get into a 1-person channel.
Serialise the check per room and give each admitted user a 30 s
reservation, counted like a present user until LiveKit lists them or
it expires.

Refs #25

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017PCb59uY3UKqDqt7B6hzd5

README.md

@@ -67,7 +67,7 @@ matrix/
 - coturn config: `/etc/turnserver.conf`
 - LiveKit config: `/etc/livekit/config.yaml`
 - LiveKit service: `livekit-server.service`
-- lk-jwt-service: `lk-jwt-service.service` (now binds `:8071` via drop-in `/etc/systemd/system/lk-jwt-service.service.d/override.conf`; serves JWT tokens for MatrixRTC at `/sfu/get` and legacy `/get_token`)
+- lk-jwt-service: `lk-jwt-service.service` (now binds `127.0.0.1:8071` via drop-in `/etc/systemd/system/lk-jwt-service.service.d/override.conf`; serves JWT tokens for MatrixRTC at `/sfu/get` and legacy `/get_token`)
 - voice-limit-guard: `voice-limit-guard.service` (binds `:8070`, fronts lk-jwt-service — enforces hard per-room voice participant limits **and publish permissions (screenshare/camera via JWT re-signing)** for ALL clients; script `/opt/voice-limit-guard/voice-limit-guard.py`) — see [Voice Channel Limits & Call Permissions](#voice-channel-limits--call-permissions)
 - Hookshot: `/opt/hookshot/`, service: `matrix-hookshot.service`
 - Hookshot config: `/opt/hookshot/config.yml`
@@ -238,7 +238,9 @@ install -D -m644 /opt/matrix-config/livekit/voice-limit-guard.py /opt/voice-limi
 install -m644 /opt/matrix-config/systemd/voice-limit-guard.service /etc/systemd/system/voice-limit-guard.service
 # one-time: rebind lk-jwt-service to :8071
 mkdir -p /etc/systemd/system/lk-jwt-service.service.d
-printf '[Service]\nEnvironment=LIVEKIT_JWT_BIND=:8071\n' > /etc/systemd/system/lk-jwt-service.service.d/override.conf
+# Loopback only (matrix #24): the guard runs on this LXC; binding all
+# interfaces let any LAN host mint unguarded tokens straight from :8071.
+printf '[Service]\nEnvironment=LIVEKIT_JWT_BIND=127.0.0.1:8071\n' > /etc/systemd/system/lk-jwt-service.service.d/override.conf
 systemctl daemon-reload && systemctl restart lk-jwt-service && systemctl enable --now voice-limit-guard
 ```
 
@@ -290,7 +292,7 @@ The token in `draupnir/production.yaml` in this repo is **intentionally redacted
 | 7880 | LiveKit HTTP | 0.0.0.0 |
 | 7881 | LiveKit RTC TCP | 0.0.0.0 |
 | 8070 | voice-limit-guard (fronts lk-jwt-service) | 0.0.0.0 |
-| 8071 | lk-jwt-service (behind guard) | 0.0.0.0 |
+| 8071 | lk-jwt-service (behind guard) | 127.0.0.1 (matrix #24; was 0.0.0.0) |
 | 8080 | synapse-admin (nginx) | 0.0.0.0 |
 | 3478 | coturn STUN/TURN | 0.0.0.0 |
 | 5349 | coturn TURNS/TLS | 0.0.0.0 |

cinny/config.json

@@ -8,9 +8,16 @@
   "allowCustomHomeservers": false,
   "featuredCommunities": {
     "openAsDefault": false,
-    "spaces": [],
-    "rooms": [],
-    "servers": []
+    "spaces": [
+      "!-1ZBnAH-JiCOV8MGSKN77zDGTuI3pgSdy8Unu_DrDyc",
+      "#homelab:codestorm.net"
+    ],
+    "rooms": [
+      "#jellyfin:matrix.org"
+    ],
+    "servers": [
+      "matrixrooms.info"
+    ]
   },
   "hashRouter": {
     "enabled": false,

cinny/lotus_deploy.sh

@@ -160,7 +160,13 @@ echo "[$(date '+%Y-%m-%d %H:%M:%S')] Deploying to $WEBROOT..."
 # /var/www/html/config.json by lxc106-cinny.sh. The build ships a DEV default
 # (allowCustomHomeservers:true); rsyncing it would clobber the production config
 # on every deploy. Keep the app bundle and the runtime config separate.
-rsync -a --delete --exclude config.json dist/ "$WEBROOT/"
+# [matrix #23] Keep the previous builds' hashed assets for a while: a browser
+# still holding an older index.html (or service-worker precache) asks for its
+# assets/index-<old hash>.js, and deleting them on every deploy broke the app
+# for those users until their cached shell expired. Prune after 14 days.
+rsync -a --delete --exclude config.json --exclude assets/ dist/ "$WEBROOT/"
+rsync -a dist/assets/ "$WEBROOT/assets/"
+find "$WEBROOT/assets" -type f -mtime +14 -delete
 
 echo "[$(date '+%Y-%m-%d %H:%M:%S')] ===== Deploy complete ($VITE_APP_VERSION) ====="
 

cinny/nginx-security-headers.conf

@@ -12,4 +12,4 @@ add_header X-XSS-Protection "1; mode=block" always;
 add_header Referrer-Policy strict-origin-when-cross-origin always;
 add_header Strict-Transport-Security "max-age=63072000; includeSubDomains; preload" always;
 add_header Permissions-Policy 'accelerometer=(), autoplay=(self "https://call.chat.lotusguild.org"), camera=(self "https://call.chat.lotusguild.org"), display-capture=(self "https://call.chat.lotusguild.org"), encrypted-media=(self), fullscreen=(self), geolocation=(self), gyroscope=(), magnetometer=(), microphone=(self "https://call.chat.lotusguild.org"), midi=(), payment=(), usb=()' always;
-add_header Content-Security-Policy "default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' blob:; style-src 'self' 'unsafe-inline'; img-src 'self' data: blob: https://matrix.lotusguild.org https://matrix.org https://*.matrix.org https://mozilla.org https://mozilla.modular.im https://drive.lotusguild.org https://media.giphy.com https://media0.giphy.com https://media1.giphy.com https://media2.giphy.com https://media3.giphy.com https://media4.giphy.com https://www.openstreetmap.org https://tile.openstreetmap.org; font-src 'self' data:; connect-src 'self' https://matrix.lotusguild.org wss://matrix.lotusguild.org https://isitup.lotusguild.org https://matrix.org https://*.matrix.org https://mozilla.org https://mozilla.modular.im https://chat.mozilla.org https://vector.im https://api.giphy.com https://*.giphy.com wss:; media-src 'self' https: blob:; frame-src 'self' https:; worker-src 'self' blob:; object-src 'none'; frame-ancestors 'none'; base-uri 'self'; form-action 'self';" always;
+add_header Content-Security-Policy "default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' blob:; style-src 'self' 'unsafe-inline'; img-src 'self' data: blob: https://matrix.lotusguild.org https://matrix.org https://*.matrix.org https://mozilla.org https://mozilla.modular.im https://drive.lotusguild.org https://media.giphy.com https://media0.giphy.com https://media1.giphy.com https://media2.giphy.com https://media3.giphy.com https://media4.giphy.com https://www.openstreetmap.org https://tile.openstreetmap.org; font-src 'self' data:; connect-src 'self' https://matrix.lotusguild.org wss://matrix.lotusguild.org https://isitup.lotusguild.org https://matrix.org https://*.matrix.org https://mozilla.org https://mozilla.modular.im https://chat.mozilla.org https://www.mozilla.org https://vector.im https://api.giphy.com https://*.giphy.com https://www.tiktok.com wss:; media-src 'self' https: blob:; frame-src 'self' https:; worker-src 'self' blob:; object-src 'none'; frame-ancestors 'none'; base-uri 'self'; form-action 'self';" always;

cinny/nginx.conf

@@ -1,3 +1,12 @@
+# [matrix #23] SPA routes (/, /home/…, /login/…) are rewritten to /index.html
+# inside `location /`, where no cache headers were set: browsers then reused a
+# heuristically fresh shell after a deploy and requested deleted assets. Only
+# the rewritten shell gets no-cache; other files there keep their defaults.
+map $uri $lotus_shell_cache_control {
+    /index.html "no-cache, no-store, must-revalidate";
+    default     "";
+}
+
 server {
     listen 80;
     listen [::]:80;
@@ -99,6 +108,9 @@ server {
     }
 
     location / {
+        # add_header here drops the server-level headers, so include them again.
+        include snippets/cinny-security-headers.conf;
+        add_header Cache-Control $lotus_shell_cache_control always;
         rewrite ^/config\.json$          /config.json break;
         rewrite ^/manifest\.json$        /manifest.json break;
         rewrite ^/sw\.js$                /sw.js break;

livekit/test_voice_limit_guard.py

@@ -389,3 +389,31 @@ class NormalizePermissionTest(unittest.TestCase):
         guard.livekit_update_participant = lambda *a: None
         participant = {"identity": "@a:x:DEV", "permission": {"canPublish": True, "canPublishSources": ["CAMERA"]}}
         self.assertFalse(guard.reconcile_participant("!r:x", participant, {"SCREEN_SHARE"}))
+
+
+class SlotReservationTests(unittest.TestCase):
+    """[matrix #25] Simultaneous joins can't both pass a full room."""
+
+    def test_second_simultaneous_join_is_blocked(self):
+        r = guard.SlotReservations(ttl=30)
+        present = set()
+        counted = present | r.reserved("room", present, now=0)
+        self.assertFalse(guard.should_block(1, counted, "@a:x"))
+        r.reserve("room", "@a:x", now=0)
+        # @b asks a moment later, before @a has connected to LiveKit.
+        counted = present | r.reserved("room", present, now=1)
+        self.assertTrue(guard.should_block(1, counted, "@b:x"))
+        # @a asking again (second device) is still allowed.
+        self.assertFalse(guard.should_block(1, counted, "@a:x"))
+
+    def test_reservation_expires_and_clears_once_present(self):
+        r = guard.SlotReservations(ttl=30)
+        r.reserve("room", "@a:x", now=0)
+        self.assertEqual(r.reserved("room", set(), now=31), set())
+        r.reserve("room", "@a:x", now=40)
+        self.assertEqual(r.reserved("room", {"@a:x"}, now=41), set())
+
+    def test_room_lock_is_per_room(self):
+        r = guard.SlotReservations()
+        self.assertIs(r.room_lock("a"), r.room_lock("a"))
+        self.assertIsNot(r.room_lock("a"), r.room_lock("b"))

livekit/voice-limit-guard.py

@@ -145,6 +145,41 @@ def should_block(limit: int, present_users: set, requester: str) -> bool:
     return len(present_users) >= limit
 
 
+# [matrix #25] Tokens issued but not yet connected weren't counted, so two
+# users pressing Join together could both pass a 1-person limit. Each admitted
+# user holds a short reservation (counted like a present user) until LiveKit
+# lists them or it expires; checks for a room are serialised with a lock.
+RESERVATION_TTL = 30.0
+
+
+class SlotReservations:
+    """Per-room reservations for admitted-but-not-yet-connected users."""
+
+    def __init__(self, ttl: float = RESERVATION_TTL):
+        self.ttl = ttl
+        self._by_room = {}  # alias -> {user: expiry}
+        self._guard = threading.Lock()
+        self._room_locks = {}
+
+    def room_lock(self, alias: str) -> threading.Lock:
+        with self._guard:
+            return self._room_locks.setdefault(alias, threading.Lock())
+
+    def reserved(self, alias: str, present: set, now: float) -> set:
+        """Unexpired reservations; drops expired ones and users now present."""
+        room = self._by_room.get(alias, {})
+        for user in [u for u, exp in room.items() if exp <= now or u in present]:
+            del room[user]
+        return set(room)
+
+    def reserve(self, alias: str, user: str, now: float) -> None:
+        if user:
+            self._by_room.setdefault(alias, {})[user] = now + self.ttl
+
+
+RESERVATIONS = SlotReservations()
+
+
 def allowed_sources(policy: dict):
     """Pure decision: the narrowed `canPublishSources` list, or None.
 
@@ -618,11 +653,16 @@ class Handler(BaseHTTPRequestHandler):
         # LiveKit-admin outage here cannot skip the publish-source policy below.
         if limit > 0 and alias:
             try:
-                present = livekit_present_users(alias)
-                if should_block(limit, present, requester):
-                    log(f"blocked {requester or '?'} from {room_id}: {len(present)}/{limit}")
-                    self._send_blocked()
-                    return
+                with RESERVATIONS.room_lock(alias):
+                    present = livekit_present_users(alias)
+                    now = time.monotonic()
+                    counted = present | RESERVATIONS.reserved(alias, present, now)
+                    if should_block(limit, counted, requester):
+                        log(f"blocked {requester or '?'} from {room_id}: {len(counted)}/{limit}")
+                        self._send_blocked()
+                        return
+                    if requester not in present:
+                        RESERVATIONS.reserve(alias, requester, now)
             except Exception as exc:
                 # Fail open on the limit only; still apply the policy below.
                 log(f"limit check error for {room_id}: {exc}")