Merge pull request 'fix(companion): TUN reader no longer dies on non-blocking fd + VPN not metered' (#110) from fix/tun-blocking-fd-metered into main

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

Android/app/build.gradle.kts

@@ -11,8 +11,8 @@ android {
         applicationId = "com.archipelago.app"
         minSdk = 26
         targetSdk = 35
-        versionCode = 23
-        versionName = "0.5.3"
+        versionCode = 24
+        versionName = "0.5.4"
 
         vectorDrawables {
             useSupportLibrary = true

Android/app/src/main/java/com/archipelago/app/fips/ArchyVpnService.kt

@@ -68,6 +68,14 @@ class ArchyVpnService : VpnService() {
                 // And let apps that bind their own network skip the TUN
                 // entirely — this is mesh reachability, not a privacy VPN.
                 .allowBypass()
+                .apply {
+                    // Android 10+ treats VPN networks as METERED by default,
+                    // which flips the whole phone into data-saver behaviour
+                    // (background sync off, "metered" warnings) while the
+                    // mesh is up. It inherits the underlying network's real
+                    // metered state instead.
+                    if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.Q) setMetered(false)
+                }
                 .establish()
         } catch (e: Exception) {
             Log.e(TAG, "VPN establish failed", e)

Android/rust/archy-fips-core/Cargo.lock

@@ -86,6 +86,7 @@ dependencies = [
  "getrandom 0.2.17",
  "hex",
  "jni",
+ "libc",
  "paranoid-android",
  "serde_json",
  "tokio",

Android/rust/archy-fips-core/Cargo.toml

@@ -31,6 +31,8 @@ hex = "0.4"
 getrandom = "0.2"
 tokio = { version = "1", features = ["rt-multi-thread", "sync", "time", "macros"] }
 tracing = "0.1"
+# fcntl: force the VpnService TUN fd into blocking mode (see mesh::start).
+libc = "0.2"
 
 # The JNI surface only exists on Android; host builds skip it and drive the
 # mesh module directly (tests).

Android/rust/archy-fips-core/src/mesh.rs

@@ -97,6 +97,19 @@ pub fn parse_peers(peers_json: &str) -> Result<Vec<PeerConfig>> {
 pub fn start(secret: &str, peers_json: &str, tun_fd: i32) -> Result<(String, String)> {
     stop();
 
+    // Android hands the VpnService TUN fd over in non-blocking mode on some
+    // OS builds. The fips TUN reader is a dedicated blocking-read thread that
+    // treats EAGAIN as fatal — the loop died at startup ("TUN read error …
+    // Try again (os error 11)" on-device), so sessions came up but no packet
+    // ever entered the mesh. Force the fd into the blocking mode the reader
+    // is designed for.
+    unsafe {
+        let flags = libc::fcntl(tun_fd, libc::F_GETFL);
+        if flags >= 0 && (flags & libc::O_NONBLOCK) != 0 {
+            libc::fcntl(tun_fd, libc::F_SETFL, flags & !libc::O_NONBLOCK);
+        }
+    }
+
     let peers = parse_peers(peers_json)?;
     let config = build_config(secret, peers);
     let mut node = Node::new(config).map_err(|e| anyhow!("node init: {e}"))?;

docs/HANDOFF-2026-07-23-companion-apk-deploy.md

@@ -48,9 +48,40 @@ user's hands.
    verify `sudo -n fipsctl show status` reports the anchor connected —
    `fips.reconnect` RPC if not. A phone can dial the anchor perfectly and
    still fail if the node never enrolled with it.
-5. Re-test the user's exact flows with vc23 (updates any older install in
+5. Re-test the user's exact flows with **vc24** (updates any older install in
    place): (a) pair ON the LAN, then switch the phone to 5G — the UI must
    come up via the mesh ULA; (b) pair while ALREADY on 5G (never on the
    node's LAN) — scan, VPN consent, and the connect must succeed through
-   the anchor. If either fails, capture `adb logcat` around the attempt and
-   `fipsctl show sessions` on the node, and report back.
+   the anchor.
+
+## Live diagnosis update (22:30–22:50, phone on adb — Mac agent)
+
+vc23 on-device testing found and fixed the phone-side blocker, and narrowed
+what remains to the node side. State as of vc24:
+
+- **Fixed: TUN reader died at startup.** Android hands the VpnService fd over
+  non-blocking; the fips fork's blocking reader thread treats EAGAIN as fatal
+  ("TUN read error … Try again (os error 11)") — so mesh sessions came up but
+  NO packet ever entered the tunnel. archy-fips-core now forces the fd
+  blocking before `start_with_tun_fd`. Verified on-device: reader survives,
+  and the 30s anchor-link flap disappeared with it (stable 8+ min on 5G).
+- **Fixed: VPN marked not-metered** (`setMetered(false)`) — Android 10+
+  defaults VPNs to metered, putting the phone into data-restricted behaviour
+  while the mesh is up. Note the user's phone also has system **always-on
+  VPN** enabled for the app (`always_on_vpn_app`), a Settings-side toggle.
+- **Verified good on-device**: peer store has node (LAN udp/tcp hints) + vps2
+  anchor; saved server is npub-keyed with ULA; anchor session establishes
+  from 5G in ~6s; VPN is bypassable, VALIDATED, only fd00::/8 routed.
+- **REMAINING BLOCKER (node side)**: from the phone (app uid), ping6 and
+  HTTP to the node's ULA `fd79:1aa:b9e9:4c9f:1f80:5376:9385:1824` get no
+  reply — packets enter the mesh, nothing returns. Phone↔anchor works, so
+  suspect phone-fork ↔ node-daemon session/routing mismatch (FIPS wire
+  format is not stable across revs; phone pins fips-native fork 46494a74).
+  From Framework PT please capture:
+    - `fipsctl show status` (daemon version + anchor state)
+    - `fipsctl show sessions` and `show bloom` while the phone pings
+    - `ping6 <phone ULA fd68:496d:fe34:a06d:cf1:6e4:b6a4:3586>` from the
+      node (tests the reverse path)
+    - `ip addr show fips0` + confirm the web server listens on `[::]:80`
+  Report whether the node ever sees a session attempt from
+  `npub132c5whrsa6ccs0eylcpzaejq9uxul5ldvczz0axq78dh7fxkqj9st4uvzu`.