core: survive a failed net-stack rebuild instead of silently dying

The four live-rebuild sites (deferred rebuild on Join/Leave, idle
SetNetworkMode, idle RegenerateIdentity) all did
`net.shutdown().await` then `build_net_stack(...).await?` — a build
failure propagated out of run_core_loop, which its supervisor only
logs. Every subsequent command went nowhere: window alive, app dead,
user told nothing. (The initial startup build already reported.)

New replace_net_stack() helper: tear down the old stack, build for the
requested posture, and on failure fall back to the posture the old
stack was actually running (tracked in the new `net_mode` local; when
the postures are equal the fallback is a plain retry — e.g. identity
regeneration, where reverting the already-persisted key would be
wrong). If the fallback lands, the UI is told the change didn't stick
and `network_mode` reverts so state stays honest and the change stays
re-attemptable. If both builds fail the UI gets a fatal 'Networking
lost … restart' error before the loop exits — informed, not a zombie.

Retry policy isolated in rebuild_with_fallback(), generic over the
builder: 4 new unit tests cover first-try success, fall-back, plain
retry, and double failure without binding sockets.

Fixes finding 2 of the 2026-07-16 full-codebase review.

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

.cargo/audit.toml

@@ -0,0 +1,11 @@
+# cargo-audit configuration. Keep the ignore list in sync with deny.toml,
+# which carries the full justification for each entry.
+[advisories]
+ignore = [
+    # quick-xml DoS advisories: build-time only, reached solely via the
+    # wayland-scanner proc-macro parsing trusted vendored protocol XML.
+    # Fix (0.41.0) is semver-incompatible with wayland-scanner's `^0.39`;
+    # drop once wayland-scanner bumps. See deny.toml.
+    "RUSTSEC-2026-0194",
+    "RUSTSEC-2026-0195",
+]

.gitea/workflows/cargo-deny.yml

@@ -1,34 +0,0 @@
-name: cargo-deny
-
-# Enforce the supply-chain policy in deny.toml (advisories / bans / licenses /
-# sources) on every push to main and every PR. Runs on a *locked* tree so the
-# pinned, vetted versions in Cargo.lock are exactly what get audited — see the
-# deny.toml header and VERSIONING.md. A new poisoned release of a dependency
-# cannot reach CI until Cargo.lock is deliberately updated.
-
-on:
-  push:
-    branches: [main]
-  pull_request:
-
-jobs:
-  cargo-deny:
-    runs-on: ubuntu-latest
-    # rust:1 provides the cargo toolchain that cargo-deny shells out to for
-    # `cargo metadata`. Adjust the runner label if your act_runner uses a
-    # different one.
-    container: rust:1
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install cargo-deny (pinned prebuilt)
-        run: |
-          set -euo pipefail
-          version=0.19.9
-          curl -sSfL \
-            "https://github.com/EmbarkStudios/cargo-deny/releases/download/${version}/cargo-deny-${version}-x86_64-unknown-linux-musl.tar.gz" \
-            | tar -xz -C /usr/local/bin --strip-components=1 --wildcards '*/cargo-deny'
-          cargo-deny --version
-
-      - name: cargo deny check
-        run: cargo deny --locked check

.gitea/workflows/ci.yml

@@ -36,7 +36,9 @@ jobs:
         run: cargo test --doc
 
       - name: cargo-deny (advisories, bans, licenses, sources)
-        run: cargo deny check
+        # --locked so the pinned, vetted versions in Cargo.lock are exactly
+        # what get audited (the lockfile-as-review-checkpoint model).
+        run: cargo deny --locked check
 
       - name: cargo-audit
         run: cargo audit

.gitea/workflows/windows-build.yml

@@ -7,11 +7,20 @@ name: windows-build
 # alias) so a Unix-only assumption can't sneak back in and break Windows.
 #
 # RUNNER REQUIREMENT: this needs a Windows act_runner registered with the
-# `windows-latest` label (the Linux `cargo-deny` job's container approach does
-# NOT apply here — Windows jobs run on the host, not a Linux container). If your
-# runner advertises a different label, change `runs-on` below. Until a Windows
-# runner exists this workflow is simply skipped/queued, not a failure of the
-# Linux CI.
+# `windows-latest` label (a Linux-container approach does NOT apply here —
+# Windows jobs run on the host, not a Linux container). If your runner
+# advertises a different label, change `runs-on` below.
+#
+# MANUAL-ONLY until that runner exists: with push/PR triggers enabled, every
+# push queued a run no runner could claim and Gitea auto-cancelled it ~24h
+# later, littering the Actions page with cancelled runs. Restore the push/PR
+# triggers when a Windows runner is registered:
+#
+#   on:
+#     push:
+#       branches: [main, "windows-port-**"]
+#     pull_request:
+#     workflow_dispatch:
 #
 # BUILD-HOST REQUIREMENTS (validated by the opus spike, see
 # peerspeak-windows-opus-spike.md):
@@ -23,12 +32,7 @@ name: windows-build
 # must provide both.
 
 on:
-  push:
-    # `main` plus the in-progress port branches, so the Windows path is exercised
-    # before merge rather than only after.
-    branches: [main, "windows-port-**"]
-  pull_request:
-  # Allow manual runs from the Gitea Actions UI.
+  # Manual runs from the Gitea Actions UI only — see the header comment.
   workflow_dispatch:
 
 permissions:

Cargo.lock

@@ -1207,9 +1207,9 @@ dependencies = [
 
 [[package]]
 name = "crossbeam-epoch"
-version = "0.9.18"
+version = "0.9.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
+checksum = "2d6914041f254d6e9176c01941b21115dcfb7089e55135a35411081bd106ef3f"
 dependencies = [
  "crossbeam-utils",
 ]

deny.toml

@@ -24,6 +24,19 @@ ignore = [
     # audiopus_sys: unmaintained FFI bindings to the stable libopus C library,
     # pulled in via our direct `opus 0.3.1` dep. No drop-in replacement.
     "RUSTSEC-2026-0150",
+    # ttf-parser: unmaintained, transitive via iced/cosmic-text (font parsing
+    # for the GUI). Inputs are system + embedded fonts, not network data. No
+    # upstream migration yet; revisit when iced moves off it.
+    "RUSTSEC-2026-0192",
+    # quick-xml 0.39.4 DoS advisories (quadratic dup-attr check; unbounded
+    # namespace allocation). Build-time only: quick-xml is reached solely via
+    # the wayland-scanner PROC-MACRO, which parses the wayland protocol XML
+    # files vendored inside the wayland-* crates at compile time. Attacker
+    # input never reaches it and it is not in the shipped binary. The fix
+    # (0.41.0) is semver-incompatible with wayland-scanner 0.31.x's `^0.39`
+    # requirement; drop both ignores once wayland-scanner releases a bump.
+    "RUSTSEC-2026-0194",
+    "RUSTSEC-2026-0195",
 ]
 
 # ---------------------------------------------------------------------------

src/app/mod.rs

@@ -6239,7 +6239,11 @@ fn view(state: &AppState) -> Element<'_, AppMessage> {
                         // Rendered only while the audio link is live — the
                         // Connecting/Reconnecting indicator covers the rest.
                         if let Some(info) = state.conn_stats.get(peer_id) {
-                            let dot_color = if info.relay { color_yellow } else { color_green };
+                            let dot_color = if info.relay {
+                                color_yellow
+                            } else {
+                                color_green
+                            };
                             let badge = row![
                                 text("●").size(9).color(dot_color),
                                 text(conn_badge_label(info)).size(11).color(color_subtext),
@@ -6248,7 +6252,9 @@ fn view(state: &AppState) -> Element<'_, AppMessage> {
                             .align_y(iced::alignment::Vertical::Center);
                             let detail = column![
                                 text(conn_tooltip_path(info)).size(11).color(color_text),
-                                text(conn_loss_label(info.loss_pct)).size(11).color(color_subtext),
+                                text(conn_loss_label(info.loss_pct))
+                                    .size(11)
+                                    .color(color_subtext),
                                 text(format!(
                                     "↑ {}   ↓ {}",
                                     conn_rate_label(info.up_kbps),
@@ -6261,9 +6267,11 @@ fn view(state: &AppState) -> Element<'_, AppMessage> {
                             name_col = name_col.push(
                                 tooltip(
                                     badge,
-                                    container(detail)
-                                        .padding(8)
-                                        .style(c_style(color_crust, color_surface, 6.0)),
+                                    container(detail).padding(8).style(c_style(
+                                        color_crust,
+                                        color_surface,
+                                        6.0,
+                                    )),
                                     iced::widget::tooltip::Position::Bottom,
                                 )
                                 .gap(6),

src/core/mod.rs

@@ -888,6 +888,103 @@ async fn build_net_stack(
     })
 }
 
+/// Retry policy for a live net-stack replacement, generic over the builder so
+/// it is unit-testable without binding sockets: build for `requested`; if that
+/// fails, build for `live` (the posture the old stack was actually running) so
+/// a bad posture change degrades to the previous posture instead of leaving no
+/// stack at all. When `requested == live` the second attempt is a plain retry.
+///
+/// `Ok((stack, mode, primary_err))` — a stack is up on `mode`; `primary_err`
+/// is `Some` when the first attempt failed. `Err((primary, fallback))` — both
+/// attempts failed and networking is gone.
+async fn rebuild_with_fallback<T, E, F, Fut>(
+    mut build: F,
+    requested: NetworkMode,
+    live: NetworkMode,
+) -> Result<(T, NetworkMode, Option<E>), (E, E)>
+where
+    F: FnMut(NetworkMode) -> Fut,
+    Fut: std::future::Future<Output = Result<T, E>>,
+{
+    match build(requested).await {
+        Ok(stack) => Ok((stack, requested, None)),
+        Err(primary) => match build(live).await {
+            Ok(stack) => Ok((stack, live, Some(primary))),
+            Err(fallback) => Err((primary, fallback)),
+        },
+    }
+}
+
+/// Tear down `old` and stand up a replacement stack for `requested_mode`.
+///
+/// A build failure here is rare (only the local socket bind can fail; the
+/// relay handshake is backgrounded), but it used to propagate straight out of
+/// `run_core_loop` with no `UiEvent`, silently killing every future command —
+/// the app looked alive and did nothing. Instead, fall back to `live_mode`
+/// via `rebuild_with_fallback`, tell the UI when the requested change did not
+/// stick, and return the mode the new stack actually runs so the caller can
+/// keep its state honest. `Err` only when both builds fail: networking is
+/// gone (already reported to the UI as fatal) and the caller should exit.
+#[allow(clippy::too_many_arguments)]
+async fn replace_net_stack(
+    old: NetStack,
+    what: &str,
+    secret_key: &SecretKey,
+    requested_mode: NetworkMode,
+    live_mode: NetworkMode,
+    friends_handler: &crate::presence_net::Handler,
+    publish: bool,
+    ui_tx: &mpsc::Sender<UiEvent>,
+) -> Result<(NetStack, NetworkMode), anyhow::Error> {
+    let lookup = old.memory_lookup.clone();
+    old.shutdown().await;
+    let outcome = rebuild_with_fallback(
+        |mode| {
+            build_net_stack(
+                secret_key.clone(),
+                mode,
+                lookup.clone(),
+                friends_handler.clone(),
+                publish,
+            )
+        },
+        requested_mode,
+        live_mode,
+    )
+    .await;
+    match outcome {
+        Ok((stack, mode, None)) => Ok((stack, mode)),
+        Ok((stack, mode, Some(primary))) => {
+            if mode == requested_mode {
+                // Same-posture retry succeeded — everything the user asked for
+                // is in effect, so log it rather than raising a UI error.
+                crate::log_msg(&format!(
+                    "{what}: net stack build failed once ({primary:#}); retry succeeded"
+                ));
+            } else {
+                let _ = ui_tx
+                    .send(UiEvent::Error(format!(
+                        "{what} failed ({primary:#}); staying on the previous \
+                         network mode for this session"
+                    )))
+                    .await;
+            }
+            Ok((stack, mode))
+        }
+        Err((primary, fallback)) => {
+            let _ = ui_tx
+                .send(UiEvent::Error(format!(
+                    "Networking lost: {primary:#} (recovery attempt also failed: \
+                     {fallback:#}). Restart PeerSpeak to reconnect."
+                )))
+                .await;
+            Err(anyhow::anyhow!(
+                "net stack rebuild failed: {primary:#}; fallback: {fallback:#}"
+            ))
+        }
+    }
+}
+
 /// Maximum number of *automatic* chat-attachment fetches in flight at once.
 ///
 /// Auto-fetch (inline image preview) is triggered by an untrusted peer's chat
@@ -1335,6 +1432,10 @@ async fn run_core_loop(
     // rebuilt on the next Leave (or before the next Join), preserving the old
     // "applies on next join" semantics while keeping the endpoint up while idle.
     let mut net_rebuild_pending = false;
+    // The posture the live stack was actually built with. Trails `network_mode`
+    // while a rebuild is pending, and is the fallback posture when a rebuild
+    // fails (see `replace_net_stack`).
+    let mut net_mode = network_mode;
 
     // When Discoverable is on, the instant it auto-reverts to Normal (W7 P6 time-box).
     // `None` = not Discoverable, no pending revert. Set on SetPresenceMode(Discoverable),
@@ -1552,17 +1653,24 @@ async fn run_core_loop(
                 // active, rebuild the persistent stack now — after the old session is
                 // gone, before the new one binds — so this join uses the new posture.
                 if net_rebuild_pending {
-                    let lookup = net.memory_lookup.clone();
-                    net.shutdown().await;
                     let publish = presence_mode.lock().unwrap().publishes_to_discovery();
-                    net = build_net_stack(
-                        secret_key.clone(),
+                    let (stack, live) = replace_net_stack(
+                        net,
+                        "Applying deferred network settings",
+                        &secret_key,
                         network_mode,
-                        lookup,
-                        friends_handler.clone(),
+                        net_mode,
+                        &friends_handler,
                         publish,
+                        &ui_tx,
                     )
                     .await?;
+                    net = stack;
+                    net_mode = live;
+                    // If the new posture failed and we fell back, keep the mode
+                    // state honest (and re-attemptable) rather than pretending
+                    // the change applied. The join proceeds on the live stack.
+                    network_mode = live;
                     net_rebuild_pending = false;
                 }
 
@@ -2594,17 +2702,21 @@ async fn run_core_loop(
                 // Apply any network-mode / identity change that was deferred while we
                 // were in the call (rebuild while idle keeps the endpoint reachable).
                 if net_rebuild_pending {
-                    let lookup = net.memory_lookup.clone();
-                    net.shutdown().await;
                     let publish = presence_mode.lock().unwrap().publishes_to_discovery();
-                    net = build_net_stack(
-                        secret_key.clone(),
+                    let (stack, live) = replace_net_stack(
+                        net,
+                        "Applying deferred network settings",
+                        &secret_key,
                         network_mode,
-                        lookup,
-                        friends_handler.clone(),
+                        net_mode,
+                        &friends_handler,
                         publish,
+                        &ui_tx,
                     )
                     .await?;
+                    net = stack;
+                    net_mode = live;
+                    network_mode = live;
                     net_rebuild_pending = false;
                 }
             }
@@ -2750,17 +2862,21 @@ async fn run_core_loop(
                     // idle; if a call is active, defer to the next Leave/Join so the
                     // live call isn't disrupted (preserves "applies on next join").
                     if active_session.is_none() {
-                        let lookup = net.memory_lookup.clone();
-                        net.shutdown().await;
                         let publish = presence_mode.lock().unwrap().publishes_to_discovery();
-                        net = build_net_stack(
-                            secret_key.clone(),
+                        let (stack, live) = replace_net_stack(
+                            net,
+                            "Network mode change",
+                            &secret_key,
                             network_mode,
-                            lookup,
-                            friends_handler.clone(),
+                            net_mode,
+                            &friends_handler,
                             publish,
+                            &ui_tx,
                         )
                         .await?;
+                        net = stack;
+                        net_mode = live;
+                        network_mode = live;
                     } else {
                         net_rebuild_pending = true;
                     }
@@ -2798,17 +2914,22 @@ async fn run_core_loop(
                 // key unchanged, so a rebuild would be pointless churn).
                 if regenerated {
                     if active_session.is_none() {
-                        let lookup = net.memory_lookup.clone();
-                        net.shutdown().await;
                         let publish = presence_mode.lock().unwrap().publishes_to_discovery();
-                        net = build_net_stack(
-                            secret_key.clone(),
+                        // Same mode both attempts — the fallback is a plain
+                        // retry under the (already persisted) new key.
+                        let (stack, live) = replace_net_stack(
+                            net,
+                            "Endpoint restart after identity change",
+                            &secret_key,
                             network_mode,
-                            lookup,
-                            friends_handler.clone(),
+                            net_mode,
+                            &friends_handler,
                             publish,
+                            &ui_tx,
                         )
                         .await?;
+                        net = stack;
+                        net_mode = live;
                     } else {
                         net_rebuild_pending = true;
                     }
@@ -3322,10 +3443,10 @@ fn replace_viewer_index<T>(viewers: &[(String, T)], ticket: &str) -> Option<usiz
 mod tests {
     use super::{
         KnownPeers, MAX_OPUS_PAYLOAD, MAX_RETAINED_PEERS, MIC_LEVEL_REPORT_SAMPLES, MicLevelMeter,
-        PLAYBACK_HANDOFF_QUEUE_FRAMES, PeerSpeakTicket, admit_retained, apply_peer_volume,
-        apply_volume, audio_datagram_len_ok, coalesce_insert, coalesce_pop, frame_level,
-        mix_frames, mix_stereo_frames, next_game_change, replace_viewer_index, send_playback_frame,
-        should_auto_fetch, stereo_to_mono,
+        NetworkMode, PLAYBACK_HANDOFF_QUEUE_FRAMES, PeerSpeakTicket, admit_retained,
+        apply_peer_volume, apply_volume, audio_datagram_len_ok, coalesce_insert, coalesce_pop,
+        frame_level, mix_frames, mix_stereo_frames, next_game_change, rebuild_with_fallback,
+        replace_viewer_index, send_playback_frame, should_auto_fetch, stereo_to_mono,
     };
     use crate::core::messages::{CoalesceKey, CoreCommand, coalesce_key};
     use std::collections::{HashMap, HashSet};
@@ -3349,6 +3470,101 @@ mod tests {
         assert_eq!(replace_viewer_index::<u8>(&[], "ticket-A"), None);
     }
 
+    // --- rebuild_with_fallback: the retry policy behind replace_net_stack ---
+    // The builder is injected, so these cover the policy without sockets. The
+    // closure does its bookkeeping synchronously and returns a ready future.
+
+    #[tokio::test]
+    async fn rebuild_keeps_requested_posture_on_first_success() {
+        let calls = std::cell::RefCell::new(Vec::new());
+        let out = rebuild_with_fallback(
+            |mode| {
+                calls.borrow_mut().push(mode);
+                std::future::ready(Ok::<u8, String>(7))
+            },
+            NetworkMode::DirectOnly,
+            NetworkMode::N0Full,
+        )
+        .await;
+        assert_eq!(out, Ok((7, NetworkMode::DirectOnly, None)));
+        // No second build: the live posture is only a fallback.
+        assert_eq!(*calls.borrow(), vec![NetworkMode::DirectOnly]);
+    }
+
+    #[tokio::test]
+    async fn rebuild_falls_back_to_the_live_posture_when_the_requested_one_fails() {
+        let calls = std::cell::RefCell::new(Vec::new());
+        let out = rebuild_with_fallback(
+            |mode| {
+                calls.borrow_mut().push(mode);
+                std::future::ready(if mode == NetworkMode::DirectOnly {
+                    Err("bind failed".to_string())
+                } else {
+                    Ok(7u8)
+                })
+            },
+            NetworkMode::DirectOnly,
+            NetworkMode::N0Full,
+        )
+        .await;
+        // A stack is up on the OLD posture and the caller learns both that it
+        // fell back (mode) and why (the primary error) — no silent zombie.
+        assert_eq!(
+            out,
+            Ok((7, NetworkMode::N0Full, Some("bind failed".to_string())))
+        );
+        assert_eq!(
+            *calls.borrow(),
+            vec![NetworkMode::DirectOnly, NetworkMode::N0Full]
+        );
+    }
+
+    #[tokio::test]
+    async fn rebuild_reports_both_errors_when_networking_is_gone() {
+        let out = rebuild_with_fallback(
+            |_| std::future::ready(Err::<u8, String>("bind failed".to_string())),
+            NetworkMode::DirectOnly,
+            NetworkMode::N0Full,
+        )
+        .await;
+        assert_eq!(
+            out,
+            Err(("bind failed".to_string(), "bind failed".to_string()))
+        );
+    }
+
+    #[tokio::test]
+    async fn rebuild_with_equal_postures_is_a_plain_retry() {
+        // RegenerateIdentity rebuilds under the same mode: the fallback is a
+        // second attempt with identical parameters, not a posture change.
+        let calls = std::cell::Cell::new(0u8);
+        let out = rebuild_with_fallback(
+            |mode| {
+                calls.set(calls.get() + 1);
+                assert_eq!(mode, NetworkMode::RelayNoDiscovery);
+                std::future::ready(if calls.get() == 1 {
+                    Err("transient".to_string())
+                } else {
+                    Ok(7u8)
+                })
+            },
+            NetworkMode::RelayNoDiscovery,
+            NetworkMode::RelayNoDiscovery,
+        )
+        .await;
+        // Succeeded on the requested posture, so the caller treats the change
+        // as applied (the Some(err) is logged, not surfaced as a UI error).
+        assert_eq!(
+            out,
+            Ok((
+                7,
+                NetworkMode::RelayNoDiscovery,
+                Some("transient".to_string())
+            ))
+        );
+        assert_eq!(calls.get(), 2);
+    }
+
     #[test]
     fn admit_retained_rejects_only_new_ids_at_the_cap() {
         // Below the cap, a brand-new identity is retained.

src/screenshare/mod.rs

@@ -374,7 +374,11 @@ pub async fn spawn_host(
     // Log the exact argv we hand pixelpass so a field log can confirm which
     // encode/quality flags (e.g. --bitrate) actually reached the host — these
     // are local flags with no ticket/secret, so logging them verbatim is safe.
-    crate::log_msg(&format!("pixelpass host spawn: {} {}", bin.display(), args.join(" ")));
+    crate::log_msg(&format!(
+        "pixelpass host spawn: {} {}",
+        bin.display(),
+        args.join(" ")
+    ));
     let mut child = Command::new(bin)
         .args(&args)
         .stdin(Stdio::null())

src/widget/context_input.rs

@@ -766,7 +766,11 @@ where
                 }
             }
             MenuAction::Paste => {
-                let clip = sanitize_clip(&clipboard.read(clipboard::Kind::Standard).unwrap_or_default());
+                let clip = sanitize_clip(
+                    &clipboard
+                        .read(clipboard::Kind::Standard)
+                        .unwrap_or_default(),
+                );
                 let edit = paste(self.value, start, end, &clip);
 
                 self.publish_paste(edit, shell);

tests/transport_loopback.rs

@@ -304,7 +304,9 @@ async fn connection_stats_report_a_direct_path_with_live_counters() {
     assert_eq!(info.remote_addr, s2.remote_addr);
     assert!(info.rtt_ms < 1000, "localhost RTT should be sane");
     assert!(
-        info.up_kbps.expect("same path + positive window has a rate") > 0.0,
+        info.up_kbps
+            .expect("same path + positive window has a rate")
+            > 0.0,
         "audio was flowing, so the upstream rate must be non-zero"
     );
 }