fix(portainer): repair same-node Git routing with recoverable network migration

apps/gitea/manifest.yml

@@ -106,10 +106,3 @@ app:
       - Issue tracking and pull requests
       - CI/CD via Gitea Actions
       - Lightweight SQLite deployment
-
-  nginx_proxy:
-    listen: 3000
-    proxy_pass: http://127.0.0.1:3001
-    extra_headers:
-      - proxy_hide_header X-Frame-Options
-      - proxy_hide_header Content-Security-Policy

apps/portainer/manifest.yml

@@ -14,8 +14,16 @@ app:
   container:
     image: source.archipelago-foundation.org/lfg2025/portainer:2.45.0
     pull_policy: if-not-present
+    # Portainer fetches Git sources and images from services on this same node.
+    # Rootless pasta copies the host LAN address into its namespace, so a LAN
+    # URL points back at Portainer itself. Give it a private address with the
+    # supported rootless slirp backend; public app URLs still traverse the gate.
+    network: slirp4netns
     data_uid: "1000:1000"
 
+  # Snapshot state before an upgrade recreates this app with new networking.
+  backup_on_network_change: true
+
   dependencies:
     - storage: 1Gi
 

core/archipelago/src/api/rpc/package/async_lifecycle.rs

@@ -89,6 +89,15 @@ impl RpcHandler {
             match handler.handle_package_install(params).await {
                 Ok(_) => {
                     info!("package.install {}: complete", package_id_spawn);
+                    for id in [&package_id_spawn, &format!("archy-{}", package_id_spawn)] {
+                        crate::crash_recovery::clear_user_uninstalled(&handler.config.data_dir, id)
+                            .await;
+                    }
+                    crate::crash_recovery::mark_installed(
+                        &handler.config.data_dir,
+                        &package_id_spawn,
+                    )
+                    .await;
                     // The install pipeline has verified the container is up
                     // and healthy (see install.rs post-start exit check).
                     // Kick the scanner first so the fresh manifest (with
@@ -184,17 +193,20 @@ impl RpcHandler {
                     // phase is cleared (None) so no stale InstallPhase
                     // lingers on the card.
                     let err_msg = format!("Install failed: {:#}", e);
-                    let (mut data, _) = handler.state_manager.get_snapshot().await;
+                    handler
-                    if let Some(entry) = data.package_data.get_mut(&package_id_spawn) {
+                        .state_manager
-                        entry.state = PackageState::Stopped;
+                        .mutate_data(|data| {
-                        entry.install_progress = Some(crate::data_model::InstallProgress {
+                            if let Some(entry) = data.package_data.get_mut(&package_id_spawn) {
-                            size: 0,
+                                entry.state = PackageState::Stopped;
-                            downloaded: 0,
+                                entry.install_progress = Some(crate::data_model::InstallProgress {
-                            phase: None,
+                                    size: 0,
-                            message: Some(err_msg),
+                                    downloaded: 0,
-                        });
+                                    phase: None,
-                        handler.state_manager.update_data(data).await;
+                                    message: Some(err_msg),
-                    }
+                                });
+                            }
+                        })
+                        .await;
                 }
             }
         });
@@ -252,6 +264,11 @@ impl RpcHandler {
             match handler.handle_package_uninstall(params).await {
                 Ok(_) => {
                     info!("package.uninstall {}: complete", package_id_spawn);
+                    for id in [&package_id_spawn, &format!("archy-{}", package_id_spawn)] {
+                        crate::crash_recovery::mark_user_uninstalled(&handler.config.data_dir, id)
+                            .await;
+                        crate::crash_recovery::clear_installed(&handler.config.data_dir, id).await;
+                    }
                     // Inner handler already removed the package entry on
                     // success. Nothing more to do here.
                 }
@@ -382,52 +399,56 @@ impl RpcHandler {
 /// call, but fires before the spawn so the UI sees it immediately.
 async fn flip_to_installing(state_manager: &StateManager, package_id: &str) {
     use crate::data_model::{Description, Manifest, PackageDataEntry, StaticFiles};
-    let (mut data, _) = state_manager.get_snapshot().await;
+    state_manager
-    let entry = data
+        .mutate_data(|data| {
-        .package_data
+            let entry = data
-        .entry(package_id.to_string())
+                .package_data
-        .or_insert_with(|| PackageDataEntry {
+                .entry(package_id.to_string())
-            state: PackageState::Installing,
+                .or_insert_with(|| PackageDataEntry {
-            health: None,
+                    ui_ready: None,
-            exit_code: None,
+                    state: PackageState::Installing,
-            static_files: StaticFiles {
+                    health: None,
-                license: String::new(),
+                    exit_code: None,
-                instructions: String::new(),
+                    static_files: StaticFiles {
-                // Leave icon empty during the transient Installing window:
+                        license: String::new(),
-                // hardcoding `<id>.png` is wrong for ~half our apps (many use
+                        instructions: String::new(),
-                // `.svg` / `.webp`), producing a broken-image flicker until
+                        // Leave icon empty during the transient Installing window:
-                // the scanner refreshes the entry. The frontend's `icon`
+                        // hardcoding `<id>.png` is wrong for ~half our apps (many use
-                // computed falls through to `curatedMap.get(id)?.icon` which
+                        // `.svg` / `.webp`), producing a broken-image flicker until
-                // has the correct extensions for known apps.
+                        // the scanner refreshes the entry. The frontend's `icon`
-                icon: String::new(),
+                        // computed falls through to `curatedMap.get(id)?.icon` which
-            },
+                        // has the correct extensions for known apps.
-            manifest: Manifest {
+                        icon: String::new(),
-                id: package_id.to_string(),
+                    },
-                title: package_id.to_string(),
+                    manifest: Manifest {
-                version: String::new(),
+                        id: package_id.to_string(),
-                description: Description {
+                        title: package_id.to_string(),
-                    short: "Installing...".to_string(),
+                        version: String::new(),
-                    long: String::new(),
+                        description: Description {
-                },
+                            short: "Installing...".to_string(),
-                release_notes: String::new(),
+                            long: String::new(),
-                license: String::new(),
+                        },
-                wrapper_repo: String::new(),
+                        release_notes: String::new(),
-                upstream_repo: String::new(),
+                        license: String::new(),
-                support_site: String::new(),
+                        wrapper_repo: String::new(),
-                marketing_site: String::new(),
+                        upstream_repo: String::new(),
-                donation_url: None,
+                        support_site: String::new(),
-                author: None,
+                        marketing_site: String::new(),
-                website: None,
+                        donation_url: None,
-                interfaces: None,
+                        author: None,
-                tier: None,
+                        website: None,
-            },
+                        interfaces: None,
-            installed: None,
+                        tier: None,
-            install_progress: None,
+                    },
-            uninstall_stage: None,
+                    installed: None,
-            available_update: None,
+                    install_progress: None,
-        });
+                    uninstall_stage: None,
-    entry.state = PackageState::Installing;
+                    available_update: None,
-    state_manager.update_data(data).await;
+                });
+            entry.ui_ready = Some(false);
+            entry.state = PackageState::Installing;
+        })
+        .await;
 }
 
 /// True when the failed install still has a real footprint: any container
@@ -485,20 +506,23 @@ async fn remove_entry_with_notification(
     id_prefix: &str,
     message: &str,
 ) {
-    let (mut data, _) = handler.state_manager.get_snapshot().await;
+    handler
-    data.package_data.remove(package_id);
+        .state_manager
-    data.notifications.push(crate::data_model::Notification {
+        .mutate_data(|data| {
-        id: format!("{id_prefix}-{package_id}"),
+            data.package_data.remove(package_id);
-        level: crate::data_model::NotificationLevel::Error,
+            data.notifications.push(crate::data_model::Notification {
-        title: format!("Could not install {package_id}"),
+                id: format!("{id_prefix}-{package_id}"),
-        message: message.to_string(),
+                level: crate::data_model::NotificationLevel::Error,
-        timestamp: chrono::Utc::now().to_rfc3339(),
+                title: format!("Could not install {package_id}"),
-        app_id: Some(package_id.to_string()),
+                message: message.to_string(),
-    });
+                timestamp: chrono::Utc::now().to_rfc3339(),
-    while data.notifications.len() > 20 {
+                app_id: Some(package_id.to_string()),
-        data.notifications.remove(0);
+            });
-    }
+            while data.notifications.len() > 20 {
-    handler.state_manager.update_data(data).await;
+                data.notifications.remove(0);
+            }
+        })
+        .await;
 }
 
 /// Flip an existing entry's state and return the pre-flip value (or None if
@@ -508,18 +532,23 @@ async fn flip_package_state(
     package_id: &str,
     new_state: PackageState,
 ) -> Option<PackageState> {
-    let (mut data, _) = state_manager.get_snapshot().await;
+    state_manager
-    let prev = data.package_data.get(package_id).map(|e| e.state.clone());
+        .mutate_data(|data| {
-    if let Some(entry) = data.package_data.get_mut(package_id) {
+            let prev = data.package_data.get(package_id).map(|e| e.state.clone());
-        entry.state = new_state;
+            if let Some(entry) = data.package_data.get_mut(package_id) {
-        state_manager.update_data(data).await;
+                if new_state != PackageState::Running {
-    } else {
+                    entry.ui_ready = Some(false);
-        warn!(
+                }
-            "flip_package_state: no entry for {} — cannot flip",
+                entry.state = new_state;
-            package_id
+            } else {
-        );
+                warn!(
-    }
+                    "flip_package_state: no entry for {} — cannot flip",
-    prev
+                    package_id
+                );
+            }
+            prev
+        })
+        .await
 }
 
 /// Set state unconditionally (no-op if entry no longer exists).
@@ -528,13 +557,18 @@ async fn set_package_state(
     package_id: &str,
     new_state: PackageState,
 ) {
-    let (mut data, _) = state_manager.get_snapshot().await;
+    state_manager
-    if let Some(entry) = data.package_data.get_mut(package_id) {
+        .mutate_data(|data| {
-        if entry.state != new_state {
+            if let Some(entry) = data.package_data.get_mut(package_id) {
-            entry.state = new_state;
+                if entry.state != new_state {
-            state_manager.update_data(data).await;
+                    if new_state != PackageState::Running {
-        }
+                        entry.ui_ready = Some(false);
-    }
+                    }
+                    entry.state = new_state;
+                }
+            }
+        })
+        .await
 }
 
 /// Set state and clear the uninstall_stage label. Used when an uninstall
@@ -545,12 +579,17 @@ async fn set_package_state_and_clear_uninstall_stage(
     package_id: &str,
     new_state: PackageState,
 ) {
-    let (mut data, _) = state_manager.get_snapshot().await;
+    state_manager
-    if let Some(entry) = data.package_data.get_mut(package_id) {
+        .mutate_data(|data| {
-        entry.state = new_state;
+            if let Some(entry) = data.package_data.get_mut(package_id) {
-        entry.uninstall_stage = None;
+                if new_state != PackageState::Running {
-        state_manager.update_data(data).await;
+                    entry.ui_ready = Some(false);
-    }
+                }
+                entry.state = new_state;
+                entry.uninstall_stage = None;
+            }
+        })
+        .await
 }
 
 /// Kick the container scanner to run immediately and wait for it to finish

core/archipelago/src/api/rpc/package/install.rs

@@ -545,7 +545,7 @@ impl RpcHandler {
         // Keep legacy install flow as default while migration is in progress.
         if orchestrator_managed {
             let orchestrator_app_id = orchestrator_install_app_id(package_id);
-            self.set_install_phase(package_id, InstallPhase::CreatingContainer)
+            self.set_install_phase(package_id, InstallPhase::PreparingApp)
                 .await;
             install_log(&format!(
                 "INSTALL ORCH: {} — attempting orchestrator install as {}",
@@ -1699,32 +1699,10 @@ autopilot.active=false\n",
             patch_indeedhub_nostr_provider().await;
         }
 
-        // Gitea: keep it on its native host port (3001). The UI opens Gitea
+        // Gitea owns its public URL and security settings in app.ini, including
-        // in a new tab on that direct port so absolute asset URLs must be
+        // values chosen in its first-run setup. Do not rewrite operator values
-        // rooted at the host port rather than Archipelago's /app/gitea/ path.
+        // or claim success from best-effort grep/sed commands. The app gate
-        if package_id == "gitea" {
+        // fronts its declared HTTP port and handles frame headers separately.
-            let _ = tokio::fs::remove_file("/etc/nginx/conf.d/gitea-iframe.conf").await;
-
-            // Set ROOT_URL to the direct launch route so links/assets stay
-            // anchored under the same origin Gitea is launched from.
-            let host_ip = &self.config.host_ip;
-            let _ = tokio::process::Command::new("podman")
-                .args(["exec", "gitea", "sh", "-c",
-                       &format!("grep -q ROOT_URL /data/gitea/conf/app.ini && sed -i 's|ROOT_URL.*|ROOT_URL = http://{}:3001/|' /data/gitea/conf/app.ini || true", host_ip)])
-                .output()
-                .await;
-            // Also ensure X_FRAME_OPTIONS is empty so Gitea doesn't send the header
-            let _ = tokio::process::Command::new("podman")
-                .args(["exec", "gitea", "sh", "-c",
-                       "grep -q X_FRAME_OPTIONS /data/gitea/conf/app.ini && sed -i 's|X_FRAME_OPTIONS.*|X_FRAME_OPTIONS =|' /data/gitea/conf/app.ini || sed -i '/^\\[security\\]/a X_FRAME_OPTIONS =' /data/gitea/conf/app.ini"])
-                .output()
-                .await;
-
-            info!(
-                "Gitea: ROOT_URL set to http://{}:3001/, X_FRAME_OPTIONS cleared",
-                host_ip
-            );
-        }
 
         if package_id == "nextcloud" {
             let host_ip = &self.config.host_ip;
@@ -2053,25 +2031,8 @@ fn parse_setup_token(lines: &[&str]) -> Option<String> {
 }
 
 async fn cleanup_stale_package_ports(package_id: &str) {
-    match package_id {
+    // Never kill by port: another app or the management gate may own it.
-        "grafana" => cleanup_stale_pasta_port("3000").await,
+    crate::container::ghost_reaper::reap_for_app(package_id).await;
-        "homeassistant" | "home-assistant" => cleanup_stale_pasta_port("8123").await,
-        "searxng" => cleanup_stale_pasta_port("8888").await,
-        "uptime-kuma" => cleanup_stale_pasta_port("3002").await,
-        "gitea" => {
-            cleanup_stale_pasta_port("3001").await;
-            cleanup_stale_pasta_port("2222").await;
-            cleanup_stale_pasta_port("3000").await;
-        }
-        "nginx-proxy-manager" => {
-            cleanup_stale_pasta_port("8081").await;
-            cleanup_stale_pasta_port("8084").await;
-            cleanup_stale_pasta_port("8444").await;
-        }
-        "nextcloud" => cleanup_stale_pasta_port("8085").await,
-        "portainer" => cleanup_stale_pasta_port("9000").await,
-        _ => {}
-    }
 }
 
 fn install_command_tail(
@@ -2196,93 +2157,11 @@ async fn cleanup_start_conflict(package_id: &str, stderr: &str) -> bool {
         return true;
     }
 
-    match package_id {
+    if stderr.contains("pasta failed") || stderr.contains("address already in use") {
-        "grafana"
+        crate::container::ghost_reaper::reap_for_app(package_id).await;
-            if stderr.contains("pasta failed") || stderr.contains("address already in use") =>
+        return true;
-        {
-            cleanup_stale_pasta_port("3000").await;
-            true
-        }
-        "homeassistant" | "home-assistant"
-            if stderr.contains("pasta failed") || stderr.contains("address already in use") =>
-        {
-            cleanup_stale_pasta_port("8123").await;
-            true
-        }
-        "searxng"
-            if stderr.contains("pasta failed") || stderr.contains("address already in use") =>
-        {
-            cleanup_stale_pasta_port("8888").await;
-            true
-        }
-        "uptime-kuma"
-            if stderr.contains("pasta failed") || stderr.contains("address already in use") =>
-        {
-            cleanup_stale_pasta_port("3002").await;
-            true
-        }
-        "gitea" if stderr.contains("pasta failed") || stderr.contains("address already in use") => {
-            cleanup_stale_pasta_port("3001").await;
-            cleanup_stale_pasta_port("2222").await;
-            cleanup_stale_pasta_port("3000").await;
-            true
-        }
-        "nginx-proxy-manager"
-            if stderr.contains("pasta failed") || stderr.contains("address already in use") =>
-        {
-            cleanup_stale_pasta_port("8081").await;
-            cleanup_stale_pasta_port("8084").await;
-            cleanup_stale_pasta_port("8444").await;
-            true
-        }
-        "nextcloud"
-            if stderr.contains("pasta failed") || stderr.contains("address already in use") =>
-        {
-            cleanup_stale_pasta_port("8085").await;
-            true
-        }
-        "portainer"
-            if stderr.contains("pasta failed") || stderr.contains("address already in use") =>
-        {
-            cleanup_stale_pasta_port("9000").await;
-            true
-        }
-        _ => false,
     }
-}
+    false
-
-async fn cleanup_stale_pasta_port(port: &str) {
-    // NEVER kill our own process. The daemon holds catalog app ports over
-    // IPv6 (the mesh app-port relay), so a blunt `fuser -k <port>/tcp` would
-    // terminate archipelago itself mid-install — installs failed and apps
-    // vanished on a test node 2026-07-27. Kill every listener on the port
-    // EXCEPT our PID (and our process group), leaving the relay/daemon alive.
-    let self_pid = std::process::id();
-    let kill_listener = format!(
-        "ss -ltnp 'sport = :{port}' 2>/dev/null | sed -n 's/.*pid=\\([0-9]*\\).*/\\1/p' | \
-         while read p; do [ \"$p\" = \"{self_pid}\" ] || kill \"$p\" 2>/dev/null; done || true",
-    );
-    let _ = tokio::process::Command::new("sh")
-        .args(["-c", &kill_listener])
-        .output()
-        .await;
-
-    // sudo fuser -k, but exclude our own PID: fuser prints the PIDs holding
-    // the port; kill each except self. (`fuser -k` has no exclusion flag.)
-    let fuser_kill = format!(
-        "for p in $(sudo fuser {port}/tcp 2>/dev/null); do [ \"$p\" = \"{self_pid}\" ] || sudo kill \"$p\" 2>/dev/null; done || true",
-    );
-    let _ = tokio::process::Command::new("sh")
-        .args(["-c", &fuser_kill])
-        .output()
-        .await;
-
-    let pattern = format!("pasta.*{}", port);
-    let _ = tokio::process::Command::new("pkill")
-        .args(["-f", &pattern])
-        .output()
-        .await;
-    tokio::time::sleep(std::time::Duration::from_secs(1)).await;
 }
 
 async fn repair_nextcloud_permissions() {

core/archipelago/src/api/rpc/package/progress.rs

@@ -14,20 +14,23 @@ impl RpcHandler {
     /// the rare case where the pull stream actually parses, but podman
     /// almost never emits parseable progress on a piped stderr.
     pub(super) async fn set_install_progress(&self, package_id: &str, downloaded: u64, size: u64) {
-        let (mut data, _rev) = self.state_manager.get_snapshot().await;
+        self.state_manager
-        let entry = data
+            .mutate_data(|data| {
-            .package_data
+                let entry = data
-            .entry(package_id.to_string())
+                    .package_data
-            .or_insert_with(|| create_installing_entry(package_id));
+                    .entry(package_id.to_string())
-        entry.state = PackageState::Installing;
+                    .or_insert_with(|| create_installing_entry(package_id));
-        let existing_phase = entry.install_progress.as_ref().and_then(|p| p.phase);
+                entry.ui_ready = Some(false);
-        entry.install_progress = Some(InstallProgress {
+                entry.state = PackageState::Installing;
-            size,
+                let existing_phase = entry.install_progress.as_ref().and_then(|p| p.phase);
-            downloaded,
+                entry.install_progress = Some(InstallProgress {
-            phase: existing_phase,
+                    size,
-            message: None,
+                    downloaded,
-        });
+                    phase: existing_phase,
-        self.state_manager.update_data(data).await;
+                    message: None,
+                });
+            })
+            .await;
     }
 
     /// Set the install pipeline phase and broadcast. This is the
@@ -35,76 +38,86 @@ impl RpcHandler {
     /// percentage and a user-facing label. Byte counters are retained
     /// for the rare case podman emits parseable progress.
     pub(super) async fn set_install_phase(&self, package_id: &str, phase: InstallPhase) {
-        let (mut data, _rev) = self.state_manager.get_snapshot().await;
+        self.state_manager
-        let entry = data
+            .mutate_data(|data| {
-            .package_data
+                let entry = data
-            .entry(package_id.to_string())
+                    .package_data
-            .or_insert_with(|| create_installing_entry(package_id));
+                    .entry(package_id.to_string())
-        // Preparing / PullingImage / CreatingContainer / StartingContainer /
+                    .or_insert_with(|| create_installing_entry(package_id));
-        // WaitingHealthy / PostInstall all map to the Installing state.
+                // Preparing / PullingImage / CreatingContainer / StartingContainer /
-        // Updates use Updating state — the wrapper has already flipped
+                // WaitingHealthy / PostInstall all map to the Installing state.
-        // state to Updating, so don't clobber it.
+                // Updates use Updating state — the wrapper has already flipped
-        if entry.state != PackageState::Updating {
+                // state to Updating, so don't clobber it.
-            entry.state = PackageState::Installing;
+                if entry.state != PackageState::Updating {
-        }
+                    entry.ui_ready = Some(false);
-        let (size, downloaded) = entry
+                    entry.state = PackageState::Installing;
-            .install_progress
+                }
-            .as_ref()
+                let (size, downloaded) = entry
-            .map(|p| (p.size, p.downloaded))
+                    .install_progress
-            .unwrap_or((0, 0));
+                    .as_ref()
-        entry.install_progress = Some(InstallProgress {
+                    .map(|p| (p.size, p.downloaded))
-            size,
+                    .unwrap_or((0, 0));
-            downloaded,
+                entry.install_progress = Some(InstallProgress {
-            phase: Some(phase),
+                    size,
-            message: None,
+                    downloaded,
-        });
+                    phase: Some(phase),
-        self.state_manager.update_data(data).await;
+                    message: None,
+                });
+            })
+            .await;
     }
 
     /// Set a user-facing install status message (e.g. "Waiting for Bitcoin
     /// to start…") without disturbing the current phase/byte counters.
     pub(super) async fn set_install_message(&self, package_id: &str, message: &str) {
-        let (mut data, _rev) = self.state_manager.get_snapshot().await;
+        self.state_manager
-        let entry = data
+            .mutate_data(|data| {
-            .package_data
+                let entry = data
-            .entry(package_id.to_string())
+                    .package_data
-            .or_insert_with(|| create_installing_entry(package_id));
+                    .entry(package_id.to_string())
-        if entry.state != PackageState::Updating {
+                    .or_insert_with(|| create_installing_entry(package_id));
-            entry.state = PackageState::Installing;
+                if entry.state != PackageState::Updating {
-        }
+                    entry.ui_ready = Some(false);
-        let (size, downloaded, phase) = entry
+                    entry.state = PackageState::Installing;
-            .install_progress
+                }
-            .as_ref()
+                let (size, downloaded, phase) = entry
-            .map(|p| (p.size, p.downloaded, p.phase))
+                    .install_progress
-            .unwrap_or((0, 0, None));
+                    .as_ref()
-        entry.install_progress = Some(InstallProgress {
+                    .map(|p| (p.size, p.downloaded, p.phase))
-            size,
+                    .unwrap_or((0, 0, None));
-            downloaded,
+                entry.install_progress = Some(InstallProgress {
-            phase,
+                    size,
-            message: Some(message.to_string()),
+                    downloaded,
-        });
+                    phase,
-        self.state_manager.update_data(data).await;
+                    message: Some(message.to_string()),
+                });
+            })
+            .await;
     }
 
     /// Clear install progress after pull completes or fails.
     pub(super) async fn clear_install_progress(&self, package_id: &str) {
-        let (mut data, _rev) = self.state_manager.get_snapshot().await;
+        self.state_manager
-        if let Some(entry) = data.package_data.get_mut(package_id) {
+            .mutate_data(|data| {
-            entry.install_progress = None;
+                if let Some(entry) = data.package_data.get_mut(package_id) {
-        }
+                    entry.install_progress = None;
-        self.state_manager.update_data(data).await;
+                }
+            })
+            .await;
     }
 
     /// Set the uninstall stage label so the UI can show what's happening
     /// instead of a generic spinner. Each call broadcasts a state change
     /// — call sparingly (one per pipeline phase, not per container).
     pub(super) async fn set_uninstall_stage(&self, package_id: &str, stage: &str) {
-        let (mut data, _rev) = self.state_manager.get_snapshot().await;
+        self.state_manager
-        if let Some(entry) = data.package_data.get_mut(package_id) {
+            .mutate_data(|data| {
-            entry.uninstall_stage = Some(stage.to_string());
+                if let Some(entry) = data.package_data.get_mut(package_id) {
-            entry.state = crate::data_model::PackageState::Removing;
+                    entry.uninstall_stage = Some(stage.to_string());
-        }
+                    entry.state = crate::data_model::PackageState::Removing;
-        self.state_manager.update_data(data).await;
+                }
+            })
+            .await;
     }
 
     /// Update install progress (static method for use in async closures).
@@ -114,25 +127,28 @@ impl RpcHandler {
         downloaded: u64,
         total: u64,
     ) {
-        let (mut data, _rev) = state_manager.get_snapshot().await;
+        state_manager
-        let entry = data
+            .mutate_data(|data| {
-            .package_data
+                let entry = data
-            .entry(package_id.to_string())
+                    .package_data
-            .or_insert_with(|| create_installing_entry(package_id));
+                    .entry(package_id.to_string())
-        let existing_phase = entry.install_progress.as_ref().and_then(|p| p.phase);
+                    .or_insert_with(|| create_installing_entry(package_id));
-        entry.install_progress = Some(InstallProgress {
+                let existing_phase = entry.install_progress.as_ref().and_then(|p| p.phase);
-            size: total,
+                entry.install_progress = Some(InstallProgress {
-            downloaded,
+                    size: total,
-            phase: existing_phase,
+                    downloaded,
-            message: None,
+                    phase: existing_phase,
-        });
+                    message: None,
-        state_manager.update_data(data).await;
+                });
+            })
+            .await;
     }
 }
 
 /// Create a minimal PackageDataEntry for a package being installed.
 fn create_installing_entry(package_id: &str) -> PackageDataEntry {
     PackageDataEntry {
+        ui_ready: None,
         state: PackageState::Installing,
         health: None,
         exit_code: None,

core/archipelago/src/api/rpc/package/runtime.rs

@@ -1431,10 +1431,9 @@ async fn repair_before_package_start(container_name: &str) {
     // published port and the data-dir file locks, so the replacement either
     // fails to bind (`address already in use`) or starts and dies on the
     // lock — and `Restart=always` loops it there forever. Ordered before
-    // the port cleanup below: killing the owner is what actually frees the
+    // starting the replacement. A port sweep cannot distinguish a ghost
-    // port, and the port sweep alone cannot tell a ghost from a live app.
+    // from the dashboard gate or another live app and must never kill it.
     crate::container::ghost_reaper::reap_for_app(container_name).await;
-    cleanup_runtime_host_ports(container_name).await;
 }
 
 async fn wait_before_package_start(container_name: &str) {
@@ -1579,7 +1578,6 @@ async fn repair_netbird_network() {
 async fn repair_nginx_proxy_manager_container() {
     repair_nginx_proxy_manager_dirs().await;
     if !nginx_proxy_manager_has_legacy_admin_port().await {
-        cleanup_nginx_proxy_manager_ports().await;
         return;
     }
 
@@ -1588,7 +1586,7 @@ async fn repair_nginx_proxy_manager_container() {
     )
     .await;
     let _ = podman_control(&["rm", "-f", "nginx-proxy-manager"]).await;
-    cleanup_nginx_proxy_manager_ports().await;
+    crate::container::ghost_reaper::reap_for_app("nginx-proxy-manager").await;
     if let Err(err) = recreate_nginx_proxy_manager_container().await {
         tracing::warn!(error = %err, "failed to recreate stale nginx-proxy-manager container");
     }
@@ -1812,6 +1810,9 @@ fn manifest_host_ports(container_name: &str) -> Vec<u16> {
 
 pub(super) fn manifest_apps_dirs() -> Vec<std::path::PathBuf> {
     let mut dirs = Vec::new();
+    if let Some(root) = std::env::var_os("ARCHIPELAGO_APPS_DIR") {
+        dirs.push(root.into());
+    }
     if let Ok(manifest_dir) = std::env::var("CARGO_MANIFEST_DIR") {
         dirs.push(Path::new(&manifest_dir).join("../../apps"));
     }
@@ -2032,51 +2033,10 @@ async fn cleanup_start_conflict(container_name: &str, stderr: &str) {
         return;
     }
 
-    let ports = runtime_host_ports(container_name);
+    // Only reap processes proven to belong to an absent container. The app
-    if !ports.is_empty() {
+    // gate shares the app's port on other addresses and lives in this daemon;
-        cleanup_ports(&ports).await;
+    // killing port owners (or matching argv with pkill) kills the dashboard.
-        return;
+    crate::container::ghost_reaper::reap_for_app(container_name).await;
-    }
-}
-
-async fn cleanup_runtime_host_ports(container_name: &str) {
-    let ports = runtime_host_ports(container_name);
-    if !ports.is_empty() {
-        cleanup_ports(&ports).await;
-    }
-}
-
-async fn cleanup_nginx_proxy_manager_ports() {
-    cleanup_ports(&[8081, 8084, 8444]).await;
-}
-
-async fn cleanup_ports(ports: &[u16]) {
-    for port in ports {
-        cleanup_stale_pasta_port(&port.to_string()).await;
-    }
-}
-
-async fn cleanup_stale_pasta_port(port: &str) {
-    let kill_listener = format!(
-        "ss -ltnp 'sport = :{}' 2>/dev/null | sed -n 's/.*pid=\\([0-9]*\\).*/\\1/p' | xargs -r kill 2>/dev/null || true",
-        port
-    );
-    let _ = tokio::process::Command::new("sh")
-        .args(["-c", &kill_listener])
-        .output()
-        .await;
-
-    let pattern = format!("pasta.*{}", port);
-    let _ = tokio::process::Command::new("pkill")
-        .args(["-f", &pattern])
-        .output()
-        .await;
-    let pattern = format!("rootlessport.*{}", port);
-    let _ = tokio::process::Command::new("pkill")
-        .args(["-f", &pattern])
-        .output()
-        .await;
-    tokio::time::sleep(std::time::Duration::from_secs(1)).await;
 }
 
 pub(super) fn is_missing_companion_ok(name: &str, stderr: &str) -> bool {
@@ -2095,13 +2055,16 @@ async fn flip_package_state(
     package_id: &str,
     transitional: PackageState,
 ) -> Option<PackageState> {
-    let (mut data, _) = state_manager.get_snapshot().await;
+    state_manager
-    let prev = data.package_data.get(package_id).map(|e| e.state.clone());
+        .mutate_data(|data| {
-    if let Some(entry) = data.package_data.get_mut(package_id) {
+            let prev = data.package_data.get(package_id).map(|e| e.state.clone());
-        entry.state = transitional;
+            if let Some(entry) = data.package_data.get_mut(package_id) {
-        state_manager.update_data(data).await;
+                entry.ui_ready = Some(false);
-    }
+                entry.state = transitional;
-    prev
+            }
+            prev
+        })
+        .await
 }
 
 /// Write the package entry's final state. No-op if the entry has since
@@ -2111,13 +2074,18 @@ async fn set_package_state(
     package_id: &str,
     new_state: PackageState,
 ) {
-    let (mut data, _) = state_manager.get_snapshot().await;
+    state_manager
-    if let Some(entry) = data.package_data.get_mut(package_id) {
+        .mutate_data(|data| {
-        if entry.state != new_state {
+            if let Some(entry) = data.package_data.get_mut(package_id) {
-            entry.state = new_state;
+                if entry.state != new_state {
-            state_manager.update_data(data).await;
+                    if new_state != PackageState::Running {
-        }
+                        entry.ui_ready = Some(false);
-    }
+                    }
+                    entry.state = new_state;
+                }
+            }
+        })
+        .await
 }
 
 pub(super) async fn reconcile_companions_for(package_id: &str) {
@@ -2185,6 +2153,20 @@ pub(super) fn orchestrator_uninstall_app_ids(package_id: &str) -> Vec<String> {
 mod tests {
     use super::*;
 
+    #[tokio::test]
+    async fn port_conflict_cleanup_preserves_live_host_listener() {
+        // The previous ss|kill sweep terminated the daemon's app gate on a
+        // restart. Keep a real listening socket owned by this test process.
+        let listener = tokio::net::TcpListener::bind("127.0.0.2:2342")
+            .await
+            .unwrap();
+        let addr = listener.local_addr().unwrap();
+        cleanup_start_conflict("photoprism", "address already in use").await;
+        let client = tokio::net::TcpStream::connect(addr).await.unwrap();
+        let _connection = listener.accept().await.unwrap();
+        drop(client);
+    }
+
     #[test]
     fn missing_container_classifier_covers_podman5_phrasings() {
         // Regression (.228 gate 2026-07-08): podman 5.x `inspect` on a missing

core/archipelago/src/api/rpc/transitional.rs

@@ -150,23 +150,31 @@ async fn flip_to_transitional(
     app_id: &str,
     transitional: PackageState,
 ) -> Option<PackageState> {
-    let (mut data, _) = state_manager.get_snapshot().await;
+    state_manager
-    let prev = data.package_data.get(app_id).map(|e| e.state.clone());
+        .mutate_data(|data| {
-    if let Some(entry) = data.package_data.get_mut(app_id) {
+            let prev = data.package_data.get(app_id).map(|e| e.state.clone());
-        entry.state = transitional;
+            if let Some(entry) = data.package_data.get_mut(app_id) {
-        state_manager.update_data(data).await;
+                entry.ui_ready = Some(false);
-    }
+                entry.state = transitional;
-    prev
+            }
+            prev
+        })
+        .await
 }
 
 /// Set the entry's state to `new_state`. No-ops if the entry has since been
 /// removed (e.g. uninstall ran concurrently).
 async fn set_state(state_manager: &StateManager, app_id: &str, new_state: PackageState) {
-    let (mut data, _) = state_manager.get_snapshot().await;
+    state_manager
-    if let Some(entry) = data.package_data.get_mut(app_id) {
+        .mutate_data(|data| {
-        if entry.state != new_state {
+            if let Some(entry) = data.package_data.get_mut(app_id) {
-            entry.state = new_state;
+                if entry.state != new_state {
-            state_manager.update_data(data).await;
+                    if new_state != PackageState::Running {
-        }
+                        entry.ui_ready = Some(false);
-    }
+                    }
+                    entry.state = new_state;
+                }
+            }
+        })
+        .await
 }

core/archipelago/src/appgate/identity.rs

@@ -114,6 +114,9 @@ impl PortMap {
 /// there.
 fn apps_dirs() -> Vec<PathBuf> {
     let mut dirs = Vec::new();
+    if let Some(root) = std::env::var_os("ARCHIPELAGO_APPS_DIR") {
+        dirs.push(root.into());
+    }
     if let Ok(manifest_dir) = std::env::var("CARGO_MANIFEST_DIR") {
         dirs.push(PathBuf::from(manifest_dir).join("../../apps"));
     }

core/archipelago/src/appgate/listener.rs

@@ -144,6 +144,34 @@ pub fn shared_status() -> Arc<RwLock<GateStatus>> {
         .clone()
 }
 
+static REFRESH_KICK: std::sync::LazyLock<tokio::sync::Notify> =
+    std::sync::LazyLock::new(tokio::sync::Notify::new);
+static REFRESH_REV: std::sync::LazyLock<tokio::sync::watch::Sender<u64>> =
+    std::sync::LazyLock::new(|| tokio::sync::watch::channel(0).0);
+
+/// Installation must not wait for the minute sweep before becoming reachable.
+/// Wait for a completed sweep, bounded if shutdown/startup prevents one.
+pub async fn refresh_now() {
+    let mut completed = REFRESH_REV.subscribe();
+    REFRESH_KICK.notify_one();
+    let _ = tokio::time::timeout(std::time::Duration::from_secs(3), completed.changed()).await;
+}
+
+pub fn port_claimed(status: &GateStatus, port: u16) -> bool {
+    let mut external = false;
+    let mut tor = false;
+    for (claimed_port, address) in &status.claimed {
+        if *claimed_port != port {
+            continue;
+        }
+        if let Ok(ip) = address.parse::<IpAddr>() {
+            tor |= ip == GATE_TOR_UPSTREAM;
+            external |= !ip.is_loopback();
+        }
+    }
+    external && tor
+}
+
 /// Run the gate. Returns only on shutdown.
 pub async fn run(
     gate: Arc<AppGate>,
@@ -162,11 +190,12 @@ pub async fn run(
 
     loop {
         tokio::select! {
-            _ = interval.tick() => {
+            _ = interval.tick() => {}
-                sweep(&gate, &status, &mut held, &shutdown_rx).await;
+            _ = REFRESH_KICK.notified() => {}
-            }
             _ = shutdown_rx.changed() => return,
         }
+        sweep(&gate, &status, &mut held, &shutdown_rx).await;
+        REFRESH_REV.send_modify(|revision| *revision = revision.wrapping_add(1));
     }
 }
 
@@ -461,3 +490,19 @@ mod tests {
         assert!(!status.is_fully_enforced());
     }
 }
+
+#[cfg(test)]
+mod readiness_tests {
+    use super::*;
+    #[test]
+    fn readiness_requires_external_and_tor_claims_for_the_same_port() {
+        let mut status = GateStatus::default();
+        assert!(!port_claimed(&status, 3001));
+        status.claimed.push((3001, "127.0.0.2".into()));
+        assert!(!port_claimed(&status, 3001));
+        status.claimed.push((3002, "192.0.2.10".into()));
+        assert!(!port_claimed(&status, 3001));
+        status.claimed.push((3001, "192.0.2.10".into()));
+        assert!(port_claimed(&status, 3001));
+    }
+}

core/archipelago/src/assistant/evals.rs

@@ -322,6 +322,7 @@ async fn eval_rpc_handler() -> (Arc<RpcHandler>, tempfile::TempDir) {
 fn installed_entry(app_id: &str) -> crate::data_model::PackageDataEntry {
     use crate::data_model::{Description, Manifest, PackageDataEntry, PackageState, StaticFiles};
     PackageDataEntry {
+        ui_ready: None,
         state: PackageState::Running,
         health: None,
         exit_code: None,

core/archipelago/src/assistant/mod.rs

@@ -1069,6 +1069,7 @@ mod tests {
             Description, Manifest, PackageDataEntry, PackageState, StaticFiles,
         };
         PackageDataEntry {
+            ui_ready: None,
             state: PackageState::Running,
             health: None,
             exit_code: None,

core/archipelago/src/container/docker_packages.rs

@@ -3,8 +3,9 @@
 
 use anyhow::Result;
 use archipelago_container::{
-    ContainerRuntime as ContainerRuntimeTrait, ContainerState, PodmanClient,
+    ContainerRuntime as ContainerRuntimeTrait, ContainerState, ContainerStatus, PodmanClient,
 };
+use futures_util::StreamExt;
 use std::collections::HashMap;
 use std::sync::Arc;
 use tracing::{debug, info};
@@ -25,8 +26,15 @@ impl DockerPackageScanner {
     }
 
     /// Scan Docker containers and convert to package data
-    pub async fn scan_containers(&self) -> Result<HashMap<String, PackageDataEntry>> {
+    pub async fn scan_containers(
-        let containers = self.runtime.list_containers().await?;
+        &self,
+        data_dir: &std::path::Path,
+        cached: &HashMap<String, PackageDataEntry>,
+    ) -> Result<HashMap<String, PackageDataEntry>> {
+        let mut containers = self.runtime.list_containers().await?;
+        let installed = crate::crash_recovery::load_installed_apps(data_dir).await;
+        let uninstalled = crate::crash_recovery::load_user_uninstalled(data_dir).await;
+        restore_absent_installed(&mut containers, &installed, &uninstalled);
 
         debug!("Found {} containers", containers.len());
 
@@ -139,6 +147,18 @@ impl DockerPackageScanner {
                 continue;
             }
 
+            if container.id.is_empty() {
+                if let Some(previous) = cached.get(&app_id) {
+                    let mut held = previous.clone();
+                    held.state = PackageState::Stopped;
+                    held.ui_ready = Some(false);
+                    held.health = None;
+                    held.exit_code = None;
+                    packages.insert(app_id.clone(), held);
+                    continue;
+                }
+            }
+
             // Get metadata for this app
             let metadata = get_app_metadata(&app_id);
             // Manifest-owned metadata (icon) wins over the static table: the
@@ -179,14 +199,22 @@ impl DockerPackageScanner {
             let tor_address = read_tor_address(&app_id).await;
 
             // Extract actual version from container image tag
-            let running_version = image_versions::extract_version_from_image(&container.image);
+            let running_version = if container.id.is_empty() {
+                String::new() // Absence cannot establish the installed image version.
+            } else {
+                image_versions::extract_version_from_image(&container.image)
+            };
 
             // Decoupled from the binary OTA: prefer the remote app catalog,
             // falling back to the image-versions.sh pin when uncovered/offline.
-            let available_update =
+            let available_update = if container.id.is_empty() {
-                crate::container::app_catalog::available_update_for_app(&app_id, &container.image);
+                None
+            } else {
+                crate::container::app_catalog::available_update_for_app(&app_id, &container.image)
+            };
 
             let package = PackageDataEntry {
+                ui_ready: Some(false),
                 state: package_state.clone(),
                 health: container.health.clone(),
                 exit_code: if package_state == PackageState::Exited {
@@ -283,10 +311,215 @@ impl DockerPackageScanner {
             );
         }
 
+        let probes: Vec<_> = packages
+            .iter()
+            .filter_map(|(id, pkg)| {
+                if pkg.state != PackageState::Running {
+                    return None;
+                }
+                let url = pkg
+                    .installed
+                    .as_ref()?
+                    .interface_addresses
+                    .get("main")?
+                    .lan_address
+                    .clone()?;
+                Some((id.clone(), url))
+            })
+            .collect();
+        let mut results = futures_util::stream::iter(
+            probes
+                .into_iter()
+                .map(|(id, url)| async move { (id, launch_http_ready(&url).await) }),
+        )
+        .buffer_unordered(8);
+        while let Some((id, ready)) = results.next().await {
+            if let Some(pkg) = packages.get_mut(&id) {
+                pkg.ui_ready = Some(ready);
+            }
+        }
+        // HTTP on loopback can precede the LAN/Tor listener after install.
+        let port_map = crate::appgate::identity::build_port_map();
+        let gated: Vec<_> = packages
+            .iter()
+            .filter_map(|(id, pkg)| {
+                if pkg.ui_ready != Some(true) {
+                    return None;
+                }
+                let url = pkg
+                    .installed
+                    .as_ref()?
+                    .interface_addresses
+                    .get("main")?
+                    .lan_address
+                    .as_deref()?;
+                let port = launch_url_port(url)?;
+                port_map
+                    .gated(port)
+                    .filter(|gate| gate.declared)
+                    .map(|_| (id.clone(), port))
+            })
+            .collect();
+        if !gated.is_empty() {
+            use crate::appgate::listener::{port_claimed, refresh_now, shared_status};
+            let status = shared_status();
+            let needs_refresh = {
+                let current = status.read().await;
+                gated.iter().any(|(_, port)| !port_claimed(&current, *port))
+            };
+            if needs_refresh {
+                refresh_now().await;
+            }
+            let current = status.read().await;
+            for (id, port) in gated {
+                if !port_claimed(&current, port) {
+                    packages.get_mut(&id).unwrap().ui_ready = Some(false);
+                }
+            }
+        }
         Ok(packages)
     }
 }
 
+/// Quadlet removes containers during ordinary stops/restarts. Rebuild installed
+/// entries even on the daemon's first scan; a runtime absence is not uninstall.
+fn restore_absent_installed(
+    containers: &mut Vec<ContainerStatus>,
+    installed: &std::collections::HashSet<String>,
+    uninstalled: &std::collections::HashSet<String>,
+) {
+    fn canonical(name: &str) -> &str {
+        let name = name.strip_prefix("archy-").unwrap_or(name);
+        match name {
+            "immich_server" => "immich",
+            _ => name,
+        }
+    }
+    let mut present: std::collections::HashSet<String> = containers
+        .iter()
+        .map(|c| canonical(&c.name).to_owned())
+        .collect();
+    let removed: std::collections::HashSet<_> =
+        uninstalled.iter().map(|id| canonical(id)).collect();
+    for name in installed {
+        let id = canonical(name);
+        if removed.contains(id) || !present.insert(id.to_owned()) {
+            continue;
+        }
+        containers.push(ContainerStatus {
+            id: String::new(),
+            name: id.to_owned(),
+            state: ContainerState::Stopped,
+            health: None,
+            exit_code: None,
+            started_at: None,
+            image: String::new(),
+            created: String::new(),
+            ports: Vec::new(),
+            lan_address: None,
+        });
+    }
+}
+
+/// Probe the actual loopback upstream, not the app gate's login page. A bound
+/// TCP socket alone can still reset requests or serve a startup 503.
+async fn launch_http_ready(candidate: &str) -> bool {
+    let Ok(mut url) = reqwest::Url::parse(candidate) else {
+        return false;
+    };
+    if !matches!(url.scheme(), "http" | "https") {
+        return false;
+    }
+    if url.set_host(Some("127.0.0.1")).is_err() {
+        return false;
+    }
+    static CLIENT: std::sync::OnceLock<reqwest::Client> = std::sync::OnceLock::new();
+    let client = CLIENT.get_or_init(|| {
+        reqwest::Client::builder()
+            .no_proxy()
+            .timeout(std::time::Duration::from_secs(2))
+            .redirect(reqwest::redirect::Policy::none())
+            // Self-signed local app certificates are normal. This client only
+            // contacts loopback and never sends credentials or follows redirects.
+            .danger_accept_invalid_certs(true)
+            .build()
+            .expect("local readiness client")
+    });
+    match client.get(url).send().await {
+        Ok(response) => matches!(response.status().as_u16(), 200..=399 | 401 | 403),
+        Err(_) => false,
+    }
+}
+
+#[cfg(test)]
+mod lifecycle_regression_tests {
+    use super::*;
+    use tokio::io::{AsyncReadExt, AsyncWriteExt};
+
+    #[test]
+    fn registry_survives_empty_runtime_and_deduplicates_aliases() {
+        let installed = ["archy-gitea", "gitea", "immich_server", "archy-removed"]
+            .into_iter()
+            .map(str::to_owned)
+            .collect();
+        let removed = ["removed".to_owned()].into_iter().collect();
+        let mut containers = Vec::new();
+        restore_absent_installed(&mut containers, &installed, &removed);
+        assert_eq!(containers.len(), 2);
+        assert!(containers
+            .iter()
+            .all(|c| c.state == ContainerState::Stopped));
+        containers[0].state = ContainerState::Running;
+        restore_absent_installed(&mut containers, &installed, &removed);
+        assert_eq!(containers.len(), 2);
+        assert_eq!(containers[0].state, ContainerState::Running);
+    }
+
+    #[tokio::test]
+    async fn readiness_rejects_startup_errors_and_accepts_auth_and_redirects() {
+        for (status, expected) in [
+            (200, true),
+            (302, true),
+            (401, true),
+            (403, true),
+            (404, false),
+            (500, false),
+            (502, false),
+            (503, false),
+        ] {
+            let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
+            let port = listener.local_addr().unwrap().port();
+            let task = tokio::spawn(async move {
+                let (mut stream, _) = listener.accept().await.unwrap();
+                let mut buf = [0; 2048];
+                let n = stream.read(&mut buf).await.unwrap();
+                assert!(String::from_utf8_lossy(&buf[..n]).starts_with("GET /start HTTP/1.1"));
+                stream.write_all(format!("HTTP/1.1 {status} Test\r\nContent-Length: 0\r\nConnection: close\r\n\r\n").as_bytes()).await.unwrap();
+            });
+            assert_eq!(
+                launch_http_ready(&format!("http://localhost:{port}/start")).await,
+                expected,
+                "status {status}"
+            );
+            task.await.unwrap();
+        }
+    }
+
+    #[tokio::test]
+    async fn readiness_rejects_tcp_accept_without_http() {
+        let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
+        let port = listener.local_addr().unwrap().port();
+        let task = tokio::spawn(async move {
+            let (stream, _) = listener.accept().await.unwrap();
+            drop(stream);
+        });
+        assert!(!launch_http_ready(&format!("http://localhost:{port}/")).await);
+        task.await.unwrap();
+        assert!(!launch_http_ready(&format!("http://localhost:{port}/")).await);
+        assert!(!launch_http_ready("file:///tmp/test").await);
+    }
+}
+
 struct AppMetadata {
     title: String,
     description: String,

core/archipelago/src/container/migration_backup.rs

@@ -0,0 +1,251 @@
+//! Consistent, private snapshots for declaratively opted-in network migrations.
+use anyhow::{bail, Context, Result};
+use archipelago_container::AppManifest;
+use std::os::unix::fs::PermissionsExt;
+use std::path::{Path, PathBuf};
+
+pub fn enabled(manifest: &AppManifest) -> Result<bool> {
+    match manifest.app.extensions.get("backup_on_network_change") {
+        None => Ok(false),
+        Some(value) => value
+            .as_bool()
+            .context("backup_on_network_change must be boolean"),
+    }
+}
+
+fn relative_sources(manifest: &AppManifest, data_dir: &Path) -> Result<Vec<PathBuf>> {
+    let mut sources = Vec::new();
+    for volume in &manifest.app.volumes {
+        if volume.options.iter().any(|v| v == "ro") || volume.volume_type == "tmpfs" {
+            continue;
+        }
+        // A runtime socket is a connection, not application state.
+        if volume.source == "/run/user/1000/podman/podman.sock" {
+            continue;
+        }
+        if volume.volume_type != "bind" {
+            bail!("network migration backup requires bind-mounted persistent state");
+        }
+        let path = Path::new(&volume.source);
+        let relative = path
+            .strip_prefix(data_dir)
+            .context("network migration state must be inside the node data directory")?;
+        if relative.as_os_str().is_empty()
+            || relative
+                .components()
+                .any(|c| !matches!(c, std::path::Component::Normal(_)))
+        {
+            bail!("invalid network migration state path");
+        }
+        sources.push(relative.to_path_buf());
+    }
+    sources.sort();
+    sources.dedup();
+    let mut roots: Vec<PathBuf> = Vec::new();
+    for source in sources {
+        if !roots.iter().any(|root| source.starts_with(root)) {
+            roots.push(source);
+        }
+    }
+    if roots.is_empty() {
+        bail!("network migration backup has no persistent state mounts");
+    }
+    Ok(roots)
+}
+
+/// Caller must gracefully stop the app before this function, and resume the old
+/// service if it fails. No source files are changed or deleted by this operation.
+pub async fn snapshot(
+    manifest: &AppManifest,
+    data_dir: &Path,
+    previous_unit: Option<&[u8]>,
+) -> Result<PathBuf> {
+    let mut command = tokio::process::Command::new("podman");
+    command.args(["unshare", "tar"]);
+    snapshot_with_command(manifest, data_dir, previous_unit, command).await
+}
+
+async fn snapshot_with_command(
+    manifest: &AppManifest,
+    data_dir: &Path,
+    previous_unit: Option<&[u8]>,
+    mut command: tokio::process::Command,
+) -> Result<PathBuf> {
+    let sources = relative_sources(manifest, data_dir)?;
+    let canonical_root = tokio::fs::canonicalize(data_dir).await?;
+    for source in &sources {
+        let path = data_dir.join(source);
+        if tokio::fs::symlink_metadata(&path)
+            .await?
+            .file_type()
+            .is_symlink()
+        {
+            bail!("network migration state mount is a symlink; explicit backup required");
+        }
+        let canonical = tokio::fs::canonicalize(&path).await?;
+        if !canonical.starts_with(&canonical_root) {
+            bail!("network migration state path resolves outside node data directory");
+        }
+    }
+    let root = data_dir.join("migration-backups");
+    tokio::fs::create_dir_all(&root).await?;
+    tokio::fs::set_permissions(&root, std::fs::Permissions::from_mode(0o700)).await?;
+    let dir = root.join(uuid::Uuid::new_v4().to_string());
+    tokio::fs::create_dir(&dir).await?;
+    tokio::fs::set_permissions(&dir, std::fs::Permissions::from_mode(0o700)).await?;
+    if let Some(unit) = previous_unit {
+        let path = dir.join("previous.container");
+        tokio::fs::write(&path, unit).await?;
+        tokio::fs::set_permissions(&path, std::fs::Permissions::from_mode(0o600)).await?;
+        tokio::fs::File::open(&path).await?.sync_all().await?;
+    }
+    let partial = dir.join("state.tar.partial");
+    let archive = dir.join("state.tar");
+    let output = command
+        .args([
+            "--create",
+            "--numeric-owner",
+            "--acls",
+            "--xattrs",
+            "--file",
+        ])
+        .arg(&partial)
+        .arg("--directory")
+        .arg(data_dir)
+        .arg("--")
+        .args(&sources)
+        .output()
+        .await
+        .context("start rootless migration snapshot")?;
+    if !output.status.success() {
+        // No tar stderr in public logs: it can contain private filenames.
+        let _ = tokio::fs::remove_file(&partial).await;
+        bail!("persistent-state snapshot failed; original state was left intact");
+    }
+    tokio::fs::set_permissions(&partial, std::fs::Permissions::from_mode(0o600)).await?;
+    tokio::fs::File::open(&partial).await?.sync_all().await?;
+    tokio::fs::rename(&partial, &archive).await?;
+    let metadata = serde_json::json!({"app": manifest.app.id, "version": manifest.app.version,
+        "network": manifest.app.container.network, "sources": sources});
+    tokio::fs::write(
+        dir.join("metadata.json"),
+        serde_json::to_vec_pretty(&metadata)?,
+    )
+    .await?;
+    tokio::fs::File::open(&dir).await?.sync_all().await?;
+    Ok(archive)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    fn portainer() -> AppManifest {
+        AppManifest::parse(include_str!("../../../../apps/portainer/manifest.yml")).unwrap()
+    }
+    #[tokio::test]
+    async fn stopped_state_archive_round_trips_database_compose_and_old_unit() {
+        let dir = tempfile::tempdir().unwrap();
+        let state = dir.path().join("portainer");
+        tokio::fs::create_dir_all(state.join("compose"))
+            .await
+            .unwrap();
+        tokio::fs::write(state.join("portainer.db"), b"fixture database")
+            .await
+            .unwrap();
+        tokio::fs::write(state.join("compose/stack.yml"), b"services: {}\n")
+            .await
+            .unwrap();
+        let mut m = portainer();
+        m.app.volumes[0].source = state.display().to_string();
+        m.app.volumes[1].source = state.join("compose").display().to_string();
+        let archive = snapshot_with_command(
+            &m,
+            dir.path(),
+            Some(b"old unit"),
+            tokio::process::Command::new("tar"),
+        )
+        .await
+        .unwrap();
+        assert_eq!(
+            std::fs::metadata(&archive).unwrap().permissions().mode() & 0o777,
+            0o600
+        );
+        assert_eq!(
+            tokio::fs::read(archive.parent().unwrap().join("previous.container"))
+                .await
+                .unwrap(),
+            b"old unit"
+        );
+        let restored = tempfile::tempdir().unwrap();
+        assert!(tokio::process::Command::new("tar")
+            .arg("-xf")
+            .arg(archive)
+            .arg("-C")
+            .arg(restored.path())
+            .status()
+            .await
+            .unwrap()
+            .success());
+        assert_eq!(
+            tokio::fs::read(restored.path().join("portainer/portainer.db"))
+                .await
+                .unwrap(),
+            b"fixture database"
+        );
+        assert_eq!(
+            tokio::fs::read(restored.path().join("portainer/compose/stack.yml"))
+                .await
+                .unwrap(),
+            b"services: {}\n"
+        );
+        assert_eq!(
+            tokio::fs::read(state.join("portainer.db")).await.unwrap(),
+            b"fixture database"
+        );
+    }
+
+    #[tokio::test]
+    async fn failed_snapshot_never_publishes_archive_or_changes_original_state() {
+        let dir = tempfile::tempdir().unwrap();
+        let state = dir.path().join("portainer");
+        tokio::fs::create_dir_all(state.join("compose"))
+            .await
+            .unwrap();
+        tokio::fs::write(state.join("portainer.db"), b"unchanged")
+            .await
+            .unwrap();
+        let mut m = portainer();
+        m.app.volumes[0].source = state.display().to_string();
+        m.app.volumes[1].source = state.join("compose").display().to_string();
+        assert!(
+            snapshot_with_command(&m, dir.path(), None, tokio::process::Command::new("false"))
+                .await
+                .is_err()
+        );
+        assert_eq!(
+            tokio::fs::read(state.join("portainer.db")).await.unwrap(),
+            b"unchanged"
+        );
+        for entry in std::fs::read_dir(dir.path().join("migration-backups")).unwrap() {
+            assert!(!entry.unwrap().path().join("state.tar").exists());
+        }
+    }
+
+    #[test]
+    fn backup_covers_all_portainer_state_once_and_excludes_runtime_socket() {
+        let m = portainer();
+        assert!(enabled(&m).unwrap());
+        assert_eq!(
+            relative_sources(&m, Path::new("/var/lib/archipelago")).unwrap(),
+            vec![PathBuf::from("portainer")]
+        );
+    }
+    #[test]
+    fn backup_refuses_unknown_state_locations_instead_of_silently_omitting_them() {
+        let mut m = portainer();
+        m.app.volumes[0].source = "/other/operator/state".into();
+        assert!(relative_sources(&m, Path::new("/var/lib/archipelago")).is_err());
+        m.app.volumes[0].source = "/var/lib/archipelago/../secret".into();
+        assert!(relative_sources(&m, Path::new("/var/lib/archipelago")).is_err());
+    }
+}

core/archipelago/src/container/mod.rs

@@ -12,6 +12,7 @@ pub mod hooks;
 pub mod image_policy;
 pub mod image_versions;
 pub mod lnd;
+pub mod migration_backup;
 pub mod prod_orchestrator;
 pub mod quadlet;
 pub mod registry;

core/archipelago/src/container/prod_orchestrator.rs

@@ -91,6 +91,14 @@ fn is_builtin_network_mode(network: &str) -> bool {
     )
 }
 
+// Only an explicitly selected rootless mode establishes drift. An omitted
+// network delegates to Podman and must not recreate unrelated installed apps.
+fn rootless_network_mode_drifted(expected: Option<&str>, actual: &str) -> bool {
+    matches!(expected, Some("slirp4netns" | "pasta"))
+        && !actual.trim().is_empty()
+        && actual.trim().split(':').next() != expected
+}
+
 fn uses_pasta_network(manifest: &AppManifest) -> bool {
     manifest.app.container.network.as_deref() == Some("pasta")
 }
@@ -2499,6 +2507,7 @@ impl ProdContainerOrchestrator {
                                 return Ok(ReconcileAction::NoOp);
                             }
                             tracing::info!(app_id = %app_id, container = %name, "container env drift detected — recreating");
+                            self.backup_network_change(&name, &resolved_manifest).await?;
                             let _ = self.runtime.stop_container(&name).await;
                             let _ = self.runtime.remove_container(&name).await;
                             self.install_fresh(lm).await?;
@@ -2555,6 +2564,7 @@ impl ProdContainerOrchestrator {
                                 .await
                         {
                             tracing::info!(app_id = %app_id, container = %name, "stopped container env/port drift detected — recreating");
+                            self.backup_network_change(&name, &resolved_manifest).await?;
                             let _ = self.runtime.remove_container(&name).await;
                             self.install_fresh(lm).await?;
                             return Ok(ReconcileAction::Installed);
@@ -3080,13 +3090,9 @@ impl ProdContainerOrchestrator {
     /// app is a companion (companion.rs owns those units), or when no
     /// unit file exists yet (install_via_quadlet handles first-write).
     ///
-    /// We DON'T restart the .service when content changes — running
+    /// Ordinary metadata changes wait for an operator restart. Runtime-affecting
-    /// containers keep their current config until an operator-initiated
+    /// changes restart the service and retain a durable pending marker until
-    /// restart picks up the new file. That's the right tradeoff: file
+    /// that succeeds, including across daemon restarts and failed reloads.
-    /// updates are cheap and non-destructive; service restarts are
-    /// destructive (the SIGKILL cascade we're trying to eliminate).
-    /// systemctl --user daemon-reload runs only when content actually
-    /// changed, so steady-state reconcile ticks pay just one fs read.
     async fn sync_quadlet_unit(&self, lm: &LoadedManifest, name: &str) -> Result<()> {
         // Companions: same reasoning as migrate_to_quadlet_if_needed —
         // companion.rs renders these units with a different shape, syncing
@@ -3106,7 +3112,7 @@ impl ProdContainerOrchestrator {
         }
         let old_body = tokio::fs::read_to_string(&unit_path)
             .await
-            .unwrap_or_default();
+            .with_context(|| format!("read existing quadlet for {name}"))?;
         let restart_required = quadlet::contains_stale_health_gate(&old_body);
 
         let mut resolved = lm.manifest.clone();
@@ -3122,49 +3128,47 @@ impl ProdContainerOrchestrator {
             quadlet::network_aliases_changed(&old_body, &new_body);
         let restart_for_exec_change = quadlet::exec_changed(&old_body, &new_body);
         let restart_for_health_change = quadlet::health_cmd_changed(&old_body, &new_body);
+        let needs_restart = restart_required
+            || restart_for_port_change
+            || restart_for_network_alias_change
+            || restart_for_exec_change
+            || restart_for_health_change;
+        // Record the obligation BEFORE replacing the unit. A failed reload or
+        // restart must not become a no-op on the next tick just because the
+        // generated file already matches the manifest.
+        let pending = quadlet::RestartObligation::prepare(&unit_path, needs_restart).await?;
+        if pending.is_pending() {
+            self.ensure_resolved_source_available(lm).await?;
+        }
+        if restart_for_network_alias_change {
+            self.backup_network_change(name, &resolved).await?;
+        }
         let changed = quadlet::write_if_changed(&unit, &unit_dir)
             .await
             .with_context(|| format!("drift-sync quadlet unit for {name}"))?;
-        if changed {
+        if changed || pending.is_pending() {
             quadlet::daemon_reload_user()
                 .await
                 .context("systemctl --user daemon-reload after drift-syncing quadlet unit")?;
-            tracing::info!(
-                app_id = %lm.manifest.app.id,
-                container = %name,
-                "Quadlet unit drift-synced — file rewritten, .service NOT restarted (operator restart picks up new config)"
-            );
         }
-        if changed
+        if pending.is_pending() {
-            && (restart_required
-                || restart_for_port_change
-                || restart_for_network_alias_change
-                || restart_for_exec_change
-                || restart_for_health_change)
-        {
-            self.ensure_resolved_source_available(lm).await?;
             let service = unit.service_name();
-            let reason = if restart_required {
-                "stale health gate"
-            } else if restart_for_port_change {
-                "port binding drift"
-            } else if restart_for_network_alias_change {
-                "network alias drift"
-            } else if restart_for_health_change {
-                "health command drift"
-            } else {
-                "exec drift"
-            };
             tracing::info!(
                 app_id = %lm.manifest.app.id,
                 container = %name,
                 service = %service,
-                reason = reason,
+                "Applying pending Quadlet runtime change"
-                "Quadlet unit rewrite requires service restart"
             );
             quadlet::restart_service(&service)
                 .await
                 .with_context(|| format!("restart drifted quadlet service {service}"))?;
+            pending.complete().await?;
+        } else if changed {
+            tracing::info!(
+                app_id = %lm.manifest.app.id,
+                container = %name,
+                "Quadlet metadata updated; operator restart will apply it"
+            );
         }
         Ok(())
     }
@@ -3483,11 +3487,9 @@ impl ProdContainerOrchestrator {
     }
 
     async fn cleanup_stale_grafana_port(&self) {
-        let _ = tokio::process::Command::new("pkill")
+        // Port 3001 can belong to Gitea or the daemon's gate. Reap only a
-            .args(["-f", "pasta.*3001"])
+        // Grafana container proven absent from Podman's inventory.
-            .output()
+        crate::container::ghost_reaper::reap_for_app("grafana").await;
-            .await;
-        tokio::time::sleep(std::time::Duration::from_secs(1)).await;
     }
 
     async fn detect_host_facts(&self) -> HostFacts {
@@ -3868,6 +3870,61 @@ impl ProdContainerOrchestrator {
         Ok(())
     }
 
+    async fn backup_network_change(&self, name: &str, manifest: &AppManifest) -> Result<()> {
+        if !crate::container::migration_backup::enabled(manifest)? {
+            return Ok(());
+        }
+        // Only back up an actual network migration, not ordinary env drift.
+        let output = tokio::process::Command::new("podman")
+            .args(["inspect", name, "--format", "{{.HostConfig.NetworkMode}}"])
+            .output().await.context("inspect network before migration backup")?;
+        let present = if output.status.success() {
+            if !rootless_network_mode_drifted(manifest.app.container.network.as_deref(), &String::from_utf8_lossy(&output.stdout)) {
+                return Ok(());
+            }
+            true
+        } else {
+            // A crash after gracefully stopping a --rm Quadlet container can
+            // leave only its data and old unit. Prove absence before snapshotting
+            // stopped state; an inspect/Podman failure is not proof of absence.
+            let exists = tokio::process::Command::new("podman")
+                .args(["container", "exists", name]).status().await?;
+            if exists.code() != Some(1) {
+                anyhow::bail!("cannot verify existing container before network migration backup");
+            }
+            false
+        };
+        let service = format!("{name}.service");
+        let managed = quadlet::unit_exists(name).await;
+        let previous_unit = if managed {
+            Some(tokio::fs::read(quadlet::unit_dir().await?.join(format!("{name}.container"))).await?)
+        } else {
+            None
+        };
+        if managed {
+            quadlet::stop_service(&service).await?;
+        } else if present {
+            self.runtime.stop_container(name).await?;
+        }
+        match crate::container::migration_backup::snapshot(manifest, &self.data_dir, previous_unit.as_deref()).await {
+            Ok(archive) => {
+                tracing::info!(container = %name, backup = %archive.display(), "Persistent state saved before network migration");
+                Ok(())
+            }
+            Err(error) => {
+                // The unit has not been rewritten yet. Restore its previous
+                // service on backup failure and report the migration failure.
+                let restored = if managed {
+                    quadlet::enable_now(&service).await
+                } else {
+                    self.runtime.start_container(name).await
+                };
+                restored.context("restore original app after failed migration snapshot")?;
+                Err(error)
+            }
+        }
+    }
+
     async fn container_env_drifted(&self, name: &str, manifest: &AppManifest) -> bool {
         if cfg!(test) {
             return false;
@@ -3877,6 +3934,23 @@ impl ProdContainerOrchestrator {
             return true;
         }
 
+        // Quadlet handles declarative Network= drift above. Legacy rootless
+        // Podman containers need the same convergence when no unit owns them.
+        if matches!(manifest.app.container.network.as_deref(), Some("slirp4netns" | "pasta")) {
+            if let Ok(output) = tokio::process::Command::new("podman")
+                .args(["inspect", name, "--format", "{{.HostConfig.NetworkMode}}"])
+                .output()
+                .await
+            {
+                if output.status.success() && rootless_network_mode_drifted(
+                    manifest.app.container.network.as_deref(),
+                    &String::from_utf8_lossy(&output.stdout),
+                ) {
+                    return true;
+                }
+            }
+        }
+
         let inspect = tokio::process::Command::new("podman")
             .args([
                 "inspect",
@@ -4919,6 +4993,17 @@ mod tests {
     /// recovered when its siblings have live containers (the stack is
     /// installed), and left alone when the whole stack is gone or the app
     /// is not a stack member at all.
+    #[test]
+    fn explicit_rootless_network_change_converges_without_guessing_defaults() {
+        assert!(rootless_network_mode_drifted(Some("slirp4netns"), "pasta"));
+        assert!(rootless_network_mode_drifted(Some("slirp4netns"), "bridge"));
+        assert!(!rootless_network_mode_drifted(Some("slirp4netns"), "slirp4netns"));
+        assert!(!rootless_network_mode_drifted(Some("slirp4netns"), "slirp4netns:allow_host_loopback=true"));
+        assert!(!rootless_network_mode_drifted(None, "pasta"));
+        assert!(!rootless_network_mode_drifted(Some("slirp4netns"), ""));
+        assert!(!rootless_network_mode_drifted(Some("archy-net"), "bridge"));
+    }
+
     #[test]
     fn absent_stack_member_recovery_requires_a_live_sibling() {
         let present: HashSet<String> = ["indeedhub-redis", "indeedhub-relay", "indeedhub"]

core/archipelago/src/container/quadlet.rs

@@ -938,6 +938,53 @@ pub fn health_cmd_changed(old_body: &str, new_body: &str) -> bool {
             != directive_values(new_body, "HealthRetries=")
 }
 
+/// A unit rewrite and a successful systemd restart are separate operations.
+/// Keep the restart obligation across errors or a management-daemon restart.
+pub struct RestartObligation {
+    marker: PathBuf,
+    pending: bool,
+}
+
+impl RestartObligation {
+    pub async fn prepare(unit_path: &Path, newly_required: bool) -> Result<Self> {
+        let marker = unit_path.with_extension("restart-pending");
+        if newly_required {
+            // Contents contain no manifest environment or credentials. sync_all
+            // makes the obligation durable before the subsequent unit rename.
+            let file = tokio::fs::OpenOptions::new()
+                .write(true)
+                .create(true)
+                .truncate(false)
+                .open(&marker)
+                .await
+                .context("record pending Quadlet restart")?;
+            file.sync_all().await?;
+            if let Some(parent) = marker.parent() {
+                tokio::fs::File::open(parent).await?.sync_all().await?;
+            }
+        }
+        let pending = tokio::fs::try_exists(&marker).await?;
+        Ok(Self { marker, pending })
+    }
+
+    pub fn is_pending(&self) -> bool {
+        self.pending
+    }
+
+    /// Call only after systemd accepted the replacement service successfully.
+    pub async fn complete(self) -> Result<()> {
+        if self.pending {
+            tokio::fs::remove_file(&self.marker)
+                .await
+                .context("clear completed Quadlet restart")?;
+            if let Some(parent) = self.marker.parent() {
+                tokio::fs::File::open(parent).await?.sync_all().await?;
+            }
+        }
+        Ok(())
+    }
+}
+
 pub fn publish_ports_changed(old_body: &str, new_body: &str) -> bool {
     let old_ports = directive_values(old_body, "PublishPort=");
     let new_ports = directive_values(new_body, "PublishPort=");
@@ -1541,6 +1588,28 @@ app:
         assert!(!s.contains("Network=host"));
     }
 
+    #[test]
+    fn portainer_catalog_network_repairs_same_node_routing_without_exposing_backend() {
+        let manifest = AppManifest::parse(include_str!(
+            "../../../../apps/portainer/manifest.yml"
+        ))
+        .expect("shipped Portainer manifest must parse");
+        let new = QuadletUnit::from_manifest(&manifest, "portainer").render();
+        assert!(new.contains("Network=slirp4netns\n"));
+        assert!(!new.contains("NetworkAlias="));
+        assert!(new.contains("PublishPort=127.0.0.1:9000:9000/tcp"));
+        assert!(!new.contains("PublishPort=0.0.0.0"));
+        // The upgrade changes networking only: retain both state mounts and the
+        // existing rootless socket, without an app.ini or repository rewrite.
+        assert!(new.contains("Volume=/var/lib/archipelago/portainer:/data"));
+        assert!(new.contains("Volume=/var/lib/archipelago/portainer/compose:/data/compose"));
+        assert!(new.contains("Volume=/run/user/1000/podman/podman.sock:/var/run/docker.sock"));
+        let old = new.replace("Network=slirp4netns\n", "");
+        assert!(network_aliases_changed(&old, &new));
+        assert!(!network_aliases_changed(&new, &new));
+        assert!(!publish_ports_changed(&old, &new));
+    }
+
     #[test]
     fn from_manifest_slirp4netns_omits_network_alias() {
         let yaml = r#"
@@ -1891,6 +1960,35 @@ app:
         assert!(!network_aliases_changed(new, new));
     }
 
+    #[tokio::test]
+    async fn failed_runtime_change_remains_pending_when_unit_already_matches() {
+        let dir = tempfile::tempdir().unwrap();
+        let unit = dir.path().join("portainer.container");
+        tokio::fs::write(&unit, "[Container]\n").await.unwrap();
+        let pending = RestartObligation::prepare(&unit, true).await.unwrap();
+        assert!(pending.is_pending());
+        tokio::fs::write(&unit, "[Container]\nNetwork=slirp4netns\n")
+            .await
+            .unwrap();
+        // Simulate systemctl failure or daemon interruption after unit rewrite.
+        drop(pending);
+        let retry = RestartObligation::prepare(&unit, false).await.unwrap();
+        assert!(retry.is_pending(), "matching unit must not discard failed restart");
+        retry.complete().await.unwrap();
+        assert!(!RestartObligation::prepare(&unit, false).await.unwrap().is_pending());
+    }
+
+    #[tokio::test]
+    async fn pending_runtime_change_errors_are_not_reported_as_success() {
+        let dir = tempfile::tempdir().unwrap();
+        let missing = dir.path().join("missing/app.container");
+        assert!(RestartObligation::prepare(&missing, true).await.is_err());
+        let unit = dir.path().join("app.container");
+        let pending = RestartObligation::prepare(&unit, true).await.unwrap();
+        tokio::fs::remove_file(unit.with_extension("restart-pending")).await.unwrap();
+        assert!(pending.complete().await.is_err());
+    }
+
     #[test]
     fn network_aliases_changed_detects_network_mode_drift() {
         let old = "[Container]\nNetwork=slirp4netns\n";

core/archipelago/src/crash_recovery.rs

@@ -194,6 +194,7 @@ pub async fn clear_user_stopped(data_dir: &Path, name: &str) {
 // Installation is a decision, not a runtime observation, so it gets a record
 // of its own that no amount of downtime erodes.
 const INSTALLED_APPS_FILE: &str = "installed-apps.json";
+static INSTALLED_APPS_LOCK: tokio::sync::Mutex<()> = tokio::sync::Mutex::const_new(());
 
 /// Load the durable set of installed app ids / container names.
 pub async fn load_installed_apps(data_dir: &Path) -> std::collections::HashSet<String> {
@@ -220,12 +221,23 @@ pub async fn load_installed_apps_if_recorded(
 async fn save_installed_apps(data_dir: &Path, installed: &std::collections::HashSet<String>) {
     let path = data_dir.join(INSTALLED_APPS_FILE);
     if let Ok(json) = serde_json::to_string_pretty(installed) {
-        let _ = fs::write(&path, json).await;
+        let tmp = path.with_extension("json.tmp");
+        let result = async {
+            fs::write(&tmp, json).await?;
+            fs::File::open(&tmp).await?.sync_all().await?;
+            fs::rename(&tmp, &path).await?;
+            fs::File::open(data_dir).await?.sync_all().await
+        }
+        .await;
+        if let Err(error) = result {
+            warn!(%error, "could not persist installed apps");
+        }
     }
 }
 
 /// Record that an app is installed. Called when an install succeeds.
 pub async fn mark_installed(data_dir: &Path, name: &str) {
+    let _guard = INSTALLED_APPS_LOCK.lock().await;
     let mut installed = load_installed_apps(data_dir).await;
     if installed.insert(name.to_string()) {
         save_installed_apps(data_dir, &installed).await;
@@ -235,6 +247,7 @@ pub async fn mark_installed(data_dir: &Path, name: &str) {
 /// Forget an app. Called on uninstall, beside `mark_user_uninstalled` — the
 /// two must move together or a reinstall-after-uninstall leaves a stale claim.
 pub async fn clear_installed(data_dir: &Path, name: &str) {
+    let _guard = INSTALLED_APPS_LOCK.lock().await;
     let mut installed = load_installed_apps(data_dir).await;
     if installed.remove(name) {
         save_installed_apps(data_dir, &installed).await;
@@ -252,6 +265,7 @@ pub async fn clear_installed(data_dir: &Path, name: &str) {
 /// need it. Runs on every boot, so an app installed before the upgrade is
 /// still picked up whenever it is next seen alive.
 pub async fn backfill_installed_apps(data_dir: &Path, present_container_names: &[String]) {
+    let _guard = INSTALLED_APPS_LOCK.lock().await;
     if present_container_names.is_empty() {
         return;
     }
@@ -1497,3 +1511,26 @@ mod tests {
         );
     }
 }
+
+#[cfg(test)]
+mod installed_concurrency_tests {
+    use super::*;
+    #[tokio::test]
+    async fn concurrent_install_records_are_not_lost() {
+        let dir = tempfile::tempdir().unwrap();
+        let mut tasks = Vec::new();
+        for i in 0..24 {
+            let path = dir.path().to_owned();
+            tasks.push(tokio::spawn(async move {
+                mark_installed(&path, &format!("app-{i}")).await;
+            }));
+        }
+        for task in tasks {
+            task.await.unwrap();
+        }
+        assert_eq!(load_installed_apps(dir.path()).await.len(), 24);
+        clear_installed(dir.path(), "app-3").await;
+        assert_eq!(load_installed_apps(dir.path()).await.len(), 23);
+        assert!(!dir.path().join("installed-apps.json.tmp").exists());
+    }
+}

core/archipelago/src/data_model.rs

@@ -146,6 +146,10 @@ pub enum PackageState {
 
 #[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
 pub struct PackageDataEntry {
+    /// Whether the app's HTTP upstream answered this scan (independent of
+    /// container health and blockchain sync). Missing on older nodes.
+    #[serde(rename = "ui-ready", default, skip_serializing_if = "Option::is_none")]
+    pub ui_ready: Option<bool>,
     pub state: PackageState,
     /// Container health: "healthy", "unhealthy", "starting", or null
     #[serde(skip_serializing_if = "Option::is_none")]
@@ -297,6 +301,8 @@ pub enum InstallPhase {
     /// `podman pull` in progress (the longest phase — up to several
     /// minutes for large images on slow networks).
     PullingImage,
+    /// Orchestrator owns download/build and startup as one operation.
+    PreparingApp,
     /// Creating data directories, writing app-specific configs
     /// (bitcoin.conf, lnd.conf, searxng settings.yml, chown).
     CreatingContainer,

core/archipelago/src/server.rs

@@ -1765,12 +1765,17 @@ fn merge_preserving_transitional(
     };
 
     crate::data_model::PackageDataEntry {
-        state,
+        state: state.clone(),
         // install_progress and uninstall_stage are also owned by the
         // initiating op (same reason as state) — keep them.
         install_progress: existing.install_progress.clone(),
         uninstall_stage: existing.uninstall_stage.clone(),
         // Everything else comes from the fresh scan.
+        ui_ready: if state == crate::data_model::PackageState::Running {
+            fresh.ui_ready
+        } else {
+            Some(false)
+        },
         health: fresh.health.clone(),
         exit_code: fresh.exit_code,
         static_files: fresh.static_files.clone(),
@@ -1809,7 +1814,10 @@ async fn scan_and_update_packages(
     absence_tracker: &mut HashMap<String, u32>,
     transitional_since: &mut HashMap<String, Instant>,
 ) -> Result<()> {
-    let mut packages = scanner.scan_containers().await?;
+    let (before_scan, _) = state.get_snapshot().await;
+    let mut packages = scanner
+        .scan_containers(data_dir, &before_scan.package_data)
+        .await?;
     let user_stopped = crate::crash_recovery::load_user_stopped(data_dir).await;
     for (id, pkg) in packages.iter_mut() {
         if pkg.state == crate::data_model::PackageState::Exited && user_stopped.contains(id) {
@@ -1870,11 +1878,14 @@ async fn scan_and_update_packages(
     // once at load ~2). Better to keep saying "scanning…" than to say "empty".
     if packages.is_empty() && (!first_scan || !installed_registry.is_empty()) {
         if tor_changed || update_changed {
-            let mut data = current_data;
+            state
-            data.server_info.tor_address = tor_addr.clone();
+                .mutate_data(|data| {
-            data.server_info.node_address = tor_addr.as_ref().map(|t| identity.node_address(t));
+                    data.server_info.tor_address = tor_addr.clone();
-            data.server_info.status_info.updated = update_available;
+                    data.server_info.node_address =
-            state.update_data(data).await;
+                        tor_addr.as_ref().map(|t| identity.node_address(t));
+                    data.server_info.status_info.updated = update_available;
+                })
+                .await;
         }
         return Ok(());
     }
@@ -1899,6 +1910,13 @@ async fn scan_and_update_packages(
     // died without cleanup and let the scan override it.
     let now = Instant::now();
     for (id, pkg) in &packages {
+        if user_uninstalled.contains(id)
+            || user_uninstalled.contains(&format!("archy-{id}"))
+            || (before_scan.package_data.contains_key(id)
+                && !current_data.package_data.contains_key(id))
+        {
+            continue;
+        }
         absence_tracker.remove(id);
         let existing = merged.get(id);
         let overwrite = match existing {
@@ -2054,22 +2072,40 @@ async fn scan_and_update_packages(
     }
 
     if changed || tor_changed || first_scan || update_changed {
-        let mut data = current_data;
+        state
-        data.package_data = merged;
+            .mutate_data(|data| {
-        data.server_info.tor_address = tor_addr.clone();
+                // A lifecycle operation may have started/finished while this scan
-        data.server_info.node_address = tor_addr.as_ref().map(|t| identity.node_address(t));
+                // awaited probes or disk I/O. Never overwrite that newer entry or
-        data.server_info.status_info.containers_scanned = true;
+                // resurrect one that an uninstall removed in the meantime.
-        data.server_info.status_info.updated = update_available;
+                apply_scanned_packages(&mut data.package_data, &current_data.package_data, &merged);
-        state.update_data(data).await;
+                data.server_info.tor_address = tor_addr.clone();
-        debug!(
+                data.server_info.node_address = tor_addr.as_ref().map(|t| identity.node_address(t));
-            "📦 State changed (packages={}, tor={}, first_scan={}, update={}), broadcasting update",
+                data.server_info.status_info.containers_scanned = true;
-            changed, tor_changed, first_scan, update_changed
+                data.server_info.status_info.updated = update_available;
-        );
+            })
+            .await;
     }
 
     Ok(())
 }
 
+fn apply_scanned_packages(
+    latest: &mut HashMap<String, crate::data_model::PackageDataEntry>,
+    base: &HashMap<String, crate::data_model::PackageDataEntry>,
+    scanned: &HashMap<String, crate::data_model::PackageDataEntry>,
+) {
+    for (id, fresh) in scanned {
+        if latest.get(id) == base.get(id) {
+            latest.insert(id.clone(), fresh.clone());
+        }
+    }
+    for id in base.keys() {
+        if !scanned.contains_key(id) && latest.get(id) == base.get(id) {
+            latest.remove(id);
+        }
+    }
+}
+
 async fn normalize_reachable_package_health(
     packages: &mut HashMap<String, crate::data_model::PackageDataEntry>,
 ) {
@@ -2268,6 +2304,7 @@ mod merge_tests {
 
     fn make_entry(state: PackageState, health: Option<&str>) -> PackageDataEntry {
         PackageDataEntry {
+            ui_ready: None,
             state,
             health: health.map(|s| s.to_string()),
             exit_code: None,
@@ -2280,6 +2317,37 @@ mod merge_tests {
         }
     }
 
+    #[test]
+    fn stale_scan_cannot_remove_new_installs_or_overwrite_lifecycle_changes() {
+        let running = make_entry(PackageState::Running, Some("healthy"));
+        let restarting = make_entry(PackageState::Restarting, None);
+        let base = [
+            ("restart".into(), running.clone()),
+            ("uninstalled".into(), running.clone()),
+        ]
+        .into_iter()
+        .collect();
+        let mut latest = [
+            ("restart".into(), restarting.clone()),
+            ("new".into(), running.clone()),
+        ]
+        .into_iter()
+        .collect();
+        let scanned = [
+            ("restart".into(), running.clone()),
+            ("uninstalled".into(), running.clone()),
+        ]
+        .into_iter()
+        .collect();
+        apply_scanned_packages(&mut latest, &base, &scanned);
+        assert_eq!(latest.get("restart"), Some(&restarting));
+        assert_eq!(latest.get("new"), Some(&running));
+        assert!(!latest.contains_key("uninstalled"));
+        apply_scanned_packages(&mut latest, &base, &HashMap::new());
+        assert_eq!(latest.get("restart"), Some(&restarting));
+        assert!(latest.contains_key("new"));
+    }
+
     #[test]
     fn peer_path_filter_allows_content_catalog_and_items() {
         // Regression: the content *catalog* is exactly "/content" (no trailing

core/archipelago/src/state.rs

@@ -54,6 +54,21 @@ impl StateManager {
         let _ = self.broadcast_tx.send(message);
     }
 
+    /// Apply a small state change while holding the write lock. A lifecycle
+    /// task must not replace the entire model from an earlier snapshot.
+    pub async fn mutate_data<T>(&self, change: impl FnOnce(&mut DataModel) -> T) -> T {
+        let mut data = self.data.write().await;
+        let result = change(&mut data);
+        let mut rev = self.revision.write().await;
+        *rev += 1;
+        let _ = self.broadcast_tx.send(WebSocketMessage {
+            rev: *rev,
+            data: Some(data.clone()),
+            patch: None,
+        });
+        result
+    }
+
     /// Get a WebSocket message with the current state
     pub async fn get_initial_message(&self) -> WebSocketMessage {
         let (data, rev) = self.get_snapshot().await;
@@ -190,3 +205,29 @@ mod tests {
         assert_eq!(rev, 1);
     }
 }
+
+#[cfg(test)]
+mod atomic_mutation_tests {
+    use super::*;
+    #[tokio::test]
+    async fn concurrent_updates_preserve_independent_entries() {
+        let state = Arc::new(StateManager::new());
+        let mut tasks = Vec::new();
+        for i in 0..24 {
+            let state = state.clone();
+            tasks.push(tokio::spawn(async move {
+                state
+                    .mutate_data(|data| {
+                        data.peer_health.insert(format!("peer-{i}"), true);
+                    })
+                    .await;
+            }));
+        }
+        for task in tasks {
+            task.await.unwrap();
+        }
+        let (data, revision) = state.get_snapshot().await;
+        assert_eq!(data.peer_health.len(), 24);
+        assert_eq!(revision, 24);
+    }
+}

core/container/src/manifest.rs

@@ -1746,40 +1746,28 @@ app:
             }
         }
         exempt.sort();
-        // 28 as of 2026-08-23: the 26 below plus cuprate's two exemptions —
+        // Reviewed 2026-09-30: lightning-stack's three retired endpoints
-        // 18183 (Monero p2p gossip, same reasoning as bitcoin's 8333) and
+        // disappeared; Cuprate restricted RPC moved from none to gate-open.
-        // 18090 (host mapping for Monero's canonical 18089 restricted RPC,
+        // Compare exact endpoints, not just a count that can hide substitutions.
-        // upstream's own safe-for-public
+        let expected = [
-        // subset that wallets connect to directly as a "remote node" over
+            ("bitcoin-core", 8333), ("bitcoin-knots", 8333),
-        // plain HTTP JSON-RPC — same reasoning as electrumx's 50001).
+            ("core-lightning", 9736), ("core-lightning", 9835),
-        // cuprate's unrestricted RPC (full node control) stays loopback-only
+            ("cuprate", 18183), ("electrumx", 50001),
-        // (auth: local), not in this set.
+            ("fedimint", 8173), ("fedimint", 8174),
-        //
+            ("fedimint-gateway", 8176), ("fedimint-gateway", 9737),
-        // 26 as of 2026-08-16: the 25 below plus phoenixd 9740, a
+            ("gitea", 2222), ("lnd", 9735), ("lnd", 10009), ("lnd", 18080),
-        // loopback-only JSON API whose own generated http password
+            ("netbird", 8087), ("netbird-server", 3478), ("netbird-server", 8086),
-        // authenticates every request (added with the phoenixd onboarding,
+            ("phoenixd", 9740), ("pine", 10381), ("pine-openwakeword", 10400),
-        // which did not update this count — exactly the drift this test
+            ("pine-piper", 10200), ("pine-whisper", 10300),
-        // exists to catch).
+            ("router", 1900), ("router", 5353),
-        //
+        ].into_iter().map(|(id, port)| (id.to_owned(), port)).collect::<Vec<_>>();
-        // 25 as of the v1.7.123 port-policy round: bitcoin p2p (8333 ×2),
+        assert_eq!(exempt, expected, "unauthenticated endpoint set changed; review each exemption");
-        // core-lightning 9736/9835, electrumx 50001, fedimint 8173/8174,
-        // fedimint-gateway 8176/9737, gitea ssh 2222, lightning-stack
-        // 8091/9738/10010, lnd 9735/10009/18080, netbird 3478/8086/8087,
-        // pine TLS 10381 + the three voice ports (10200/10300/10400 — the
-        // disclosed known gap), router SSDP/mDNS 1900/5353. Every one is a
-        // deliberate, rationale-carrying exemption; the release-gate test
-        // stage timed out that cycle, so the count here lagged at 17.
-        assert_eq!(
-            exempt.len(),
-            28,
-            "unauthenticated port set changed — review before updating this count: {exempt:?}"
-        );
     }
 
     /// `auth: open` ports are served by the gate WITHOUT its login challenge,
     /// so they are the second unauthenticated-by-the-gate surface and get the
-    /// same review guard as `auth: none`. Each one must be an app that
+    /// same review guard as `auth: none`. Each must enforce its own login or
-    /// enforces a real login of its own.
+    /// have an explicitly reviewed public protocol purpose.
     #[test]
     fn gate_open_ports_are_all_accounted_for() {
         let apps = std::path::Path::new(env!("CARGO_MANIFEST_DIR")).join("../../apps");
@@ -1801,6 +1789,8 @@ app:
             }
         }
         open.sort();
+        // Cuprate 18090 is its deliberately public restricted RPC subset;
+        // unrestricted node-control RPC remains container-loopback-only.
         // Gitea 3001 (git clients speak basic-auth, not browser cookies),
         // BTCPay 23000 (checkout/invoice/webhook endpoints must be reachable
         // by anonymous payers), and — since the v1.8.7 platform round — the
@@ -1812,11 +1802,12 @@ app:
             open,
             vec![
                 ("btcpay-server".to_string(), 23000u16),
+                ("cuprate".to_string(), 18090u16),
                 ("gitea".to_string(), 3001u16),
                 ("nginx-proxy-manager".to_string(), 8081u16),
                 ("tailscale".to_string(), 8240u16),
             ],
-            "gate-open port set changed — every entry must be an app with its own login"
+            "gate-open port set changed — review login or intentional public protocol purpose"
         );
     }
 

core/container/src/podman_client.rs

@@ -310,59 +310,7 @@ impl PodmanClient {
                 );
                 continue;
             }
-            // Honour the manifest's protocol (default tcp). netbird's STUN port
+            port_mappings.push(podman_publish_mapping(port));
-            // is 3478/udp; forcing tcp here would publish the wrong protocol and
-            // silently break relay discovery.
-            let protocol = match port.protocol.to_ascii_lowercase().as_str() {
-                "udp" => "udp",
-                "sctp" => "sctp",
-                _ => "tcp",
-            };
-            // Effective bind. A gated port with no declared bind would
-            // publish 0.0.0.0 — the app would own every host address, which
-            // is both the exposure itself and the reason the daemon's app
-            // gate cannot bind those addresses to authenticate them. Pin it
-            // to loopback so the gate can take the external addresses.
-            //
-            // Doing it HERE, at container creation, is the point: the pin and
-            // the gate's takeover then both come from the daemon and cannot
-            // disagree. The earlier attempt put this decision in manifest
-            // data instead, and a node whose manifests lagged the binary
-            // published Bitcoin's loopback-only RPC across the LAN
-            // (test node, 2026-08-03).
-            //
-            // A port that already declares a bind is never overridden — that
-            // is exactly what keeps `bind: 127.0.0.1` ports host-local and
-            // leaves `auth: none` protocol ports (LND gRPC/REST, electrum)
-            // published as they are, so remote wallets keep working.
-            // NOTE: the daemon deliberately does NOT rewrite this. Pinning a
-            // published port to loopback is how an app hands its external
-            // addresses to the gate, but it belongs in the manifest, not in
-            // daemon-side inference:
-            //
-            //   * `bind` is already honoured by every publish path (here and
-            //     in package::install), so a manifest edit needs no code.
-            //   * inference here would cover only THIS path — proven on
-            //     a test node, where a recreate went through another one and
-            //     the pin never applied.
-            //   * and inferring from an ABSENT field is what republished
-            //     Bitcoin's loopback RPC across the LAN, and came within one
-            //     container-recreate of pinning LND's gRPC/REST and breaking
-            //     every remote wallet.
-            //
-            // So the migration ships as `bind: 127.0.0.1` in the signed
-            // catalog. Verified 2026-08-03 that a disk-only manifest edit is
-            // overridden by the catalog, which is precisely why the catalog is
-            // the right and only place to carry it.
-            let mut mapping = serde_json::json!({
-                "container_port": port.container,
-                "host_port": port.host,
-                "protocol": protocol,
-            });
-            if !port.bind.is_empty() {
-                mapping["host_ip"] = serde_json::json!(port.bind);
-            }
-            port_mappings.push(mapping);
         }
 
         let mut mounts = Vec::new();
@@ -751,6 +699,25 @@ pub fn image_uses_insecure_registry(image: &str) -> bool {
         .is_some_and(|host| INSECURE_REGISTRY_HOSTS.contains(&host))
 }
 
+// Keep the explicitly declared bind and transport identical to Quadlet. The
+// app gate owns external listeners; container publication must not bypass it.
+fn podman_publish_mapping(port: &crate::manifest::PortMapping) -> serde_json::Value {
+    let protocol = match port.protocol.to_ascii_lowercase().as_str() {
+        "udp" => "udp",
+        "sctp" => "sctp",
+        _ => "tcp",
+    };
+    let mut mapping = serde_json::json!({
+        "container_port": port.container,
+        "host_port": port.host,
+        "protocol": protocol,
+    });
+    if !port.bind.is_empty() {
+        mapping["host_ip"] = serde_json::json!(port.bind);
+    }
+    mapping
+}
+
 fn podman_network_settings(
     network: Option<&str>,
     network_policy: &str,
@@ -1110,6 +1077,15 @@ mod tests {
         ));
     }
 
+    #[test]
+    fn portainer_manifest_keeps_private_network_and_loopback_api_publication() {
+        let m = AppManifest::parse(include_str!("../../../apps/portainer/manifest.yml")).unwrap();
+        assert_eq!(podman_network_settings(m.app.container.network.as_deref(), &m.app.security.network_policy), ("slirp4netns", None));
+        assert_eq!(podman_publish_mapping(&m.app.ports[0]), serde_json::json!({
+            "container_port": 9000, "host_port": 9000, "protocol": "tcp", "host_ip": "127.0.0.1"
+        }));
+    }
+
     #[test]
     fn podman_network_settings_uses_networks_map_for_custom_networks() {
         assert_eq!(

core/container/src/runtime.rs

@@ -618,6 +618,28 @@ impl DockerRuntime {
     }
 }
 
+// Docker is a development fallback. Refuse Podman-only network modes instead
+// of silently installing a different topology; still honor binds for other apps.
+fn docker_network_and_ports(manifest: &AppManifest, offset: u16) -> Result<Vec<String>> {
+    let network = manifest.app.container.network.as_deref()
+        .filter(|v| !v.is_empty())
+        .unwrap_or(&manifest.app.security.network_policy);
+    if matches!(network, "slirp4netns" | "pasta") {
+        anyhow::bail!("this app requires rootless Podman networking ({network})");
+    }
+    let mut args = Vec::new();
+    if !network.is_empty() && network != "isolated" {
+        args.extend(["--network".to_owned(), network.to_owned()]);
+    }
+    for port in &manifest.app.ports {
+        let host = port.host.checked_add(offset).context("published port offset overflow")?;
+        let bind = if port.bind.is_empty() { String::new() } else { format!("{}:", port.bind) };
+        let protocol = if port.protocol.is_empty() { "tcp" } else { &port.protocol };
+        args.extend(["-p".to_owned(), format!("{bind}{host}:{}/{protocol}", port.container)]);
+    }
+    Ok(args)
+}
+
 #[async_trait]
 impl ContainerRuntime for DockerRuntime {
     async fn pull_image(&self, image: &str, signature: Option<&str>) -> Result<()> {
@@ -657,25 +679,7 @@ impl ContainerRuntime for DockerRuntime {
             cmd.arg("--read-only");
         }
 
-        match manifest.app.security.network_policy.as_str() {
+        cmd.args(docker_network_and_ports(manifest, port_offset)?);
-            "host" => {
-                cmd.arg("--network").arg("host");
-            }
-            "isolated" => {
-                // Docker uses bridge network by default
-            }
-            _ => {
-                cmd.arg("--network")
-                    .arg(&manifest.app.security.network_policy);
-            }
-        }
-
-        // Port mappings with offset
-        for port in &manifest.app.ports {
-            let host_port = port.host + port_offset;
-            cmd.arg("-p")
-                .arg(format!("{}:{}", host_port, port.container));
-        }
 
         // Volumes
         for volume in &manifest.app.volumes {
@@ -1035,6 +1039,17 @@ mod tests {
     use super::*;
     use std::collections::HashMap;
 
+    #[test]
+    fn docker_fallback_rejects_rootless_only_topology_and_preserves_bind_protocol() {
+        let mut m = AppManifest::parse(include_str!("../../../apps/portainer/manifest.yml")).unwrap();
+        assert!(docker_network_and_ports(&m, 0).is_err());
+        m.app.container.network = Some("bridge".into());
+        m.app.ports[0].protocol = "udp".into();
+        let args = docker_network_and_ports(&m, 1).unwrap();
+        assert_eq!(args, vec!["--network", "bridge", "-p", "127.0.0.1:9001:9000/udp"]);
+        assert!(docker_network_and_ports(&m, u16::MAX).is_err());
+    }
+
     #[test]
     fn missing_container_classifier_covers_podman5_phrasings() {
         // podman 5.x `inspect` phrasing for a missing container.

docker/archipelago-source/UPSTREAM.md

@@ -16,9 +16,11 @@ lookup relays from the defaults. It does not replace GitWorkshop's NIP-34,
 GRASP, repository browser, issue, pull-request, or review interfaces.
 
 The separate dependency patch refreshes the npm lockfile and moves `fflate` to
-0.8.3, `react-router-dom` to 7.18.3, and Vitest to 5.0.0. The resulting clean
+0.8.3, `react-router-dom` to 7.18.3, and Vitest to 5.0.0. On 2026-09-30 the lockfile was refreshed again for `brace-expansion`
-install reports zero npm advisories; its type-check, 152 unit tests, and
+1.1.21/5.0.12, `fast-uri` 3.1.8 and `ip-address` 10.7.2 after fresh node
-Archipelago subpath production build pass. Keeping this mechanical security
+installs failed the retained dependency audit. The resulting clean install
+reports zero npm advisories; its type-check, 152 unit tests, and Archipelago
+subpath production build pass. The complete image also builds on the X250. Keeping this mechanical security
 update separate makes both the upstream integration and future dependency
 refreshes auditable.
 

docker/archipelago-source/gitworkshop-dependencies.patch

@@ -1,5 +1,5 @@
 diff --git a/package-lock.json b/package-lock.json
-index 20631bb..0933917 100644
+index 20631bb..86b6f86 100644
 --- a/package-lock.json
 +++ b/package-lock.json
 @@ -63,7 +63,7 @@
@@ -495,9 +495,9 @@ index 20631bb..0933917 100644
 -      "version": "5.0.7",
 -      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.7.tgz",
 -      "integrity": "sha512-7oFy703dxfY3/NLxC1fh2SUCQ0H9rmAY+5EpDVfXjUTTs+HEwR2nYaqLv+GWcTsumwxPfiz6CzCNkwXwBUwqCA==",
-+      "version": "5.0.9",
++      "version": "5.0.12",
-+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.9.tgz",
++      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.12.tgz",
-+      "integrity": "sha512-ScQ4IuvIEF1TMlP7Zt+vjJ//9zlPb2SDcxWxM3bk8s6t6GGdJ7KO1dCcTidOPJKePW30LE/2cT7wCyPho9/Wxg==",
++      "integrity": "sha512-YovQ3rzhaLMIrDjNDMkNS01tea93qhEhG5xy8f6+R0l+dw3Ki+5sCoIoI942iuLZTHWogWktgwVDhU09iNEimQ==",
        "dev": true,
        "license": "MIT",
        "dependencies": {
@@ -678,9 +678,9 @@ index 20631bb..0933917 100644
 -      "version": "1.1.15",
 -      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.15.tgz",
 -      "integrity": "sha512-EwOCDEex4quD37XhqM3omwtMoJjr//isUZz1JopUNWms+4Z2ViyM/k1YIRePpoVNnQhENnxtFjLaxNHrT7xIUg==",
-+      "version": "1.1.18",
++      "version": "1.1.21",
-+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.18.tgz",
++      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.21.tgz",
-+      "integrity": "sha512-Edep/X9fGqVNmzKBVsDYIOtD+z1tuezV70LBjdCst9Tqu76lsnvRiZ6oTic1n+/BIwX6QDGAO94PN4N2SADvtw==",
++      "integrity": "sha512-9zeA+KLZNNzglF2TPKRQEDyx6Yby7daAkuy8MiPzpXPsYDWi/DRM8jmwUDxokQjYqBpv5DgPiwD4h4ZZSy1Ujw==",
        "dev": true,
        "license": "MIT",
        "dependencies": {
@@ -833,9 +833,9 @@ index 20631bb..0933917 100644
 -      "version": "3.1.3",
 -      "resolved": "https://registry.npmjs.org/fast-uri/-/fast-uri-3.1.3.tgz",
 -      "integrity": "sha512-i70LwGWUduXqzicKXWshooq+sWL1K3WUU5rKZNG/0i3a1OSoX3HqhH5WbWwTmqWfor4urUakGPiRQcleRZTwOg==",
-+      "version": "3.1.7",
++      "version": "3.1.8",
-+      "resolved": "https://registry.npmjs.org/fast-uri/-/fast-uri-3.1.7.tgz",
++      "resolved": "https://registry.npmjs.org/fast-uri/-/fast-uri-3.1.8.tgz",
-+      "integrity": "sha512-dOvZVzjdZdz7phd9v6jCbwxrBW3fK6n8Rc0CtdmM4bumzMnxywBYhuph6J819RRw/ku+rLbelwfMunktuzVVHg==",
++      "integrity": "sha512-GZMtZUTNRpOVIECoXwLNZS5xUGE+mVNbTB8h/7Rwh2TFWcBQiPzTgyZi05BF9UMZKkLJv8XBRJTlU7zg8+ZfMg==",
        "funding": [
          {
            "type": "github",
@@ -859,9 +859,9 @@ index 20631bb..0933917 100644
 -      "version": "5.0.7",
 -      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.7.tgz",
 -      "integrity": "sha512-7oFy703dxfY3/NLxC1fh2SUCQ0H9rmAY+5EpDVfXjUTTs+HEwR2nYaqLv+GWcTsumwxPfiz6CzCNkwXwBUwqCA==",
-+      "version": "5.0.9",
++      "version": "5.0.12",
-+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.9.tgz",
++      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.12.tgz",
-+      "integrity": "sha512-ScQ4IuvIEF1TMlP7Zt+vjJ//9zlPb2SDcxWxM3bk8s6t6GGdJ7KO1dCcTidOPJKePW30LE/2cT7wCyPho9/Wxg==",
++      "integrity": "sha512-YovQ3rzhaLMIrDjNDMkNS01tea93qhEhG5xy8f6+R0l+dw3Ki+5sCoIoI942iuLZTHWogWktgwVDhU09iNEimQ==",
        "dev": true,
        "license": "MIT",
        "dependencies": {
@@ -893,9 +893,9 @@ index 20631bb..0933917 100644
 -      "version": "10.2.0",
 -      "resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.2.0.tgz",
 -      "integrity": "sha512-/+S6j4E9AHvW9SWMSEY9Xfy66O5PWvVEJ08O0y5JGyEKQpojb0K0GKpz/v5HJ/G0vi3D2sjGK78119oXZeE0qA==",
-+      "version": "10.7.0",
++      "version": "10.7.2",
-+      "resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.7.0.tgz",
++      "resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.7.2.tgz",
-+      "integrity": "sha512-BGFsyJd5mpXp3rK6jIdADLNgpJUK1jnjzvYF8lK+VyDab9JAmqN0YOKDdP17HlgKb2+ehPgDc8EtnRLbGCAMhA==",
++      "integrity": "sha512-7H/2gFSIitxc0hG3nOI1glS8QLo/EHBFFLk8vEUjXY/xu0AdL8jZ9U1IzO2PUm0d2D/ofQcAifb0g6OBkt8U7w==",
        "license": "MIT",
        "engines": {
          "node": ">= 12"
@@ -1445,4 +1445,3 @@ index bd7190c..6aa5a6f 100644
  import { vi } from "vitest";
  
  // Mock window.matchMedia
-

docs/TODO.md

@@ -14,6 +14,17 @@ doc. See [`ROADMAP.md`](ROADMAP.md) for the curated, public-facing direction.
 
 ## Next release after 1.8.21 — reported 2026-09-30
 
+- [x] Review and repair open paid-download PRs #161 and #162, refresh both
+  branches from main, run independent and combined isolated suites, and verify
+  rootless file permissions in disposable scratch storage. Combined result:
+  1,585 passed, zero failed, four existing tests ignored. See the
+  [review evidence and remaining acceptance work](pr-review-20260930.md).
+- [ ] Integrate the reviewed PR branches into the next release and run funded
+  candidate acceptance, including Tor-only transport and payments with change.
+  PRs remain open; the reviewed code has not been deployed to live wallets.
+- [ ] Design durable recovery for an accepted payment whose response is lost.
+  Preserve the truthful unconfirmed-refund warning and prevent automatic
+  duplicate payment while that recovery work is outstanding.
 - [ ] **ThinkPad X250 kiosk: Bitcoin installation version selector is unreadable
   and appears underneath the pruning information.** Operator reports white
   styling with invisible text on the actual kiosk; the same flow works in remote
@@ -28,20 +39,21 @@ doc. See [`ROADMAP.md`](ROADMAP.md) for the curated, public-facing direction.
   alone do not establish that the kiosk rendering is fixed. Track for the next
   release; the signed 1.8.21 artifacts remain unchanged.
 
-## Current repair and release tasks — 2026-09-29
+## 1.8.21 repair and release tasks — completed 2026-09-30
 
-Release is blocked until these pass; see [execution record](repair-release-20260929.md).
+See the [execution record](repair-release-20260929.md) for evidence and limits.
 
-- [ ] Fix Cashu paid-file redemption between dev and Shorty; test keyset IDs,
+- [x] Fix Cashu paid-file redemption between dev and Shorty; test keyset IDs,
   mint errors, fees, and refund reporting before live validation.
-- [ ] Complete the remaining Framework incident verification and evidence.
+- [x] Record Framework verification and the operator's acceptance of the
-- [ ] Replace the unavailable tx1138.com explorer default with mempool.space;
+  remaining display check before release.
+- [x] Replace the unavailable tx1138.com explorer default with mempool.space;
   migrate the old default with fresh consent and preserve custom/local explorers.
-- [ ] Offer pruning in the Bitcoin installation version modal, using the same
+- [x] Offer pruning in the Bitcoin installation version modal, using the same
   pruning settings as automatic pruning even on large disks.
-- [ ] Explain Bitcoin warmup without raw RPC errors; gate LND unlock on Bitcoin
+- [x] Explain Bitcoin warmup without raw RPC errors; gate LND unlock on Bitcoin
   RPC readiness and show install/start/sync waiting states with automatic recovery.
-- [ ] Test the completed changes on this development box, then publish a new
+- [x] Test the completed changes on this development box, then publish a new
   signed OTA and raw ISO release. Record any remaining verification gaps.
 
 ## Dev & build process (priority)

docs/app-manifest-spec.md

@@ -290,3 +290,15 @@ app:
 Validate with `scripts/validate-app-manifest.sh` and regenerate the catalog
 with `scripts/generate-app-catalog.py` (drift-checked in CI by
 `scripts/check-app-catalog-drift.py`).
+
+### Persistent-state backup for network migrations
+
+`app.backup_on_network_change: true` opts an app into a stopped-state snapshot
+before an explicitly selected rootless network mode is migrated. The orchestrator
+archives writable persistent bind mounts under the node data directory, collapses
+nested mounts, excludes the runtime Podman socket, and preserves the previous
+Quadlet definition for rollback. Named volumes, outside-data-root state and
+symlinked mount roots fail closed rather than silently producing an incomplete
+backup. A failed snapshot resumes the original service and leaves migration
+pending. Private archives are retained under `migration-backups/`; fresh installs
+and unchanged network configurations do not create migration snapshots.

docs/gitea-portainer-repair-20260930.md

@@ -0,0 +1,104 @@
+# Same-node Gitea sources in Portainer
+
+Status: root cause reproduced and network repair verified in disposable Portainer
+instances; final migration integration and release acceptance remain in progress.
+This change belongs to the next signed catalog, OTA and ISO. It does not modify
+published 1.8.21 artifacts.
+
+## Confirmed cause
+
+On the affected X250, Gitea 1.27.3 and Portainer 2.45.0 run in rootless Podman
+5.4.2, managed by user Quadlet services. Gitea publishes HTTP on loopback and the
+Archipelago app gate serves its public port. Gitea's public ROOT_URL already
+matches that gate URL.
+
+Portainer had no explicit network selection and Podman selected pasta. Its
+network namespace contained the host's LAN address. A Git request to that same
+LAN address therefore reached Portainer's namespace rather than the host gate:
+connection refused before authentication. The exact smart-HTTP request from the
+host returned 200 with `application/x-git-upload-pack-advertisement`. From
+Portainer's actual namespace the LAN request was refused, while its host mapping
+returned a Git advertisement and the expected branch tip. Direct container-IP
+requests timed out. Container health and host-only HTTP checks missed the defect.
+
+A disposable Portainer using `slirp4netns` successfully created a Source through
+Portainer's own API, using the original LAN clone URL. Returning that fixture to
+pasta reproduced the refusal; recreating with slirp repaired it while preserving
+its account and saved Source. Restart also passed. The requested branch tip and
+Compose file were read from that actual Portainer network namespace. No user
+stack was deployed. Deployment addresses and repository details are kept outside
+this public record.
+
+## Source changes
+
+- Declare Portainer's rootless `slirp4netns` mode in its manifest. No shared static
+  container IP, host networking, all-interface backend publication or auth bypass.
+- Keep Gitea's loopback HTTP backend and gate port; machine Git uses Gitea's
+  authentication. Remove obsolete port-3000 nginx metadata/template and the old
+  best-effort installer commands which silently rewrote app.ini and falsely
+  claimed success. Gitea owns first-run setup and operator configuration.
+- Existing Quadlet reconciliation applies Network= drift. Record a durable
+  pending restart before updating the unit and clear it only after a successful
+  restart, so failed reloads/restarts and management interruptions retry.
+- Detect explicit rootless network-mode drift in the older Podman runtime too.
+  Unspecified networks do not trigger inferred changes to unrelated apps.
+- Portainer opts into `backup_on_network_change`. Before recreation, gracefully
+  stop the app and archive its writable persistent bind mounts, including nested
+  Compose state, once each. Runtime sockets are excluded. Save the previous
+  Quadlet definition, where present. Archives live under the node data directory's
+  private `migration-backups/<id>/` directory; state is never deleted. Backup
+  failures resume the original service and fail the migration visibly.
+- Keep Podman API and Quadlet bind/network behavior covered by actual-manifest
+  tests. Docker remains a development fallback: it now preserves bind/protocol
+  declarations and rejects Podman-only networking instead of silently changing it.
+
+## Operator use and diagnostics
+
+Use Gitea's advertised HTTP(S) clone URL in Portainer Sources, with the Gitea
+username and token in the credential fields. On first-run Gitea setup, the public
+base URL must match the origin opened through Archipelago (including its port).
+Keep a deliberately configured HTTPS/domain origin when one exists. Do not use a
+container IP or put a token into the URL. A private repository requires repository
+read permission. A successful Source check fetches Git refs; it does not deploy
+a stack or establish that a Compose build uses a desired application revision.
+
+`scripts/check-portainer-git-source.py` calls Portainer's own read-only Source
+connection test. Supply a private mode-600 JSON credential file containing
+`api_key` or `jwt`, and optionally `git: {username, password}`. Pass
+`--portainer-url`, `--repository-url` and `--credentials-file`. It does not create
+Sources or stacks and prints no credentials or raw server errors. It distinguishes
+Portainer login/API failures from Git connection refusal, timeout, DNS/TLS
+failure, HTML/login interception and repository authentication failure. TLS
+verification stays enabled and API redirects are refused.
+
+## Upgrade and rollback
+
+The signed catalog embeds manifests and overrides installed disk copies. A disk
+edit alone cannot deliver this fix. Publish the matching catalog with the tested
+runtime, then verify the generated unit, actual network mode and Source API.
+Expect a Portainer interruption while the snapshot and recreation run; duration
+depends on its saved state size.
+Gitea does not need recreation or an app.ini rewrite for this repair.
+
+Keep the previous trusted catalog/runtime for rollback. Restore that catalog
+before restoring the saved `previous.container`, reloading user systemd and
+starting Portainer; otherwise reconciliation will correctly reapply the new
+manifest. The archive is a stopped-state emergency backup, not an instruction to
+roll back a live database automatically. Restore it only with Portainer stopped
+and after preserving any newer state. Do not replace Gitea data/config, keys,
+repositories or the production Portainer database with disposable test data.
+
+## Validation and remaining gates
+
+- Disposable X250 Portainer Source API: old mode refuses; repaired mode succeeds;
+  saved account/Source survive recreation; restart succeeds.
+- Invalid Git credentials produce a repository-authentication error, distinct
+  from TCP refusal. Requested branch and Compose file read from Portainer context.
+- Final expanded backend suite: 1,575 passed, zero failed, four existing ignored
+  tests, including stopped-state archive round trips and failure preservation. Container runtime suite: 78 passed.
+  Five diagnostic regression tests passed. Combined tests with the merged
+  paid-download PRs remain pending.
+- Still required before release: live automatic migration with the new runtime,
+  snapshot/rollback verification, private-repository and install-order acceptance,
+  lifecycle/reboot convergence, and signed-catalog delivery to the existing app.
+  Record LFS/registry/SSH/browser checks and actual hardware/runtime coverage.

docs/pr-review-20260930.md

@@ -0,0 +1,113 @@
+# Paid-download PR review — 2026-09-30
+
+## Scope and result
+
+Reviewed both open PRs from the repository pull-request list: [#161](https://source.archipelago-foundation.org/lfg2025/archy/pulls/161)
+and [#162](https://source.archipelago-foundation.org/lfg2025/archy/pulls/162).
+Both branches were updated from main, repaired and tested independently and
+together. Their existing remote branches were advanced without rewriting the
+contributors' history. They remain open for integration into the release after
+1.8.21; no reviewed code was merged into main or deployed to a live wallet.
+The signed 1.8.21 artifacts are unchanged.
+
+| Candidate | Tested commit | Isolated backend result |
+| --- | --- | --- |
+| PR #161 | `971d4777` | 1,576 passed, 0 failed, 4 existing tests ignored |
+| PR #162 | `0677924a` | 1,568 passed, 0 failed, 4 existing tests ignored |
+| Both together | `4bf4bf1a` | 1,585 passed, 0 failed, 4 existing tests ignored |
+
+Both individual branches also passed production `cargo check`, with the
+repository's existing 16 warnings. The combined merge required no conflict
+resolution. Backend tests ran through `scripts/test-backend-isolated.sh` so they
+could not access host wallets, native services or production container storage.
+
+## Findings and repairs
+
+### #161 — payment delivery and file readability
+
+- The branch conflicted with newer mint-fee, keyset-ID and truthful refund
+  reporting fixes. Preserve those implementations from main; do not reintroduce
+  its older unconditional “refunded” messages or duplicate keyset resolution.
+- Opening a file before charging, then reopening/reading it afterward, still
+  permits a read failure after payment. Prepare the complete requested bytes
+  before redemption, including ranged reads. Tests delete or alter the backing
+  file during payment verification and still receive the prepared original data.
+- Empty/out-of-bounds/reversed ranges could fail after redemption, and empty
+  files could underflow the range calculation. Validate ranges before charging
+  and return HTTP 416 when unsatisfiable.
+- `chmod a+r` unnecessarily changed the permissions of shared paid/private
+  files. Read restricted FileBrowser files through the rootless namespace while
+  retaining their mode. Scope the fallback to regular files canonically inside
+  FileBrowser storage, and reject unauthorized peers before reading.
+- A single-delivery flag must also prevent redirects and ambiguous transport
+  retries. Payment-bearing GET and POST requests now retain the first HTTP
+  response and do not retry after timeouts or disconnects that might follow
+  delivery. Refused connections and normal nonpayment browsing retain the
+  appropriate retry behavior.
+- Interrupted response bodies now report the outcome using the actual local
+  refund result. Seller explanations are bounded, stripped of control
+  characters and explicitly identified as peer text.
+- Original permission tests silently returned when run as root. Replacement
+  tests inject read/payment boundary failures, exercise them under the isolated
+  runner, and assert that read failures never invoke redemption.
+
+### #162 — saving purchases in Files
+
+- Its host-permission repair overlapped 1.8.21's authenticated Files API path.
+  Review of [FileBrowser v2.63.23's resource handler](https://github.com/filebrowser/filebrowser/blob/v2.63.23/http/resource.go)
+  showed that `override=false` checks for existence separately from opening
+  with truncation. It does not guarantee no overwrites under concurrent saves.
+- The proposed direct path exposed the final filename before the write
+  completed. Both direct and namespace paths now finish a private temporary
+  file and publish it through a no-clobber hard link, retrying numbered names.
+- Plain `ln` could place a temporary file inside an existing directory instead
+  of treating the destination as a collision. Use `ln -T`; existing directories
+  and dangling symlinks are conflicts, never replacement targets.
+- Add filename and destination checks, unique temporary names, bounded name
+  retries, synchronization before publication, and exact input-length checks.
+  Truncated pipe input cannot become a completed purchased file.
+- Files storage remains optional. An unavailable copy destination does not
+  undo the purchase or create a fake FileBrowser installation; the durable
+  purchased-content cache remains primary.
+
+## Additional verification on the development node
+
+Used disposable scratch directories only, then removed them:
+
+- Reproduced a FileBrowser-style rootless-owned 0640 upload. The host backend
+  UID could not read it. `podman unshare cat` returned identical bytes without
+  changing its 0640 mode.
+- Ran the exact namespace writer script with four concurrent writers against
+  a directory owned by the container UID range. Every file had unique naming,
+  exact bytes, the expected owner and mode, and no remaining temporary file.
+- Sent truncated input to the namespace writer and verified refusal, no final
+  file and temporary-file cleanup.
+
+The isolated tests additionally exercised 24 simultaneous direct writes,
+existing-file preservation, symlink/directory conflicts, collision exhaustion,
+root-independent permission failures, read-before-redemption ordering,
+authorization, redirects and peer disconnects.
+
+Logs on the development box:
+`/tmp/archy-pr161-tests.log`, `/tmp/archy-pr162-tests.log`,
+`/tmp/archy-pr-integration-tests.log`, `/tmp/archy-pr161-check.log`,
+`/tmp/archy-pr162-check.log`, `/tmp/archy-pr-userns-scratch-test.log`.
+
+## Next-release acceptance and limits
+
+- Integrate the reviewed branches and repeat the release gates against the
+  final release commit if additional code changes land.
+- Perform funded peer-to-peer acceptance on the candidate build, including a
+  Tor-only purchase and a purchase requiring change, before the next release.
+  The new review branches were not deployed to funded live wallets here.
+- These PRs do not implement durable payment receipts. If a seller redeems a
+  payment and the connection subsequently loses the response, the buyer may
+  receive an unconfirmed-refund warning. Do not represent that warning as proof
+  of a refund or automatically charge the buyer again. Receipt-based recovery
+  remains separate follow-up work.
+- Abrupt process termination can leave a hidden namespace temporary file;
+  ordinary write failures and truncated input are tested to clean up. The final
+  filename is published only after complete input, and existing files remain
+  protected.
+- The separately reported X250 kiosk version-selector rendering issue remains
+  open in `TODO.md` and requires validation on the actual kiosk.

docs/repair-release-20260929.md

@@ -356,3 +356,42 @@ Bitcoin and LND IDs/start times remained unchanged, with generated stop settings
 still verified. No temporary graceful-stop overrides remain. Catalog signature
 verifies against the pinned release root; final 1.8.21 artifact validator passes.
 The candidate is ready for the user's local OTA signing ceremony.
+
+### 1.8.21 publication completed — 2026-09-30
+
+The operator signed the OTA manifest and subsequently the ISO checksum JSON.
+Both signatures verified against the pinned release root. The signed OTA was
+published on git/ngit, and the operator confirmed that Framework could see the
+update. Source main and the annotated `v1.8.21-alpha` tag were published.
+
+Raw ISO:
+`archipelago-installer-1.8.21-alpha-unbundled-x86_64_RC1.iso`
+
+- Size: 2,682,419,200 bytes.
+- SHA256: `8667b5522c476a40e29abba19df4180086191527a194a88765aa70ed527f9406`.
+- Build and ISO smoke checks passed. The mounted backend matched the staged
+  OTA backend hash, and the full dashboard/AIUI tree matched the fresh build.
+- An isolated UEFI QEMU guest, with no network or host disks attached, booted to
+  the installer prompt. The VM was stopped and the ISO unmounted afterward.
+  This was an installer boot check, not a full installation onto hardware.
+- Uploaded the raw ISO, plain SHA256 sidecar and signed checksum JSON to the
+  [1.8.21 release](https://source.archipelago-foundation.org/lfg2025/archy/releases/tag/v1.8.21-alpha).
+  The stored server file hashes matched, the public ISO headers and first/last
+  byte samples matched, and both public checksum files matched byte-for-byte.
+- The ngit downloader's full-ISO acquisition exceeded its fixed 30-minute
+  deadline on the available connection. Published Nostr asset records using
+  the already verified hashes, sizes and public URLs with the existing ngit
+  signer; both repository relays acknowledged them. Ngit then accepted those
+  records and final readback resolved all five release assets with the expected
+  hashes and sizes. No new release-root signing was performed by the assistant.
+
+Final publication evidence: `/tmp/archy-1821-finish-events.log`,
+`/tmp/archy-ngit-1821-complete-view.json`, and
+`/tmp/archy-1821-verified-asset-events.log` on the development box.
+
+Subsequent review of PRs #161/#162 found additional delivery and concurrent
+file-save edge cases. Their repaired, tested branches are recorded in
+[the next-release review](pr-review-20260930.md); those changes are not in the
+signed 1.8.21 artifacts. The X250 kiosk selector report is also tracked for the
+next release. No claim of exhaustive hardware or network-failure coverage is
+made for this release.

image-recipe/_archived/build-auto-installer-iso.sh

@@ -2607,21 +2607,14 @@ if [ -f "$SCRIPT_DIR/../../scripts/image-versions.sh" ]; then
     echo "   ✅ Bundled image-versions.sh"
 fi
 
-# Bundle docker UI source files for building custom UIs on first boot
+# Build-source apps need their complete contexts even on unbundled ISOs.
-# Always bundle — these are tiny HTML/CSS files, not container images
+# Keep this identical to the OTA runtime payload; a per-app allowlist silently
-if true; then
+# omitted GitWorkshop, FIPS and Cuprate and made fresh installs fail at 70%.
-    DOCKER_UI_DIR="$SCRIPT_DIR/../../docker"
+DOCKER_UI_DIR="$SCRIPT_DIR/../../docker"
-    if [ -d "$DOCKER_UI_DIR" ]; then
+[ -d "$DOCKER_UI_DIR" ] || { echo "Missing docker build sources" >&2; exit 1; }
-        echo "   Bundling docker UI source files..."
+mkdir -p "$ARCH_DIR/docker"
-        mkdir -p "$ARCH_DIR/docker"
+cp -a "$DOCKER_UI_DIR/." "$ARCH_DIR/docker/"
-        for ui_dir in bitcoin-ui lnd-ui electrs-ui; do
+python3 "$SCRIPT_DIR/../../scripts/check-app-build-contexts.py" "$ARCH_DIR"
-            if [ -d "$DOCKER_UI_DIR/$ui_dir" ]; then
-                cp -r "$DOCKER_UI_DIR/$ui_dir" "$ARCH_DIR/docker/"
-                echo "   ✅ Bundled $ui_dir source"
-            fi
-        done
-    fi
-fi
 
 if [ "$UNBUNDLED" = "1" ]; then
     echo "   ✅ Unbundled build ready (Tor setup included, no container images)"

image-recipe/configs/nginx-gitea-iframe.conf

@@ -1,21 +0,0 @@
-# Gitea iframe proxy — strips X-Frame-Options so Gitea works in Archipelago iframe.
-# Gitea container binds to port 3001, this proxy listens on port 3000 (the public port).
-# Deployed to /etc/nginx/conf.d/gitea-iframe.conf
-server {
-    listen 3000;
-    server_name _;
-    client_max_body_size 1G;
-
-    location / {
-        proxy_pass http://127.0.0.1:3001;
-        proxy_set_header Host $http_host;
-        proxy_set_header X-Real-IP $remote_addr;
-        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        proxy_set_header X-Forwarded-Proto $scheme;
-        proxy_http_version 1.1;
-        proxy_set_header Upgrade $http_upgrade;
-        proxy_set_header Connection "upgrade";
-        proxy_hide_header X-Frame-Options;
-        proxy_hide_header Content-Security-Policy;
-    }
-}

neode-ui/src/components/InstallVersionModal.vue

@@ -25,13 +25,22 @@
     <div v-if="loading" class="py-6 text-center text-white/60 text-sm">{{ t('common.loading') }}</div>
 
     <div v-else class="space-y-2">
-      <label class="block text-white/60 text-sm">{{ t('appDetails.selectVersion') }}</label>
+      <fieldset class="space-y-2">
-      <select
+        <legend class="text-white/60 text-sm mb-2">{{ t('appDetails.selectVersion') }}</legend>
-        v-model="selected"
+        <!-- Inline options avoid native popup rendering in the kiosk WebView.
-        class="w-full rounded-lg bg-white/[0.06] border border-white/10 text-white pl-3 pr-9 py-2 text-sm focus:outline-none focus:border-blue-400/60"
+             They stay in document flow above the pruning explanation. -->
-      >
+        <div class="max-h-40 overflow-y-auto space-y-2 rounded-lg">
-        <option v-for="v in versions" :key="v.version" :value="v.version">{{ optionLabel(v) }}</option>
+          <label
-      </select>
+            v-for="v in versions"
+            :key="v.version"
+            class="flex items-center gap-3 rounded-lg border px-3 py-2.5 text-sm text-white cursor-pointer"
+            :class="selected === v.version ? 'border-blue-400/60 bg-slate-800' : 'border-white/10 bg-slate-900'"
+          >
+            <input v-model="selected" type="radio" :name="`install-version-${appId}`" :value="v.version" class="shrink-0 accent-blue-400" />
+            <span>{{ optionLabel(v) }}</span>
+          </label>
+        </div>
+      </fieldset>
       <p class="text-white/40 text-xs">{{ t('marketplace.installModalHint') }}</p>
     </div>
 
@@ -113,6 +122,7 @@ async function load() {
   } catch (err) {
     if (import.meta.env.DEV) console.warn('[InstallVersionModal] getPackageVersions failed:', err)
     // Fall back to the floating "latest" so the install can still proceed.
+    versions.value = [{ version: 'latest' } as CatalogVersionInfo]
     selected.value = 'latest'
   } finally {
     loading.value = false

neode-ui/src/components/__tests__/InstallVersionModal.test.ts

@@ -16,12 +16,14 @@ describe('Bitcoin install storage choice', () => {
     versions.mockResolvedValue({ bitcoinPrune: false, default: 'latest', versions: [{ version: 'latest' }, { version: '28.4' }] })
     const wrapper = modal(id)
     await flushPromises()
-    await wrapper.get('select').setValue('28.4')
+    await wrapper.get('input[type=radio][value="28.4"]').setValue(true)
     await wrapper.get('input[type=checkbox]').setValue(true)
     await wrapper.get('button').trigger('click')
     expect(wrapper.emitted('confirm')).toEqual([['28.4', true]])
     expect(wrapper.text()).toContain('automatic pruning')
     expect(wrapper.text()).toContain('Mempool')
+    expect(wrapper.find('select').exists()).toBe(false)
+    expect(wrapper.findAll('input[type=radio]')).toHaveLength(2)
   })
   it('keeps automatic disk selection by default and resets on reopening', async () => {
     versions.mockResolvedValue({ bitcoinPrune: false, versions: [{ version: 'latest' }] })
@@ -29,17 +31,17 @@ describe('Bitcoin install storage choice', () => {
     await flushPromises()
     await wrapper.get('button').trigger('click')
     expect(wrapper.emitted('confirm')).toEqual([['latest', false]])
-    await wrapper.get('input').setValue(true)
+    await wrapper.get('input[type=checkbox]').setValue(true)
     await wrapper.setProps({ show: false })
     await wrapper.setProps({ show: true })
     await flushPromises()
-    expect((wrapper.get('input').element as HTMLInputElement).checked).toBe(false)
+    expect((wrapper.get('input[type=checkbox]').element as HTMLInputElement).checked).toBe(false)
   })
   it('still allows choosing pruning when version lookup fails', async () => {
     versions.mockRejectedValue(new Error('offline'))
     const wrapper = modal()
     await flushPromises()
-    await wrapper.get('input').setValue(true)
+    await wrapper.get('input[type=checkbox]').setValue(true)
     await wrapper.get('button').trigger('click')
     expect(wrapper.emitted('confirm')).toEqual([['latest', true]])
   })
@@ -47,7 +49,7 @@ describe('Bitcoin install storage choice', () => {
     versions.mockResolvedValue({ bitcoinPrune: true, versions: [{ version: 'latest' }] })
     const wrapper = modal('bitcoin-knots')
     await flushPromises()
-    expect((wrapper.get('input').element as HTMLInputElement).checked).toBe(true)
+    expect((wrapper.get('input[type=checkbox]').element as HTMLInputElement).checked).toBe(true)
     await wrapper.get('button').trigger('click')
     expect(wrapper.emitted('confirm')).toEqual([['latest', true]])
   })
@@ -62,6 +64,6 @@ describe('Bitcoin install storage choice', () => {
     versions.mockResolvedValue({ bitcoinPrune: false, versions: [{ version: 'latest' }] })
     const wrapper = modal('other')
     await flushPromises()
-    expect(wrapper.find('input').exists()).toBe(false)
+    expect(wrapper.find('input[type=checkbox]').exists()).toBe(false)
   })
 })

neode-ui/src/stores/__tests__/appLauncher.test.ts

@@ -34,6 +34,7 @@ vi.mock('@/api/rpc-client', () => ({
 vi.stubGlobal('open', mockWindowOpen)
 
 import { useAppLauncherStore, senderMatchesApp } from '../appLauncher'
+import { useAppStore } from '../app'
 
 describe('useAppLauncherStore', () => {
   beforeEach(() => {
@@ -54,6 +55,25 @@ describe('useAppLauncherStore', () => {
     })
   })
 
+  it('blocks both browser and embedded launch while HTTP is unready', () => {
+    const app = useAppStore()
+    app.data = { 'package-data': { gitea: { state: 'running', 'ui-ready': false, health: 'healthy', manifest: { id: 'gitea', title: 'Gitea' } } } } as never
+    const launcher = useAppLauncherStore()
+    launcher.openSession('gitea')
+    expect(launcher.panelAppId).toBeNull()
+    launcher.open({ url: 'http://192.0.2.10:3001/', title: 'Gitea', openInNewTab: true })
+    expect(mockWindowOpen).not.toHaveBeenCalled()
+    expect(launcher.isOpen).toBe(false)
+  })
+
+  it('also gates a dynamic app resolved through its runtime URL', () => {
+    useAppStore().data = { 'package-data': { custom: { state: 'running', 'ui-ready': false, manifest: { id: 'custom', title: 'Custom' }, installed: { 'interface-addresses': { main: { 'lan-address': 'http://localhost:18993/' } } } } } } as never
+    const launcher = useAppLauncherStore()
+    launcher.open({ url: 'http://192.0.2.10:18993/', title: 'Custom', openInNewTab: true })
+    expect(mockWindowOpen).not.toHaveBeenCalled()
+    expect(launcher.isOpen).toBe(false)
+  })
+
   it('starts closed with empty state', () => {
     const store = useAppLauncherStore()
     expect(store.isOpen).toBe(false)

neode-ui/src/stores/__tests__/server.test.ts

@@ -0,0 +1,42 @@
+import { beforeEach, describe, expect, it, vi } from 'vitest'
+import { createPinia, setActivePinia } from 'pinia'
+import { reactive, nextTick } from 'vue'
+
+const fake = reactive<{ packages: Record<string, unknown> }>({ packages: {} })
+vi.mock('../sync', () => ({ useSyncStore: () => fake }))
+vi.mock('../../api/rpc-client', () => ({ rpcClient: {} }))
+import { useServerStore } from '../server'
+
+function installing(phase = 'preparing-app') {
+  return { state: 'installing', manifest: { title: 'Git Workshop' }, 'install-progress': { phase, size: 0, downloaded: 0 } }
+}
+
+describe('installation state after hard refresh', () => {
+  beforeEach(() => {
+    setActivePinia(createPinia())
+    fake.packages = {}
+  })
+
+  it('restores an in-flight install from an already-loaded server snapshot', () => {
+    fake.packages = { 'archipelago-source': installing() }
+    const store = useServerStore()
+    expect(store.isInstalling('archipelago-source')).toBe(true)
+    expect(store.installingApps.get('archipelago-source')).toMatchObject({
+      progress: 20,
+      message: 'Downloading, building and starting app…',
+    })
+  })
+
+  it('keeps a long download visible and clears it on terminal success', async () => {
+    const store = useServerStore()
+    fake.packages = { 'nginx-proxy-manager': installing() }
+    await nextTick()
+    expect(store.isInstalling('nginx-proxy-manager')).toBe(true)
+    fake.packages = { 'nginx-proxy-manager': installing() }
+    await nextTick()
+    expect(store.installingApps.get('nginx-proxy-manager')?.progress).toBe(20)
+    fake.packages = { 'nginx-proxy-manager': { state: 'running' } }
+    await nextTick()
+    expect(store.isInstalling('nginx-proxy-manager')).toBe(false)
+  })
+})

neode-ui/src/stores/appLauncher.ts

@@ -239,6 +239,11 @@ export const useAppLauncherStore = defineStore('appLauncher', () => {
   const panelPath = ref<string | null>(null)
 
   function openSessionNow(appId: string, opts: LaunchOptions = {}) {
+    const pkg = useAppStore().data?.['package-data']?.[appId]
+    if (pkg?.['ui-ready'] === false) {
+      useToast().info(`${pkg.manifest?.title || appId} is not ready to open yet`)
+      return
+    }
     recordAppLaunch(appId)
     const mobile = isMobileViewport()
 
@@ -295,7 +300,7 @@ export const useAppLauncherStore = defineStore('appLauncher', () => {
     // Apply the same readiness gate here so a container that has just entered
     // `running` cannot race nginx and show a transient 502 to the user.
     const pkg = useAppStore().data?.['package-data']?.[appId]
-    if (pkg && pkg.state === 'running' && !isAppReadyForLaunch(pkg)) {
+    if (pkg && (pkg['ui-ready'] === false || (pkg.state === 'running' && !isAppReadyForLaunch(pkg)))) {
       useToast().info(`${pkg.manifest?.title || appId} is still starting — try again in a moment`)
       return
     }
@@ -394,6 +399,12 @@ export const useAppLauncherStore = defineStore('appLauncher', () => {
     let launchUrl = normalizeLaunchUrl(payload.url, titleHintId)
     const resolvedId = resolveAppIdFromUrl(launchUrl) || titleHintId
 
+    const pkg = resolvedId ? useAppStore().data?.['package-data']?.[resolvedId] : undefined
+    if (pkg?.['ui-ready'] === false) {
+      useToast().info(`${pkg.manifest?.title || resolvedId} is not ready to open yet`)
+      return
+    }
+
     // Scheme discipline for everything launched on this host. Ports fronted
     // by the node's app gate (manifest auth gated/open) serve TLS on the same
     // port — on an HTTPS connection those must open over https. Ports that
@@ -472,6 +483,17 @@ export const useAppLauncherStore = defineStore('appLauncher', () => {
       // Check /app/{id}/ path-style routes first (HTTPS proxy mode)
       const m = u.pathname.match(/^\/app\/([a-z0-9._-]+)(?:\/|$)/i)
       if (m?.[1]) return m[1].toLowerCase()
+      // Dynamic/sideloaded apps have no entry in the static port map.
+      if (u.hostname === window.location.hostname && u.port) {
+        for (const [id, pkg] of Object.entries(useAppStore().data?.['package-data'] || {})) {
+          const address = pkg.installed?.['interface-addresses']?.main?.['lan-address']
+          if (!address) continue
+          try {
+            const runtime = new URL(address)
+            if (runtime.port === u.port && ['localhost', '127.0.0.1', window.location.hostname].includes(runtime.hostname)) return id
+          } catch { /* malformed runtime address is not a launch target */ }
+        }
+      }
       // Check port-based apps
       const appId = PORT_TO_APP_ID[u.port]
       if (appId) return appId

neode-ui/src/stores/server.ts

@@ -25,6 +25,7 @@ import type { InstallPhase } from '../types/api'
 const PHASE_INFO: Record<InstallPhase, { progress: number; message: string; status: InstallProgress['status'] }> = {
   'preparing':          { progress: 5,  message: 'Preparing…',                status: 'downloading' },
   'pulling-image':      { progress: 20, message: 'Downloading image…',        status: 'downloading' },
+  'preparing-app':      { progress: 20, message: 'Downloading, building and starting app…', status: 'downloading' },
   'creating-container': { progress: 70, message: 'Creating container…',       status: 'installing' },
   'starting-container': { progress: 80, message: 'Starting container…',       status: 'starting' },
   'waiting-healthy':    { progress: 88, message: 'Finalizing first start…',   status: 'starting' },
@@ -149,7 +150,7 @@ export const useServerStore = defineStore('server', () => {
         uninstallingApps.value.delete(appId)
       }
     }
-  }, { deep: true })
+  }, { deep: true, immediate: true })
 
   function setInstallProgress(appId: string, progress: Partial<InstallProgress> & { id: string; title: string }) {
     const existing = installingApps.value.get(appId)

neode-ui/src/types/api.ts

@@ -88,6 +88,7 @@ export const PackageState = {
 export type PackageState = typeof PackageState[keyof typeof PackageState]
 
 export interface PackageDataEntry {
+  'ui-ready'?: boolean // HTTP upstream readiness, separate from container health
   state: PackageState
   health?: string | null // "healthy", "unhealthy", "starting", or null
   'exit-code'?: number | null // container exit code: 0 = clean stop, non-zero = crash
@@ -180,6 +181,7 @@ export type ServiceStatus = typeof ServiceStatus[keyof typeof ServiceStatus]
 export type InstallPhase =
   | 'preparing'
   | 'pulling-image'
+  | 'preparing-app'
   | 'creating-container'
   | 'starting-container'
   | 'waiting-healthy'

neode-ui/src/views/AppDetails.vue

@@ -259,7 +259,7 @@ const canLaunch = computed(() => {
   const hasRuntimeAddress = !!pkg.value.installed?.['interface-addresses']?.main?.['lan-address']
   const hasKnownLaunchUrl = typeof window !== 'undefined' && !!resolveAppUrl(pkg.value.manifest.id)
   const hasUI = !!(pkg.value.manifest.interfaces?.main?.ui || hasRuntimeAddress || hasKnownLaunchUrl)
-  return hasUI && pkg.value.state === 'running' && pkg.value.health !== 'starting' && pkg.value.health !== 'unhealthy'
+  return hasUI && pkg.value['ui-ready'] !== false && pkg.value.state === 'running' && pkg.value.health !== 'starting' && pkg.value.health !== 'unhealthy'
 })
 
 const features = computed(() => {

neode-ui/src/views/AppSession.vue

@@ -39,6 +39,7 @@
         :must-open-new-tab="mustOpenNewTab"
         :auto-retry-count="autoRetryCount"
         :refresh-key="refreshKey"
+        :ui-ready-blocked="packageEntry?.['ui-ready'] === false"
         :blocked-reason="blockedReason"
         :blocked-title="blockedTitle"
         :warming-up="warmingUp"
@@ -375,6 +376,20 @@ const panelClasses = computed(() => {
   return `${base} app-session-overlay`
 })
 
+// A cold/restarting upstream is held outside the iframe. Start one fresh
+// load when the scanner observes HTTP readiness; no manual refresh required.
+watch(() => packageEntry.value?.['ui-ready'], (ready, previous) => {
+  if (ready === false) {
+    if (loadTimeoutId) clearTimeout(loadTimeoutId)
+    if (autoRetryId) clearTimeout(autoRetryId)
+    if (iframeCheckId) clearTimeout(iframeCheckId)
+    loading.value = false
+  } else if (previous === false && ready === true) {
+    autoRetryCount.value = 0
+    refresh()
+  }
+})
+
 // --- Lifecycle handlers ---
 
 function onLoad() {
@@ -433,6 +448,7 @@ function refresh() {
 
 function startLoadTimeout() {
   if (loadTimeoutId) clearTimeout(loadTimeoutId)
+  if (packageEntry.value?.['ui-ready'] === false) return
   loadTimeoutId = setTimeout(() => {
     if (loading.value) {
       loading.value = false
@@ -442,11 +458,13 @@ function startLoadTimeout() {
 }
 
 function openNewTabAndBack() {
+  if (packageEntry.value?.['ui-ready'] === false) return
   if (appUrl.value) openExternalUrl(appUrl.value)
   closeSession()
 }
 
 function openNewTab() {
+  if (packageEntry.value?.['ui-ready'] === false) return
   if (appUrl.value) openExternalUrl(appUrl.value)
 }
 

neode-ui/src/views/appSession/AppSessionFrame.vue

@@ -6,7 +6,7 @@
            first, then sync status arrives), and the sync screen is strictly
            more informative, so it takes precedence instead of the two
            rendering on top of each other. -->
-      <AppLoadingScreen v-if="loading && !(electrsSync && !electrsSync.stale)" :icon="appIcon" :title="appTitle" :progress="loadProgress" />
+      <AppLoadingScreen v-if="loading && !uiReadyBlocked && !(electrsSync && !electrsSync.stale)" :icon="appIcon" :title="appTitle" :progress="loadProgress" />
     </Transition>
 
     <!-- ElectrumX sync screen — shown before the real UI while the on-chain
@@ -43,7 +43,7 @@
     </Transition>
 
     <div
-      v-if="appUrl && !iframeBlocked && (!electrsSync || electrsSync.stale)"
+      v-if="appUrl && !iframeBlocked && !uiReadyBlocked && (!electrsSync || electrsSync.stale)"
       class="absolute inset-0 app-session-frame-scroll-host"
       tabindex="-1"
       @pointerdown="focusIframe"
@@ -66,7 +66,7 @@
          reachable yet, so the "App not reachable / retry" overlay would just
          paint over the sync progress and read as a hard error. -->
     <Transition name="content-fade">
-      <div v-if="iframeBlocked && !electrsSync" class="absolute inset-0 z-10 flex flex-col items-center justify-center">
+      <div v-if="(iframeBlocked || uiReadyBlocked) && !electrsSync" class="absolute inset-0 z-10 flex flex-col items-center justify-center">
         <div class="text-center px-8">
           <!-- Warm-up uses the app's own icon, pulsing, rather than the padlock:
                the padlock reads as "blocked/denied" and this state is neither. -->
@@ -78,7 +78,8 @@
           </div>
           <h3 class="text-lg font-semibold text-white mb-2">{{ warmingUp ? `${appTitle} is starting…` : blockedReason ? blockedTitle : (mustOpenNewTab ? 'This app opens in a new tab' : 'App not reachable') }}</h3>
           <p class="text-white/50 text-sm mb-6">
-            <template v-if="mustOpenNewTab">{{ appTitle }} sets security headers that prevent iframe embedding.<br>Open it in a new browser tab instead.</template>
+            <template v-if="uiReadyBlocked">{{ blockedReason }} This screen opens automatically when it is ready.</template>
+            <template v-else-if="mustOpenNewTab">{{ appTitle }} sets security headers that prevent iframe embedding.<br>Open it in a new browser tab instead.</template>
             <template v-else-if="warmingUp">The container is running but hasn't finished warming up yet.<br>This screen opens on its own as soon as it answers.<span v-if="autoRetryCount > 0" class="block text-yellow-400/70">Checking again automatically ({{ autoRetryCount }})...</span></template>
             <template v-else-if="blockedReason">{{ blockedReason }}<br><span v-if="autoRetryCount > 0" class="text-yellow-400/70">Checking again automatically ({{ autoRetryCount }})...</span></template>
             <template v-else>{{ appTitle }} may still be starting up or the container is stopped.<br><span v-if="autoRetryCount > 0" class="text-yellow-400/70">Retrying automatically ({{ autoRetryCount }})...</span></template>
@@ -95,6 +96,7 @@
               Retry now
             </button>
             <button
+              v-if="!uiReadyBlocked"
               @click="$emit('openNewTabAndBack')"
               class="glass-button px-6 py-3 rounded-lg text-sm font-semibold inline-flex items-center gap-2"
             >
@@ -108,7 +110,7 @@
       </div>
     </Transition>
 
-    <div v-if="!appUrl" class="absolute inset-0 flex items-center justify-center">
+    <div v-if="!appUrl && !uiReadyBlocked" class="absolute inset-0 flex items-center justify-center">
       <div class="text-center px-8">
         <h3 class="text-lg font-semibold text-white mb-2">App not configured</h3>
         <p class="text-white/50 text-sm">No URL found for {{ appId }}</p>
@@ -133,6 +135,7 @@ const props = defineProps<{
   mustOpenNewTab: boolean
   autoRetryCount: number
   refreshKey: number
+  uiReadyBlocked?: boolean
   blockedReason?: string
   blockedTitle?: string
   // True while the container is up but its probe hasn't answered yet and the

neode-ui/src/views/appSession/__tests__/AppSessionFrame.test.ts

@@ -66,3 +66,19 @@ describe('AppSessionFrame warm-up state', () => {
     expect(text).toContain('This app opens in a new tab')
   })
 })
+
+describe('HTTP readiness gate', () => {
+  it('does not show a missing-configuration error during initial installation', () => {
+    const frame = mountFrame({ appUrl: '', uiReadyBlocked: true, blockedReason: 'Waiting for the app to be ready…' })
+    expect(frame.text()).not.toContain('App not configured')
+    expect(frame.find('iframe').exists()).toBe(false)
+  })
+  it('does not mount an iframe before readiness, then opens automatically', async () => {
+    const frame = mountFrame({ iframeBlocked: false, uiReadyBlocked: true, blockedReason: 'Waiting for the app to be ready…', blockedTitle: 'App not ready' })
+    expect(frame.find('iframe').exists()).toBe(false)
+    expect(frame.text()).toContain('opens automatically')
+    expect(frame.text()).not.toContain('Open in new tab')
+    await frame.setProps({ uiReadyBlocked: false, blockedReason: '' })
+    expect(frame.find('iframe').exists()).toBe(true)
+  })
+})

neode-ui/src/views/apps/__tests__/appsConfig.test.ts

@@ -184,3 +184,24 @@ describe('appsConfig service filtering', () => {
     expect(canLaunch(pkg)).toBe(true)
   })
 })
+
+describe('HTTP readiness independent of container health', () => {
+  it('blocks fixed launch URLs while the HTTP upstream is unavailable', () => {
+    for (const id of ['gitea', 'filebrowser', 'fedimint', 'lnd']) {
+      const pkg = makePkg(id, id, 'other')
+      pkg['ui-ready'] = false
+      pkg.health = 'healthy'
+      expect(canLaunch(pkg)).toBe(false)
+      expect(isAppReadyForLaunch(pkg)).toBe(false)
+      expect(launchBlockedReason(id, pkg)).toContain('Waiting')
+      pkg['ui-ready'] = true
+      expect(isAppReadyForLaunch(pkg)).toBe(true)
+    }
+  })
+  it('allows a ready companion while its backend is syncing', () => {
+    const pkg = makePkg('lnd', 'Lightning', 'bitcoin')
+    pkg.health = 'starting'
+    pkg['ui-ready'] = true
+    expect(isAppReadyForLaunch(pkg)).toBe(true)
+  })
+})

neode-ui/src/views/apps/appsConfig.ts

@@ -244,6 +244,7 @@ export function resolveAppIcon(id: string, pkg: PackageDataEntry, curatedIcon?:
 
 export function canLaunch(pkg: PackageDataEntry): boolean {
   if (isWebOnlyApp(pkg.manifest.id)) return true
+  if (pkg['ui-ready'] === false) return false
   // Headless backends never get a Launch button, even with a published port.
   if (isServicePackage(pkg.manifest.id, pkg)) return false
   const hasRuntimeAddress = !!pkg.installed?.['interface-addresses']?.main?.['lan-address']
@@ -277,6 +278,7 @@ export function canLaunch(pkg: PackageDataEntry): boolean {
  * health check retain the legacy state/port behaviour.
  */
 export function isAppReadyForLaunch(pkg: PackageDataEntry): boolean {
+  if (pkg['ui-ready'] !== undefined) return pkg['ui-ready']
   const manifest = pkg.manifest as unknown as Record<string, unknown>
   const hasHealthCheck = Boolean(manifest.health_check || manifest['health-check'])
   if (!hasHealthCheck) return pkg.health !== 'unhealthy'
@@ -285,6 +287,10 @@ export function isAppReadyForLaunch(pkg: PackageDataEntry): boolean {
 
 export function launchBlockedReason(id: string, pkg?: PackageDataEntry | null): string {
   const appId = pkg?.manifest?.id || id
+  if (pkg?.['ui-ready'] === false && !isServicePackage(appId, pkg)) {
+    if (pkg.state === PackageState.Stopped || pkg.state === PackageState.Exited) return 'App is stopped. Start it to open it.'
+    return 'Waiting for the app to be ready…'
+  }
   if (
     (appId === 'fedimint' || appId === 'fedimintd') &&
     (pkg?.state === PackageState.Starting || (pkg?.state === PackageState.Running && pkg?.health === 'starting'))

scripts/check-app-build-contexts.py

@@ -0,0 +1,39 @@
+#!/usr/bin/env python3
+"""Validate build-source apps against an OTA/ISO runtime payload before shipping."""
+import sys
+from pathlib import Path
+import yaml
+
+
+def check(root: Path) -> int:
+    root = root.resolve()
+    manifests = sorted((root / 'apps').glob('*/manifest.y*ml'))
+    if not manifests:
+        raise ValueError(f'No app manifests in {root / "apps"}')
+    count = 0
+    for manifest in manifests:
+        app = yaml.safe_load(manifest.read_text())['app']
+        build = app.get('container', {}).get('build')
+        if not build:
+            continue
+        context = Path(build['context'])
+        if context.is_absolute():
+            context = root / context.relative_to('/opt/archipelago')
+        else:
+            context = manifest.parent / context
+        context = context.resolve()
+        if not context.is_relative_to(root) or not context.is_dir():
+            raise ValueError(f'{app["id"]}: missing or out-of-payload build context: {context}')
+        dockerfile = (context / build.get('dockerfile', 'Dockerfile')).resolve()
+        if not dockerfile.is_relative_to(context) or not dockerfile.is_file():
+            raise ValueError(f'{app["id"]}: missing or out-of-context Dockerfile: {dockerfile}')
+        count += 1
+    return count
+
+
+if __name__ == '__main__':
+    try:
+        count = check(Path(sys.argv[1] if len(sys.argv) > 1 else '.'))
+    except (ValueError, KeyError, OSError, yaml.YAMLError) as error:
+        sys.exit(f'Invalid app build payload: {error}')
+    print(f'Validated {count} app build contexts and Dockerfiles.')

scripts/check-portainer-git-source.py

@@ -0,0 +1,95 @@
+#!/usr/bin/env python3
+"""Test Git from Portainer's server context without creating a Source or stack."""
+import argparse
+import json
+import pathlib
+import socket
+import stat
+import urllib.error
+import urllib.parse
+import urllib.request
+
+
+class NoRedirect(urllib.request.HTTPRedirectHandler):
+    def redirect_request(self, req, fp, code, msg, headers, newurl):
+        return None
+
+
+def classify(error):
+    text = error.lower()
+    for category, patterns in (
+        ('connection-refused', ('connection refused',)),
+        ('dns-failure', ('no such host', 'name resolution', 'server misbehaving')),
+        ('timeout', ('timeout', 'timed out', 'deadline exceeded')),
+        ('tls-failure', ('x509:', 'certificate', 'tls handshake')),
+        ('proxy-or-login-interception', ('text/html', '<html', '<!doctype', 'unexpected content-type', 'invalid pkt-len')),
+        ('repository-authentication', ('authentication required', 'authentication failed', 'authorization failed', '401', '403')),
+        ('repository-not-found-or-private', ('repository not found', '404')),
+    ):
+        if any(pattern in text for pattern in patterns):
+            return category
+    return 'git-error'
+
+
+def safe_url(value):
+    parsed = urllib.parse.urlsplit(value)
+    if parsed.scheme not in ('http', 'https') or not parsed.hostname:
+        raise ValueError('Use an HTTP(S) URL')
+    if parsed.username is not None or parsed.password is not None or parsed.query or parsed.fragment:
+        raise ValueError('URLs must not contain credentials, query parameters or fragments')
+    return value.rstrip('/')
+
+
+def private_json(path):
+    path = pathlib.Path(path)
+    if stat.S_IMODE(path.stat().st_mode) & 0o077:
+        raise ValueError('Credential file must be private (chmod 600)')
+    return json.loads(path.read_text())
+
+
+def check(base, repository, credentials, opener=None):
+    base, repository = safe_url(base), safe_url(repository)
+    # JWT/API keys and Git credentials travel in headers/body, never URLs or logs.
+    headers = {'Content-Type': 'application/json'}
+    if credentials.get('api_key'):
+        headers['X-API-Key'] = credentials['api_key']
+    elif credentials.get('jwt'):
+        headers['Authorization'] = 'Bearer ' + credentials['jwt']
+    else:
+        raise ValueError('Credential file needs api_key or jwt')
+    payload = {'url': repository, 'tlsSkipVerify': False, 'interval': '5m'}
+    if credentials.get('git'):
+        payload['authentication'] = credentials['git']
+    request = urllib.request.Request(base + '/api/gitops/sources/test',
+                                     data=json.dumps(payload).encode(), headers=headers)
+    opener = opener or urllib.request.build_opener(NoRedirect())
+    try:
+        with opener.open(request, timeout=45) as response:
+            result = json.load(response)
+    except urllib.error.HTTPError as error:
+        return {'success': False, 'category': 'portainer-authentication' if error.code in (401, 403) else 'portainer-api-error', 'http_status': error.code}
+    except (urllib.error.URLError, TimeoutError, socket.timeout) as error:
+        return {'success': False, 'category': 'portainer-api-' + classify(str(error))}
+    except (ValueError, UnicodeError):
+        return {'success': False, 'category': 'portainer-api-invalid-response'}
+    if not isinstance(result, dict) or not isinstance(result.get('success'), bool):
+        return {'success': False, 'category': 'portainer-api-invalid-response'}
+    return {'success': result['success'], 'category': 'git-refs-readable' if result['success'] else classify(str(result.get('error', '')))}
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument('--portainer-url', required=True, help='Reachable Portainer origin, without /api')
+    parser.add_argument('--repository-url', required=True, help='The same clone URL entered in Portainer')
+    parser.add_argument('--credentials-file', required=True, help='Mode 600 JSON: api_key or jwt; optional git: {username,password}')
+    args = parser.parse_args()
+    try:
+        result = check(args.portainer_url, args.repository_url, private_json(args.credentials_file))
+    except (OSError, ValueError):
+        parser.exit(2, 'Invalid URL or private credential file; no credentials were printed.\n')
+    print(json.dumps(result))
+    return 0 if result['success'] else 1
+
+
+if __name__ == '__main__':
+    raise SystemExit(main())

scripts/create-release-manifest.sh

@@ -101,6 +101,7 @@ if [ -z "$FRONTEND_ARCHIVE" ]; then
                 cp -r "$PROJECT_ROOT/$runtime_path" "$RUNTIME_DIR/$runtime_path"
             fi
         done
+        python3 "$PROJECT_ROOT/scripts/check-app-build-contexts.py" "$RUNTIME_DIR"
         # KEEP IN SYNC with the `for unit in [...]` array in
         # core/archipelago/src/bootstrap.rs (run_runtime_assets). A unit that
         # bootstrap installs but this list does not ship simply never reaches a

scripts/iso-smoke-test.sh

@@ -64,6 +64,13 @@ for f in live/vmlinuz live/initrd.img live/filesystem.squashfs \
     fi
 done
 
+# Verify the mounted artifact carries every manifest-declared build source.
+if python3 "$REPO/scripts/check-app-build-contexts.py" "$MNT/archipelago"; then
+    ok "app build contexts and Dockerfiles"
+else
+    bad "incomplete app build payload"
+fi
+
 # ── GRUB must boot the live system ───────────────────────────────────
 if grep -q "boot=live" "$MNT/boot/grub/grub.cfg" 2>/dev/null; then
     ok "grub.cfg has boot=live"

scripts/test-backend-isolated.sh

@@ -9,7 +9,12 @@ command -v setpriv >/dev/null
 sudo -n true || { echo 'Isolated backend tests require noninteractive sudo for systemd namespaces.' >&2; exit 1; }
 metadata=$(mktemp)
 trap 'rm -f "$metadata"' EXIT
-if ! cargo test --manifest-path "$REPO/core/Cargo.toml" -p archipelago --bin archipelago \
+case "${ARCHY_TEST_PACKAGE:-archipelago}" in
+  archipelago) test_target=(-p archipelago --bin archipelago) ;;
+  archipelago-container) test_target=(-p archipelago-container --lib) ;;
+  *) echo 'Unsupported isolated test package' >&2; exit 2 ;;
+esac
+if ! cargo test --manifest-path "$REPO/core/Cargo.toml" "${test_target[@]}" \
   --locked --no-run --message-format=json --config 'profile.test.package.archipelago.opt-level=0' > "$metadata"; then
     python3 - "$metadata" <<'PYDIAG'
 import json,sys

tests/regression/app-build-contexts.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+"""Exercise release payload checks with complete, incomplete and escaping contexts."""
+import importlib.util
+import shutil
+import tempfile
+import unittest
+from pathlib import Path
+
+REPO = Path(__file__).resolve().parents[2]
+spec = importlib.util.spec_from_file_location('contexts', REPO / 'scripts/check-app-build-contexts.py')
+contexts = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(contexts)
+
+
+class BuildPayloadTests(unittest.TestCase):
+    def setUp(self):
+        self.temp = tempfile.TemporaryDirectory()
+        self.addCleanup(self.temp.cleanup)
+        self.root = Path(self.temp.name)
+        shutil.copytree(REPO / 'apps', self.root / 'apps')
+        shutil.copytree(REPO / 'docker', self.root / 'docker')
+
+    def test_complete_payload(self):
+        self.assertGreaterEqual(contexts.check(self.root), 6)
+
+    def test_iso_old_allowlist_rejected(self):
+        shutil.rmtree(self.root / 'docker/archipelago-source')
+        with self.assertRaisesRegex(ValueError, 'archipelago-source.*missing'):
+            contexts.check(self.root)
+
+    def test_missing_dockerfile_rejected(self):
+        (self.root / 'docker/archipelago-source/Dockerfile').unlink()
+        with self.assertRaisesRegex(ValueError, 'archipelago-source.*Dockerfile'):
+            contexts.check(self.root)
+
+    def test_context_symlink_cannot_escape_payload(self):
+        target = self.root / 'docker/archipelago-source'
+        shutil.rmtree(target)
+        target.symlink_to(REPO / 'docker/archipelago-source', target_is_directory=True)
+        with self.assertRaisesRegex(ValueError, 'out-of-payload'):
+            contexts.check(self.root)
+
+    def test_empty_payload_rejected(self):
+        shutil.rmtree(self.root / 'apps')
+        with self.assertRaisesRegex(ValueError, 'No app manifests'):
+            contexts.check(self.root)
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/regression/portainer-git-diagnostics.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+import importlib.util
+import io
+import json
+import pathlib
+import unittest
+import urllib.error
+
+ROOT = pathlib.Path(__file__).resolve().parents[2]
+spec = importlib.util.spec_from_file_location('diagnostic', ROOT / 'scripts/check-portainer-git-source.py')
+m = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(m)
+
+
+class Response(io.BytesIO):
+    pass
+
+
+class FakeAPI:
+    def __init__(self, result=None, error=None):
+        self.result, self.error, self.request = result, error, None
+    def open(self, request, timeout):
+        self.request = request
+        if self.error:
+            raise self.error
+        return Response(json.dumps(self.result).encode())
+
+
+class Diagnostics(unittest.TestCase):
+    def test_server_context_credentials_not_in_url_and_tls_stays_enabled(self):
+        api = FakeAPI({'success': True})
+        result = m.check('http://localhost:9000', 'http://node:3001/user/repo',
+                         {'jwt': 'test-jwt', 'git': {'username': 'test-user', 'password': 'test-secret'}}, api)
+        self.assertTrue(result['success'])
+        self.assertEqual(api.request.full_url, 'http://localhost:9000/api/gitops/sources/test')
+        payload = json.loads(api.request.data)
+        self.assertFalse(payload['tlsSkipVerify'])
+        self.assertEqual(payload['authentication']['password'], 'test-secret')
+        self.assertNotIn('test-secret', json.dumps(result))
+
+    def test_failure_categories_from_source_api(self):
+        cases = [('dial tcp: connection refused', 'connection-refused'),
+                 ('lookup node: no such host', 'dns-failure'),
+                 ('context deadline exceeded', 'timeout'),
+                 ('unexpected content-type text/html', 'proxy-or-login-interception'),
+                 ('authentication required', 'repository-authentication'),
+                 ('x509: certificate signed by unknown authority', 'tls-failure'),
+                 ('repository not found', 'repository-not-found-or-private')]
+        for error, expected in cases:
+            with self.subTest(error=error):
+                result = m.check('http://localhost:9000', 'http://node/repo', {'jwt': 'test'}, FakeAPI({'success': False, 'error': error}))
+                self.assertEqual(result['category'], expected)
+                self.assertFalse(result['success'])
+
+    def test_portainer_auth_is_distinct_from_repository_auth(self):
+        api = FakeAPI(error=urllib.error.HTTPError('http://localhost', 401, 'Unauthorized', {}, None))
+        self.assertEqual(m.check('http://localhost', 'http://node/repo', {'jwt': 'bad'}, api)['category'], 'portainer-authentication')
+
+    def test_html_or_malformed_api_response_never_proves_git_success(self):
+        for value in ({'status': 1}, {'success': 'true'}, [], '<html>login</html>'):
+            self.assertFalse(m.check('http://localhost', 'http://node/repo', {'jwt': 'test'}, FakeAPI(value))['success'])
+
+    def test_credential_urls_rejected_before_request(self):
+        for value in ('http://user:secret@node/repo', 'http://node/repo?token=secret', 'file:///data/repo'):
+            with self.assertRaises(ValueError):
+                m.check('http://localhost', value, {'jwt': 'test'}, FakeAPI())
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/release/run.sh

@@ -71,6 +71,7 @@ summary() {
 # ── Stage 1: static ──────────────────────────────────────────────────
 stage "git-diff-check"   git diff --check
 stage "cargo-fmt"        timeout 240 cargo fmt --manifest-path core/Cargo.toml --all --check
+stage "app-build-contexts" python3 tests/regression/app-build-contexts.py
 stage "manifest-shell"  python3 scripts/check-manifest-shell.py
 stage "doctor-ports" bash tests/regression/container-doctor-ports.sh
 stage "bitcoin-pruning" python3 tests/regression/bitcoin-prune-entrypoint.py