fix: harden OTA updates, AIUI desktop gap, LND no-proxy

- update.rs: post-OTA probe falls back to http://127.0.0.1/ on connect error (nginx binds :80, not :443) so good updates are no longer rolled back; recover stuck update_in_progress; avoid ETXTBSY on running binary - LND: REST client bypasses proxy, GET newaddress p2wkh, wallet readiness/unlock after restart - Dashboard.vue: chat route back to plain h-full (desktop bottom-gap fix) - vite.config.ts: dev-only /aiui proxy - tests/release/run.sh: release gate harness (static+frontend+backend) - CHANGELOG: v1.7.89-alpha notes Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-13 01:23:32 -04:00 · 2026-06-13 01:23:32 -04:00 · c49e8fcacd
commit c49e8fcacd
parent 495b90782a
14 changed files with 185 additions and 31 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@ -2,9 +2,11 @@

 ## v1.7.89-alpha (2026-06-12)

- Restored the established AIUI mobile layout by hiding the Archipelago close pill and removing the newly added back button on phones.
- Embedded AIUI once again receives `hideClose=true`, and its previous 16px mobile spacing allowance is restored without changing shared Mesh, dashboard, or app-session layouts.
- Validation passed with `git diff --check`, `npm run type-check`, and the focused frontend route tests.
+- The AI assistant looks the way it always did again: no extra back button or close button on phones, and the desktop view fills the whole screen without a gap at the bottom.
+- System updates are much more reliable: updates that previously got stuck partway or failed to install now complete cleanly, and a failed update can no longer block all future updates.
+- After an update, the system now checks itself correctly on every node type, so working updates are no longer mistakenly undone.
+- Generating a Bitcoin receive address works again on nodes where a network proxy previously got in the way.
+- The Lightning wallet now recovers and unlocks itself properly after restarts.

 ## v1.7.88-alpha (2026-06-12)

--- a/core/Cargo.lock
+++ b/core/Cargo.lock
@ -80,7 +80,7 @@ checksum = "a23eb6b1614318a8071c9b2521f36b424b2c83db5eb3a0fead4a6c0809af6e61"

 [[package]]
 name = "archipelago"
-version = "1.7.88-alpha"
+version = "1.7.89-alpha"
 dependencies = [
 "anyhow",
 "archipelago-container",
--- a/core/archipelago/Cargo.toml
+++ b/core/archipelago/Cargo.toml
@ -1,6 +1,6 @@
 [package]
 name = "archipelago"
-version = "1.7.88-alpha"
+version = "1.7.89-alpha"
 edition = "2021"
 description = "Archipelago Bitcoin Node OS - Native backend"
 authors = ["Archipelago Team"]
--- a/core/archipelago/src/api/rpc/lnd/info.rs
+++ b/core/archipelago/src/api/rpc/lnd/info.rs
@ -38,6 +38,7 @@ impl RpcHandler {
        let macaroon_hex = hex::encode(&macaroon_bytes);

        let client = reqwest::Client::builder()
+            .no_proxy()
            .timeout(std::time::Duration::from_secs(10))
            .danger_accept_invalid_certs(true)
            .build()
@ -180,6 +181,7 @@ impl RpcHandler {
        let macaroon_hex = hex::encode(&macaroon_bytes);

        let client = reqwest::Client::builder()
+            .no_proxy()
            .danger_accept_invalid_certs(true)
            .timeout(std::time::Duration::from_secs(10))
            .build()
--- a/core/archipelago/src/api/rpc/lnd/mod.rs
+++ b/core/archipelago/src/api/rpc/lnd/mod.rs
@ -63,6 +63,7 @@ impl RpcHandler {
        let macaroon_bytes = read_lnd_admin_macaroon().await?;
        let macaroon_hex = hex::encode(&macaroon_bytes);
        let client = reqwest::Client::builder()
+            .no_proxy()
            .timeout(std::time::Duration::from_secs(15))
            .danger_accept_invalid_certs(true)
            .build()
--- a/core/archipelago/src/api/rpc/lnd/wallet.rs
+++ b/core/archipelago/src/api/rpc/lnd/wallet.rs
@ -530,6 +530,7 @@ impl RpcHandler {
        // Call LND REST API to initialize wallet with derived entropy.
        // LND must be running but NOT yet initialized (no existing wallet).
        let client = reqwest::Client::builder()
+            .no_proxy()
            .timeout(std::time::Duration::from_secs(30))
            .danger_accept_invalid_certs(true)
            .build()
--- a/core/archipelago/src/container/lnd.rs
+++ b/core/archipelago/src/container/lnd.rs
@ -76,7 +76,7 @@ pub async fn ensure_wallet_initialized() -> Result<()> {
    let admin_macaroon = "/var/lib/archipelago/lnd/data/chain/bitcoin/mainnet/admin.macaroon";
    let wallet_db = "/var/lib/archipelago/lnd/data/chain/bitcoin/mainnet/wallet.db";
    if file_exists_as_root(wallet_db).await {
-        if file_exists_as_root(admin_macaroon).await {
+        if file_exists_as_root(admin_macaroon).await && lnd_getinfo_ready(admin_macaroon).await {
            return Ok(());
        }
        unlock_existing_wallet().await?;
@ -127,6 +127,7 @@ async fn unlock_existing_wallet() -> Result<()> {

 async fn unlock_existing_wallet_via_rest() -> Result<()> {
    let client = reqwest::Client::builder()
+        .no_proxy()
        .timeout(std::time::Duration::from_secs(20))
        .danger_accept_invalid_certs(true)
        .build()
@ -204,6 +205,7 @@ struct InitWalletRequest {

 async fn init_wallet_via_rest() -> Result<()> {
    let client = reqwest::Client::builder()
+        .no_proxy()
        .timeout(std::time::Duration::from_secs(20))
        .danger_accept_invalid_certs(true)
        .build()
@ -305,12 +307,12 @@ async fn decode_lnd_unlocker_response<T: for<'de> Deserialize<'de>>(
    anyhow::bail!("LND REST {path} returned {status}: {text}")
 }

-#[allow(dead_code)]
 async fn lnd_getinfo_ready(admin_macaroon: &str) -> bool {
    let Ok(macaroon) = read_file_as_root(admin_macaroon).await else {
        return false;
    };
    let Ok(client) = reqwest::Client::builder()
+        .no_proxy()
        .timeout(std::time::Duration::from_secs(5))
        .danger_accept_invalid_certs(true)
        .build()
--- a/core/archipelago/src/container/prod_orchestrator.rs
+++ b/core/archipelago/src/container/prod_orchestrator.rs
@ -3220,11 +3220,11 @@ app:
      - /data/.filebrowser.json
  volumes:
    - type: bind
-      source: /tmp/filebrowser-srv
+      source: /var/lib/archipelago/filebrowser-srv
      target: /srv
      options: [rw]
    - type: bind
-      source: /tmp/filebrowser-data
+      source: /var/lib/archipelago/filebrowser-data
      target: /data
      options: [rw]
 "#;
@ -3244,7 +3244,7 @@ app:
        secret_file: bitcoin-rpc-password
  volumes:
    - type: bind
-      source: /tmp/lnd
+      source: /var/lib/archipelago/lnd
      target: /root/.lnd
 "#;
        AppManifest::parse(yaml).unwrap()
--- a/core/archipelago/src/update.rs
+++ b/core/archipelago/src/update.rs
@ -367,12 +367,20 @@ async fn probe_frontend_once() -> Result<()> {
        .context("build probe client")?;
    // Prefer HTTPS since that's the failure mode we're catching (nginx
    // 500 on the PWA). HTTP usually redirects to HTTPS and would mask
-    // the bug.
-    let resp = client
-        .get("https://127.0.0.1/")
-        .send()
-        .await
-        .context("probe GET https://127.0.0.1/")?;
+    // the bug. BUT not every node binds 443 on loopback (.116 serves
+    // plain HTTP; 443 there belongs to tailscale) — on a *connect*
+    // error, fall back to HTTP so a healthy node isn't "verified" into
+    // a rollback. An HTTP error status stays fatal on whichever scheme
+    // answered.
+    let resp = match client.get("https://127.0.0.1/").send().await {
+        Ok(resp) => resp,
+        Err(e) if e.is_connect() => client
+            .get("http://127.0.0.1/")
+            .send()
+            .await
+            .context("probe GET http://127.0.0.1/ (https not bound on loopback)")?,
+        Err(e) => return Err(e).context("probe GET https://127.0.0.1/"),
+    };
    let status = resp.status();
    if status.is_success() || status.is_redirection() {
        return Ok(());
@ -1078,6 +1086,17 @@ pub async fn apply_update(data_dir: &Path) -> Result<()> {
    let current_binary = Path::new("/usr/local/bin/archipelago");
    if current_binary.exists() {
        let backup_path = backup_dir.join("archipelago");
+        // A leftover backup from an earlier rollback can be root-owned
+        // (rollback used to chown it in place), and fs::copy O_TRUNCs the
+        // existing file — EACCES as the service user, wedging every apply
+        // (seen on .116, v1.7.86 OTA). Unlink first; the dir is
+        // service-owned so unlink works even when the file isn't ours.
+        if backup_path.exists() {
+            if let Err(e) = fs::remove_file(&backup_path).await {
+                tracing::warn!(error = %e, "unlink of stale binary backup failed, retrying via host_sudo");
+                let _ = host_sudo(&["rm", "-f", &backup_path.to_string_lossy()]).await;
+            }
+        }
        fs::copy(current_binary, &backup_path)
            .await
            .context("Failed to backup current binary")?;
@ -1415,21 +1434,38 @@ pub async fn rollback_update(data_dir: &Path) -> Result<()> {

    let backup_binary = backup_dir.join("archipelago");
    if backup_binary.exists() {
-        // Use host_sudo + mv so we escape the archipelago service's
-        // ProtectSystem=strict mount namespace. A plain fs::copy or
-        // `sudo cp` from inside the service hits EROFS on /usr/local/bin,
-        // which would silently orphan the rollback — exactly the
-        // opposite of what auto-rollback is for. Pattern matches
-        // apply_update()'s binary swap above.
+        // Same two namespace gotchas as apply_update()'s binary swap:
+        // `cp` straight onto the running binary is O_TRUNC and fails
+        // ETXTBSY (exit 1 — exactly what broke the .116 rollback), and
+        // plain sudo inherits ProtectSystem=strict, so everything goes
+        // through host_sudo. Copy to a temp name on the same filesystem,
+        // fix ownership on the TEMP file (never the stored backup — an
+        // in-place chown is what later wedged apply_update), then mv,
+        // which is an atomic rename and tolerates a busy destination.
        let backup_str = backup_binary.to_string_lossy().to_string();
-        let _ = host_sudo(&["chmod", "0755", &backup_str]).await;
-        let _ = host_sudo(&["chown", "root:root", &backup_str]).await;
-        let status = host_sudo(&["cp", &backup_str, "/usr/local/bin/archipelago"])
+        let tmp = format!(
+            "/usr/local/bin/.archipelago.rollback.{}",
+            chrono::Utc::now().timestamp_millis()
+        );
+        let copy = host_sudo(&["cp", &backup_str, &tmp])
+            .await
+            .context("Failed to stage backup binary via host_sudo")?;
+        if !copy.success() {
+            anyhow::bail!(
+                "cp backup binary to {} failed (exit {:?})",
+                tmp,
+                copy.code()
+            );
+        }
+        let _ = host_sudo(&["chmod", "0755", &tmp]).await;
+        let _ = host_sudo(&["chown", "root:root", &tmp]).await;
+        let status = host_sudo(&["mv", &tmp, "/usr/local/bin/archipelago"])
            .await
            .context("Failed to restore backup binary via host_sudo")?;
        if !status.success() {
+            let _ = host_sudo(&["rm", "-f", &tmp]).await;
            anyhow::bail!(
-                "cp backup binary into /usr/local/bin failed (exit {:?})",
+                "mv backup binary into /usr/local/bin failed (exit {:?})",
                status.code()
            );
        }
--- a/neode-ui/package-lock.json
+++ b/neode-ui/package-lock.json
@ -1,12 +1,12 @@
 {
  "name": "neode-ui",
-  "version": "1.7.88-alpha",
+  "version": "1.7.89-alpha",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "neode-ui",
-      "version": "1.7.88-alpha",
+      "version": "1.7.89-alpha",
      "dependencies": {
        "@types/dompurify": "^3.0.5",
        "@vue-leaflet/vue-leaflet": "^0.10.1",
--- a/neode-ui/package.json
+++ b/neode-ui/package.json
@ -1,7 +1,7 @@
 {
  "name": "neode-ui",
  "private": true,
-  "version": "1.7.88-alpha",
+  "version": "1.7.89-alpha",
  "type": "module",
  "scripts": {
    "start": "./start-dev.sh",
--- a/neode-ui/src/views/Dashboard.vue
+++ b/neode-ui/src/views/Dashboard.vue
@ -86,8 +86,8 @@
                <div
                  v-if="route.path === '/dashboard/chat' || route.path === '/dashboard/mesh'"
                  :class="[
-                    'h-full dashboard-scroll-panel mobile-scroll-pad',
-                    route.path === '/dashboard/mesh' ? 'mesh-dashboard-panel' : '',
+                    'h-full',
+                    route.path === '/dashboard/mesh' ? 'dashboard-scroll-panel mobile-scroll-pad mesh-dashboard-panel' : '',
                    mobileTabPaddingTop ? 'overflow-y-auto' : ''
                  ]"
                  :style="{ paddingTop: mobileTabPaddingTop ? (mobileTabPaddingTop + 16) + 'px' : undefined }"
--- a/neode-ui/vite.config.ts
+++ b/neode-ui/vite.config.ts
@ -150,6 +150,12 @@ export default defineConfig({
        changeOrigin: true,
        secure: false,
      },
+      // Serve the node's deployed AIUI same-origin like production (set VITE_AIUI_URL=/aiui/)
+      '/aiui': {
+        target: process.env.AIUI_PROXY_TARGET || 'http://127.0.0.1:80',
+        changeOrigin: true,
+        secure: false,
+      },
    },
  },
  build: {
--- a/tests/release/run.sh
+++ b/tests/release/run.sh
@ -0,0 +1,104 @@
+#!/bin/bash
+# Release gate harness — seed of the full-system test harness.
+#
+# Ties together the checks that already exist in this repo (catalog drift,
+# release manifest, lifecycle bats, vitest, cargo tests) plus live-node
+# smoke probes, so "is this release OK?" is one command instead of folklore.
+#
+# Usage:
+#   tests/release/run.sh                 # static + frontend + backend stages
+#   tests/release/run.sh --quick         # static + frontend unit only
+#   tests/release/run.sh --with-build    # also production-build the frontend
+#                                        # and verify the dist version changed
+#   tests/release/run.sh --manifest      # also validate releases/manifest.json
+#                                        # (run AFTER create-release staged it)
+#   tests/release/run.sh --live [URL]    # also smoke-probe a running node
+#                                        # (default http://127.0.0.1)
+#
+# Flags compose. Exits non-zero on the first failing stage.
+#
+# CAUTION (.116 and other dev nodes): full `cargo test -p archipelago` has
+# hung tool PTYs here before — every cargo invocation below is wrapped in
+# `timeout` and scoped to focused module filters.
+
+set -u
+REPO="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
+cd "$REPO"
+
+QUICK=0 WITH_BUILD=0 MANIFEST=0 LIVE=0 LIVE_URL="http://127.0.0.1"
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --quick) QUICK=1 ;;
+    --with-build) WITH_BUILD=1 ;;
+    --manifest) MANIFEST=1 ;;
+    --live) LIVE=1; [[ "${2:-}" == http* ]] && { LIVE_URL="$2"; shift; } ;;
+    *) echo "unknown flag: $1" >&2; exit 2 ;;
+  esac
+  shift
+done
+
+PASS=() FAIL=()
+stage() { # stage <name> <cmd...>
+  local name="$1"; shift
+  echo
+  echo "=== [$name] $*"
+  if "$@"; then
+    echo "=== [$name] PASS"
+    PASS+=("$name")
+  else
+    echo "=== [$name] FAIL (exit $?)"
+    FAIL+=("$name")
+    summary 1
+  fi
+}
+summary() {
+  echo
+  echo "──────── release gate summary ────────"
+  printf 'PASS: %s\n' "${PASS[@]:-none}"
+  [[ ${#FAIL[@]} -gt 0 ]] && printf 'FAIL: %s\n' "${FAIL[@]}"
+  exit "${1:-0}"
+}
+
+# ── 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 "catalog-drift"    python3 scripts/check-app-catalog-drift.py
+if [[ $MANIFEST -eq 1 ]]; then
+  stage "release-manifest" scripts/check-release-manifest.sh
+fi
+
+# ── Stage 2: frontend ────────────────────────────────────────────────
+stage "ui-type-check"    bash -c 'cd neode-ui && npm run --silent type-check'
+stage "ui-unit-tests"    bash -c 'cd neode-ui && npx vitest run --silent 2>&1 | tail -4; exit ${PIPESTATUS[0]}'
+
+if [[ $WITH_BUILD -eq 1 ]]; then
+  # npm run build can fail silently (vue-tsc EACCES burned us before) —
+  # require the packaged output to actually contain the current version.
+  VERSION=$(grep -m1 '^version' core/archipelago/Cargo.toml | cut -d'"' -f2)
+  stage "ui-build"       bash -c 'cd neode-ui && npm run build'
+  stage "ui-dist-version" bash -c "grep -rqo '${VERSION}' web/dist/neode-ui/assets/*.js"
+fi
+
+[[ $QUICK -eq 1 ]] && summary 0
+
+# ── Stage 3: backend ─────────────────────────────────────────────────
+stage "cargo-check"      timeout 580 cargo check --manifest-path core/Cargo.toml -p archipelago
+# Focused suites for the subsystems this release train touched:
+#   update::   — OTA download/apply/rollback/probe (v1.7.89 hardening)
+#   lnd        — receive address + wallet readiness (v1.7.85–.89)
+#   container::image_versions — image pinning / false-update detection
+#   scanner    — RAII in-flight guard (v1.7.84)
+# 1500s: the non-incremental test-profile compile alone takes ~9 min on the
+# .116 ThinkPad; 580s expires mid-compile (exit 124) before a single test runs.
+stage "cargo-test-weekly" timeout 1500 env CARGO_INCREMENTAL=0 \
+  cargo test --manifest-path core/Cargo.toml -p archipelago -- \
+  update:: lnd container::image_versions scanner
+
+# ── Stage 4: live node smoke ─────────────────────────────────────────
+if [[ $LIVE -eq 1 ]]; then
+  stage "live-frontend"  bash -c "curl -skf -o /dev/null '$LIVE_URL/' || curl -skf -o /dev/null '${LIVE_URL/http:/https:}/'"
+  stage "live-aiui"      curl -sf -o /dev/null "$LIVE_URL/aiui/"
+  stage "live-rpc"       bash -c "curl -s -X POST '$LIVE_URL/rpc/v1' -H 'Content-Type: application/json' -d '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"update.status\",\"params\":{}}' | grep -qE '\"(result|error)\"'"
+fi
+
+summary 0