fix: container orchestration stability, AIUI inclusion, lnd-ui port, version 1.3.0

Container stability:
- Merge scan results instead of full replacement (prevents UI flapping)
- Absence threshold: 3 consecutive missed scans before removing from state
- container-list RPC uses cached scanner state for consistency
- Increased Podman API timeout 30s → 60s (scanner + health monitor)
- Keep crashed containers visible as "exited" instead of podman rm -f
- Resolve host-gateway IP via ip route (podman 4.3.x compatibility)

ISO build fixes:
- AIUI web app inclusion: searches 5 paths + CI step to copy from build server
- Claude API proxy: systemctl enable with symlink fallback
- AIUI nginx: try_files =404 (was /aiui/index.html redirect loop)
- Build version set to 1.3.0

Container fixes:
- lnd-ui: nginx listens on 8080 (was 80, Permission denied in rootless)
- first-boot: image-versions.sh sourced from correct path with validation
- first-boot: host-gateway resolved to actual gateway IP

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Dorian
2026-04-02 01:28:11 +01:00
co-authored by Claude Opus 4.6
parent 134de9fe3f
commit c62d7f77b5
13 changed files with 206 additions and 71 deletions
+58 -9
View File
@@ -11,6 +11,7 @@ use crate::state::StateManager;
use anyhow::Result;
use hyper::server::conn::Http;
use hyper::service::service_fn;
use std::collections::HashMap;
use std::net::SocketAddr;
use std::sync::Arc;
use std::time::Duration;
@@ -269,7 +270,10 @@ impl Server {
// Brief delay for containers to stabilize after boot
tokio::time::sleep(Duration::from_secs(3)).await;
info!("🐳 Scanning containers...");
if let Err(e) = scan_and_update_packages(&scanner, &state, identity_clone.as_ref()).await {
// Tracks how many consecutive scans each container has been absent from.
// Prevents UI flapping when podman intermittently returns incomplete results.
let mut absence_tracker: HashMap<String, u32> = HashMap::new();
if let Err(e) = scan_and_update_packages(&scanner, &state, identity_clone.as_ref(), &mut absence_tracker).await {
error!("Failed to scan containers: {}", e);
}
@@ -284,7 +288,7 @@ impl Server {
continue;
}
scanning.store(true, std::sync::atomic::Ordering::Relaxed);
if let Err(e) = scan_and_update_packages(&scanner, &state, identity_clone.as_ref()).await {
if let Err(e) = scan_and_update_packages(&scanner, &state, identity_clone.as_ref(), &mut absence_tracker).await {
error!("Failed to update containers: {}", e);
}
scanning.store(false, std::sync::atomic::Ordering::Relaxed);
@@ -458,15 +462,19 @@ async fn refresh_tor_address(state: &StateManager, identity: &NodeIdentity) -> R
Ok(())
}
/// Number of consecutive absent scans before removing a container from state.
/// 3 scans × 30s = 90 seconds of absence before removal.
const CONTAINER_ABSENCE_THRESHOLD: u32 = 3;
async fn scan_and_update_packages(
scanner: &DockerPackageScanner,
state: &StateManager,
identity: &NodeIdentity,
absence_tracker: &mut HashMap<String, u32>,
) -> Result<()> {
let packages = scanner.scan_containers().await?;
let (current_data, _) = state.get_snapshot().await;
let packages_changed = !packages.is_empty() && current_data.package_data != packages;
let tor_addr = docker_packages::read_tor_address("archipelago").await;
let tor_changed = tor_addr != current_data.server_info.tor_address;
let first_scan = !current_data.server_info.status_info.containers_scanned;
@@ -478,17 +486,58 @@ async fn scan_and_update_packages(
.unwrap_or(false);
let update_changed = update_available != current_data.server_info.status_info.updated;
if packages_changed || tor_changed || first_scan || update_changed {
let mut data = current_data;
if !packages.is_empty() {
data.package_data = packages;
// Empty scan result = podman failure or timeout, preserve existing state
if packages.is_empty() && !first_scan {
if tor_changed || update_changed {
let mut data = current_data;
data.server_info.tor_address = tor_addr.clone();
data.server_info.node_address = tor_addr.as_ref().map(|t| identity.node_address(t));
data.server_info.status_info.updated = update_available;
state.update_data(data).await;
}
return Ok(());
}
// Merge scan results with current state instead of full replacement.
// This prevents containers from vanishing when podman intermittently
// returns incomplete results under heavy load.
let mut merged = current_data.package_data.clone();
let mut changed = false;
// Update/add containers found in this scan
for (id, pkg) in &packages {
absence_tracker.remove(id);
if merged.get(id) != Some(pkg) {
merged.insert(id.clone(), pkg.clone());
changed = true;
}
}
// Track containers in state but missing from this scan.
// Only remove after CONTAINER_ABSENCE_THRESHOLD consecutive absent scans.
let current_ids: Vec<String> = merged.keys().cloned().collect();
for id in current_ids {
if !packages.contains_key(&id) {
let count = absence_tracker.entry(id.clone()).or_insert(0);
*count += 1;
if *count >= CONTAINER_ABSENCE_THRESHOLD {
debug!("Removing {} from state after {} consecutive absent scans", id, count);
merged.remove(&id);
absence_tracker.remove(&id);
changed = true;
}
}
}
if changed || tor_changed || first_scan || update_changed {
let mut data = current_data;
data.package_data = merged;
data.server_info.tor_address = tor_addr.clone();
data.server_info.node_address = tor_addr.as_ref().map(|t| identity.node_address(t));
data.server_info.status_info.containers_scanned = true;
data.server_info.status_info.updated = update_available;
state.update_data(data).await;
debug!("📦 State changed (packages={}, tor={}, first_scan={}, update={}), broadcasting update", packages_changed, tor_changed, first_scan, update_changed);
debug!("📦 State changed (packages={}, tor={}, first_scan={}, update={}), broadcasting update", changed, tor_changed, first_scan, update_changed);
}
Ok(())