fix(apps): preserve lifecycle state and wait for usable launch endpoints

This commit is contained in:
archipelago
2026-09-30 09:10:30 -04:00
parent 27d81e956d
commit 6ac26f637c
26 changed files with 933 additions and 403 deletions
@@ -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>> {
let containers = self.runtime.list_containers().await?;
pub async fn scan_containers(
&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 =
crate::container::app_catalog::available_update_for_app(&app_id, &container.image);
let available_update = if container.id.is_empty() {
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,