Compare commits

...
9 Commits
14 changed files with 642 additions and 104 deletions
+7
View File
@@ -2,6 +2,13 @@
## Unreleased
## v1.8.21-alpha (2026-09-30)
- Fixed Bitcoin and other containers being forcibly stopped after ten seconds during managed updates and restarts.
- Existing installations now receive the same graceful shutdown allowance as new containers, without restarting apps just to apply this setting.
- Prevented unnecessary Lightning restarts when Bitcoin has stayed running; dependency restarts now require an observed Bitcoin container change.
- Includes the Cashu payment, optional Bitcoin pruning, Lightning readiness, and explorer improvements from 1.8.20.
## v1.8.20-alpha (2026-09-29)
- Fixed Cashu file payments rejected despite a shared mint, and preserved the payment amount when mint fees reduce change.
+1 -1
View File
@@ -104,7 +104,7 @@ dependencies = [
[[package]]
name = "archipelago"
version = "1.8.20-alpha"
version = "1.8.21-alpha"
dependencies = [
"anyhow",
"archipelago-container",
+1 -1
View File
@@ -1,6 +1,6 @@
[package]
name = "archipelago"
version = "1.8.20-alpha"
version = "1.8.21-alpha"
edition = "2021"
license.workspace = true
description = "Archipelago Bitcoin Node OS - Native backend"
@@ -1174,15 +1174,21 @@ impl ReconcileReport {
fn cascade_pairs_for_report<'r>(
report: &'r ReconcileReport,
user_stopped: &std::collections::HashSet<String>,
changed_backends: &HashSet<String>,
) -> Vec<(&'r str, &'static str)> {
let mut pairs = Vec::new();
for (backend, action) in &report.actions {
if !matches!(
action,
ReconcileAction::Installed | ReconcileAction::Started
ReconcileAction::NoOp | ReconcileAction::Started | ReconcileAction::Installed
) {
continue;
}
// A successful systemctl start can be a no-op after a transient
// Podman inspect failure. Require a witnessed lifecycle change.
if !changed_backends.contains(backend) {
continue;
}
for dep in crate::app_ops::address_caching_dependents(backend) {
let dep_untouched = report
.actions
@@ -1196,6 +1202,25 @@ fn cascade_pairs_for_report<'r>(
pairs
}
/// Only positive runtime evidence permits disrupting an address-caching wallet.
/// A known absent/stopped backend becoming running, a new container ID, or a
/// changed start timestamp qualifies. A failed observation never does.
fn backend_instance_changed(before: Option<&ContainerStatus>, after: &ContainerStatus) -> bool {
if after.state != ContainerState::Running || after.id.is_empty() {
return false;
}
let Some(before) = before else {
return true;
};
if before.id.is_empty() {
return false;
}
if before.id != after.id || before.state != ContainerState::Running {
return true;
}
matches!((&before.started_at, &after.started_at), (Some(a), Some(b)) if !a.is_empty() && !b.is_empty() && a != b)
}
#[derive(Debug, Default)]
pub struct AdoptionReport {
pub adopted: Vec<String>,
@@ -1909,12 +1934,33 @@ impl ProdContainerOrchestrator {
_ => 2,
});
// Live container names (any state), for the same recovery check.
let present_containers: std::collections::HashSet<String> = self
.runtime
.list_containers()
.await
.map(|cs| cs.into_iter().map(|c| c.name).collect())
let listed_containers = self.runtime.list_containers().await.ok();
let present_containers: HashSet<String> = listed_containers
.as_ref()
.map(|cs| cs.iter().map(|c| c.name.clone()).collect())
.unwrap_or_default();
// Keep unknown distinct from confirmed absence. Runtime queries can
// fail under load while systemd still has a healthy running backend.
let mut backend_before: HashMap<String, Option<ContainerStatus>> = HashMap::new();
for lm in &manifests {
let id = &lm.manifest.app.id;
if crate::app_ops::address_caching_dependents(id).is_empty() {
continue;
}
let name = compute_container_name(&lm.manifest);
match self.runtime.get_container_status(&name).await {
Ok(status) => {
backend_before.insert(id.clone(), Some(status));
}
Err(_) if listed_containers.is_some() && !present_containers.contains(&name) => {
backend_before.insert(id.clone(), None);
}
Err(err) => {
tracing::warn!(backend = %id, error = %err,
"cannot observe backend before reconcile; will not infer a dependency restart from an action report");
}
}
}
let mut report = ReconcileReport::default();
let disk_gb = self.disk_gb().await;
let bitcoin_pruned = disk_gb < ARCHIVAL_BITCOIN_DISK_GB
@@ -2096,7 +2142,20 @@ impl ProdContainerOrchestrator {
// state recovery, repair recreate, boot InstallMissing) moves the
// address behind a running dependent's back — §C "restart lnd after
// ANY bitcoin recreate".
for (backend, dep) in cascade_pairs_for_report(&report, &user_stopped) {
let mut changed_backends = HashSet::new();
for (backend, before) in &backend_before {
let Some(name) = container_name_by_app_id.get(backend) else {
continue;
};
if let Ok(after) = self.runtime.get_container_status(name).await {
if backend_instance_changed(before.as_ref(), &after) {
changed_backends.insert(backend.clone());
}
}
}
// A user stop during a slow reconcile pass still takes precedence.
let user_stopped = crate::crash_recovery::load_user_stopped(&self.data_dir).await;
for (backend, dep) in cascade_pairs_for_report(&report, &user_stopped, &changed_backends) {
// Same rule as the RPC cascade: hold the dependent's op lock
// across the restart; skip when a worker is mid-sequence.
let lock = crate::app_ops::op_lock(dep);
@@ -6409,6 +6468,67 @@ app:
);
}
#[test]
fn backend_cascade_requires_observed_instance_change() {
let running = ContainerStatus {
id: "container-1".into(),
name: "bitcoin-core".into(),
state: ContainerState::Running,
started_at: Some("start-1".into()),
health: None,
exit_code: None,
image: "bitcoin:1".into(),
created: "created-1".into(),
ports: vec![],
lan_address: None,
};
assert!(!backend_instance_changed(Some(&running), &running));
assert!(backend_instance_changed(None, &running));
let mut before = running.clone();
before.state = ContainerState::Exited;
assert!(backend_instance_changed(Some(&before), &running));
before = running.clone();
before.id = "old-container".into();
assert!(backend_instance_changed(Some(&before), &running));
before = running.clone();
before.started_at = Some("earlier-start".into());
assert!(backend_instance_changed(Some(&before), &running));
before.started_at = None;
assert!(!backend_instance_changed(Some(&before), &running));
before.id.clear();
assert!(!backend_instance_changed(Some(&before), &running));
let mut after = running.clone();
after.state = ContainerState::Exited;
assert!(!backend_instance_changed(None, &after));
after = running.clone();
after.id.clear();
assert!(!backend_instance_changed(None, &after));
}
#[test]
fn cascade_ignores_false_started_report_but_detects_real_exec_drift() {
let none = HashSet::new();
let mut report = ReconcileReport {
actions: vec![
("bitcoin-core".into(), ReconcileAction::Started),
("lnd".into(), ReconcileAction::NoOp),
],
failures: vec![],
};
// systemctl start of an already active unit does not move its address.
assert!(cascade_pairs_for_report(&report, &none, &none).is_empty());
// A unit exec rewrite can restart Bitcoin while the outer reconcile
// action remains NoOp. Runtime evidence still requires LND to reconnect.
let changed = ["bitcoin-core".into()].into();
report.actions[0].1 = ReconcileAction::NoOp;
assert_eq!(
cascade_pairs_for_report(&report, &none, &changed),
vec![("bitcoin-core", "lnd")]
);
report.actions[0].1 = ReconcileAction::Left("lifecycle-op-in-flight".into());
assert!(cascade_pairs_for_report(&report, &none, &changed).is_empty());
}
#[test]
fn cascade_pairs_cover_backend_recreate_with_running_dependent() {
use std::collections::HashSet;
@@ -6420,6 +6540,7 @@ app:
failures: vec![],
};
let none = HashSet::new();
let changed: HashSet<String> = ["bitcoin-core".into(), "bitcoin-knots".into()].into();
// Backend recreated while lnd sat running (NoOp) → cascade.
let r = report(vec![
@@ -6427,7 +6548,7 @@ app:
("lnd", ReconcileAction::NoOp),
]);
assert_eq!(
cascade_pairs_for_report(&r, &none),
cascade_pairs_for_report(&r, &none, &changed),
vec![("bitcoin-knots", "lnd")]
);
@@ -6437,7 +6558,7 @@ app:
("lnd", ReconcileAction::NoOp),
]);
assert_eq!(
cascade_pairs_for_report(&r, &none),
cascade_pairs_for_report(&r, &none, &changed),
vec![("bitcoin-core", "lnd")]
);
@@ -6446,7 +6567,7 @@ app:
("bitcoin-knots", ReconcileAction::NoOp),
("lnd", ReconcileAction::NoOp),
]);
assert!(cascade_pairs_for_report(&r, &none).is_empty());
assert!(cascade_pairs_for_report(&r, &none, &none).is_empty());
// Dependent itself (re)started this pass → it already resolved the
// fresh address; no cascade.
@@ -6454,7 +6575,7 @@ app:
("bitcoin-knots", ReconcileAction::Installed),
("lnd", ReconcileAction::Started),
]);
assert!(cascade_pairs_for_report(&r, &none).is_empty());
assert!(cascade_pairs_for_report(&r, &none, &changed).is_empty());
// User-stopped dependent is never bounced.
let r = report(vec![
@@ -6462,14 +6583,14 @@ app:
("lnd", ReconcileAction::NoOp),
]);
let stopped: HashSet<String> = ["lnd".to_string()].into();
assert!(cascade_pairs_for_report(&r, &stopped).is_empty());
assert!(cascade_pairs_for_report(&r, &stopped, &changed).is_empty());
// Non-backend recreates don't cascade anything.
let r = report(vec![
("grafana", ReconcileAction::Installed),
("lnd", ReconcileAction::NoOp),
]);
assert!(cascade_pairs_for_report(&r, &none).is_empty());
assert!(cascade_pairs_for_report(&r, &none, &changed).is_empty());
}
#[tokio::test]
+155 -5
View File
@@ -184,6 +184,7 @@ pub struct QuadletUnit {
pub no_new_privileges: bool,
pub cpu_quota: Option<u32>,
pub restart_policy: RestartPolicy,
pub stop_grace_secs: Option<u64>,
}
impl QuadletUnit {
@@ -216,6 +217,10 @@ impl QuadletUnit {
let _ = writeln!(s, "[Container]");
let _ = writeln!(s, "ContainerName={}", self.name);
let _ = writeln!(s, "Image={}", self.image);
let grace = self
.stop_grace_secs
.unwrap_or_else(|| archipelago_container::runtime::stop_grace_secs_for(&self.name));
let _ = writeln!(s, "StopTimeout={grace}");
// Pull=never: companions are pre-pulled or built. A missing image
// must surface as a unit start failure, not a silent retry storm.
let _ = writeln!(s, "Pull=never");
@@ -350,6 +355,15 @@ impl QuadletUnit {
// the unit stuck in deactivating. Health/status remains app-level state,
// not a systemd start gate.
let _ = writeln!(s, "TimeoutStartSec=0");
let _ = writeln!(s, "TimeoutStopSec={}", grace.saturating_add(15));
// Stop explicitly before Quadlet's generated `podman rm -f`. The
// existing container may still carry Podman's old 10-second default;
// StopTimeout alone only protects containers created after migration.
let _ = writeln!(s, "ExecStop=");
let _ = writeln!(
s,
"ExecStop=/usr/bin/podman stop --ignore --time={grace} --cidfile=%t/%N.cid"
);
// Restart policy + 10s backoff. RestartSec keeps a crash-loop
// from saturating the journal. Companions: Always. Backends:
// OnFailure (clean stops stay stopped).
@@ -525,6 +539,9 @@ impl QuadletUnit {
// Always, not OnFailure: with quadlet's `--rm`, OnFailure left a
// cleanly-exited app deleted and unrestarted. See RestartPolicy.
restart_policy: RestartPolicy::Always,
stop_grace_secs: Some(super::prod_orchestrator::resolve_stop_grace_secs(
manifest, name,
)),
}
}
}
@@ -792,7 +809,11 @@ pub async fn stop_service(service: &str) -> Result<()> {
/// corruption — so the orchestrator passes the per-app grace here. Never waits
/// less than `QUADLET_STOP_TIMEOUT`.
pub async fn stop_service_with_timeout(service: &str, timeout: Duration) -> Result<()> {
let timeout = timeout.max(QUADLET_STOP_TIMEOUT);
let name = service.strip_suffix(".service").unwrap_or(service);
let body = fs::read_to_string(unit_dir().await?.join(format!("{name}.container")))
.await
.unwrap_or_default();
let timeout = timeout.max(stop_wait_timeout(name, &body));
match systemctl_user_status(&["stop", service], timeout).await {
Ok(status) if status.success() => Ok(()),
Ok(status) => Err(anyhow!("systemctl --user stop {service} exited {status}")),
@@ -813,6 +834,20 @@ pub async fn stop_service_with_timeout(service: &str, timeout: Duration) -> Resu
}
}
/// The command waiter must outlive both the container grace and systemd's
/// stop deadline. Restart/repair callers must not kill Bitcoin at 45 seconds.
fn stop_wait_timeout(name: &str, unit_body: &str) -> Duration {
Duration::from_secs(stop_grace_from_unit(name, unit_body).saturating_add(30))
.max(QUADLET_STOP_TIMEOUT)
}
fn stop_grace_from_unit(name: &str, unit_body: &str) -> u64 {
directive_values(unit_body, "StopTimeout=")
.last()
.and_then(|value| value.parse::<u64>().ok())
.unwrap_or_else(|| archipelago_container::runtime::stop_grace_secs_for(name))
}
async fn systemctl_user_status(
args: &[&str],
timeout: Duration,
@@ -939,6 +974,10 @@ fn directive_values(unit_body: &str, prefix: &str) -> Vec<String> {
/// that systemd no longer knows about.
pub async fn disable_remove(unit_name: &str, dir: &Path) -> Result<()> {
let svc = format!("{unit_name}.service");
let path = dir.join(format!("{unit_name}.container"));
let body = fs::read_to_string(&path).await.unwrap_or_default();
let timeout = stop_wait_timeout(unit_name, &body);
let grace = stop_grace_from_unit(unit_name, &body).to_string();
// Stop first; ignore failure (unit may already be down). BOUNDED — on
// rootless podman a generated unit can wedge in "deactivating" while
// `podman rm -f` hangs underneath it, and an unbounded `systemctl stop`
@@ -946,13 +985,12 @@ pub async fn disable_remove(unit_name: &str, dir: &Path) -> Result<()> {
// the package entry is stranded in `Removing` (a ghost in My Apps that also
// blocks reinstall). If the graceful stop times out, escalate to
// SIGKILL + reset-failed so teardown always proceeds.
if systemctl_user_status(&["stop", &svc], QUADLET_STOP_TIMEOUT)
if systemctl_user_status(&["stop", &svc], timeout)
.await
.is_err()
{
let _ = kill_and_reset_service(&svc).await;
}
let path = dir.join(format!("{unit_name}.container"));
if fs::try_exists(&path).await.unwrap_or(false) {
match fs::remove_file(&path).await {
Ok(()) => {}
@@ -965,9 +1003,9 @@ pub async fn disable_remove(unit_name: &str, dir: &Path) -> Result<()> {
// Bounded so a hung podman store can't re-introduce the stall this function
// exists to avoid.
let _ = tokio::time::timeout(
QUADLET_STOP_TIMEOUT,
timeout,
Command::new("podman")
.args(["rm", "-f", unit_name])
.args(["rm", "-f", "--ignore", "--time", &grace, unit_name])
.status(),
)
.await;
@@ -992,6 +1030,118 @@ mod tests {
use super::*;
use tempfile::tempdir;
#[test]
fn shutdown_grace_covers_container_systemd_and_caller() {
for (name, grace) in [
("bitcoin-core", 600),
("bitcoin-knots", 600),
("lnd", 330),
("electrumx", 300),
("other", 30),
] {
let unit = QuadletUnit {
name: name.into(),
..Default::default()
};
let body = unit.render();
assert!(body.contains(&format!("StopTimeout={grace}\n")));
assert!(body.contains(&format!("TimeoutStopSec={}\n", grace + 15)));
assert!(body.contains(&format!("podman stop --ignore --time={grace} --cidfile=")));
assert_eq!(
stop_wait_timeout(name, &body),
Duration::from_secs(grace + 30)
);
// Legacy units have no StopTimeout directive yet.
assert_eq!(stop_wait_timeout(name, ""), Duration::from_secs(grace + 30));
}
}
#[test]
fn custom_stop_grace_survives_render_and_restart_budget() {
let manifest: AppManifest = serde_yaml::from_str(
r#"
app:
id: custom-db
name: Custom database
version: 1.0.0
stop_grace_secs: 900
container:
image: example/db:1
"#,
)
.unwrap();
let unit = QuadletUnit::from_manifest(&manifest, "custom-db");
assert_eq!(unit.stop_grace_secs, Some(900));
assert_eq!(
stop_wait_timeout("custom-db", &unit.render()),
Duration::from_secs(930)
);
assert_eq!(
stop_wait_timeout("lnd", "StopTimeout=invalid"),
Duration::from_secs(360)
);
}
#[test]
fn stop_grace_migration_does_not_request_an_execution_restart() {
let unit = sample_unit();
let new = unit.render();
let old = new
.lines()
.filter(|line| {
!line.starts_with("StopTimeout=")
&& !line.starts_with("TimeoutStopSec=")
&& !line.starts_with("ExecStop=")
})
.collect::<Vec<_>>()
.join("\n");
assert!(!exec_changed(&old, &new));
assert!(!publish_ports_changed(&old, &new));
assert!(!network_aliases_changed(&old, &new));
assert!(!health_cmd_changed(&old, &new));
}
#[test]
fn actual_quadlet_generator_stops_before_forced_removal() {
let generator = Path::new("/usr/lib/systemd/system-generators/podman-system-generator");
if !generator.exists() {
eprintln!(
"Quadlet generator unavailable; run this regression on the Linux release host"
);
return;
}
let dir = tempdir().unwrap();
let unit = QuadletUnit {
name: "grace-test".into(),
image: "localhost/test:latest".into(),
stop_grace_secs: Some(600),
..Default::default()
};
std::fs::write(dir.path().join("grace-test.container"), unit.render()).unwrap();
let output = std::process::Command::new(generator)
.args(["--user", "--dryrun"])
.env("QUADLET_UNIT_DIRS", dir.path())
.output()
.unwrap();
assert!(
output.status.success(),
"{}",
String::from_utf8_lossy(&output.stderr)
);
let generated = String::from_utf8_lossy(&output.stdout).to_string()
+ &String::from_utf8_lossy(&output.stderr);
let stop = generated
.find("ExecStop=/usr/bin/podman stop --ignore --time=600")
.unwrap();
let remove = generated.find("ExecStop=/usr/bin/podman rm ").unwrap();
assert!(
stop < remove,
"Legacy container must stop gracefully before removal"
);
assert!(generated.contains("--stop-timeout 600"));
assert!(generated.contains("TimeoutStopSec=615"));
}
#[test]
fn render_emits_secret_env_by_reference_never_value() {
let u = QuadletUnit {
+41 -13
View File
@@ -3,29 +3,57 @@
Working backlog of forward-looking items not yet scoped into a dedicated plan
doc. See [`ROADMAP.md`](ROADMAP.md) for the curated, public-facing direction.
## Blocking incident — before unrelated work
## Framework incident — closed with operator acceptance
- **OPEN: Framework LND startup / missing Receive address / false zero balance.**
User requires investigation and a verified fix on the actual node before later
unrelated work. Startup and native balances were verified on the actual node;
final display confirmation is pending. See the incident record for evidence.
- **CLOSED WITH OPERATOR ACCEPTANCE (2026-09-30): Framework LND startup /
missing Receive address / false zero balance.** Startup, native balances,
Cashu address and source integration were verified; the operator accepted the
remaining display check and authorized release. See the incident record for evidence.
See [incident evidence and closure criteria](incident-framework-lnd-startup.md)
and the repository `AGENTS.md` session-start instructions.
## Current repair and release tasks — 2026-09-29
## Next release after 1.8.21 — reported 2026-09-30
Release is blocked until these pass; see [execution record](repair-release-20260929.md).
- [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
Brave. Reproduce on the X250's kiosk engine and record its version, display
scale and resolution. Inspect the native `<select>` in
`neode-ui/src/components/InstallVersionModal.vue`, its option colors, and the
scroll/stacking behavior in `BaseModal.vue`; these are investigation leads,
not a confirmed cause. Fix contrast and popup visibility without changing
version selection or pruning behavior. Validate Core and Knots, open/closed
and scrolled dropdowns, keyboard/touch selection, and pruning on/off on the
actual kiosk, with remote Brave and mobile regression checks. Browser mocks
alone do not establish that the kiosk rendering is fixed. Track for the next
release; the signed 1.8.21 artifacts remain unchanged.
- [ ] Fix Cashu paid-file redemption between dev and Shorty; test keyset IDs,
## 1.8.21 repair and release tasks — completed 2026-09-30
See the [execution record](repair-release-20260929.md) for evidence and limits.
- [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.
- [ ] Replace the unavailable tx1138.com explorer default with mempool.space;
- [x] Record Framework verification and the operator's acceptance of the
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)
+113
View File
@@ -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.
+138
View File
@@ -257,3 +257,141 @@ Both catalog and OTA signatures verify against the pinned release root. Staged
artifact hash/size checks and catalog drift/trust checks pass. User accepted the
remaining Framework display check and explicitly authorized release. Publication
and ISO build may proceed; do not regenerate the signed manifest or artifacts.
### Published OTA; ISO withheld after live shutdown defect — 2026-09-30
Signed 1.8.20 OTA/catalog published to git and ngit, with public asset hashes
verified. Catalog rollout triggered a Bitcoin command update at 08:34 UTC.
Although the orchestrator allowed a long stop, Quadlet's generated Podman removal
still used its ten-second default and killed Bitcoin. Core replayed its block
index; LND later lost its connection to the previous Bitcoin container IP.
Stopped the ISO build and queued boot check; any partial 1.8.20 ISO is invalid
and must not be published. Preparing 1.8.21 to supersede the immutable signed OTA.
Installed explicit graceful-stop systemd overrides on dev and Shorty without
restarting native services. Candidate Quadlet fix adds per-app container, systemd,
and command-wait budgets, including existing containers and uninstall fallback.
Focused 43 tests pass, including actual Quadlet generator stop-before-remove order.
Full tests, disposable slow-stop verification, build and deployment remain pending.
Disposable live regression passed: started an Alpine container with its legacy
ten-second stop setting, rewrote and reloaded its Quadlet with explicit twenty-
second graceful stop, verified the same container ID and old internal timeout
remained running, then stopped it. Its twelve-second shutdown handler completed
in 12.6 seconds, emitted the completion marker, and exited without SIGKILL/137.
Fixture had no network or wallet mounts and was removed afterward.
Core finished index loading and resumed unpruned initial sync. LND automatically
unlocked at 08:47 UTC. The existing backend-address cascade then performed a
graceful LND restart at 08:57 UTC after Bitcoin reconciliation completed; LND
automatically unlocked again and reached chain-sync waiting. No manual wallet
unlock or restart was used for this recovery.
### False dependency restart exposed during monitoring — 09:08 UTC
The initial 1.8.21 candidate passed all 1,557 isolated backend tests and 1,120
frontend tests. Monitoring nevertheless found another managed LND restart at
09:08:32 while Bitcoin's container/start timestamp remained unchanged. Management
logs explicitly attribute it to the backend-address cascade. This also makes
the earlier 08:57 cascade suspect; it must not be described as a proven necessary
restart. These service restarts preceded the isolated test executable, whose
namespace boundaries remain intact.
The cascade trusted Started/Installed action reports. A failed runtime inspection
followed by successful systemctl start of an already active unit can produce
Started without changing Bitcoin. Dependency restarts now require observed
container-ID, running-state, or start-time changes. Failed observations remain
unknown, not absence; a known absent backend becoming running still qualifies.
Actual exec-drift restarts are recognized even when their outer report is NoOp.
Stopped/lifecycle-in-flight dependents remain excluded, and user stop markers
are re-read after the potentially slow pass. Added runtime-observation and
false-action/real-exec-drift regression cases; full isolated rerun pending.
Stopped the first optimized build and preparing new artifacts from this correction.
### Final 1.8.21 artifacts and live verification — 2026-09-30
Source and frontend/AIUI attribution: c993d9dd. Full isolated backend suite:
1,559 passed, zero failed, four existing hardware/live tests ignored. Frontend
suite: 1,120 passed; final production type-check/build passed after the last
release-note-only edit. Optimized backend built in 13m22s.
Staged unsigned 1.8.21 OTA manifest and artifacts:
- Backend: 64,748,176 bytes; SHA256
ff602e85f340aff7e43d9d94f7f84f11f713735c964c0d8ba150e23b065c30eb.
- Frontend archive: 97,152,546 bytes; SHA256
6c0842ec83a440269a353808a4cf154174f5232c9989b4a5448bc6486e1d0620.
Artifact validator passed. Actual archive has flat paths, readable root index,
and exact fresh AIUI, doctor and LND UI payload bytes. Exact files deployed to
dev at 09:32 UTC and Shorty at 09:35 UTC; rollback binaries and dashboards under
root-only /var/lib/archipelago/support/release-1821 on each node. Only management
services restarted. Existing Bitcoin/Core-or-Knots and native LND container IDs
and start times were preserved. Correct generated graceful-stop commands are
present before forced removal on both nodes; temporary grace overrides removed.
Dev systemd deadlines are 615 seconds for Bitcoin and 345 seconds for LND.
Desktop/mobile Lightning UI checks passed again: waiting for Bitcoin sync,
unknown balance, no unavailable native RPC requests. Served dashboard and AIUI
attribution bytes match the release. Native LND states: dev RPC_ACTIVE while
Bitcoin syncs; Shorty SERVER_ACTIVE. Dev completed full reconciliation passes
at 09:34:21 and 09:36:40 with Bitcoin/LND NoOp, and no dependency restart.
Shorty's first full pass completed 09:36:55 with Knots/LND NoOp.
Final paid-file check on these exact binaries passed: fresh one-sat dev-to-Shorty
purchase, exact one-sat refund on underpayment, identical response aliases,
correct Files copy, and zero-charge cached repeat. Removed temporary seller
entries/files and Files copy; retained purchase audit and owned cache. Total net
transfer across all three live payment rounds in this repair session: three sats.
Remaining: finish Shorty observation and remove temporary diagnostic logging;
user-local 1.8.21 OTA signature (existing catalog signature remains valid),
publish git/ngit, build/boot-test/sign and publish the raw 1.8.21 ISO.
No 1.8.21 release tag or public OTA yet. Do not publish the quarantined partial
1.8.20 ISO. The existing 1.8.20 git/ngit release notes now explain the withheld ISO
and pending hotfix; signed 1.8.20 assets remain immutable.
Shorty's second clean full pass completed at 09:38:06 UTC. Removed temporary
diagnostic logging on both nodes and restarted only management again; native
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.
+2 -2
View File
@@ -1,12 +1,12 @@
{
"name": "neode-ui",
"version": "1.8.19-alpha",
"version": "1.8.21-alpha",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "neode-ui",
"version": "1.8.19-alpha",
"version": "1.8.21-alpha",
"dependencies": {
"@scure/bip39": "^2.2.0",
"@types/dompurify": "^3.0.5",
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "neode-ui",
"private": true,
"version": "1.8.20-alpha",
"version": "1.8.21-alpha",
"type": "module",
"scripts": {
"start": "./start-dev.sh",
@@ -362,6 +362,19 @@ init()
</button>
</div>
<div class="overflow-y-auto flex-1 min-h-0 space-y-6 pr-1">
<!-- v1.8.21-alpha -->
<div>
<div class="flex items-center gap-2 mb-3">
<span class="text-xs font-mono px-2 py-0.5 rounded bg-orange-500/20 text-orange-300">v1.8.21-alpha</span>
<span class="text-xs text-white/40">September 30, 2026</span>
</div>
<div class="space-y-3 text-sm text-white/80 pl-3 border-l border-white/10">
<p>Fixed Bitcoin and other containers being forcibly stopped after ten seconds during managed updates and restarts.</p>
<p>Existing installations now receive the same graceful shutdown allowance as new containers, without restarting apps just to apply this setting.</p>
<p>Prevented unnecessary Lightning restarts when Bitcoin has stayed running; dependency restarts now require an observed Bitcoin container change.</p>
<p>Includes the Cashu payment, optional Bitcoin pruning, Lightning readiness, and explorer improvements from 1.8.20.</p>
</div>
</div>
<!-- v1.8.20-alpha -->
<div>
<div class="flex items-center gap-2 mb-3">
+18 -17
View File
@@ -1,29 +1,30 @@
{
"changelog": [
"Fixed the embedded AIUI chat page painting a second background and dark scrim over Archy’s dashboard background.",
"Embedded AIUI now stays transparent so the dashboard background appears once.",
"AIUI background fixes are now included reliably in OTA updates and fresh installations."
"Fixed Bitcoin and other containers being forcibly stopped after ten seconds during managed updates and restarts.",
"Existing installations now receive the same graceful shutdown allowance as new containers, without restarting apps just to apply this setting.",
"Prevented unnecessary Lightning restarts when Bitcoin has stayed running; dependency restarts now require an observed Bitcoin container change.",
"Includes the Cashu payment, optional Bitcoin pruning, Lightning readiness, and explorer improvements from 1.8.20."
],
"components": [
{
"current_version": "1.8.19-alpha",
"download_url": "https://source.archipelago-foundation.org/lfg2025/archy/releases/download/v1.8.19-alpha/archipelago",
"current_version": "1.8.21-alpha",
"download_url": "https://source.archipelago-foundation.org/lfg2025/archy/releases/download/v1.8.21-alpha/archipelago",
"name": "archipelago",
"new_version": "1.8.19-alpha",
"sha256": "bb500d02567ad16179179d43138cc6fdafee680835262026eeaa7d1bc8cdd307",
"size_bytes": 64495784
"new_version": "1.8.21-alpha",
"sha256": "ff602e85f340aff7e43d9d94f7f84f11f713735c964c0d8ba150e23b065c30eb",
"size_bytes": 64748176
},
{
"current_version": "1.8.19-alpha",
"download_url": "https://source.archipelago-foundation.org/lfg2025/archy/releases/download/v1.8.19-alpha/archipelago-frontend-1.8.19-alpha.tar.gz",
"name": "archipelago-frontend-1.8.19-alpha.tar.gz",
"new_version": "1.8.19-alpha",
"sha256": "fbbaa237e2ea4e9e576dda9b15fdcf3c59c40bc55bfee4ebbea303b0172fc49b",
"size_bytes": 97142031
"current_version": "1.8.21-alpha",
"download_url": "https://source.archipelago-foundation.org/lfg2025/archy/releases/download/v1.8.21-alpha/archipelago-frontend-1.8.21-alpha.tar.gz",
"name": "archipelago-frontend-1.8.21-alpha.tar.gz",
"new_version": "1.8.21-alpha",
"sha256": "6c0842ec83a440269a353808a4cf154174f5232c9989b4a5448bc6486e1d0620",
"size_bytes": 97152546
}
],
"release_date": "2026-09-28",
"signature": "4da9bf766d94c2de6641619a36663106791c7a1d342b729c666662cdde1feabdf11c51994c1cbbe2a0e2b270c316d77763435e976ce22730855b3822bc9d390a",
"release_date": "2026-09-30",
"signature": "2ba21dde08284a13f511f11f0b925f09a56c1b36e40424558601b9ab6beea17edfa316e0baa51474bf084fd4da25429ec35a77d9a831554b309845c8226d4f0d",
"signed_by": "did:key:z6Mkfu5LT8d4DjETtrkATvHh9Dvcbnr7zBCUwfau8Sw7DLWT",
"version": "1.8.19-alpha"
"version": "1.8.21-alpha"
}
+18 -17
View File
@@ -1,29 +1,30 @@
{
"changelog": [
"Fixed the embedded AIUI chat page painting a second background and dark scrim over Archy’s dashboard background.",
"Embedded AIUI now stays transparent so the dashboard background appears once.",
"AIUI background fixes are now included reliably in OTA updates and fresh installations."
"Fixed Bitcoin and other containers being forcibly stopped after ten seconds during managed updates and restarts.",
"Existing installations now receive the same graceful shutdown allowance as new containers, without restarting apps just to apply this setting.",
"Prevented unnecessary Lightning restarts when Bitcoin has stayed running; dependency restarts now require an observed Bitcoin container change.",
"Includes the Cashu payment, optional Bitcoin pruning, Lightning readiness, and explorer improvements from 1.8.20."
],
"components": [
{
"current_version": "1.8.19-alpha",
"download_url": "https://source.archipelago-foundation.org/lfg2025/archy/releases/download/v1.8.19-alpha/archipelago",
"current_version": "1.8.21-alpha",
"download_url": "https://source.archipelago-foundation.org/lfg2025/archy/releases/download/v1.8.21-alpha/archipelago",
"name": "archipelago",
"new_version": "1.8.19-alpha",
"sha256": "bb500d02567ad16179179d43138cc6fdafee680835262026eeaa7d1bc8cdd307",
"size_bytes": 64495784
"new_version": "1.8.21-alpha",
"sha256": "ff602e85f340aff7e43d9d94f7f84f11f713735c964c0d8ba150e23b065c30eb",
"size_bytes": 64748176
},
{
"current_version": "1.8.19-alpha",
"download_url": "https://source.archipelago-foundation.org/lfg2025/archy/releases/download/v1.8.19-alpha/archipelago-frontend-1.8.19-alpha.tar.gz",
"name": "archipelago-frontend-1.8.19-alpha.tar.gz",
"new_version": "1.8.19-alpha",
"sha256": "fbbaa237e2ea4e9e576dda9b15fdcf3c59c40bc55bfee4ebbea303b0172fc49b",
"size_bytes": 97142031
"current_version": "1.8.21-alpha",
"download_url": "https://source.archipelago-foundation.org/lfg2025/archy/releases/download/v1.8.21-alpha/archipelago-frontend-1.8.21-alpha.tar.gz",
"name": "archipelago-frontend-1.8.21-alpha.tar.gz",
"new_version": "1.8.21-alpha",
"sha256": "6c0842ec83a440269a353808a4cf154174f5232c9989b4a5448bc6486e1d0620",
"size_bytes": 97152546
}
],
"release_date": "2026-09-28",
"signature": "4da9bf766d94c2de6641619a36663106791c7a1d342b729c666662cdde1feabdf11c51994c1cbbe2a0e2b270c316d77763435e976ce22730855b3822bc9d390a",
"release_date": "2026-09-30",
"signature": "2ba21dde08284a13f511f11f0b925f09a56c1b36e40424558601b9ab6beea17edfa316e0baa51474bf084fd4da25429ec35a77d9a831554b309845c8226d4f0d",
"signed_by": "did:key:z6Mkfu5LT8d4DjETtrkATvHh9Dvcbnr7zBCUwfau8Sw7DLWT",
"version": "1.8.19-alpha"
"version": "1.8.21-alpha"
}
@@ -1,34 +0,0 @@
{
"changelog": [
"Fixed Cashu file payments rejected despite a shared mint, and preserved the payment amount when mint fees reduce change.",
"Payment failures now report whether a refund actually succeeded; missing files and unsupported payment methods are rejected before charging.",
"Improved saving paid files into Files and reopening purchases without paying again.",
"Bitcoin Core and Knots installation offers optional pruning on larger disks, using the same settings as automatic pruning.",
"Fixed false missing-port checks that unnecessarily restarted Bitcoin and LND; recovery now respects managed shutdown timeouts.",
"LND explains when it is waiting for Bitcoin installation, startup, or sync, without treating normal synchronization as a restart-worthy failure.",
"Bitcoin startup messages explain block-index loading without exposing raw RPC errors, and Lightning keeps known balances clearly marked during outages.",
"Changed the public transaction-explorer default to mempool.space while preserving local explorers and custom choices."
],
"components": [
{
"current_version": "1.8.20-alpha",
"download_url": "https://source.archipelago-foundation.org/lfg2025/archy/releases/download/v1.8.20-alpha/archipelago",
"name": "archipelago",
"new_version": "1.8.20-alpha",
"sha256": "16a173129672cbb40c250446ec52ba4a9bd1974cbb3a4988f90c6f3187b7a1f7",
"size_bytes": 64716656
},
{
"current_version": "1.8.20-alpha",
"download_url": "https://source.archipelago-foundation.org/lfg2025/archy/releases/download/v1.8.20-alpha/archipelago-frontend-1.8.20-alpha.tar.gz",
"name": "archipelago-frontend-1.8.20-alpha.tar.gz",
"new_version": "1.8.20-alpha",
"sha256": "658b78fce0dfa20a627c987dd153b24cbac15adbde905cc6518744c637e12802",
"size_bytes": 97152297
}
],
"release_date": "2026-09-29",
"signature": "326cab454902abcb4f8037751af67aaae2860ecf00300177ec377a1f223a6a85b6e92d49297e7bc29a73220d501e6f4c83ee23477e2b688e33e19d093c6d210b",
"signed_by": "did:key:z6Mkfu5LT8d4DjETtrkATvHh9Dvcbnr7zBCUwfau8Sw7DLWT",
"version": "1.8.20-alpha"
}