Uninstalling immich/grafana could hang with a frozen full-red progress
bar, leave a ghost entry stuck in My Apps, and then refuse reinstall.
Single root cause: quadlet::disable_remove() — called first in the
uninstall task (via companion + orchestrator teardown) — ran
`systemctl --user stop`, daemon-reload, and `podman rm -f` with NO
timeout. On rootless podman a generated unit can wedge in "deactivating"
while podman hangs underneath, so `systemctl stop` blocks forever. The
spawned uninstall task then never returns Ok or Err, so:
- set_uninstall_stage() (after the stop) never fires → progress frozen;
- remove_package_state_entry() never runs → entry stranded in
`Removing` → ghost in My Apps;
- the install guard rejects reinstall with "already Removing".
The spawn wrapper already reverts state on Err and removes the entry on
Ok — the only failure mode was a hang that returns neither. Bound the
teardown so it always terminates:
- systemctl stop → QUADLET_STOP_TIMEOUT, escalate to kill+reset-failed
on timeout (reuses the existing helpers);
- daemon_reload_user() → bounded systemctl_user_status (30s);
- defensive `podman rm -f` → wrapped in tokio timeout.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Gitea publishes two host ports — SSH on 2222 and the web UI on 3001.
The launch URL comes from manifest_lan_address_for() (the manifest's
interfaces.main → 3001), but Gitea had no entry in the static
lan_address_for() fallback map. On a node where the gitea manifest is
absent or stale (no interfaces block), the lookup returns None and the
code falls through to extract_lan_address(), which returns whichever
port podman lists first — frequently the SSH port. Result: the app
launched at :2222 instead of :3001 (observed on tailscale node
100.82.34.38).
Add the canonical "gitea" => http://localhost:3001 entry to the static
map, matching every other core app, so the web UI is pinned regardless
of manifest presence.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
podman trusts its own state DB: when a container's conmon dies without
podman observing it (cgroup-cascade SIGKILL on archipelago.service
restart, a crash), `podman ps` keeps reporting it "Up" long after the
process is gone. The reconciler NoOp'd such a zombie forever, so a dead
dependency with no published host port never recovered.
Observed live on .228 (2026-06-25): netbird-dashboard reported "Up" with
a dead State.Pid → its nginx proxy 502'd → NetBird login broke
("Unauthenticated"). The dashboard publishes no host port, so the
Running branch had nothing to probe and never recreated it.
Add a zombie guard to the Running branch: verify the recorded State.Pid
is alive (its /proc entry exists) before trusting "running"; on a
concrete dead PID, stop+remove+install_fresh from the manifest.
Conservative by design — any uncertainty (inspect failed, PID
unparseable) assumes alive, so a transient podman hiccup never destroys
a healthy container. Unit test covers live/dead/out-of-range PIDs.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
netbird is fully manifest-driven (apps/netbird-*/manifest.yml via the signed
catalog): install_stack_via_orchestrator renders the 3-member stack with
generated_certs (self-signed TLS for the #15 OIDC secure context), base64
generated_secrets, and templated config — and adopts the running stack by live
container name. The hardcoded `podman run` fallback was therefore dead code on
any node with the embedded catalog (verified live: .228 https:8087 -> 200).
Removes the per-app Rust installer anti-pattern the master plan calls out:
- install_netbird_stack: orchestrator -> adopt -> bail! (no in-Rust installer)
- deletes 6 now-dead helpers (write_netbird_config_files, ensure_netbird_tls_cert,
read_or_generate_b64_secret, netbird_net_resolver_ip, detect_netbird_public_host_ip,
wait_for_netbird_oidc_ready), 3 NETBIRD_*_IMAGE consts, unused base64::Engine import
- ~485 lines removed; prod_orchestrator doc-comments updated
Behavioural parity: the manifest path already executed on the fleet, so this
changes no live behavior. The legacy #10 OIDC-readiness wait was already bypassed
by the manifest path; if that race resurfaces, add an OIDC-ready gate to the
manifest rather than resurrecting the Rust fn.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
NOT yet validated on a node or fleet-deployed — cargo check passes, release build
+ .228 canary validation pending. Committed as a checkpoint so the work survives.
Two fixes the immich .198 incident exposed:
Fix A (reconcile_all_with_mode): a previously-running app whose container vanished
(e.g. a wedged podman teardown cleared by a reboot) was left absent on boot. Now,
when boot reconcile would leave an app 'absent' but it was running at the last
running-containers snapshot, recreate it (install_fresh). New
crash_recovery::load_last_running_names() reads the snapshot without the PID/crash
gate (+2 unit tests). Match is exact on compute_container_name (incl stack
members); user-stopped + uninstalled apps are already excluded, so no false
positives.
Fix B (ensure_bind_mount_dirs): a freshly-created bind dir was left root:root, so a
no-data_uid app running as container-root (→ host rootless user) hit EACCES and
crash-looped (the exact immich upload-dir failure). Now a newly-created bind dir
for a no-data_uid app is chowned via --reference=<parent> to match the rootless
data root — no host-uid guessing, only fresh dirs (no regression for existing
installs).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
ensure_running_container_ownership re-probed and re-attempted the in-container
chown on every reconcile pass. For a mount that can't be re-owned from inside the
userns (observed: mempool-api /data -> 'Operation not permitted'), this burned
CPU and logged a WARN on every pass, forever (~6x/30min on .228/.116).
Remember hard chown failures in a process-lifetime set keyed by (container-id,
dest) and skip the probe+chown for known-unrepairable mounts. Keyed by Id (not
name) so a recreated container gets a fresh repair attempt. Verified on .116:
one recorded failure at startup, then silent across subsequent reconciles.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
handle_package_uninstall lumped every teardown failure into one `errors` vec
and returned Err on any of them BEFORE removing the package state entry — so a
non-fatal cleanup hiccup (a slow/failed `sudo rm -rf` of a large data dir, a
volume/network removal) left the app's containers gone but its entry in
package_data → a ghost in My Apps, and the spawned task reverted it to Installed.
Split the failures: container removal that even force-rm can't complete (app
genuinely still present) keeps the entry + returns Err; everything after the
containers are gone is best-effort. Remove the state entry as soon as the
containers are gone — BEFORE the slow volume/data teardown — so My Apps updates
immediately and residue can never ghost the app. set_uninstall_stage is a no-op
once the entry is gone (if-let guard), so the later stages don't re-create it.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
wait_for_manifest_host_ports TCP-connect-probed every published port, including
UDP/SCTP. netbird's 3478/udp STUN can never answer a TCP connect, so the probe
failed forever and drove an endless host-port repair/reconcile loop on .228
(netbird-server restarting ~every 60s). Filter to tcp (empty protocol = tcp).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Turn on registry-distributed manifests for all apps: generate-app-catalog.sh now
embeds each apps/<id>/manifest.yml by default (EMBED_MANIFESTS opt-out), so nodes
install from the signed catalog (origin-wins overlay, disk = fallback) with no
OTA-shipped disk manifest. main.rs awaits a bounded (25s) refresh_catalog before
load_manifests so a fresh boot overlays the latest embedded catalog instead of a
restart later; offline/ISO boot falls through to disk and never hangs.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
image_exists ran `podman image inspect <image>` via .status() (inherits the
service stdout) with no --format, so every hit dumped the image's full ~249-line
manifest JSON into the journal — once per companion image, every reconcile pass
(.228: 21.6k journal lines / 10 min, 4131 inspect dumps). The service never
crashed (NRestarts=0); the sustained journald/IO flood starved the async runtime
and dropped the UI /ws/db websocket -> constant "connection lost"/reconnect.
Discard the child's stdout/stderr; only the exit status is used.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
package.restart resolved its container list via
ordered_containers_for_start, which injected every name from the
union startup_order list that wasn't already present — including
variant names not live on a given node (mysql-mempool,
archy-mempool-api, archy-mempool-web). The phantom mysql-mempool is
2nd in the mempool start order, so do_orchestrator_package_start hit
its unknown-app-id fallback, do_package_start failed the inspect
("no such object"), and the `?` aborted the whole start sequence —
leaving mempool-api + the frontend down until the health monitor
recovered them minutes later. That was the source of the 5× gate
flakes #73 (frontend not running in 180s) and #74 (api not queryable
in 300s); root-caused from the .228 journal
("Start failed: mysql-mempool").
Replace the inject-then-sort logic with a pure helper
order_present_containers that orders only the actually-present
containers and never adds phantom entries. startup_order remains a
union of name variants across install generations — it's now used
purely to order what's live, not to inject what isn't. +3 unit tests.
Also harden bitcoin-knots.bats "valid state" probe: poll ≤30s for a
settled state instead of a single-shot read, so a container caught
mid-reconcile (transient restarting/configured) can't flake a 20-min
iteration. A genuinely-stuck container never settles, so real
breakage is still caught.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Rename run-20x.sh → run-gate.sh, default ARCHY_ITERATIONS 20→5, and scrub
20× references across CLAUDE.md, the master plan, TESTING.md, app-registry
status, the orchestrator/config doc-comments, and the bats suites. Also add
a minimal fail() helper to mempool.bats so guard failures report cleanly.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The companion-unit repair stage ran at the END of each boot-reconciler tick, after
reconcile_existing(). On a heavily loaded node that per-app pass takes >60-90s, so a
deleted/lost companion unit (electrs-ui, bitcoin-ui, …) wasn't repaired within any
reasonable window (gate test 31 'deleted unit recreated within one reconcile tick'
timed out at 90s on the 45-app .228 node). Detecting + rewriting a companion unit is
cheap, so spawn it as its own ~interval(30s) loop, independent of the slow app pass.
Handle is aborted when the main loop exits (shutdown uses notify_one, so a second
waiter would steal the wake permit). tick() is now app-reconcile only.
All 4 boot_reconciler cadence tests still green (companion_stage=false in tests).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A user-stopped backend (electrumx, bitcoin, lnd, fedimint) kept reading 'running'
in container-list because its UI companion (electrs-ui, …) still serves the launch
port, and the state-refresh upgrades any reachable launch port to 'running'. The
gate's wait_for_container_status <app> stopped therefore never saw 'stopped'.
Fix: load the user_stopped marker in handle_container_list and force 'stopped' for
those apps before the launch-port refresh. The reconcile guard keeps the backend
down, so the marker is authoritative. package.start clears it first, so a started
app reports 'running' normally.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
package.stop a dependency (e.g. electrumx, a mempool dep) and the reconciler
restarts it within ~8s: the reconcile filter's dependency_required override
re-includes a user-stopped app that an active app depends on, and the in-memory
disabled set is wiped on manifest reload — so ensure_running runs, the stopped
app's unreachable ports look like a fault, the host-port repair restarts it, and
package.stop never sticks (gate 'transitions to stopped' times out).
Fix: guard ensure_running_with_mode on the on-disk user_stopped marker (the single
choke point every reconcile flows through) → Left('user-stopped'). Explicit
install/start clear the marker first (added clear_user_stopped to orchestrator
install/start, symmetric with disabled.remove; start/restart RPC already cleared
it) so user actions are unaffected. The container itself already stopped correctly
— this stops the resurrection.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Live on .228 the post_install `exec` steps failed with "crun: write
cgroup.procs: Permission denied / OCI permission denied": a `podman exec`
launched from archipelago.service can't place its child in the container's
cgroup (under the service's own slice). Wrap `exec` in
`systemd-run --user --scope --quiet --collect podman exec …` so it gets its own
delegated cgroup — same trick as `podman_user_scope` for pasta starts.
`copy_from_host` (a host-side `cp`, no in-container process) stays direct.
Without this only copy_from_host worked; indeedhub happened to be unaffected
(its image pre-bakes the nginx config so the exec steps were no-ops), but the
hook capability is only generally useful with exec working. hooks unit tests
pass; live verify on .228 next.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The fresh-create path was blocked by hardcoded indeedhub orchestrator logic
that predated and conflicted with the manifest migration:
- ensure_running routed app_id=="indeedhub" → reconcile_indeedhub_stack, which
REFUSED to create the frontend from its manifest (returned Left("stack-managed")).
- run_pre_start_hooks("indeedhub") → start_indeedhub_backends →
wait_for_indeedhub_dependencies_ready(120) — a DNS gate with a chicken-and-egg
bug (required the frontend's own alias present before the frontend could be
created), which failed install_fresh with "dependencies were not ready within
120s" and left the frontend down (caught live on .228).
Delete all of it (−382 lines): reconcile_indeedhub_stack, start_indeedhub_backends,
wait_for_indeedhub_dependencies_ready, indeedhub_api_dependency_dns_ready,
indeedhub_required_aliases_present, repair_indeedhub_network_aliases,
indeedhub_alias_present, patch_indeedhub_nostr_provider, and the INDEEDHUB_*
consts. The manifests now carry everything these did: network_aliases (short
hostnames), generated_secrets, dependencies, and the post_install nginx hook. So
"indeedhub" + every member flows through the generic install_fresh/reconcile path
— the frontend fresh-creates normally and runs its hook.
(crash_recovery.rs's frontend-after-deps ordering guard is kept — it's beneficial
startup ordering, not a blocker.) cargo check + release build green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Author the IndeedHub stack as 7 manifests (postgres/redis/minio/relay/api/
ffmpeg + frontend) and route install_indeedhub_stack through the
orchestrator first (immich pattern), falling back to the legacy installer
only when the manifests aren't deployed.
Data-preserving by construction — the manifests reproduce the live install
exactly so an existing node ADOPTS rather than recreates:
- container_name = the live hyphenated names the runtime already references
(health_monitor tiers/deps, crash_recovery).
- named volumes indeedhub-{postgres,redis,minio,relay}-data (not bind mounts).
- dedicated indeedhub-net + network_aliases [postgres|redis|minio|relay|api]
so the api/ffmpeg env hostnames and the frontend nginx upstreams resolve
unchanged.
- generated_secrets (indeedhub-db-password/-minio-password owned by their
backends, indeedhub-jwt by the api) reuse the live /var/lib/archipelago/
secrets values (ensure_one no-ops on existing files; postgres pw is fixed
at PGDATA init). minio user "indeeadmin" + AES_MASTER_SECRET literal kept.
The frontend carries the post_install hook (#20) that replaces the hardcoded
patch_indeedhub_nostr_provider: strip X-Frame-Options, refresh
nostr-provider.js from /opt/archipelago/web-ui, inject the <script> if
absent, reload nginx — defensive/idempotent since indeedhub:1.0.0 already
bakes these. Frontend manifest also corrected off its dead Next.js shape
(health check now nginx :7777, tmpfs /run + /var/cache/nginx).
Builds + unit-tested; live adoption/lifecycle verification on .228 next.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add `container.network_aliases: Vec<String>` (serde default, DNS-label
validated) so a stack member can answer to short hostnames its peers bake
in, beyond its own container name. Rendered in both runtime paths:
- podman_client: merged (deduped) into the custom-network aliases array.
- quadlet from_manifest: appended after the container name; emitted only
for Bridge networks (slirp/pasta reject aliases).
Needed for the indeedhub migration: its frontend nginx proxies to
`api:4000` / `minio:9000` / `relay:8080`, so those members declare
`network_aliases: [api|minio|relay]` to keep the short names resolvable on
the dedicated indeedhub-net (vs. colliding generic aliases on archy-net).
Also fixes 4 pre-existing from_manifest test failures (unrelated to this
change, surfaced now that the quadlet suite runs green): test manifests
used the long-invalid `network_policy: archy-net` (allowlist is
isolated/bridge/host → moved to network_policy: isolated + container.network)
and bind sources outside /var/lib/archipelago.
Tests: container crate 53 pass; archipelago quadlet+alias 47 pass.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add container::hooks::run_post_install — runs an app's declarative
post_install hooks against its own running container:
- Exec -> podman exec <container> <args…> (60s timeout-bounded)
- CopyFromHost -> resolve src against allowlist roots (<data_dir>/<app>
and /opt/archipelago), canonicalise + prefix-check (defeats symlink
escape), then podman cp <abs-src> <container>:<dest>
Best-effort + idempotent: a failed step is warned and skipped, never
fails the install — matching the legacy patch_indeedhub_nostr_provider
behaviour this replaces. Wired into install_fresh after the container is
up, so it runs only on a freshly created container (not plain start), and
re-applies on recreate-after-drift.
5 unit tests on resolve_copy_src (accept in-data-dir, reject absolute /
traversal / missing / symlink-escape). cargo test -p archipelago green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add controlled post_install/pre_start hook schema to AppDefinition:
LifecycleHooks/HookStep (Exec | CopyFromHost)/HostCopy with allowlist
validation (relative src, no '..', absolute container dest, non-empty
exec). Re-exported from the crate root. Design: docs/manifest-hooks-design.md.
Also add the missing generated_secrets: vec![] field to three
pre-existing ContainerConfig test literals (the field was added to the
struct in 03a4ee1b but the container crate's own tests were never rerun,
so -p archipelago-container failed to compile). cargo test green: 53 pass.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Orchestrator-installed backends (immich, btcpay-db, …) run as plain podman
`--restart=unless-stopped` containers until the Phase-3 Quadlet rollout flips
use_quadlet_backends on. Nothing in the codebase enabled the user's
podman-restart.service, so those containers had NO reboot-survival mechanism.
Enable it (idempotent, best-effort) at orchestrator startup so unless-stopped
containers come back after a reboot. Already applied manually on .228 (covers
31 containers incl. immich + btcpay); this codifies it fleet-wide.
The deeper fix (render Quadlet for all orchestrator installs) remains the gated
Phase-3 Quadlet-everywhere rollout.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
After the manifest migration the launcher installed as "immich-server" (app_id),
which has no catalog entry → showed the raw id and no icon. Rename the server
manifest app_id immich-server→immich so it matches the catalog/curated "immich"
entry (title "Immich", icon immich.png) and is recognised as a known launcher app
(APP_CATEGORY_MAP) → stays in My Apps. immich_stack_app_ids now installs
[immich-postgres, immich-redis, immich]; orchestrator.install bypasses package
routing so there's no recursion with the "immich"→stack-installer mapping.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Completes the immich migration off the legacy hardcoded install_immich_stack
(podman run + sudo chown) to the registry-manifest + orchestrator path. Validated
live on .228 (clean single set, healthy v2.7.4, data dir ownership correct).
- install_immich_stack now tries install_stack_via_orchestrator(immich_stack_app_ids)
first; legacy remains only as the no-manifests fallback.
- immich-{postgres,redis,server} manifests corrected from live findings:
* named by app_id (dropped container_name override) — using container_name
spawned DUPLICATE containers (app_id-named install vs name-override reconcile)
on the same PGDATA, which corrupted a postgres cluster. Server reaches its
siblings via app_id aliases (DB_HOSTNAME=immich-postgres, REDIS=immich-redis).
* immich-postgres data_uid 100998:100998 (postgres drops to container 999 →
host 100998 under rootless; verified the fresh dir is chowned correctly).
* immich-server version "release"→"2.7.4" (manifest validation requires a digit;
the bad version made the manifest silently skip → partial orchestrator install
→ legacy fallback → the duplicate corruption above).
- HARDEN install_stack_via_orchestrator: only fall back to the legacy installer
when NOTHING was installed yet. An "unknown app_id" AFTER a member is up now
errors instead of double-creating containers on shared data (the corruption
root cause).
- Strict the all-manifests round-trip test: fail (not skip) on any invalid shipped
manifest — this gap let the bad immich-server version through.
Known follow-up (pre-existing, platform-wide): orchestrator-installed backends
(immich, btcpay-db) run as podman --restart, not Quadlet, and podman-restart.service
is disabled on .228 → reboot-survival gap independent of this migration.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
generate-app-catalog.sh gains opt-in EMBED_MANIFESTS=1: embeds each
apps/<id>/manifest.yml into its catalog entry's `manifest` field (whole document,
top-level app: preserved — exactly what the Rust side deserializes). Default off
so routine catalog regen is unchanged during the migration window; turn on
deliberately, then sign via the existing release-root ceremony. Verified: default
embeds 0; EMBED_MANIFESTS=1 embeds 40 manifests (generated_secrets preserved).
Adds a round-trip guard test: every shipped apps/*/manifest.yml must deserialize
+ validate through catalog_manifest_to_overlay (image apps accepted, build apps
defer to disk) — catches schema drift between disk manifests and the catalog path.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Workstream B phase 1 (node-side consume). The signed app-catalog can now carry a
full manifest per entry; the orchestrator overlays it over the disk manifest
(origin-wins) with disk as the migration fallback. Moves apps toward
registry-distributed manifests with no OTA-shipped disk file.
- app_catalog: `manifest: Option<Value>` on AppCatalogEntry (forward-compatible,
covered by the existing release-root signature over the raw JSON);
`catalog_manifest_values()` accessor.
- prod_orchestrator: `load_manifests` overlays catalog manifests after the disk
walk; `catalog_manifest_to_overlay()` returns None (→ disk fallback) on
unparseable value / app-id mismatch / failed validate() / build source
(build contexts aren't registry-distributed yet — phase 1 is image-only).
- manifest_dir stays PathBuf (build-only field); image-only apps never read it.
- 6 unit tests; compiles clean. No-op until a catalog embeds a manifest, so
existing nodes are unaffected.
See docs/registry-manifest-design.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Buyer-side paid downloads now persist: purchases are cached on disk
(content_owned.rs) keyed by (seller onion, content_id), the gallery shows
an "Owned" badge unblurred, and items view/play in-app from the local
cache with no re-payment or reliance on a browser download (which
silently failed on the mobile companion). New RPCs content.owned-list /
content.owned-get. Validated e2e .116<-.198 (paid 100 sats via Fedimint,
166KB jpeg returns, survives restart).
fedimint-clientd manifest: restore the standard container capability set
(CHOWN/DAC_OVERRIDE/FOWNER/SETUID/SETGID) so fmcd's startup chown of an
existing-federation /data succeeds instead of dying EPERM (#7). Confirmed
the orchestrator applies these to the running container.
FIPS perf: tighten the supervisor warm-path keepalive 45s -> 25s so peer
paths stay inside the ~30-60s NAT cold window. Dials now reliably land on
FIPS instead of re-punching and falling back to Tor. Measured to the same
peer: cloud browse 18-22s -> 0.4s; full Fedimint paid download 29s -> 11s
(residual is the seller-side guardian reissue round-trip).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
fmcd crash-looped "Operation not permitted (os error 1)" on .116 (kernel
6.12.74): the default rootless seccomp profile blocks a syscall its Mainline-DHT
/ iroh transport needs, so the REST API never came up (:8178 → HTTP 000) and
federations couldn't be joined. Verified: with seccomp=unconfined fmcd boots and
answers /v2/* (HTTP 401 instead of dead). fmcd works on other nodes, so this is
kernel/seccomp-specific — but the relaxation is safe for an outbound-networking
daemon and harmless where not needed.
- new `security.seccomp_unconfined` manifest flag (SecurityPolicy);
- libpod backend sets `seccomp_profile_path: "unconfined"` (== --security-opt
seccomp=unconfined); quadlet backend emits `SeccompProfile=unconfined`;
- enabled in apps/fedimint-clientd/manifest.yml.
NOTE: manifests live on-disk at /opt/archipelago/apps/<id>/manifest.yml, so the
node needs the updated manifest deployed + the fmcd container recreated to apply.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- PeerFiles: new confirmation step after "pay from ecash" — shows the amount and
which wallet will be spent (Cashu/Fedimint) with balances, lets the user switch
backends, and a styled Confirm button. The chosen backend is passed to the
payment so it spends exactly what was confirmed.
- content.download-peer-paid: accept `method` (cashu|fedimint) to honor the
confirmed choice; log the backend + outcome; backend-specific rejection errors
("not in the same Fedimint federation" / "doesn't accept your Cashu mint").
- AUTO-REFUND: a minted token whose sale fails (peer unreachable, rejected, or
error) is now reclaimed (fedimint reissue / cashu receive) so the buyer no
longer loses the spent ecash — fixes the stuck-Fedimint-notes report.
- wallet.ecash-balance already reports cashu_sats/fedimint_sats/total_sats which
the confirm screen uses to pick/show the covering wallet.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Right after install the dashboard SPA opens and, if it loads before NetBird's
embedded OIDC provider is serving, caches a bad auth state — the user appears
logged-in but can't log out until it self-corrects. Container "running" != OIDC
ready, so gate the install's Done phase on the management server's
/oauth2/.well-known/openid-configuration answering (best-effort, 60s cap, never
fails the install since the stack is already up).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Paying for a peer file minted a Cashu-only token, so a node whose ecash balance
lived in Fedimint couldn't pay even with funds. Now both backends are tried:
- payer (content.download-peer-paid): mint a Cashu token first; on failure fall
back to spending Fedimint notes. Only error if BOTH backends can't cover it.
- seller (verify_and_receive_payment): accept Fedimint notes as well as Cashu —
anything not starting with "cashu" is redeemed via reissue_into_any.
- new fedimint_client::spend_from_any() — spend from whichever joined federation
has the balance, returning the notes + federation id (mirrors reissue_into_any).
- wallet.ecash-balance now also reports fedimint_sats + combined total_sats; the
pay-for-file pre-check uses the combined total so a Fedimint-funded node isn't
wrongly blocked.
Compiles (cargo check + vue-tsc). Live cross-node federation validation pending
(dual-ecash phase 6) — needs two nodes sharing a federation.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A node reachable both over LoRa and federation has two MeshPeer rows (radio
twin: low contact_id + firmware key; federation twin: high contact_id +
archipelago key), and messages key by peer_contact_id split across the two ids
— so opening one twin shows an empty thread (the .120->.89 symptom).
- backend: new group_peer_twins() helper groups peers by arch_pubkey_hex (set on
BOTH twins by bind_federation_twins), keeps the radio id as the mesh-first
send target, and unions messages across all twin ids. Wired into
conversations.list / conversations.messages / mesh.contacts-list. +3 unit tests.
- frontend: the live chat list merges client-side (mergedPeers) and matched twins
by the "Archy-z6Mk..." advert prefix, which the Meshtastic device rename broke
(radio now advertises the server name). Merge by arch_pubkey_hex instead, which
the backend reliably sets on both twins. Expose arch_pubkey_hex on MeshPeer.
- fix unrelated stale test: EcashTransaction test missing the new `kind` field.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Meshtastic device rename was a no-op — set_advert_name only updated an
in-memory field and never told the radio, so the device kept its firmware
default ('Meshtastic xxxx') and wasn't findable from external Meshtastic
apps. MeshCore already renamed correctly (CMD_SET_ADVERT_NAME); this brings
Meshtastic to parity.
Send an AdminMessage{set_owner=User{long_name,short_name}} to the locally
connected node (admin packet to our own node_num on the ADMIN_APP port).
Local serial admin needs no session passkey, matching the official client.
long_name = server name (<=39 chars); short_name = first 4 alphanumerics,
upper-cased. Verified on real hardware: .120 -> 'Archy-X250-EXP', .5 ->
'Archy-X250-Beta' (name read back from the radio after reconnect).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A stock meshcore client (e.g. a phone) can't sign our typed envelopes, so it is
never 'authenticated' — which meant ticking it as an allowed assistant contact
had no effect and !ai stayed denied. The explicit per-contact allowlist is a
deliberate operator opt-in for a specific key, so match it regardless of
authentication, keyed on the asker's resolved identity (bound archipelago key,
else firmware routing key — how meshcore addresses the contact). The spoofable
federation-trust-list match still requires authentication.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- reissue_into_any now tries the UNION of the local registry AND fmcd's live
joined set (/v2/admin/info) before failing, so a valid Fedimint token isn't
wrongly rejected when the registry has drifted. On all-fail it returns a
friendly message: notes already redeemed into this wallet (funds safe) vs
didn't match any connected federation.
- Unified transaction history: a local Fedimint tx log (recorded on each
successful redeem) is merged with the Cashu history in wallet.ecash-history,
newest-first, each tagged kind=cashu|fedimint. Previously a Fedimint receive
appeared nowhere.
- fedimint-clientd healthcheck -> type:tcp. It was probing /health, which fmcd
doesn't serve (only /v2/*), pinning the container in (starting) forever; the
TCP probe is skipped by the Quadlet renderer (host-side lifecycle verifies),
so it reports running. Cosmetic for ecash, which worked throughout.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A !ai (or any typed message) from a trusted, federated node was denied when
it arrived over the radio. The radio half of a node that is also a federation
peer carried no archipelago identity (identity adverts are no longer broadcast
on the public channel), so the trusted_only gate and signature verification
had no key to check the asker against — and the same node showed up as two
contacts (a radio twin + a federation twin).
- bind_federation_twins(): correlate a radio contact with its federation twin
by exact, case-insensitive advert_name and copy the federation peer's
arch_pubkey_hex/did/x25519 onto the radio record. Called from
upsert_federation_peer and refresh_contacts. Ambiguous names (held by >1
federation peer) are skipped. This is only a CANDIDATE key — security is
unchanged: the inbound envelope signature must still verify against it.
- send_message now signs the typed Text envelope (new_signed) so a radio !ai
authenticates against the bound key. A meshcore node merely named like a
trusted node cannot forge the signature, so it is still denied.
Receiver-side verification (handle_typed_envelope_direct) and federation-trust
matching (is_sender_allowed) already existed; this supplies the missing key
binding and signature. Also resolves the radio/federation duplicate-contact
display for same-named nodes.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Messages to a federated peer that is out of LoRa range (e.g. on another
continent) were dropped into the radio with no fallback, or hung on a dead
FIPS path before reaching Tor — so they never arrived.
- Route a radio contact over the federation transport (FIPS->Tor) when it is
the same node as a federated peer (known archipelago identity -> onion) AND
it is not currently reachable over the radio. Reachable radio peers stay on
the mesh (preferred); oversized/file envelopes still always take federation.
- Resolve the onion via the archipelago identity key (arch_pubkey_hex), not
the firmware routing key, so a radio contact maps to its nodes.json onion.
- Add .fips_timeout(8s) to the federation message POST so an unreachable FIPS
overlay fast-fails to Tor (~3-5s) instead of burning the 120s budget.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Federated nodes failed to converge to full-mesh across the LAN<->Tailscale
boundary: nodes were invisible to peers, sync 'took ages'/timed out, and
names only updated on a manual sync. Onions were healthy in both directions
(~3-5s); the failures were app-layer.
- B: federation dials fast-fail a dead FIPS path via .fips_timeout(6s) in
sync_with_peer + notify_join, so the Tor fallback isn't stuck behind the
full 30s FIPS budget when LAN and remote peers share no FIPS path.
- A: notify_join (peer-joined) now spawns with retries+backoff instead of a
single awaited best-effort POST, so the join RPC returns instantly (no
'Request timeout') and the inviter reliably learns the joiner (was
asymmetric).
- C: new 90s periodic federation auto-sync (none existed) so renamed nodes
and roster changes propagate without a manual Sync click.
- self-heal: each auto-sync re-asserts membership to any peer that doesn't
list us back, converging the fleet to full-mesh and healing pre-existing
asymmetry with no manual re-joins.
Validated live across 7 nodes: a previously fleet-invisible node became
fully meshed automatically (logs: 'auto-sync ... reasserted=1',
'peer-joined ... delivered').
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
UI (this session):
- Global audio player now scales the whole interface into the space above it
on desktop (sidebar + main) and docks directly above the tab bar on mobile;
it stays visible while navigating.
- Mesh mobile redesign: floating Chat / BTC / Dead Man / AI / Map tab strip
with a single fixed, internally-scrolling pane (page no longer scrolls);
tabs hide while a conversation is open; floating back button; collapsible
Device panel (starts collapsed); keyboard-aware conversation sizing via
VisualViewport so the chat sits just above the keyboard.
- Cloud file grid: uniform 4/3 card heights (folders + images match).
- Swipe left/right switches tabs on the Apps and Web5 screens.
- Map tool fills its pane (no bottom gap); fix skewed Share Location toggle
on mobile (global min-height rule was deforming the switch).
- Trim redundant helper copy from the mesh AI tab.
Also bundles pre-existing in-progress work that was already in the tree:
mesh listener/session + wallet + container + bitcoin-status backend changes,
docker UI updates, and assorted other UI tweaks.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Fedimint never appeared in Wallet > Settings > Fedimint because the
fmcd (fedimint-clientd) sidecar was never installed: ensure_default_
federation() needs the fmcd password to reach the daemon, found none,
and silently no-oped, leaving the registry empty.
- prod_orchestrator: add fedimint-clientd to the baseline auto-install
set so it self-heals onto every node and auto-joins the default
federation; generate the fmcd-password secret before secret_env
resolves.
- fedimint_client: ensure_fmcd_password (random hex, 0600) shared with
the container's secret_env; from_node reads the same secret (legacy
fmcd/password kept as fallback); reissue_into_any redeems received
notes into the first joined federation that accepts them.
- wallet.ecash-receive: dual-token — cashu* tokens redeem at the mint,
anything else is reissued via fmcd; returns the kind + federation_id.
- UI: receive box advertises "Cashu or Fedimint" and reports which kind.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Meshtastic DMs were falling back to a channel broadcast, so every node
on the LoRa channel saw a "direct" message. Send a directed MeshPacket
(to = node num, decoded from the synthetic pubkey's node-id bytes)
instead — the Meshtastic analog of the meshcore CMD_SEND_TXT_MSG fix.
DMs now reach only the recipient; firmware auto-PKC-encrypts them
end-to-end once NodeInfo keys are exchanged.
Capture E2E status at the driver level (no shared-type/UI change):
- learn each peer's real Curve25519 key from User.public_key (field 8)
and inbound MeshPacket.public_key (16), kept in a side-map separate
from the synthetic routing key so unicast routing is untouched
- detect inbound MeshPacket.pki_encrypted (17) to tell a true E2E DM
from a channel-PSK fallback
- peer_is_pkc_capable() seam for a future mesh-tab E2E badge
Hot-swap preserved: no dispatched MeshRadioDevice signature or the
shared ParsedContact changed, so meshcore and meshtastic stay
interchangeable behind the listener.
Adds tests/multinode/meshtastic.sh, a two/three-radio on-air parity
harness (detect, discover, DM round-trip, DM privacy, channel
broadcast, typed envelope, reachability).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Cashu default mint was the local Fedimint guardian (:8175), wrongly surfacing
a Fedimint URL in the Cashu mints list. Default is now Minibits
(https://mint.minibits.cash/Bitcoin) — Cashu and Fedimint are distinct
protocols (Fedimint lives under its own tab).
- Peer-file (buy) invoice creation: retry the LND REST call (3× / 400ms) so a
transient LND-REST blip (swap pressure / just-restarted / TLS race) no longer
hard-fails as an opaque 503, and surface the real error chain ({:#}) in the
response + logs instead of a generic "Failed to create invoice".
- Autojoined default federation now shows a friendly name ("Archipelago
Federation") in the Fedimint tab instead of a bare federation id.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Sizes bitcoind -dbcache to host RAM (~1/16, floor 300MB, cap 4096) instead of a
fixed 2048/4096. A multi-GB UTXO cache on an 8GB node running the full app stack
pushed memory past physical RAM and triggered system-wide swap thrash: the disk
saturated, bitcoind could not answer its own RPC, and the dashboard backend's
sqlite reads stalled — surfacing as fleet-wide /rpc/v1 502s and a blank Bitcoin
UI. Applied in scripts/container-specs.sh (reconciler path) and the config.rs
bitcoin-core path.
Bitcoin status cache now polls every 5s (was 10/15) with an 8s timeout (was 20s)
and fetches the four RPCs concurrently, so the cached snapshot tracks bitcoind's
responsive windows during IBD and the UI stops dwelling on "reconnecting...".
Unifies the divergent discover AppGrid/FeaturedApps image-error handlers onto the
canonical placeholder fallback so missing app icons render the placeholder.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- DMs now use native meshcore unicast (CMD_SEND_TXT_MSG) instead of @DM2 channel
broadcasts: private (E2E-encrypted to the recipient pubkey by firmware), off the
public channel, and decodable by stock clients. Plain text (split, not MC-chunked)
to non-archipelago contacts; typed envelopes to archy peers.
- !ai replies now DM the asker privately (RadioDm) instead of broadcasting on ch0.
- Auto contact-import: a heard advert (PUSH_CONTACT_ADVERT/0x80, 32-byte pubkey) is
added via CMD_ADD_UPDATE_CONTACT (0x09) so contacts appear without a flood advert.
- clear-all now DELETES firmware contacts via CMD_REMOVE_CONTACT (0x0F) instead of
blocklisting; blocking filter removed entirely. Wiped contacts return when reachable.
- Contact reachability: MeshPeer carries last_advert + reachable (path-based); UI shows
a reachability dot.
- Peers list: contact search box (filter by name/DID/npub/pubkey) with a clear button.
- send_message routes stock contacts as plain native text (fixes garbled envelopes).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- mesh: stop broadcasting ARCHY:2 identity on the public channel (startup + every advert tick); receive path still parses inbound. No more public-channel spam.
- mesh assistant: trigger on !ai/!ask typed in 1:1 chat (was only the dead AssistQuery path + bare channel text); route the reply transport-aware via MeshService::send_message (Tor for federation peers, LoRa for radio) through a new AssistChatReply event consumed at the server layer — fixes replies never reaching federation askers.
- mesh assistant: per-contact !ai allowlist (allowed_contacts) bypassing trusted_only; config + RPC + is_sender_allowed.
- fedimint-clientd manifest: network_policy open -> bridge (invalid value made the loader skip the whole manifest, so fmcd never ran and federations never joined/listed).
- ui: AI panel — Claude model dropdown (Haiku/Sonnet/Opus presets) + allowlist contact picker.
- ui: Settings — App Updates + App Registry moved under Account.
- ui: mesh chat — overscroll-behavior: contain so chat scroll no longer bleeds to the contacts panel.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
