Compare commits

..

309 Commits

Author SHA1 Message Date
Dorian
38d2bbf570 chore(android): update companion APK download [skip ci] 2026-06-26 13:08:37 +01:00
Dorian
a90fea80ed feat(android): edit server entries from in-app settings menu (NESMenu); bump to 0.4.12 (vc16)
The 0.4.11 edit affordance only lived on ServerConnectScreen, which a
connected user never sees. Add edit to NESMenu — the settings modal
reached via two-finger hold while connected: a ✎ pencil on each saved
server opens the form pre-populated (Edit Server header + Cancel),
persists via ServerPreferences.updateSavedServer(), and reconnects when
the edited server is the live one.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 13:08:18 +01:00
Dorian
389e602097 chore(android): update companion APK download [skip ci] 2026-06-26 12:54:52 +01:00
Dorian
5677f9cca1 feat(android): edit saved server entries; bump companion to 0.4.11 (vc15)
Add an edit affordance to each saved server in ServerConnectScreen: a
pencil button loads the entry into the form (Edit Server mode) with
Save Changes / Cancel actions. Persisted via a new
ServerPreferences.updateSavedServer() that replaces by connection
identity (address/port/scheme) and keeps the active record in sync when
the edited server is the active one.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 12:54:07 +01:00
archipelago
fc64b422e7 docs(master-plan): WS-F#3 first destructive run — 3 reinstall bugs found
Full all-apps-lifecycle pass on .228: lifecycle 11/11, teardown 8/11.
Surfaced (1) fresh-install bind-dir ownership root:root → reinstall
EACCES (jellyfin/netbird; Fix B misses the install path), (2) netbird
reinstall adopts leftover containers → skips manifest cert/file render,
(3) portainer image pin lfg2025/portainer:2.19.4 unpublished (manifest
unknown), pin overrides RPC dockerImage. .228 restored.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 07:47:24 -04:00
Dorian
07b9b5a3aa docs(android): companion release + App-Not-Installed runbook
Capture the 2026-06-26 lessons durably: ship via the hardened publish
script only, v1+v2+v3 signing is enforced by apksigner (AGP ignores
enableV1Signing at minSdk>=24), diagnose install failures with adb
install FIRST, signature-key changes force a one-time uninstall, and
keep all phone/adb work scoped to com.archipelago.app.debug.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 12:21:48 +01:00
Dorian
ac59771560 fix(android): force v1+v2+v3 signing & clean-build guards in companion publish
The published companion APK was v2-only (AGP silently ignores
enableV1Signing for minSdk>=24) and clean builds broke on stray
space-named resource dirs. Harden scripts/publish-companion-apk.sh:
clean build, remove/ýreject space-named res dirs, force v1+v2+v3 via
zipalign+apksigner, and abort unless all three schemes verify. Wire
ship-companion.sh to the shared script. Re-sign the served 0.4.10 APK.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 11:53:25 +01:00
Dorian
d1f9e9ce88 chore(android): update companion apk download 2026-06-26 11:32:00 +01:00
Dorian
58847fc3d7 chore(android): bump companion to 0.4.10 (versionCode 14)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 11:31:36 +01:00
archipelago
a3e09eab57 docs(master-plan): WS-F#3 — destructive all-apps lifecycle matrix landed (43934eef)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 06:29:51 -04:00
archipelago
43934eefa5 test(gate): destructive all-apps lifecycle matrix (WS-F#3)
Active counterpart to the read-only all-apps-matrix.bats: drives
stop/start/restart for every installed app and, under
ARCHY_ALLOW_CASCADE_DESTRUCTIVE, a FULL teardown (uninstall →
no-ghost → reinstall) — the broad coverage F needs beyond the ~8 core
suites. App set is discovered from My Apps ∩ the node catalog; reinstall
spec comes from catalog.json {dockerImage, containerConfig}.

PROTECTED by default (never cycled or torn down): bitcoin*/electrum*
(expensive resync) AND lnd/btcpay*/fedimint* (teardown = irreversible
wallet/channel/guardian loss). The user asked to protect only
bitcoin+electrum; the wallet apps are added for safety and can be
removed via ARCHY_MATRIX_PROTECT. Heavy + destructive → a supervised
pass, not folded into run-gate. Validated on .228: discovery excludes
the 6 protected installed apps; lifecycle tier cycles a single app
(botfights) stop/start/restart green; teardown gated.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 06:29:22 -04:00
archipelago
80146f4476 docs(master-plan): WS-F#2 — uninstall progress bar made truthful (9f17ba68)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 06:15:11 -04:00
archipelago
9f17ba6867 fix(ui): truthful uninstall progress bar (was a solid full-red block)
AppCard's uninstall bar was hardcoded `w-full bg-red-400/60 animate-pulse`
— a solid, full-width, red, fake-pulsing block that never moved and read
as an error, no matter the actual teardown progress (the install bar, by
contrast, renders a real percentage). Derive a truthful percentage from
the backend's existing `uninstall-stage` label — "Stopping containers
(X/N)" → 10–50%, "Cleaning up volumes" → 70%, "Removing app data" → 90%
— and render it exactly like install: neutral fill, real width + percent,
shimmer (not a fake pulse) carrying motion when a stage has no number.
Frontend-only; the backend already broadcasts these stages.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 06:04:48 -04:00
archipelago
67426c0d41 docs(master-plan): cascade tier wired into the gate (b7d92107)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 05:24:07 -04:00
archipelago
b7d9210784 test(gate): optional ARCHY_GATE_CASCADE pass — wire the cascade tier in
run-gate.sh ran only the DESTRUCTIVE tier; the cascade-uninstall suite
(uninstall→no-ghost→reinstall, the #13/#14/uninstall-hang regression
guard) existed but was never enabled by the gate. Add an opt-in single
cascade pass after the 5× loop (ARCHY_GATE_CASCADE=1, requires
ARCHY_ALLOW_DESTRUCTIVE=1), counted into the pass/fail tally. Kept out
of the 5× loop deliberately — uninstall/reinstall every iteration would
balloon runtime and re-pull images; one pass guards the class. Default
gate behavior unchanged. Validated: cascade-uninstall.bats 7/7 on .228.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 05:22:45 -04:00
archipelago
292a2650df docs(master-plan): WS-F — uninstall-hang root cause fixed + cascade validated
Workstream F now in-progress: the immich/grafana uninstall hang →
ghost/stuck-bar/reinstall-block is root-caused (unbounded systemctl/
podman in quadlet::disable_remove) and fixed (71cc9ac4); cascade-
uninstall.bats 7/7 on .228. Records the remaining F items + the pending
gate-wiring decision.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 05:18:39 -04:00
archipelago
71cc9ac46a fix(uninstall): bound systemctl/podman teardown so uninstall can't hang
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>
2026-06-26 04:27:02 -04:00
archipelago
2ebcd8f9a8 docs(master-plan): backlog — smart launch-port selection + manifest-driven archival-node blocker
§10b: replace per-app static launch-port map with a manifest-first +
non-HTTP-port-skipping heuristic (the gitea :2222 class).
§10c: generalize the un-pruned/archival Bitcoin install blocker from a
hardcoded requires_unpruned_bitcoin() match to a manifest-declared
dependency, with a clear pre-install UX.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 03:47:25 -04:00
archipelago
3515344800 docs(master-plan): session h — zombie guard + gitea launch-port fix
Banner + §8b: zombie-container guard (0a8db904, live-proven on .228) and
gitea launch-port fix (670ebb06) shipped in binary 040df5ce, rolled to
the fleet. Logs the mempool env-drift recreate-loop and nostr-rs-relay
follow-ups.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 03:41:59 -04:00
archipelago
670ebb0666 fix(launcher): pin Gitea launch URL to web port 3001 (not SSH 2222)
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>
2026-06-26 03:16:41 -04:00
archipelago
0a8db9044f fix(orchestrator): recreate zombie "Up" containers whose process is dead
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>
2026-06-26 02:25:52 -04:00
archipelago
43e700498b fix(android): trust self-signed certs for the user's own node in WebView
Node apps (e.g. NetBird on :8087) terminate TLS with a self-signed cert
so the dashboard gets a secure context (OIDC / window.crypto.subtle, #15).
The WebView's default onReceivedSslError CANCELs untrusted certs, so those
apps rendered blank in the companion — exactly the netbird "won't load in
the webview" report. Override onReceivedSslError in both WebViewClients
(kiosk + in-app browser) to proceed() only when the failing cert's host
matches the connected node; reject everything else (no blanket trust).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 18:13:52 -04:00
archipelago
89d397bb74 refactor(netbird): delete legacy Rust installer — #20 ph4 (manifest-driven only)
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>
2026-06-25 11:04:01 -04:00
archipelago
41e7f500f8 test(lifecycle): tolerate slow-but-healthy heavy-app recovery under 5x churn
The 5x destructive gate on heavy nodes false-failed on transient windows
during stack recovery, not real regressions:

- immich.bats: lan_address port-publish probe 30s -> 90s. The postgres->redis
  ->server (DB migrations on boot) stack can take >30s to republish :2283 after
  a churn-induced recreate; destructive-tier immich tests already allow 180-240s.
- mempool.bats: orphan-container check now polls to steady state (<=30s) instead
  of a single-shot count, which caught a recreated member briefly visible
  alongside its replacement mid-reconcile.
- run-gate.sh: settle cap 180s -> 300s and also gate on immich's :2283 when
  installed, so the next iteration's read-only probe doesn't race a still-
  recovering stack. Settle returns the instant every probe is green.

A genuinely unexposed/orphaned/unhealthy app still fails these checks; they only
absorb the transient recreate window under sustained churn.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 09:18:34 -04:00
archipelago
a721532f55 feat(orchestrator): desired-state recovery + recreate volume-ownership [UNVALIDATED WIP]
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>
2026-06-24 09:28:40 -04:00
archipelago
80f49cac1c fix(ui): backoff remote-relay reconnects + stop cryptpad icon 404
Two console-noise fixes from a live error dump:
- remote-relay.ts reconnected on a FIXED 5s interval with no backoff, so when
  the backend is briefly down it floods the console/network with failed-WS
  attempts for the whole outage. It's a secondary feature (companion input), so
  add exponential backoff 1s->30s (mirrors websocket.ts), reset on open/start.
- cryptpad's catalog/marketplace entries pointed at a non-existent
  /assets/img/app-icons/cryptpad.webp -> a 404 on every marketplace render.
  Point it at the existing default icon (handleImageError swapped to it anyway).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 08:41:04 -04:00
archipelago
2d8ade629b fix(ui): log global errors silently instead of popping a toast + overlay
The global error handler (Vue errorHandler + window error + unhandledrejection)
fired a red 'Something went wrong: <raw msg>' toast AND an auto on-device overlay
on every caught error — deliberately loud for bug-bash, but it surfaces benign,
non-actionable noise (e.g. a transient RPC rejection during a ws reconnect, or
the service worker failing to register over a self-signed cert) right in the
user's face.

Demote the catch-all to SILENT capture: keep console.error + the
window.__archyErrors ring buffer, and expose the screenshot-able overlay
on-demand via window.__archyShowErrors() — but never auto-pop. Components that
need to report a specific, actionable failure still call toast.error() directly.

Also filter known-benign environmental noise (PWA service-worker registration
failing over a self-signed cert — needs a trusted cert, #56) so it doesn't even
occupy a ring-buffer slot and push out real errors.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 05:55:49 -04:00
archipelago
0406af522c test(lifecycle): add manifest-driven all-apps health matrix
The per-app suites cover ~8 core apps in depth; nothing covered the ~30 others
(jellyfin, vaultwarden, penpot, nextcloud, grafana, …). all-apps-matrix.bats
derives the app set from server.get-state package-data (no hardcoded list) and
asserts baseline health across EVERY installed app:
  - settles to a non-transitional state within a window (the #13/#14 stuck-ghost
    class, generalized fleet-wide — installing/removing that never settles)
  - not in error/failed
  - reports a recognized (non-garbage) state
  - every running UI app (manifest ui=="true") exposes a non-null lan-address
    (the immich/port-drift unreachable-UI failure, generalized to all UI apps)

Read-only, so it joins run.sh/run-gate.sh on every node and grows coverage as
nodes install more apps. Verified 5/5 on .228 (17 apps) and .116 (20 apps).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 05:27:10 -04:00
archipelago
57a69257c4 test(lifecycle): add CASCADE uninstall/reinstall tier (guards #13 ghost, #14 reinstall)
The 5x gate is DESTRUCTIVE-only and never exercised uninstall/reinstall — where
the worst field bugs lived (#13 app ghosting in My Apps after uninstall, #14
reinstall stalling on stale state). New cascade-uninstall.bats drives the full
teardown path on a throwaway app (default grafana, precondition-skips if already
installed so it can't destroy real data) and asserts:
  - fresh install reaches running via a truthful, non-silent progression
  - uninstall makes the entry DISAPPEAR from server.get-state package-data
    (the literal My Apps map) — no ghost, no stuck uninstall stage
  - container + (on-node) data dir are gone
  - reinstall returns to running
  - node left as found

Opt-in via ARCHY_ALLOW_CASCADE_DESTRUCTIVE=1; not yet folded into the canonical
gate. Verified 7/7 against .228.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 05:13:53 -04:00
archipelago
d1cd42c821 fix(orchestrator): stop retrying unrepairable volume chowns every reconcile
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>
2026-06-24 04:58:57 -04:00
archipelago
3e3016f2bd fix(ui): debounce connection-lost banner so transient ws blips don't flash
The reconnect banner showed 'Connection lost'/'Reconnecting' instantly on every
socket close, even ones that recover in 100ms-2s (load spikes, Tailscale/relay
TCP resets). On a healthy node the drops are brief and self-healing, but each one
flashed a jarring banner, reading as constant instability.

Debounce the transient banner by 2.5s: only surface after the connection issue
persists past the grace window; hide immediately on recovery. Deliberate server
lifecycle transitions (restart/shutdown) bypass the debounce and still show at
once. A genuine persistent outage keeps isOffline true and surfaces after 2.5s.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-24 04:58:54 -04:00
archipelago
7d89b4d8b2 chore(registry): publish embedded app-catalog.json (52 manifests) for fleet fetch
Force-add the gitignored releases/app-catalog.json so nodes resolve
146.59.87.168:3000/lfg2025/archy/raw/branch/main/releases/app-catalog.json
(currently HTTP 404 → disk-manifest fallback). Embedded-manifest delivery
is default-on; origin-wins overlay with disk as fallback. Unsigned (migration
window accepts unsigned). Includes netbird x3 manifests.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 23:45:31 -04:00
archipelago
15f65428b8 docs(master-plan): §8b — uninstall fix deployed+live-verifying, #15 guardian resolved
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 18:07:41 -04:00
archipelago
36015a19fe docs(master-plan): §8b session-b state — connection-lost+netbird+UX-merge shipped to .228, uninstall ghost fix, workstream F in progress
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 15:26:17 -04:00
archipelago
e57514b690 fix(uninstall): never ghost a removed app in My Apps on cleanup residue
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>
2026-06-23 15:23:16 -04:00
archipelago
4346007d37 fix(orchestrator): only TCP host ports get reachability-probed
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>
2026-06-23 14:40:48 -04:00
archipelago
44f7af2017 merge: companion-mobile-ux UX (loader/store-driven launch/icons + android webview) into main
# Conflicts:
#	Android/app/build.gradle.kts
#	Android/app/src/main/java/com/archipelago/app/ui/screens/WebViewScreen.kt
#	neode-ui/src/views/apps/appsConfig.ts
2026-06-23 14:07:44 -04:00
archipelago
9670af62b6 feat(registry): deliver app manifests via the signed catalog (embed by default)
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>
2026-06-23 13:39:54 -04:00
archipelago
a8b9b0f5e8 feat(netbird): manifest-driven migration via reusable orchestrator primitives
Migrate the netbird stack (server/dashboard/proxy) off ~500 lines of per-app Rust
to 3 declarative manifests, adding 4 reusable primitives:
- SecretGenKind::Base64 (netbird relay authSecret + sqlite store encryptionKey)
- GeneratedCert schema + ensure_manifest_certs (self-signed TLS so the dashboard
  gets a secure context for OIDC PKCE — issue #15; https proxy on 8087 preserved)
- templated GeneratedFile render: {{HOST_IP}}/{{HOST_MDNS}}/{{NETWORK_GATEWAY}}
  (aardvark resolver for the #15 stale-IP fix) /{{secret:NAME}} (never logged)
- legacy create_container now honours port.protocol (3478/udp STUN)
install_netbird_stack routes via the orchestrator first (legacy kept as fallback,
mirroring indeedhub); launch URL derives https://{host_ip}:8087 from host facts.
Legacy Rust deletion deferred to post-live-verify.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 13:39:53 -04:00
archipelago
3c36cf1c40 fix(companion): stop image_exists journal flood that drops the UI websocket
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>
2026-06-23 13:39:19 -04:00
archipelago
c4cd5fdc90 docs(master-plan): §8b resume — gate green + 6-node deploy + APK fix + workstream F
Comprehensive resume for the session restart: single-node gate green
(5/5 .228), latest backend + UX + one-tap companion APK deployed to 6
nodes (table w/ creds + pending 100.64.83.15 cred), workstream-F bugs
from manual testing, agreed next order (netbird → Phase-3 → F →
multinode), and loose ends (untracked AppLoadingScreen.vue, broken
gitea-local mirror, don't-delete-bitcoin-data directive).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 06:56:54 -04:00
archipelago
ccb594fb85 test(gate): fix bitcoin-knots getinfo-after-restart helper + IBD note
It called bats-assert's `fail` (not loaded in this file) → "fail:
command not found"/127, masking the real reason. Emit+return instead,
bump the cold-restart RPC window 60s→120s (block-index reload), and
note a node mid-IBD legitimately can't serve getinfo (environmental
precondition, not a product regression).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 06:28:20 -04:00
archipelago
deff380191 docs(master-plan): workstream F (lifecycle perfection) + §10 state-mgmt backlog
The 2026-06-23 5×-green gate is DESTRUCTIVE-tier / ~8 core apps only —
it skips uninstall/reinstall (cascade) and has no progress-UI or
all-apps coverage. Manual multinode testing found real bugs it never
ran (immich+grafana uninstall hangs at full-red bar + ghost in My Apps;
grafana reinstall stops; fedimint guardian "waiting for bitcoin sync").
Adds §4 row F, §6b post-deploy order (netbird→Phase-3→F), §6c scope +
observed bugs + definition-of-done, a §5 warning, and §10 backlog to
investigate TanStack-Query/push-based state management for neode-ui.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 06:28:19 -04:00
Dorian
5c43e12782 chore(android): publish companion as raw APK instead of zip
Serve the companion download as a plain .apk so a phone installs it
straight from the link/QR with no unzip step. Repoint the in-app
download URL, the ship + publish scripts, and the pre-push hook at
archipelago-companion.apk, and drop the legacy .apk.zip.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 09:41:10 +01:00
Dorian
e825bbed73 feat(android): file upload/download + in-app tab redesign
Companion WebView now supports file inputs and downloads, and apps
opened in the in-app tab get a proper loading splash and a footer
control bar matching the web app-session bar.

- onShowFileChooser wired to an ActivityResultLauncher so <input
  type=file> opens the system file browser (kiosk + in-app tab)
- DownloadListener: http(s) via DownloadManager (forwarding session
  cookies), blob: via JS->base64->MediaStore, data: decoded inline
- in-app tab: app-icon + progress loading splash (eager favicon
  fetch, upgraded via onReceivedIcon)
- footer controls (back/forward/refresh/open/close) matched to the
  web AppSession mobile bar, with the same SVG glyphs as drawables
- bump to 0.4.8 (versionCode 12)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 09:41:10 +01:00
archipelago
0dd19f0721 docs(CLAUDE.md): single-node gate GREEN — demote priority banner
run-gate.sh 5/5 on .228. Reframe the TOP PRIORITY banner as
gate-green; keep the master plan as north-star source of truth; mark
the gate definition-of-done green and point at multinode as the next
exit criterion.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 04:35:50 -04:00
archipelago
ae47897601 docs: single-node production gate GREEN (5/5 on .228) — demote banner
run-gate.sh 5×-green on .228, 0 not-ok (gate-5x5.log). Records the
milestone in the header/banner, §4 workstream E, §6 sequence, and §8b;
demotes the priority banner per §6 item 6. Next: bundled testing deploy
(.116/.198 + UX frontend), multinode pass, workstreams B/C/D.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 04:27:36 -04:00
archipelago
256d354048 docs(master-plan): tick off §8 P1 mobile app-launch UX (code-complete)
Mobile launch UX is code-complete on branch `companion-mobile-ux` (store-driven
panel, no interstitial, in-app WebView footer + loader, mesh 100dvh, ElectrumX
icon, companion v0.4.7 + shared debug keystore). Marked code-complete pending
on-device/mobile-web verification and merge to main.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 04:11:25 -04:00
archipelago
2a249b8a48 feat(android): companion in-app WebView footer controls + loader; shared debug key; v0.4.7
- InAppBrowser now has a bottom control bar (back/forward/reload/open-in-browser/
  close) mirroring the web mobile footer, plus a centered loading screen
  (app favicon + progress bar) instead of a bare top bar over black.
- Commit a repo-dedicated debug keystore and pin signingConfigs.debug to it so
  every machine — and the published companion download — signs debug builds with
  the SAME key (fixes "App not installed" signature-mismatch on update). Force v1+v2.
- Bump versionCode 10→11, versionName 0.4.6→0.4.7.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 03:48:58 -04:00
archipelago
a7c7c44843 feat(neode-ui): mobile app-launch UX — store-driven panel, loader, ElectrumX icon
- Mobile launches use the store-driven panel (no route push) so the background
  tab no longer changes and closing returns to where you launched from.
- Tab-only apps open directly (in-app WebView on companion / new tab on PWA) —
  no "this app opens in a tab" interstitial.
- Shared AppLoadingScreen (app icon + progress bar) on the app session and the
  legacy iframe overlay instead of a black screen.
- Pin the dashboard to 100dvh on mobile so the mesh chat/tools panes stop sliding
  under the bottom tab bar in mobile browsers (no-op in the companion WebView).
- ElectrumX/electrs/electrs-ui ids now resolve to the real ElectrumX icon in My Apps.
- isMobile made reactive so overlay/footer/teleport decisions track the viewport.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 03:48:57 -04:00
archipelago
2afd18c6de test(gate): poll immich lan_address to absorb mid-recreate churn
5× run #4 flaked iter4 on "immich exposes its web UI lan-address
(port 2283)": container-list returned lan_address=null because
immich_server was momentarily mid-recreate when the read-only tier
queried it (passed the other 4 iterations; immich_server does publish
0.0.0.0:2283->2283). Same single-shot-read class as the bitcoin-knots
state probe — poll <=30s for the exposed port instead of one read. A
genuinely unexposed immich never publishes 2283, so real port drift
is still caught.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 03:20:18 -04:00
archipelago
6511754545 docs: master-plan §8b — 5× triage, mempool restart bug fixed
Record the overnight 5× outcome (2/5) and the triage: all three
fails were distinct one-offs. iter1 #5 bitcoin-knots = pre-launch
churn (hardened anyway); iter2 #74 + iter5 #73 = one real
orchestrator bug (phantom stack-member injection in
ordered_containers_for_start), now fixed + live-verified on .228.
Update the resume check command to gate-5x4.log.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 02:23:07 -04:00
archipelago
92d7f52dd6 fix(orchestrator): order only live containers on package start/restart
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>
2026-06-23 02:22:50 -04:00
archipelago
57a013bc66 test(gate): make 5× the canonical gate, drop 20x naming
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>
2026-06-22 18:12:41 -04:00
archipelago
0f05f73a23 fix(mempool): self-healing nginx backend proxy (v3.0.1) + gate timeout
The frontend nginx used a literal proxy_pass host with no resolver, so it
pinned mempool-api's IP at worker startup. When the backend restarts (gate,
OTA, crash, reboot re-IPAM) podman reassigns its IP and nginx keeps proxying
to the dead one -> /api hangs, websocket 502s, UI shows 'offline' until a
manual nginx reload. Same stale-upstream-IP class as the netbird 502.

Fix: mempool-frontend:v3.0.1 rewrites the generated nginx-mempool.conf to
re-resolve the backend per-request via 'resolver' + a variable proxy_pass.
Resolver address is read from /etc/resolv.conf (podman aardvark-dns answers
on the network gateway, not Docker's 127.0.0.11). Per-location path mapping
preserved (ws -> '/', /api/v1 identity via no-URI, /api/ -> /api/v1/ rewrite).
Proven on .228: backend IP change now auto-recovers with no reload; the
literal-host control still 502s. Migrated the manifest off the retired
tx1138 registry to vps2.

Also: mempool.bats #74 waited only 180s post-restart (the slow path) and
called an undefined 'fail' helper (status 127). Bumped to 300s to match the
passing parity probes and emit a real failure instead.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 18:07:07 -04:00
archipelago
c8acc84506 docs: §2 invariant single-node (.228); multinode → separate plan 2026-06-22 17:23:19 -04:00
archipelago
8355453a7e docs: exact cutoff-proof resume in master-plan SS8b (resume from any device)
Captures: .228 1x-GREEN (110/110); hardened 5x DETACHED on .228 (/tmp/gate-5x2.log,
nohup — survives terminal close) with the exact check-from-any-machine command; all
shipped code fixes (commits) + deploy state (.228 + .198); node-state fixes NOT in
repo (lnd nginx proxy 8081->18083, home-assistant orphan unit removed, electrumx
re-registered); the run-ON-the-node lesson; and remaining work.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 17:22:29 -04:00
archipelago
98f4fa44a8 test(gate): harden readiness for sustained 5x churn + inter-iteration settle
The 1x gate is green; the 5x failed iters 1-2 on readiness-under-churn (apps DO
recover — lnd synced, mempool just mid-restart when probed — but slower than the
windows when restarted back-to-back). Hardening:
- run-20x.sh: best-effort settle_stack() before each iteration (wait for
  mempool-api/frontend + lnd RPC healthy, 180s, on-node, never fails the run).
- required containers present/running (80/81): wait-loops (180s) not single-shot.
- mempool api/frontend (87/88): retry ~180s not single-shot.
- mempool queryable (74): 60s->180s. lnd restart-running (64): 120s->240s.
  lnd getinfo (60): 90s->240s retry.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 17:11:15 -04:00
archipelago
22b05de6d9 docs(roadmap): P1 mobile app-launch UX — drop 'opens in a tab' interstitial
Companion app: open every app in the in-app WebView (not just non-iframeable),
carrying the mobile-iframe footer controls into the WebView. Mobile web (PWA):
open tab-apps directly in a new tab. No interstitial on either surface. Touch
points + prior commits (b5a9deb8, d1fbcd9b) noted.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 16:57:44 -04:00
archipelago
27299ea687 docs: make the production test gate a SINGLE-NODE (.228) criterion; split out multinode
Per direction: the gate is now 5x green ON .228 only (run on the node, not via RPC).
Fleet/multinode verification (.198 + others) moved to a new docs/multinode-testing-plan.md
with the bootstrap recipe, per-node preconditions (synced archival bitcoin, no stale
nginx proxy targets, no orphan quadlet units), node roster, and cross-node suites.
Updated CLAUDE.md, master-plan SS5/SS6/SS8b/WS-E, and TESTING.md release gates.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 16:47:34 -04:00
archipelago
892ff083c4 test(gate): fix the last 4 readiness/config false-fails (none are product bugs)
On a proper on-node .228 run (synced bitcoin, 4-fix binary) the lifecycle matrix is
green; these 4 were test-harness issues:
- lnd 'recovers after restart' (65): bump retry window 90s->240s. lnd cold-restart
  recovery (wallet unlock + bitcoind reconnect + graph sync) exceeds 90s on a loaded
  node but DOES complete (synced_to_chain:true).
- bitcoin ui responds (89): retry ~120s instead of single-shot (companion nginx may
  have just been recreated by the companion-survives test).
- probe_app_url (99 lnd proxy + all ui-coverage proxy probes): retry up to 90s for
  post-restart proxy/UI readiness instead of single-shot.
- required endpoints after restart (94): :8081 is nginx-proxy-manager, an OPTIONAL
  app (not in required_containers) — only assert it when NPM is installed; and make
  the trailing lncli getinfo a retry.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 15:43:51 -04:00
archipelago
8893055810 test(gate): retry lnd getinfo for RPC readiness (wallet-unlock lags 'running')
lnd's RPC isn't ready until its wallet auto-unlocks on (re)start, which lags the
container 'running' state — single-shot lncli getinfo raced that window and
false-failed (gate tests 60 + 85). Retry up to ~90s like a health probe. lnd is
functional (getinfo returns cleanly once ready).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 14:45:36 -04:00
archipelago
53b8e47f1d test(gate): fix two false-failing lifecycle tests (not product bugs)
- immich restart: bump wait 120s->240s. Restart = ordered stop+start of the 3-
  container stack (postgres->redis->server w/ DB migrations), so it needs at least
  as long as the start test (180s) — the old 120s was inconsistent and false-failed
  on loaded nodes. immich does return to running.
- fedimint orphan check: the unanchored 'total' regex (^fedimint) counts the
  legitimate fedimint-clientd (dual-ecash bridge) but the anchored 'known' regex
  omitted it -> total>known false orphan on every node running fedimint-clientd.
  Add fedimint-clientd to known.

Both run as LOCAL podman/systemctl on the gate runner, so they test the runner node
(.116), not the RPC target — surfaced while driving the .228 gate green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 14:11:35 -04:00
archipelago
f4727bfdb3 docs(gate): companion self-heal fix validated (10s) + test-31 harness caveat
Independent companion loop (452f05d8) validated on .228: deleted archy-electrs-ui
recreates in ~10s (was stuck 100s+). Also: companion-survives bats does LOCAL
rm/systemctl --user, so running it from .116 via RPC tests .116's companions with
.116's binary, NOT the remote target — must run ON the target node. Explains the
'failed on both nodes' runs (both silently tested .116).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 13:44:57 -04:00
archipelago
452f05d849 fix(reconciler): decouple companion self-heal onto its own cadence
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>
2026-06-22 13:04:28 -04:00
archipelago
de7d3d83dc docs(gate): final read — every failure fixed/explained, no lifecycle bugs remain
Last 2 .228 stragglers confirmed load/timing, not bugs: test 31 (companion recreate)
= contamination + ~108s reconcile cadence > 90s window; test 55 (immich restart) =
heavy stack restarts >120s under load but DOES return. Path to literally-green gate
is infra (bitcoin sync, re-quadletize .228) + minor test-window tuning. Optional
product improvement noted: independent ~30s companion-reconcile cadence.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 12:36:03 -04:00
archipelago
76b23adcc0 docs(gate): test 31 root-caused = .228 contamination (not a product bug)
companion::reconcile only recreates a deleted companion unit when its parent
backend is in manifest_ids. On contaminated .228, electrumx ran as plain podman
and was NOT a tracked manifest install (manifest on disk but unloaded), so the
reconciler never iterated it -> archy-electrs-ui companion orphaned. Proven:
package.install electrumx re-registered it + restored the companion. Self-heal
logic is sound; test 31 clears on re-quadletize. electrumx on .228 de-contaminated.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 11:34:55 -04:00
archipelago
47a5148865 docs(gate): two-node result — stop blocker FIXED; residual red is bitcoin-IBD + node prep
.228 104/110, .198 94/110 with the 3-fix binary. Every package.stop test passes on
healthy apps. .198's 14/16 failures trace to bitcoin in IBD (test 83: ~137k blocks
behind) cascading to lnd/btcpay/electrumx/mempool. 2 node-independent: companion
recreate (31, both nodes), fedimint orphan pollution (44). Path to green 5x gate is
now infra (sync bitcoin, re-quadletize .228) + minor (test 31), not lifecycle bugs.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 11:09:12 -04:00
archipelago
b090235b04 docs(gate): 3 stop bugs FIXED, electrumx suite GREEN on .228
Stop failure was 3 real product bugs (grace / reconcile-resurrection /
container-list user-stopped state), all fixed (2dad64b2, 760a32bc, 6e49ce6f) +
deployed. electrumx lifecycle suite 10/10 green (66s). fedimint 'crash loop' was
probe-induced churn (stable when left alone). Validating breadth next.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 09:49:45 -04:00
archipelago
6e49ce6f88 fix(container-list): report user-stopped apps as stopped despite live UI companion
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>
2026-06-22 09:26:30 -04:00
archipelago
760a32bccf fix(reconcile): keep user-stopped apps stopped (reconciler was resurrecting them)
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>
2026-06-22 09:04:02 -04:00
archipelago
29cd167894 docs(gate): stop-grace fix shipped+validated; gate is multi-caused (5 issues)
Fix deployed to .198+.228, vaultwarden stops clean (no regression). But validation
showed the gate failures are multi-caused: (2) fedimint crash-looping/unhealthy on
both nodes can't be stopped; (3) host-listener repair watchdog restarts
port-unreachable containers fighting stop; (4) gate waits for 'stopped' but apps end
'exited'/'absent' (Exited->Stopped conversion key mismatch); (5) grace vs 60s
gate-timeout (electrumx 300s); (6) .228 contamination. Documented + re-sequenced
NEXT STEPS (fedimint health is the new top blocker).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 08:07:43 -04:00
archipelago
2dad64b2ee fix(stop): honour per-app graceful-stop grace in orchestrator stop path
package.stop left slow-to-SIGTERM apps (fedimint/electrumx/bitcoin/btcpay/immich)
running: the orchestrator path hardcoded podman API ?t=10 / CLI -t 30 and the CLI
wrapper deadline (30s) equalled the -t grace, so the await fired exactly as podman
SIGKILLed -> stop reported failed -> state reverted to running. Reproduced live on
clean .198 (fedimint).

- container/runtime.rs: add ContainerRuntime::stop_container_with_grace (defaulted
  so mock/dev impls are unchanged); PodmanRuntime honours grace for API + CLI with
  deadline = grace + 15s buffer; AutoRuntime delegates. New canonical per-app table
  stop_grace_secs_for() + DEFAULT_STOP_GRACE_SECS / STOP_GRACE_DEADLINE_BUFFER_SECS.
- podman_client.rs: stop_container_with_grace uses ?t=<grace> + longer HTTP deadline.
- prod_orchestrator::stop: resolve grace = manifest stop_grace_secs (north-star) else
  the table; pass to quadlet::stop_service_with_timeout AND stop_container_with_grace.
- quadlet.rs: stop_service_with_timeout so slow apps aren't SIGKILLed at 45s.
- rpc/package/runtime.rs: doc-note its &str stop_timeout_secs mirrors the canonical table.
- tests: resolve_stop_grace_secs (manifest field wins / table fallback / default 30).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 06:59:40 -04:00
archipelago
470e3c649a docs(gate): ROOT-CAUSE the stop blocker — orchestrator ignores per-app stop grace
Reproduced live on CLEAN .198: package.stop fedimint -> 'podman stop -t 30
timed out after 30s' -> stop fails -> state reverts to running. Real fleet-wide
bug (NOT .228 contamination). stop_timeout_secs() per-app grace (bitcoin 600/lnd
330/electrumx 300/fedimint 60) is used by legacy stop paths but NOT the
orchestrator path: ContainerRuntime::stop_container hardcodes API ?t=10 / CLI
-t 30, and PODMAN_CLI_DEFAULT_TIMEOUT=30s == the -t grace so the await fires as
podman SIGKILLs. Fix = thread per-app grace + widen wrapper deadline; owner picks
table-based vs manifest-driven stop_grace_secs. Re-escalated to blocker.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 06:17:23 -04:00
archipelago
a111d79a05 docs(gate): downgrade stop-blocker ⚠️ — .198 has quadlet units, .228 state was my contamination
.198 ground truth: backend apps ARE quadlet (.container files present) -> quadlet
is the intended runtime. .228's plain-podman state traced to my cascade-gate
uninstall + package.start restore (no quadlet regen). Two real robustness sub-bugs
remain (start should regen quadlet; stop podman-fallback gap). Next: canonical
gate on CLEAN .198 first to tell real-bug from contamination.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 06:00:42 -04:00
archipelago
47026fae30 docs(gate): document package.stop blocker + quadlet-vs-podman finding (.228)
5x gate run surfaced a real blocker: package.stop does not stop electrumx/
bitcoin-knots/btcpay/fedimint/immich (container stays running; gate stop-wait
times out). Root cause chain: these backend apps run as plain podman
--restart=unless-stopped, NOT quadlet units (PODMAN_SYSTEMD_UNIT empty; only UI
companions + home-assistant have .container files; bitcoin-core.container is
.disabled). orchestrator.stop() podman-fallback fires for filebrowser but not
electrumx -> suspect loaded()/is_unknown_app_id_error gap. stop->stopped state
reporting itself is correct (filebrowser proof, user_stopped guard).

Also: corrected the canonical gate invocation (DESTRUCTIVE only, not CASCADE);
restored .228 after my cascade-gate left apps stranded.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 05:47:11 -04:00
archipelago
d6fa262d69 docs(#20): consolidate master-plan resume — indeedhub migration 2-node verified (.228+.198); cutoff-proof next-steps + deploy facts
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 04:23:52 -04:00
archipelago
e2a012d086 fix(indeedhub): frontend health = tcp:7777 not http GET / (stops reconcile churn)
On the loaded .198 the frontend churned (created → "unhealthy" → reconciler
recreates → loop). The http health check fetched / through nginx (SPA +
sub_filter) and false-failed under node load; the reconciler then treated the
frontend as wedged and recreated it. nginx binds 7777 at startup, so a tcp
liveness check passes immediately and stays green under load while still
catching a real "nginx not listening" failure. Generous retries/start_period.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 03:39:26 -04:00
archipelago
e4d3f94913 docs(#20): hook exec cgroup gap FIXED + verified on .228 (scoped exec)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 17:57:17 -04:00
archipelago
ff78b31212 fix(hooks): run post_install exec in a transient user scope (fixes cgroup denial)
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>
2026-06-21 17:38:23 -04:00
archipelago
fdb465f8ac docs(#20): indeedhub fresh-create FIXED + verified on .228 (special-cases deleted + nginx caps); hook exec cgroup gap noted
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 17:26:23 -04:00
archipelago
ff8f11b87e fix(indeedhub): frontend nginx needs SET{UID,GID}+CHOWN+DAC_OVERRIDE under cap-drop-ALL
Live fresh-create on .228 (post special-case removal) had nginx workers die
with "setgid(101) failed (Operation not permitted)" → workers exited code 2,
port published but nothing served (HTTP 000). The orchestrator does
--cap-drop=ALL, so unlike the legacy `podman run` (default caps) nginx's master
couldn't drop workers to the nginx user. Declare CHOWN/DAC_OVERRIDE/SETGID/SETUID
(SET* to drop the worker user, CHOWN+DAC_OVERRIDE for the tmpfs proxy cache).

Verified on .228: frontend fresh-creates, caps applied, nginx serves, UI 200
incl. /api/ and /nostr-provider.js.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 17:24:34 -04:00
archipelago
b73084dbb0 refactor(indeedhub): delete orchestrator special-cases; use generic path (#20 phase 3)
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>
2026-06-21 17:11:33 -04:00
archipelago
84031e6209 docs: temporarily reduce release lifecycle gate from 20x to 5x
Per user direction: the production test gate is 5x (ARCHY_ITERATIONS=5) on
.228 AND .198 for now, down from 20x. Restore to 20x before the final ship.
Updated CLAUDE.md, PRODUCTION-MASTER-PLAN.md, and tests/lifecycle/TESTING.md.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 17:11:00 -04:00
archipelago
9c45f718a2 docs(#20): fresh-create path blocked by legacy indeedhub orchestrator special-cases; fix plan + .228 recovered
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 16:36:22 -04:00
archipelago
8bdc857911 docs(#20): indeedhub phase 3 adoption path live-verified on .228
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 16:23:09 -04:00
archipelago
d2f7c4abf3 docs(#20): phase 3 code-complete (indeedhub manifests + orchestrator-first); next = .228 live verify
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 15:48:18 -04:00
archipelago
b1eea8c053 feat(indeedhub): manifest-driven 7-member stack, orchestrator-first (#20 phase 3)
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>
2026-06-21 15:46:26 -04:00
archipelago
b94b61f640 feat(manifest): network_aliases — extra DNS aliases on a container's network
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>
2026-06-21 15:45:11 -04:00
archipelago
ccb5b7ca39 docs(#20): mark hook phases 1+2 done; resume notes point to phase 3 (indeedhub)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 11:49:05 -04:00
archipelago
955c54b713 feat(hooks): post_install executor + install-path wiring (#20 phase 2)
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>
2026-06-21 11:45:28 -04:00
archipelago
4c1a4e5976 feat(hooks): manifest lifecycle-hooks schema (#20 phase 1) + fix container test literals
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>
2026-06-21 11:07:00 -04:00
archipelago
b0b54a96fa test(lifecycle): immich suite — package-level checks, wait-based destructive tier
container-list reports stack apps package-level (.name="immich"), so the suite
checks the "immich" package (presence, valid state, :2283 lan-address) rather than
individual container names. Destructive tier fires async stop/start/restart and
asserts on the end state via wait_for_container_status.

KNOWN: the destructive tier is flaky for slow multi-container stacks — bats runs
ops back-to-back with no settling while immich's async stack ops take 30s+, and
stopped reports as "exited" not "stopped". The immich migration itself is verified
working (manual stop/start/restart succeed; all 3 containers healthy). Hardening
the harness for stack apps (inter-op settling + stopped|exited acceptance) is a
follow-up.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 09:52:33 -04:00
archipelago
f0c6b79d1a fix(immich): name containers underscore to match runtime lifecycle code
package.stop/start/restart broke ("no containers found" / "no such object
immich_postgres") because the runtime hardcodes the immich stack's container names
as immich_server/immich_postgres/immich_redis (underscore) across 8 files
(lifecycle, health, crash-recovery, ports, config). The migration had named the
containers by app_id (hyphen), mismatching all of it.

Root cause of the earlier failed attempt: container_name was nested under an
`extensions:` block, but `app.extensions` is serde(flatten) — container_name must
be a TOP-LEVEL app key to be read by compute_container_name. Fixed: set
container_name: immich_server / immich_postgres / immich_redis at top level, and
point DB_HOSTNAME/REDIS_HOSTNAME at the underscore aliases. App ids stay hyphen
(immich/immich-postgres/immich-redis) so the catalog identity (title+icon) holds.

Manifest-only change — container names now match existing runtime references, no
code edits to the 8 files. (Deriving stack containers from manifests instead of
hardcoded lists remains a north-star follow-up.)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 09:20:38 -04:00
archipelago
b1f175b927 test(lifecycle): add immich stack lifecycle suite
RPC-based (host-agnostic) lifecycle coverage for the manifest-driven immich stack
(immich + immich-postgres + immich-redis): presence + valid state of all 3 members,
a guard that no legacy underscore containers exist (catches botched migration /
legacy-installer fallback), destructive stop/start/restart of the server with
postgres+redis staying up, and cascade uninstall/reinstall (preserve_data).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 09:01:19 -04:00
archipelago
c548705147 docs: master plan — mark registry-manifest phases 1-3 + immich + reboot-survival done
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 08:25:40 -04:00
archipelago
f160e0c404 fix(reboot): enable podman-restart.service at startup (--restart reboot-survival)
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>
2026-06-21 08:23:19 -04:00
archipelago
d5ef45731a fix(immich): restore canonical app_id "immich" (title + icon)
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>
2026-06-21 08:07:08 -04:00
archipelago
0860dfacc7 feat(ui): Services tab — backend classification, parent icons, categories sub-nav
- Classify databases/APIs/backends into Services (#10): add immich-postgres/redis
  to SERVICE_NAMES; isServiceContainer matches -postgres/-redis/-valkey/-cache/-db
  suffixes; isWebsitePackage final fallback now routes any no-UI, non-known package
  to Services ("anything that isn't the frontend UI launcher").
- Services show their parent app's icon (#14): backends reuse the app logo
  (immich-* → immich, archy-btcpay-db → btcpay, indeedhub-* → indeedhub, etc.)
  via explicit APP_ICON_FALLBACKS + prefix map, instead of 404 → 📦.
- Categories sub-nav for Services (#12): getServiceCategory + buildServiceCategories
  + useServiceCategories; Services tab gets the same desktop/mobile category strips
  (Databases/Caches/APIs/Backends), shown only for categories with items. Shared
  selectedCategory resets to 'all' on tab switch.
- Mobile swipe (#11): the tab-swipe gesture is suppressed over .mobile-category-strip
  so swiping the category chips scrolls them instead of changing tabs (covers both
  My Apps and the new Services strip).

vue-tsc build clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 07:42:48 -04:00
archipelago
9e6c5370fc feat(immich): manifest-driven stack via orchestrator — live-migrated on .228
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>
2026-06-21 07:08:45 -04:00
archipelago
011081d180 feat(immich): scaffold registry manifests for postgres/redis/server (not yet live)
immich becomes a manifest-driven stack (the legacy install_immich_stack — hardcoded
podman run + sudo chown — is the anti-pattern being retired). Three image-only
manifests modelled on the btcpay stack + the live .228 container config:

- immich-postgres / immich-redis / immich-server on archy-net; container_name set
  to the underscore form (immich_postgres/_redis/_server) so the server's
  DB_HOSTNAME/REDIS_HOSTNAME aliases resolve.
- generated_secrets: [immich-db-password] (idempotent — reuses the live secret on
  existing nodes; postgres is already initialised with it).
- server depends on postgres+redis (install ordering); upload bind preserved.

Inert for now: not added to the UI catalog and install_immich_stack still the
default, so nothing installs these until the orchestrator wiring + on-node
ownership (data_uid) validation lands. Schema validated by the all-manifests
round-trip test. See docs/PRODUCTION-MASTER-PLAN.md §6.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 05:53:58 -04:00
archipelago
7bfbe8fe40 feat(registry-manifest): phase 2 — publisher embeds manifests into signed catalog
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>
2026-06-21 05:46:17 -04:00
archipelago
220666d3a9 feat(registry-manifest): phase 1 — orchestrator consumes manifests from signed catalog
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>
2026-06-21 05:30:38 -04:00
archipelago
192238cbb8 docs: consolidate into PRODUCTION-MASTER-PLAN, add CLAUDE.md, prune 25 stale docs
Single authoritative hub (docs/PRODUCTION-MASTER-PLAN.md) for the app-platform
north star: every app manifest-driven (zero OS-level reliance), manifests via the
signed registry, developer-ready external marketplace; rootless/secure/robust/
100%-uptime. Repo CLAUDE.md (auto-loaded each session) points agents at it until
the 20x lifecycle gate is green. New design doc registry-manifest-design.md.

Consolidated docs 56 -> 28: deleted dated handoffs/resumes/transcripts and
superseded trackers (content folded into the master plan or already in memory).
Kept all evergreen design/reference docs + ADRs (the master links them).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 05:11:32 -04:00
archipelago
03a4ee1b30 feat(container): manifest-declared generated secrets + companion/quadlet hardening
Generated-secrets system: apps declare `generated_secrets` in their manifest
(kinds hex16/hex32/bcrypt); `container::secrets::ensure_generated_secrets`
materialises them 0600/rootless in resolve_dynamic_env — idempotent and
self-healing (recovers wrongly root-owned secrets with no privilege). Replaces
per-app Rust (deletes ensure_fmcd_password). fedimint-clientd/gateway manifests
now declare fmcd-password / fedimint-gateway-hash.

companion.rs: rebuild the auto-built :latest image when its build context changes
(staleness check) so baked-in fixes (e.g. guardian-UI CSS) actually reach nodes.

quadlet.rs: skip PublishPort under Network=host (podman rejects the combo, exit
125) + regression tests.

UI: "Fedimint Guardian" rename, fedimint-clientd/nostr-rs-relay/meshtastic tagged
as Services (headless backends), gateway icon fallback.

Deployed + verified on .228 (generated-secrets fixed fedimint-gateway start;
grafana/strfry orphan crash-loop units removed).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-21 05:11:07 -04:00
archipelago
db7d424bff feat(content): owned-content persistence + Fedimint paid downloads, fmcd caps fix, FIPS warm-path perf
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>
2026-06-20 18:58:52 -04:00
archipelago
b0c9bd2a0c docs: #7 exhaustive isolation — seccomp ruled out; fmcd runs standalone, orchestrator-managed fails (open)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-20 14:39:33 -04:00
archipelago
63b98599e8 Revert "fix(fedimint): run fmcd with seccomp=unconfined so its DHT can start (#7)"
This reverts commit 409543c41e78025354acbdde5ffc6445895d4508.
2026-06-20 14:37:24 -04:00
archipelago
409543c41e fix(fedimint): run fmcd with seccomp=unconfined so its DHT can start (#7)
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>
2026-06-20 13:08:13 -04:00
archipelago
d59cf6d299 docs: session 3 — ecash confirm+refund, #5 confirmed, #7 fmcd-on-.116 EPERM
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-20 12:28:24 -04:00
archipelago
12f54e390d feat(wallet): ecash pay confirmation screen + auto-refund on failed sale (#3)
- 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>
2026-06-20 12:16:02 -04:00
archipelago
242baf5deb fix(ui): on-screen error overlay so companion crashes are visible without a console
chrome://inspect isn't always reachable on the Android companion WebView, so the
real error stayed invisible. Add a plain-DOM, screenshot-able overlay (built
without Vue so it survives a crash in Vue itself) that shows the captured error
message + stack and a Copy button for the full window.__archyErrors buffer.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-20 10:23:59 -04:00
archipelago
0ab160b5c3 docs: deploy state — all 6 nodes on 4a8f2198 build (#12/#2/#3/#10)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-20 10:15:59 -04:00
archipelago
a6957a48f7 fix(netbird): wait for OIDC discovery before reporting install done (#10)
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>
2026-06-20 08:57:37 -04:00
archipelago
2761f0d70f docs: handoff — session 2 progress (#12/#2/#3 code-complete, deploy held)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-20 08:52:07 -04:00
archipelago
a8c668ee0a fix(ui): stop mobile tab bar covering last row of content (#2)
On Cloud/files (and any scrolling view), the bottom of the list could sit behind
the fixed mobile tab bar. Cause: DashboardMobileNav measured the bar's
offsetHeight and wrote it to --mobile-tab-bar-height, but when the bar was hidden
or not yet laid out the measurement was 0 — and writing "0px" defeats the
", 88px" fallback in the .mobile-scroll-pad clearance calc (an explicit 0 is
still a set value), so the clearance collapsed and the ~88px bar overlapped the
last row.

- never write 0px: only set a real measured height, else remove the var so the
  88px fallback applies.
- re-measure after first paint (rAF) and after the WebView safe-area injection,
  so the clearance reflects the bar's final laid-out height.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-20 08:50:44 -04:00
archipelago
8f06d88fbf feat(wallet): pay for peer files from BOTH Cashu and Fedimint ecash (#3)
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>
2026-06-20 08:13:23 -04:00
archipelago
b3633ec525 fix(ui): surface real error instead of generic toast + catch async errors
The global Vue errorHandler swallowed every crash into "Something went wrong.
Please refresh the page." — which hides exactly what we need to diagnose the
companion-app (Android WebView) post-login crash. Now:
- the toast shows the real (truncated) error message;
- a 25-entry ring buffer is kept on window.__archyErrors for retrieval where
  there's no console (companion WebView via chrome://inspect, or a debug view);
- window 'error' and 'unhandledrejection' listeners catch async/non-Vue errors
  that Vue's errorHandler misses (e.g. a JS API absent in an older WebView).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-20 08:05:51 -04:00
archipelago
f92e442bfc fix(mesh): collapse cross-transport twin contacts into one conversation (#12)
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>
2026-06-20 08:01:14 -04:00
archipelago
5f7e8dca80 docs: handoff — mesh rename done, .120->.89 dup-contact diagnosis, netbird TODO
Resume notes for the 1.8.0 bug-bash mesh work: Meshtastic rename shipped +
verified; .120->.89 'non-delivery' diagnosed to a duplicate-contact surfacing
bug (messages inject fine, split across federation/radio twin contact_ids);
design for the dedup fix (#12) and the netbird logout-race map (#10).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-20 06:06:03 -04:00
archipelago
d00d1b20d7 fix(mesh): rename Meshtastic radio to the node's server name
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>
2026-06-20 06:04:22 -04:00
Dorian
b00c5247f5 chore(android): update companion apk download 2026-06-20 10:34:49 +01:00
Dorian
e39e0370e2 fix(android): push icon ring to home-screen visible edge (scale 0.65, v0.4.6)
Calibrated from a device home-screen screenshot: launcher3 crops less than the
App-info view, so the ring at 0.53 sat ~78% out. Scale 0.65 reaches the edge.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-20 10:34:44 +01:00
Dorian
3b9eb35a37 chore(android): update companion apk download 2026-06-19 22:22:59 +01:00
Dorian
011f6559e1 fix(android): icon ring matching logo.svg gradient at visible edge (v0.4.5)
Ring uses logo.svg's #000->#666 gradient (stroke 22.8834) pushed to scale 0.53
so it sits at the launcher's visible crop edge (calibrated from a device
screenshot). Grid at 0.55. versionCode 9 so launcher3 refreshes its icon cache.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 22:21:58 +01:00
Dorian
979e6525b7 fix(android): icon ring at visible crop edge (scale 0.50) + version 0.4.4
Device App-info screenshot showed the launcher only renders the central ~54%
of the adaptive icon, clipping the ring. Calibrated the ring to scale 0.50 so it
lands at the visible circle edge; grid to 0.55. Bump versionCode 8 so launcher3
refreshes its icon cache (it keys the cached bitmap by versionCode).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 22:21:58 +01:00
archipelago
af816c61a5 fix(ui): reliable federation-join feedback (90s timeout + re-check + success)
Joining a Fedimint federation is heavy and routinely outlasts the default 15s
client timeout while still succeeding server-side, so the UI wrongly showed
failure. Bump the join timeout to 90s, and on any error re-check the list: if a
new federation appeared the join worked — show 'Federation joined.' instead of
a misleading error.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 16:43:30 -04:00
archipelago
63611a4453 fix(mesh): honour explicit !ai allowlist for unauthenticated stock clients
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>
2026-06-19 16:43:30 -04:00
archipelago
7831e68d13 fix(wallet): redeem across all federations, unified ecash history, fmcd healthcheck
- 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>
2026-06-19 16:43:29 -04:00
Dorian
0f2e6f6aaf chore(android): update companion apk download 2026-06-19 21:28:29 +01:00
Dorian
5afe9e4aec fix(android): whole badge in background layer, ring inset to survive mask
Put dark fill + inset metallic ring (0.88) + grid (0.58) all in the background
(renders to the mask edge, no safe-zone crop); transparent foreground. Matches
a locally-rendered, circle-masked preview so the ring is visible and uncut.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 21:28:26 +01:00
Dorian
857dc66240 chore(android): update companion apk download 2026-06-19 19:22:00 +01:00
Dorian
75f7020e3e fix(android): ring at circle edge (background layer) + smaller grid
Move the metallic ring into the background (renders to the mask edge, unlike the
foreground which is cropped to the safe zone) so the border is finally visible
at the circle's rim; shrink the grid to ~0.55 so the mark isn't too big.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 19:21:57 +01:00
Dorian
75666cdc31 chore(android): update companion apk download 2026-06-19 19:20:21 +01:00
Dorian
8977ea92e8 fix(android): shrink icon grid within the ring for more margin
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 19:20:18 +01:00
Dorian
ca38f5d8f4 chore(android): update companion apk download 2026-06-19 19:05:57 +01:00
Dorian
d72cb57545 fix(android): brighter, thicker icon rim (#555->#A5A5A5, stroke 28)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 19:05:55 +01:00
Dorian
dc2cdca549 chore(android): update companion apk download 2026-06-19 19:00:35 +01:00
Dorian
ee01ab9427 fix(android): make icon rim softly visible (#3A3A3A->#888)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 19:00:35 +01:00
archipelago
cebbde7bde fix(ui): square mobile file tiles, files scroll clearance, apps-tab swipe guard
- Apps tab: a horizontal swipe that starts on an app icon no longer flips the
  top tab — it lets the app-page scroll / icon tap win (swipe empty space to
  change tab). Fixes the swipe conflict with two pages of apps.
- Files: file cover tiles are forced square on mobile (aspect driven by CSS,
  not a Tailwind arbitrary class) so the grid is uniform and tappable.
- Files: scroll container gets bottom safe-area + tab-bar padding so the last
  row clears the mobile back button / bottom nav.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 13:57:51 -04:00
archipelago
a0b80dd27d fix(mesh): authenticate !ai over LoRa via federation-twin binding + signed Text
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>
2026-06-19 13:57:50 -04:00
Dorian
839da80e0b chore(android): update companion apk download 2026-06-19 18:50:39 +01:00
Dorian
f0e9343d74 fix(android): drop white-wrapping round PNG, single SVG-matched icon ring
Revert to a pure adaptive icon (the bare round PNG was getting legacy-wrapped
onto a white circle by the launcher). One ring only, in the foreground, using
the SVG's dark #000->#666 gradient on a plain dark tile.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 18:50:34 +01:00
Dorian
bf6d98195e chore(android): update companion apk download 2026-06-19 18:40:39 +01:00
Dorian
846b2d9646 fix(android): match icon ring to logo.svg gradient (#000->#666)
Revert the brightened grey->white ring back to the original logo.svg gradient
(black->#666, stroke 22.8834) on both the round PNG icon and the adaptive
foreground.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 18:40:37 +01:00
Dorian
6df776b25a chore(android): update companion apk download 2026-06-19 18:32:00 +01:00
Dorian
1074f89c47 feat(android): true-circle round launcher icon (PNG badge)
Render the full circular badge (bright grey->white ring + grid) to round-icon
PNGs at all densities and drop the adaptive round XML, so launchers that use
round icons show a real edge-to-edge circle instead of a mask-cropped coin.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 18:31:57 +01:00
Dorian
726cc132af chore(android): update companion apk download 2026-06-19 18:26:59 +01:00
Dorian
078c1793a9 fix(android): fit full badge (ring + grid) inside icon safe zone
Scale the whole badge to ~0.64 so the bold grey->white ring isn't clipped at
the edge by the launcher mask; bigger, brighter ring. Background is plain dark.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 18:26:54 +01:00
Dorian
b83e2c2f37 chore(android): update companion apk download 2026-06-19 18:26:34 +01:00
Dorian
a2fa57456d fix(android): scale icon badge into safe zone so the ring is visible
The ring at 0.96 sat in the adaptive-icon bleed zone (outer ~18dp cropped by the
launcher), so only the grid showed. Scale badge + grid to 0.68 so the ring lands
at the edge of the visible circle, and brighten it to grey->white.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 18:26:32 +01:00
Dorian
64937df8a2 chore(android): update companion apk download 2026-06-19 18:12:41 +01:00
Dorian
6527e66c07 fix(android): visible metallic icon ring at circle edge
Move the badge ring into the background layer (brightened grey->white so it
reads on #0A0A0A) at ~0.96 so it sits at the masked-circle edge; foreground is
just the white grid. Also honor SHIP_COMPANION in the pre-push hook.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 18:12:38 +01:00
Dorian
07b611d07d chore(android): add companion APK auto-publish hook + script
scripts/publish-companion-apk.sh builds the debug APK and refreshes the served
download neode-ui/public/packages/archipelago-companion.apk.zip; .githooks/pre-push
runs it on every push to main that touches Android. Enable per clone with
  git config core.hooksPath .githooks

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 17:53:38 +01:00
Dorian
dcedf9582a chore(android): update companion apk download 2026-06-19 17:46:44 +01:00
Dorian
f2c420d9c0 feat(android): app icon gradient ring border + companion publish script
Adaptive icon foreground now draws the full badge (black→grey gradient ring +
white grid) scaled to ~0.94 so the ring reads as a clean border at the circle
edge. Adds ship-companion.sh: builds the debug APK and publishes it to
neode-ui/public/packages/archipelago-companion.apk.zip, then commits + pushes.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 17:46:41 +01:00
Dorian
68cd1c120a fix(android): translucent glass DARK controller so backdrop shows through
The controller body/face were opaque, so the synthwave backdrop only peeked
out above/below the controller. Make the DARK palette surfaces translucent
(body/face/inlay) and drop the opaque shadow platform + the gradient's forced
0.95 alpha, so the backdrop reads through the controller as glass. CLASSIC
palette stays solid.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 16:52:02 +01:00
Dorian
993f30456f feat(neode-ui): instant press feedback + launching spinner on app icons
Tapping a dashboard app icon now scales it down immediately (CSS :active)
and shows a per-icon spinner until the app overlay opens, so the tap is
acknowledged even while the app session spins up.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 16:21:48 +01:00
Dorian
aa95e42383 feat(android): circular logo, synthwave backgrounds, glass modal, server names + UX fixes
- New circular badge logo (ic_logo) on Intro + Connect screens; launcher
  icon rebuilt as dark circle + white grid.
- Reddish synthwave backdrop (bg-intro-2) behind Intro, Connect, and the
  remote/gamepad (edge-to-edge with a light scrim); controllers no longer
  paint an opaque fill over it.
- Server name: added to ServerEntry/prefs, the Connect form, the modal
  add-form, and saved-server rows; removal now matches by connection
  identity (rename- and legacy-format-safe).
- NESMenu modal restyled to glassmorphism #0A0A0A with centered, larger
  fields. Connect-form glass cards given a darker base for legibility.
- Intro title/subtitle set to #FAFAFA.
- Deleting the last server clears the active server and returns to Connect.
- D-pad auto-repeat initial delay raised to 500ms so a tap sends one key
  (fixes doubled nav sound).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 16:21:48 +01:00
archipelago
75e470bfa4 fix(mesh): mesh-preferred message routing with FIPS/Tor fallback
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>
2026-06-19 10:09:14 -04:00
archipelago
0ac67f5092 fix(ui): companion QR absolute 146 URL + Dashboard swipe type guard
- Companion app QR encoded a relative path (/packages/...apk.zip) which
  can't resolve when scanned by a phone. Point it at the absolute 146
  release-server URL so the download works from any device.
- Dashboard tab-swipe: guard tabs[next] (noUncheckedIndexedAccess) so the
  frontend type-checks/builds.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 09:52:26 -04:00
archipelago
837cc02812 fix(federation): reliable symmetric auto-federation across LAN/Tor/FIPS
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>
2026-06-19 09:52:26 -04:00
archipelago
1bce694ebb feat(ui): mobile mesh tabs, AIUI-style audio player, cloud grid + map fixes
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>
2026-06-19 09:52:26 -04:00
archipelago
c4855526fe feat(wallet): wire fmcd as core app + dual-ecash receive
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>
2026-06-19 09:52:26 -04:00
archipelago
298595069d fix(mesh): native Meshtastic unicast DMs + driver-level E2E status
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>
2026-06-19 09:52:26 -04:00
Dorian
f636c5d505 fix(neode-ui): float connection banners as overlay
The offline/reconnecting banners were in-flow (mx-6 mt-6) and pushed the whole
dashboard down when shown. Teleport them to <body> as a fixed, top-centered
overlay with a fade/slide transition and safe-area inset, so they no longer
shift layout.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 14:40:50 +01:00
Dorian
0f43870e6c chore(android): give debug build a .debug app id
applicationIdSuffix=".debug" + versionNameSuffix so a debug/test build
installs alongside the release app instead of failing on signature mismatch.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 14:40:50 +01:00
Dorian
d1fbcd9b0a feat(neode-ui): route "open in browser" through native bridge in companion app
When ArchipelagoNative is present (the Android companion app), openInNewTab()
now calls openInApp(url) so non-iframeable apps open in the in-app WebView
instead of a suppressed window.open popup. Falls back to window.open in a
plain mobile browser. Logic only; no visual change.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 11:28:48 +01:00
Dorian
b5a9deb815 feat(android): open non-iframeable apps in in-app webview + webview perf
The kiosk's "Open in new tab" used window.open(..., 'noopener,noreferrer'),
which the WebView suppresses, so launching apps that can't be iframed did
nothing. Route such node apps (same host) into a local in-app WebView overlay
instead, keeping the kiosk view alive underneath; genuinely external links
still go to the system browser. Wired through onCreateWindow,
shouldOverrideUrlLoading, and a new ArchipelagoNative.openInApp() bridge.

Perf (no visual change): enable setOffscreenPreRaster to stop scroll
checkerboarding, and enable WebView remote debugging on debuggable builds
for chrome://inspect profiling.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 11:28:48 +01:00
archipelago
d0ca53501c feat(ui): cloud folder zoom transition on path change
Re-key FileGrid on the current folder path and wrap it in a cloud-zoom
Transition so the depth/zoom animation replays at every folder level; the
header + breadcrumb nav stay fixed.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-18 09:40:16 -04:00
archipelago
790da4bd0f fix(wallet): Minibits default Cashu mint, resilient peer-file invoices, named default federation
- 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>
2026-06-18 09:23:56 -04:00
archipelago
cc2e055e09 fix(bitcoin,ui): RAM-aware dbcache to stop swap-thrash 502s + snappier status + icon placeholder
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>
2026-06-18 09:14:47 -04:00
archipelago
549c6180a2 chore(ui): sync What's New modal for v1.8.00-alpha
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-18 08:12:12 -04:00
archipelago
ec644ab90f docs: changelog v1.8.00-alpha — mesh DM privacy, contact import/search/reachability
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-18 08:10:29 -04:00
archipelago
f0fdc23cc9 feat(mesh): native-unicast DMs, contact import/remove, reachability, contact search
- 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>
2026-06-18 08:08:52 -04:00
archipelago
9f2edf6b7a docs: changelog for v1.8.00-alpha (carry forward v1.7.99 features + mesh/fedimint fixes)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-18 04:20:10 -04:00
archipelago
3a21243be7 fix(mesh,ui,fedimint): mesh-AI chat trigger + transport-aware reply, stop ARCHY:2 public-channel spam, AI allowlist + model dropdown, Fedimint client manifest, settings reorder, chat scroll
- 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>
2026-06-18 03:33:37 -04:00
archipelago
2a017623e9 chore: release v1.7.99-alpha 2026-06-18 01:00:24 -04:00
archipelago
b59c74adfe test(ui): register $ver global in vitest setup
Component tests mounted without main.ts's bootstrap, so the $ver global
template helper (app.config.globalProperties.$ver = displayVersion) was
undefined — AppSidebar/AppHeroSection/MarketplaceAppCard tests failed with
"_ctx.$ver is not a function", blocking the release gate's ui-unit-tests
stage. Add a vitest setup file that mirrors main.ts via config.global.mocks
and wire it into vitest.config.ts.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 23:52:48 -04:00
archipelago
371be4a69c chore: sync What's New modal for v1.7.99-alpha
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 19:53:08 -04:00
archipelago
83bb589ea6 style: cargo fmt for v1.7.99-alpha release gate
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 19:50:46 -04:00
archipelago
144c4a2872 docs: changelog for v1.7.99-alpha 2026-06-17 19:48:20 -04:00
archipelago
5b2a11b8c7 Merge meshroller-50: mesh-AI assistant (#50) into release train 2026-06-17 19:22:11 -04:00
archipelago
705e2436ba chore(ops,docs): first-boot containers, image versions, design docs, android remote-input
- first-boot-containers + image-versions for fmcd/fedimint
- dual-ecash, meshroller-integration, and remaining-issues design docs
- Android remote-input two-finger scroll + external-open handling

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 19:22:02 -04:00
archipelago
87769cbfbf feat(ui): dual-ecash wallet settings, buy-peer-files, seed backup, assorted fixes
- Tabbed Wallet Settings modal (Cashu + Fedimint) and dual-balance wallet card
- Buy a peer's paid file (ecash / node Lightning / on-chain / external QR)
- Recovery-phrase reveal + backup section; onboarding seed retry resilience
- NetBird HTTPS launch, remote-control two-finger scroll + external-open
- Shared BackButton, single-v version label, mesh Bitcoin header toggles

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 19:21:42 -04:00
archipelago
bd567cd165 feat(wallet,content,seed): Fedimint dual-ecash, paid content streaming, seed ceremony
- Fedimint ecash alongside Cashu: fedimint-clientd (fmcd) HTTP bridge,
  fedimint_client, fedimint RPC, wallet wiring
- Paid peer content: content invoices + streaming content server + content RPCs
- Seed-phrase ceremony/reveal RPCs and CLI ceremony tool
- LND wallet, mesh status/messaging, app-stack (netbird HTTPS), and
  decoupled-update wiring; Fedimint Client core app in catalog

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 19:21:07 -04:00
archipelago
7a76d32e4b feat(mesh): mesh-AI assistant scheduler + config panel (#50)
Adds the assistant scheduler, MeshAssistantPanel UI, and the remaining
config-RPC / live-toggle / Ollama-detect wiring on top of Phase 1.x.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 19:19:32 -04:00
archipelago
0947ecee11 feat(mesh): assistant config RPCs + live toggle + Ollama detect (#50)
Phase 2 backend. AssistantConfig is now live-updatable (RwLock) so the UI
toggle applies without a listener restart. New RPCs:
- mesh.assistant-status  -> {enabled, model, trusted_only, default_model,
  ollama_detected, models[]} (probes local Ollama :11434/api/tags)
- mesh.assistant-configure -> set enabled/model/trusted_only live + persist

MeshService::assistant_config / configure_assistant. Compiles clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 18:29:36 -04:00
archipelago
ef601c6d26 feat(mesh): wire ARCHY identity broadcast for trust over both radios (#50)
The ARCHY:2 identity broadcast (DID + ed25519 + x25519) was unwired dead
code on both send and receive. Wiring it lets a radio peer prove its
archipelago identity, so the assistant's trusted-only gate (and encrypted
DMs) work over meshcore AND Meshtastic — the latter otherwise only exposes
synthetic node keys.

- session.rs: broadcast ARCHY:2 as channel text at startup + each advert tick
- frames.rs: parse inbound ARCHY:2 on the channel path, dedupe-keyed by
  archipelago pubkey (federation_peer_contact_id) so it MERGES with the
  federation-seeded peer instead of duplicating; self-echo guarded
- threads our_x25519_secret into handle_channel_payload (was reserved)

Reuses the existing handle_identity_received verifier (ed/x25519 consistency
check + shared-secret derivation). Compiles clean. Needs a live 2-radio test
before trusting trusted-only over radio.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 18:20:12 -04:00
archipelago
87d0d53205 feat(mesh): assistant Phase 1.5 — !ai channel trigger (issue #50)
A plain '!ai <q>' / '!ask <q>' on the channel is now answered by the node's
local model and broadcast back as plain text, so ANY client (bare meshcore
or Meshtastic) can ask. Generalised run_assist with an AssistReply target:
Typed chunks to a peer (archipelago UI path) vs plain channel-text (bare
clients). Trust/rate gate unchanged; asker identity is separate from reply
mode. Works over both radios.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 17:59:03 -04:00
archipelago
d8d014bfd9 feat(mesh): mesh-AI assistant — Phase 1.1-1.4 (issue #50)
Rust-native lift of Meshroller's LLM bridge. Adds typed AssistQuery/
AssistResponse mesh messages, a trust-gated inbound handler that answers
with the node's local Ollama model, and airtime discipline (reply cap,
chunking, one in-flight query per asker). Works over both meshcore and
Meshtastic radios via the existing MeshRadioDevice abstraction.

- message_types: AssistQuery=24 / AssistResponse=25 + payloads
- listener/assist.rs: run_assist (gate -> Ollama -> chunked reply)
- listener/dispatch.rs: AssistQuery/AssistResponse arms
- MeshConfig: assistant_enabled / assistant_model / assistant_trusted_only
- MeshState: AssistantConfig + data_dir + in-flight guard

Compiles clean (cargo check). Off by default.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 17:41:15 -04:00
archipelago
c10f2ac22e fix(apps): rename 'Websites' tab to 'Services' (#51)
Headless containers (databases, APIs, backends without a UI) belong in a
tab labelled 'Services', not 'Websites'. The categorisation logic already
routes UI-less packages there (built under #45); this finishes the rename
of the user-facing label across Apps, Marketplace, Discover and the mobile
nav, and makes 'services' the canonical tab state/query param. Old
?tab=websites bookmarks still resolve (back-compat acceptor kept).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 16:56:36 -04:00
archipelago
3ca1fadfea chore: reconcile Cargo.lock after DHT merge
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 07:50:25 -04:00
archipelago
7c458ede8e Merge agent-trust-wip (DHT Phases 0–4) into main
Integrates the DHT/peer-distribution line with the v1.7.98-alpha release
fixes:
- Phase 0 signed-catalog trust + release-root key (KAT-pinned)
- Phase 1 BLAKE3 content addressing alongside SHA-256
- Phase 2 swarm-assist fetch seam (origin always wins) + iroh-blobs
  provider — heavy iroh deps stay behind the off-by-default `iroh-swarm`
  feature, so the default build/deploy is unaffected
- Phase 3 signed Nostr seed-advertisement + discovery glue + paid swarm
  serving + "Networking Profits" Settings page
- Phase 4 paid swarm streaming (cross-mint ecash, Shape-A paid ALPN,
  streaming.prepare-payment), also iroh-swarm-gated

Conflicts resolved: seed.rs (kept release-root KAT tests), update.rs
(comment-only, OTA logic identical), Cargo.lock (regenerated against the
merged Cargo.toml). Default-feature build is clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 07:50:06 -04:00
archipelago
27a6199939 feat(dht): Phase 4 — paid swarm streaming (cross-mint ecash + Shape-A ALPN)
Fetch-side auto-pay decision layer (payment.rs), Shape-A paid-blobs
negotiation ALPN (paid_alpn.rs), cross-mint ecash swap + payer auto-swap
builder + idempotent resume/liquidity cache (ecash.rs), and the
streaming.prepare-payment RPC. All gated behind the iroh-swarm feature
(off by default). 91/91 tests pass, both build configs clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 07:36:31 -04:00
archipelago
2c93e25faf fix(mesh): satisfy strict index access in federationContactId (#39 build)
Destructure the first 4 pubkey bytes into typed locals so vue-tsc's
noUncheckedIndexedAccess doesn't fail the build (the bytes.length<4 guard
doesn't narrow per-element access). No behaviour change.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 07:06:08 -04:00
archipelago
d4c0587df0 fix(health): IndeeHub API waits for MinIO before restart (#41)
The IndeeHub API needs MinIO (object storage) up to serve, but the
health monitor's dependency map listed only postgres + redis, so it
would restart the API while MinIO was still starting — the "recovers
only after 1-2 container restarts" symptom. Add indeedhub-minio to the
API's deps; MinIO has no deps of its own so the monitor restarts it
first, no deadlock. (First-start ordering in the stack definition is a
deeper, separate follow-up.)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 06:33:04 -04:00
archipelago
ab56054aeb fix(federation): remove-node also purges the mesh contact/thread (#2)
federation.remove-node only edited nodes.json, so a removed/renamed node
(e.g. a stale "Arch HP") lingered in the mesh chat list with its old
thread. Capture the node's pubkey before removal, then purge its
synthetic mesh peer, shared secret, messages, presence, and persisted
contact entry via the new mesh::purge_federation_peer. Combined with the
#42 name refresh, stale federation contacts can now be fully cleaned from
a node.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 06:12:56 -04:00
archipelago
d2d2b9dd68 fix(apps): classify by declared UI — UI apps to My Apps, headless to Websites (#45)
Per the rule that only front-end apps with a UI belong in "My Apps"
(databases/backends/headless go to Websites), make the manifest's
interfaces.main.ui the deciding signal. isWebsitePackage now treats any
package that declares a UI as an app even when it isn't in the curated
APP_CATEGORY_MAP, and falls through headless LAN-reachable packages to
Websites. Additive — service-by-name infra and curated known apps are
unchanged, so no currently-correct app moves.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 06:09:46 -04:00
archipelago
56752ebfc0 fix(identity): Node npub in Web5 Identities matches Settings (#49)
Settings shows the node-level Nostr key (HKDF derive_node_nostr_key,
read via node.nostr-pubkey) while Web5 > Identities showed the identity
record's own key — the mirrored "Node" identity stores nostr=None and
seed identities use a different BIP-32 NIP-06 key, so the two surfaces
disagreed.

Resolve the node-level Nostr key once in identity.list and override it
onto whichever identity record is the node's own (ed25519 == server_info
.pubkey). Display-only — no stored key is rewritten, so it self-applies
to existing nodes with no migration and the discovery identity is
unchanged.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 06:03:25 -04:00
archipelago
6de8173d18 fix(mesh): refresh federation chat names + roster after sync without restart (#42)
A peer accepted via invite is seeded into the mesh peer table with
name=None, so it shows as "Archipelago <pubkey8>" in chat. Federation
sync later learns the real name (update_node_state writes it to
nodes.json) and discovers transitive peers (merge_transitive_peers),
but nothing pushed those into the live mesh peer table — the chat list
stayed stale until the next mesh restart, and transitive peers never
appeared as contacts at all.

Add RpcHandler::refresh_federation_mesh_peers() (re-runs the idempotent,
onion-deduped seed_federation_peers_into_mesh) and call it after every
periodic sync cycle (server.rs) and after the manual federation.sync-all
RPC. Names now correct themselves and the full roster meshes within a
sync cycle, no restart needed.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 05:52:41 -04:00
archipelago
1f3b03bc6d docs(dht): Phase 4 plan (paid streaming/relay/IndeeHub + cross-mint) + RESUME update
phase4-streaming-ecash-plan.md: design for ecash-paid swarm transport, paying
across different mints (§2a, Lightning-bridged swaps), networking-through-nodes
relay, and an IndeeHub "Archipelago" content source. Records the resolved
iroh-blobs paid-serving spike. dht-RESUME.md: task #12 + step F marked done.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 04:48:18 -04:00
archipelago
75b78325e4 feat(web5): Networking Profits → Settings page for paid services
Adds a Settings control to the Networking Profits card that opens a new page
where the operator controls what their node charges sats for and how much.
Drives the existing streaming.list-services / streaming.configure-service RPCs;
"free everything" is the default (all priced services ship disabled, surfaced
with a reassurance banner). New route web5/networking-profits + common.settings
i18n (en/es).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 04:48:00 -04:00
archipelago
be3ebd7fe0 feat(dht): Phase 3 discovery glue + paid swarm serving
Phase 3 wiring (task #12):
- NostrSeedDiscovery: async ProviderDiscovery that queries relays for signed
  seed adverts and parses endpoint ids (swarm/iroh_provider.rs, seed_advert.rs).
- seed_and_advertise publish path; dep-free fetch/publish helpers reuse the
  node's Nostr identity (build_nostr_client/load_or_create_nostr_keys made
  pub(crate)).
- swarm::init builds the IrohProvider once into a OnceLock runtime; providers()
  returns it; announce_held_blob() is called from update.rs after a release
  component passes both hash gates.
- config swarm_enabled (ARCHIPELAGO_SWARM_ENABLED, default off); server.rs init.

Paid swarm serving (Phase 4 step F):
- swarm/paid.rs gates the iroh-blobs provider through streaming::gate,
  intercepting connect + GET (peer push hard-disabled). Free by default
  (content-download service disabled); denies unpaid peers when enabled;
  fails open on internal error so a payment fault never blocks distribution.
  Wired into IrohProvider::new.

All iroh code behind the iroh-swarm feature; the default build is inert.
Default build clean; --features iroh-swarm: 11/11 swarm tests pass.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 04:47:18 -04:00
archipelago
06cf80d4a2 fix(apps): classify Bitcoin Core as an app, not a website (#8, #9)
bitcoin-core was missing from APP_CATEGORY_MAP, so isKnownApp() was false and
isWebsitePackage() fell through to 'has a runtime LAN address'. Once the running
container's LAN address (the bitcoind RPC port :8332) showed up ~a minute after
launch, Bitcoin Core was reclassified as a website: it dropped out of the Apps
tab and search, moved under Websites, and launching it opened :8332 (raw RPC)
instead of the :8334 custom UI that Knots opens.

Add 'bitcoin-core': 'money' alongside bitcoin-knots/bitcoin-ui so isKnownApp is
true, isWebsitePackage is false, and launchAppNow routes through openSession ->
resolveAppUrl (:8334 custom UI). Fixes search, category, and the launch URL.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 03:43:29 -04:00
archipelago
1ea3f8d65c fix(mesh): message federation contacts without a radio (fixes 'Missing contact_id')
Messaging a federation-only peer (e.g. 'Arch Dev') failed with 'Missing
contact_id'. The UI gave federation-only rows a *negative* placeholder
contact_id derived from a DID hash, but the backend parses contact_id as u64,
so a negative value deserialized to None. The negative id also never matched
the positive federation-synthetic id that federation-routed messages are stored
under, so those threads looked empty.

- Frontend: derive the SAME positive federation-synthetic id the backend uses
  (federationContactId mirrors federation_peer_contact_id) so mesh.send accepts
  it and messages thread correctly.
- Backend: send_typed_wire now resolves a federation-synthetic contact_id from
  nodes.json when it isn't in the live mesh peer table (radio-less node),
  instead of bailing 'Unknown federation peer'.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 03:24:34 -04:00
archipelago
e456c9701b fix(peer-files): stream large cloud downloads + surface real errors (#30, #38)
Large peer downloads (~178MB) failed with a generic 'Operation failed', and
the download path had three stacked problems:

- The FIPS reqwest client used a hard-coded 20s total timeout regardless of the
  caller's .timeout(), so a big transfer over the mesh aborted at 20s before
  the Tor fallback could help. Honor the per-request timeout (client_with_timeout).
- The peer-content proxy buffered the whole file into node memory via
  resp.bytes() before sending a byte, and capped the transfer at 60s. Stream
  the body through with hyper::Body::wrap_stream (constant memory) and raise the
  timeout to 900s; bump the nginx peer-content read timeout to match.
- Free downloads pulled the file as base64 over RPC, doubling it in node memory
  and the browser — fatal for large files. Download free files by streaming
  from /api/peer-content straight to disk, after a 1-byte Range probe that
  surfaces the real reason (peer offline on mesh and Tor) instead of a generic
  failure. Paid downloads now return the real error through the {error} channel
  the UI already displays.

Adds the reqwest 'stream' feature for bytes_stream().

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 03:10:21 -04:00
archipelago
3aea8c5bfa fix(orchestrator): rebuild local UI images when source changes (#34)
The prod orchestrator only checked whether a build-image tag was *present*
before deciding to skip the build. The local UI images (bitcoin-ui, lnd-ui,
electrs-ui) COPY a built neode-ui dist, so a UI update changed the source but
left the old tag in place and the new UI never shipped.

Gate the build on a content fingerprint of the build context (sorted relative
path + length + mtime, SHA-256) recorded in a per-tag stamp under data_dir.
Rebuild whenever the fingerprint differs from the one that produced the
existing image; podman's own COPY-layer cache keeps a no-op rebuild cheap.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 03:09:56 -04:00
archipelago
f14829542b docs(dht): RESUME checkpoint — state, next steps, build/worktree rules
Single source of truth for picking the DHT work back up after a restart:
worktree/branch rules, all phase commits, the exact next task (#12 Phase 3
glue), build-time facts, and the Phase 0 go-live ceremony.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 15:18:00 -04:00
archipelago
1843739e0c fix(install): restart stack containers that crash on first start (#25)
Apps could fail install when a stack member exited on its first start
because a dependency (db/redis/the bitcoin node) was not ready yet — a
transient crash, not a broken install. wait_for_stack_containers now
restarts each exited/dead container up to 3 times before declaring the
install failed; the runtime supervisor keeps it alive afterwards.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 15:14:09 -04:00
archipelago
9fa56a8274 feat(dht): Phase 3 core — signed Nostr seed-advertisement protocol
The discovery wire format that feeds the swarm's ProviderDiscovery seam: a
node announces 'I seed blake3 H from iroh endpoint E' as a signed NIP-33
addressable Nostr event. Scope is releases/catalog content ONLY (decided
2026-06-16) — never private user blobs.

- swarm/seed_advert.rs: kind 30081, d-tag = blake3 hex (one current advert
  per author+hash, latest-replaces), content {"v":1,"endpoint_id":...}.
  advertisement_builder / advertisement_filter / parse_endpoint_id /
  endpoint_ids_from_events (dedup). Endpoint ids stay opaque strings so the
  protocol is dep-light + unit-testable on the default build.

4/4 tests pass (sign->parse roundtrip, filter targeting, reject wrong-kind/
empty, dedup across nodes).

Next (task #12): gated NostrSeedDiscovery glue (query relays, parse ids ->
iroh::EndpointId), publish path, wire swarm::providers().

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 15:13:35 -04:00
archipelago
082946aa30 feat(dht): Phase 2 engine — real iroh-blobs provider behind iroh-swarm
Pulls iroh 1.0 + iroh-blobs 0.103 as OPTIONAL deps under the iroh-swarm
feature and implements a real BlobProvider over them. Verified: the full
iroh QUIC dep tree (260 pkgs) resolves and compiles against the pinned
bitcoin/nostr-sdk/reqwest-rustls stack; the provider compiles against the
0.103/1.0 API.

- swarm/iroh_provider.rs: IrohProvider::new binds a QUIC Endpoint, opens a
  persistent FsStore (data_dir/iroh-blobs), and serves blobs via the
  iroh-blobs protocol/Router — a node that fetches also SEEDS. try_fetch
  maps ContentDigest -> iroh Hash, asks discovery for seed EndpointIds, then
  downloader.download(hash, providers) (range-verified) + export to staging.
- ProviderDiscovery trait: the seam Phase 3 (signed Nostr advertisement
  events) fills. discovery=None -> no seeds -> origin-only, so enabling the
  feature is never worse than today.
- Default build untouched: iroh is optional, the module is cfg-gated, and
  providers() stays empty until Phase 3 wires discovery in.

Build: cargo build --features iroh-swarm succeeds (dev). Default build +
44 swarm/update/content_hash/blobs tests unchanged.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 14:33:31 -04:00
archipelago
83b77796fc chore: release v1.7.98-alpha 2026-06-16 14:07:49 -04:00
archipelago
a569104620 fix(web5): carry node DID through to Connected Nodes routing
The backend already sends did in federation peer lists, but the Peer
type omitted it and federationNodeToPeer() dropped it when mapping. Add
did?: string to Peer and pass node.did through, so trusted/observer
node rows route to Federation/Mesh by their real DID (falling back to
pubkey/onion) instead of failing the build on a missing property.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 14:02:16 -04:00
archipelago
2523c9e3dd feat(dht): Phase 2 — swarm-assist fetch seam, origin always wins
Lands the transport/swarm orchestration layer (the iroh engine attaches
later, behind a flag). The seam is fully exercised today with the origin
HTTP path; with no swarm providers registered the behaviour is byte-for-byte
identical to before.

- swarm/mod.rs: BlobProvider trait + fetch_content_addressed() — tries each
  provider in order, VERIFIES peer-sourced bytes against the content digest
  before accepting (untrusted seeds can't inject tampered bytes), falls back
  to the origin closure if none serve. Returns Swarm|Origin.
- Cargo: iroh-swarm feature (off by default; heavy QUIC dep tree attaches
  here). providers() is empty until enabled → every fetch hits origin.
- update.rs: components with a BLAKE3 digest route through the seam, using
  the existing resumable HTTP downloader as the origin fallback; a swarm hit
  is re-checked against the mandatory SHA-256 manifest gate (re-fetch from
  origin on any disagreement). Components without blake3 take the original
  path untouched.

44/44 swarm/update/content_hash/blobs tests pass (incl. swarm hit/miss,
tampered-bytes-rejected→origin, fall-through ordering).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 13:38:19 -04:00
archipelago
f0cb91ed76 feat(dht): Phase 1 — BLAKE3 content addressing alongside SHA-256
Adds the iroh-native, range-verifiable hash next to the incumbent SHA-256
so the swarm can later fetch/verify by BLAKE3 with the registry/origin as
fallback. Non-breaking: SHA-256 stays the mandatory gate; BLAKE3 is verified
only when present.

- content_hash.rs: HashAlg + ContentDigest (parse/verify '<alg>:<hex>'
  multihash strings), blake3_hex/sha256_hex; BLAKE3 known-answer test
- update.rs: ComponentUpdate.blake3 (serde-default); verified ALONGSIDE
  SHA-256 in the resumable download loop, re-download on mismatch
- blobs.rs: BlobMeta.blake3 computed on put (on-disk path stays
  SHA-256-keyed for back-compat; advertises the future swarm address)

Drive-by: fix a pre-existing stale test (test_save_and_load_state_roundtrip)
that never wrote the .download-complete marker #26 requires, so load_state's
self-heal cleared update_in_progress. Unrelated to BLAKE3 — surfaced by
running the full update:: suite.

40/40 content_hash/update/blobs tests pass.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 13:05:27 -04:00
archipelago
7e84434ff6 test(update): stage .download-complete marker in roundtrip test
The #26 fix makes has_staged_update require the .download-complete
marker, so the state self-heal treats a marker-less staging dir as a
partial download and clears update_in_progress. The roundtrip test
staged a binary file but not the marker, so it began failing. Write
the marker to simulate a *complete* staged update.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 12:41:18 -04:00
archipelago
27f11bf85a feat(trust): wire Phase 0 signed-catalog verification + pin release-root KAT
Completes the parked trust module and wires it into the live build:
- main.rs: register `mod trust`
- app_catalog::fetch_one: verify the release-root detached signature when
  present (verify against raw JSON so forward-compat fields stay in the
  signed preimage); accept unsigned during the migration window, hard-reject
  a present-but-bad signature so a tampering mirror can't pass altered bytes
- seed: pin release-root Ed25519 known-answer test (priv+pub) for the
  signing ceremony / pinned-anchor / external-verifier cross-check
- signed_doc: drop unused import

20/20 Phase 0 unit tests pass (trust::canonical/did/signed_doc/anchor,
seed release-root, app_catalog). Crate compiles clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 12:40:57 -04:00
archipelago
981a86cc26 style: cargo fmt (update.rs has_staged_update + #16/#36 changes) 2026-06-16 11:30:51 -04:00
archipelago
b943ca5db2 docs(whats-new): sync v1.7.98-alpha block 2026-06-16 11:29:30 -04:00
archipelago
cb3d567b7d docs(changelog): curate v1.7.98-alpha notes 2026-06-16 11:29:30 -04:00
archipelago
0fef808671 wip(trust): park agent's signed-manifest module + release-root key off main
Moved here so main stays clean for the v1.7.98 release. Contains the trust/
module (canonical.rs, did.rs, signed_doc.rs) + seed::derive_release_root_ed25519.
Not wired into the build yet. Continue this work on this branch.
2026-06-16 11:22:24 -04:00
archipelago
ee46a856de docs(whats-new): sync v1.7.98-alpha block 2026-06-16 11:19:08 -04:00
archipelago
b037a121d0 docs(changelog): curate v1.7.98-alpha notes 2026-06-16 11:19:00 -04:00
archipelago
4c4cf6d8b4 docs(dht): peer-distributed content design (iroh swarm + signed manifests)
Captures the verified 2026-06-16 design: swarm-assist/origin-always-wins,
iroh-blobs as the swarm engine, BLAKE3 addressing, signed Nostr/release-root
authenticity, and the Phase 0-4 plan. Foundation doc for the dht branch.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 11:15:47 -04:00
archipelago
45ac9be965 fix(kiosk): cap chromium resources + drop GPU rasterization when headless (#36)
The kiosk chromium pinned ~92% of a core (software-compositing spin from
--enable-gpu-rasterization on a GPU-less/headless node), saturating the machine
and starving the backend + container builds — it caused the .198 receive timeout
and the deploy storms.

- archipelago-kiosk.service: CPUQuota=75% + MemoryMax/High + Delegate, so a
  runaway kiosk can never take the whole node down.
- archipelago-kiosk-launcher.sh: detect /dev/dri — use GPU rasterization only
  when a GPU exists, else --disable-gpu (avoids the headless spin).
- bootstrap::ensure_kiosk_hardened: OTA self-heal that installs the updated
  unit+launcher on already-deployed nodes, daemon-reloads, and only try-restarts
  a *running* kiosk (never re-enables an operator-disabled one).

cargo check clean; launcher bash -n clean; unit syntax valid.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 11:10:26 -04:00
archipelago
ab6fcef6f3 fix(containers): periodically restart crashed stack members at runtime (#16/#17)
immich_server/redis/postgres + indeedhub-* are multi-container stack members
whose sub-container app_ids are NOT in package_data, so the health monitor skips
them as "orphans" and never restarts them when they exit — Immich/IndeedHub stay
down until the next reboot (the boot-only start_stopped_stack_containers was the
only recovery). Spawn a 120s supervisor that reuses that same recovery at
runtime. It cheaply skips already-running containers and honours the user-stopped
list (set on every container by package.stop), so it only revives genuinely
crashed members and never fights a user stop.

cargo check clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 10:49:36 -04:00
archipelago
c7cd068e1a feat(connected-nodes): cap tabs at ~4 w/ scroll; node→Federation, message→chat (#37)
- All four tabs (trusted/observers/messages/requests) capped at max-h-72 with
  internal scroll, so the screen stays short instead of growing very long.
- Clicking a node row navigates to that node in the Federation screen
  (?node=did); the Message button (stop-propagation) deep-links to that peer\047s
  mesh chat (?peer=), using the Mesh.vue ?peer handler.

type-check clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 10:41:00 -04:00
archipelago
82cfc8ccba fix(update): failed download returns to Download, not Install (#26)
A resumable-but-failed download leaves partial component files in update-staging.
has_staged_update() treated ANY staged file as "install-ready", so the state
self-heal kept update_in_progress=true and the UI showed Install instead of
Download (no clean retry).

- update.rs: write a .download-complete marker only after EVERY component
  downloads+verifies; has_staged_update() now checks that marker. Partial/failed
  downloads (no marker) correctly read as not-staged → self-heal clears
  update_in_progress → UI shows Download. Resume still works (partial files kept).
- SystemUpdate.vue: on a genuine download failure, reset downloaded/in_progress
  and re-sync, so the user lands back on Download immediately.

cargo check + vue-tsc clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 10:31:12 -04:00
archipelago
3a9d1db763 feat(identity): seed-derivation verifier + KAT; rename "Your DID"→"Node DID"
- scripts/verify-seed-derivation.py: stdlib-only tool to cryptographically prove
  a node's on-disk keys (node_key→DID, nostr_secret→npub, fips_key) are derived
  from its onboarding seed exactly as seed.rs documents (BIP-39 → PBKDF2-HMAC-
  SHA512 → HKDF-SHA256 with per-key domain separation).
- seed.rs: known-answer regression test cross-checking Rust node_key + nostr
  bytes against the Python verifier (locks the derivation).
- en.json: "Your DID" → "Node DID".

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 10:17:29 -04:00
archipelago
67609eea91 fix(toast): add fromPubkey to App.vue toast reset (type fix for #33)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 09:53:21 -04:00
archipelago
9c025b4cea test(toast): add fromPubkey to toastMessage literals (type fix for #33)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 09:51:14 -04:00
archipelago
ef2991a117 fix(chat): send Archipelago(Tor) group messages concurrently so 'sending' clears fast (#32)
sendArchMessage looped over every federation node sequentially (await
sendMessageToPeer per node), so the spinner stayed up until the slowest/offline
node's Tor request finished — long after online peers had received the message.
Send to all peers concurrently (Promise.allSettled); the spinner now clears
after the slowest single delivery, not the sum.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 09:42:51 -04:00
archipelago
9a518db7b8 feat(settings): show DID on every node + add seed-derived node npub (#13)
- DID: the Identity card read the DID only from localStorage('neode_did'), so
  nodes/browsers that never cached it (e.g. .116/.228) showed no DID. Fall back
  to the node.did RPC and cache it — the DID now shows everywhere.
- npub: add the node's seed-derived Nostr public key (npub) to the Identity card
  next to the DID + onion, fetched from node.nostr-pubkey, with a copy button.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 09:37:09 -04:00
archipelago
aa9e0f02b7 fix(cloud): pin peer file-card filename + action buttons to the bottom (#11)
Make each peer file card a flex column filling its grid cell (flex flex-col
h-full) and pin the body row (filename + Play/Download) with mt-auto, so cards
with a media preview and cards without line their footers up across the row.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 09:27:29 -04:00
archipelago
edd03e542d feat(storage): encrypt chat history + mesh contacts at rest, atomic writes, persist contacts (#12)
User: chat history (messages + mesh/Tor contacts) must persist and be
secure/encrypted per best practice. Root cause of the .198 loss was the B17
mount race writing empty stores over real data (B17 already fixes the trigger);
this hardens storage so it can never silently lose or expose data:

- storage_crypto: shared at-rest envelope mirroring credentials::store — key =
  SHA-256(domain ‖ node identity key) (seed-derived, per-store domain
  separation), ChaCha20-Poly1305 AEAD with a random 96-bit nonce, tamper-evident.
  Transparent migration of legacy plaintext files. Unit-tested (round-trip,
  wrong-key/tamper rejection, plaintext detection).
- messages.json: encrypted at rest + ATOMIC write (temp+rename) so a crash/
  reboot mid-write cannot corrupt history; decrypt-with-migration on load; a
  failed decrypt never overwrites the on-disk data.
- mesh contacts (alias/notes/pinned/blocked): were ONLY in memory and lost on
  every restart — now persisted to mesh-contacts.json (encrypted, atomic),
  loaded on MeshState startup, saved after contacts-save/contacts-block.

Explicit clear (mesh.clear-all) still wipes everything, as intended.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 08:54:37 -04:00
archipelago
774ca28847 feat(fips): auto-activate + reliability (retry, warm paths) — make FIPS the robust primary (B14b/#27)
User priority: FIPS is the main transport but it was unreliable and needed a
manual "Activate" button. Improvements (all in the FIPS dial/supervisor):

- Auto-activate: ensure_activated() installs the daemon config + starts the
  service on its own once seed onboarding has materialised the key — no Activate
  button needed. Idempotent; runs from the supervisor every 45s so a node that
  onboards after boot still comes up automatically.
- Dial retry: try_fips_get/post now retry ONCE on a connect/timeout error. The
  first dial to a peer triggers NAT hole-punching and often times out before the
  path is up; the retry lands on the now-warm path — the main reason calls were
  dropping to Tor despite the peer being FIPS-reachable.
- More patient connect_timeout (5s→8s) so a reachable-but-cold peer isn't
  abandoned to Tor while hole-punching completes.
- Path warmer: spawn_fips_supervisor() keeps hole-punched paths to known
  federation peers warm (every 45s, concurrent), so on-demand dials are fast and
  land on FIPS.
- Confirmed the daemon config already enables BOTH udp + tcp transports
  (render_config_yaml), so FIPS already uses TCP where UDP is blocked; the Tor
  fallback was path-establishment, addressed above.

cargo check + fmt clean. Backend — needs a binary rebuild+deploy to validate on
.116/.198 (watch last_transport flip fips, and FIPS coming up with no button).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 08:16:02 -04:00
archipelago
b602a9cea5 feat(toast): message toast opens the related chat + has a close icon (#33)
- Add a close (X) button to the message toast (closeToast, @click.stop) like the
  system notifications.
- Carry the sender pubkey on the toast; clicking now deep-links to that
  conversation (/dashboard/mesh?peer=<pubkey>) instead of the generic mesh page.
- Mesh.vue reads ?peer= on mount and opens the matching peer (by pubkey_hex/did),
  gracefully falling back to the mesh list when no match (B1/B2 identity).

type-check clean; useMessageToast tests 11/11.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 07:39:52 -04:00
archipelago
4576964be4 docs(tracker): file new backlog as gitea #32-#35; relay UI + fedimint CSS live on .116 2026-06-16 06:41:22 -04:00
archipelago
c481afc7d9 fix(media): loader before peer video/audio plays + accurate error (B3/B22)
Streaming a peer file connects over mesh/Tor before the first frame, so the
player sat blank. Add a loading state:
- PeerFiles video modal: spinner overlay ("Connecting to peer…") until the
  <video> fires playing/canplay; an error overlay on failure instead of a
  silent black box.
- useAudioPlayer: loading flag driven by loadstart/waiting vs canplay/playing;
  GlobalAudioPlayer shows a spinner in the transport button while connecting.
- Fix the misleading audio error "Could not play audio. File Browser may not be
  running." (wrong for peer content) → "Could not play this audio file. The peer
  may be offline…" (B22).

type-check clean; useAudioPlayer tests 10/10.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 05:45:17 -04:00
archipelago
921363542c fix(fedimint+home): guardian UI CSS resolves; quickstart goals full-width
- docker/fedimint-ui/nginx.conf: the local /assets/ handler 404'd the real
  fedimint guardian UI's own bundled CSS (bootstrap.min.css, style.css) →
  unstyled app. B13 fixed our local icon; this adds a @guardian_assets proxy
  fallback to :8177 so the guardian's own /assets/* resolve. Verified live on
  .116: /app/fedimint/assets/bootstrap.min.css 404→200 text/css. (needs
  archy-fedimint-ui image rebuild to persist on nodes.)
- Home.vue: Quick Start Goals card regained lg:col-span-2 so it fills its row
  on desktop instead of sitting at half width.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 05:29:57 -04:00
archipelago
82659e9f4e docs(tracker): v1.7.97-alpha cut + mid-rollout state (116 deployed, 198 deploying, fleet pending) 2026-06-16 04:31:18 -04:00
archipelago
47c16971a7 chore: release v1.7.97-alpha 2026-06-16 04:16:13 -04:00
archipelago
b08e4c4268 test(filebrowser): align listDirectory tests with B4 content-type guard
The B4 fix made listDirectory require a JSON content-type (to detect the
SPA-fallback HTML / 502 cases) and changed the non-OK error string, but its
tests still mocked headerless responses + the old message, so they failed —
which also polluted the run and tripped AppIconGrid's teardown. Give the JSON
mock a content-type, update the non-OK expectation, and add a test for the
guard's friendly-error path. Full suite now 667/667 green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 03:46:18 -04:00
archipelago
1278caa249 docs(whats-new): sync v1.7.97-alpha block into Settings What's New modal 2026-06-16 03:39:50 -04:00
archipelago
8a62ae008c docs(tracker): B17 root-caused + fixed (data-volume mount ordering), verified .198 2026-06-16 03:38:58 -04:00
archipelago
9da66da776 docs(changelog): add B17 boot-flap fix to v1.7.97-alpha notes 2026-06-16 03:33:58 -04:00
archipelago
34b1fdc1a3 fix(boot): order archipelago.service after the data volume mount (B17)
On production nodes /var/lib/archipelago (the app data dir AND podman's
graphroot=/var/lib/archipelago/containers/storage) is a separate
device-mapper volume. archipelago.service ordered only After=network-online
.target, so on cold boots it (and its ExecStartPre) could start BEFORE
var-lib-archipelago.mount, write to the bare mountpoint on rootfs, fail every
podman call, exit, and be restarted every 5s until the volume mounted — the
"~20x [FAILED] Failed to start over ~5min" boot flap. Proven live on .198:
"var-lib-archipelago.mount: Directory /var/lib/archipelago to mount over is
not empty, mounting anyway" — the service had written there pre-mount.

Fix: RequiresMountsFor=/var/lib/archipelago (adds Requires= + After= on the
mount unit).
- image-recipe/configs/archipelago.service: ships the directive on fresh ISOs.
- bootstrap::ensure_archipelago_mount_ordering(): self-heals already-deployed
  nodes' installed unit + daemon-reload (boot-ordering only, effective next
  reboot; never restarts the running service). Idempotent; harmless on rootfs
  installs (maps to the always-mounted root).

Verified on .198: after applying, systemctl shows After=var-lib-archipelago
.mount and systemd-analyze verify is clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 03:33:29 -04:00
archipelago
2943fd0c5e style(core): cargo fmt (B1/B3/B13 follow-up — satisfy release fmt gate) 2026-06-16 03:09:18 -04:00
archipelago
486f1a061c docs(changelog): curate v1.7.97-alpha notes (13 fixes + image optimization) 2026-06-16 03:07:17 -04:00
archipelago
dd0fac0e15 docs(tracker): B16 done (bitcoin tile retain/Updating…, unit-tested); image-opt staged for .97 2026-06-16 02:59:33 -04:00
archipelago
83dbd25c50 fix(home): bitcoin sync tile no longer vanishes on a transient poll (B16)
The Home > System bitcoin tile is gated on bitcoinAvailable===true, so any
transient bitcoin.getinfo failure (RPC busy during heavy IBD, route-change
scan) could blank it even though the node is fine. Add a bitcoinStale flag:
- getinfo fails while the container is Running, or package data is momentarily
  absent → retain the last-known value and mark it stale (tile stays, shows
  "Updating…" instead of a frozen figure presented as live).
- container authoritatively Stopped/Exited → flip to not-available as before
  (no stale-as-live).
- first-ever poll times out but container Running → show the tile as updating
  rather than staying hidden on a syncing node.

Harness: src/stores/__tests__/homeStatus.test.ts (6 cases) — red before, green
after. type-check clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 02:57:35 -04:00
archipelago
386d4bfc3f perf(ui): losslessly optimize background images; convert bg-mesh PNG→JPEG
- 16 JPEGs re-encoded lossless via jpegtran (optimized Huffman + progressive,
  EXIF stripped) — pixel-identical, ~4-11% smaller each.
- bg-mesh.jpg was a 5.8MB RGBA PNG mislabeled .jpg → real progressive JPEG
  (mozjpeg q92, opaque), 5.8MB → 0.76MB (-87%).
- Synced optimized assets into web/dist and per-app container UIs (lnd/bitcoin/
  fedimint/aiui) + app-icons. Source img dir 21.4MB → 16MB.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 02:19:50 -04:00
archipelago
bf24bbc15a fix(mempool): resolve CORE_RPC_HOST to the actual bitcoin node (Knots/Core) (B12)
CORE_RPC_HOST was hardcoded to bitcoin-knots in three env-render paths, so on a
bitcoin-core node (container named bitcoin-core) mempool-api could not reach
Bitcoin RPC. Both node variants are reachable on archy-net by container name —
only the name differs.

- Legacy direct-podman (stacks.rs) and config.rs::get_app_config now use a new
  dependencies::detect_bitcoin_rpc_host() (pure, unit-tested pick_bitcoin_host).
- Quadlet/manifest path (the modern fleet default): add a {{BITCOIN_HOST}}
  derived-env placeholder — HostFacts.bitcoin_host + resolve_derived_env render
  it; prod_orchestrator detects Knots/Core via podman ps, resolved on demand
  only for manifests that use the placeholder. mempool-api manifest moves
  CORE_RPC_HOST from static env to derived_env: {{BITCOIN_HOST}}.

Tests: pick_bitcoin_host (5 cases incl. substring safety), container-crate
resolve_derived_env, and orchestrator mempool_core_rpc_host_follows_bitcoin_node
(core->bitcoin-core, knots->bitcoin-knots). No-regression confirmed: picker
returns bitcoin-knots live on .198. Live bitcoin-core validation pending (no
core node available). Sibling hardcodes (lnd/btcpay/electrumx/fedimint) tracked
as B12b.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-16 02:07:39 -04:00
archipelago
987a961f4a fix(nginx): self-heal fedimint asset rewrite on deployed nodes — HTTP + HTTPS (B13)
The B13 template fix only fixed fresh ISOs. Already-deployed nodes keep their
old nginx config, where /app/fedimint/ proxies to :8175 without rewriting the
Guardian UI's root-rooted asset URLs (src="/assets/...", url("/assets/...")).
Those resolve against the SPA root: bg-network.jpg exists there by luck, but
app-icons/fedimint.jpg 404s (location /assets/ uses try_files =404) — the
visibly-broken icon.

bootstrap.rs::patch_nginx_conf now heals both paths on startup:
- Style A (main conf, HTTP): swaps the old single nostr-provider sub_filter tail
  for the full reroot set; byte-matches the shipped template.
- Style B (HTTPS app-proxy snippet): the snippet's fedimint block has no
  sub_filter and a per-node-varying trailing directive, so anchor on the unique
  :8175 proxy_pass and insert the reroot set after it (nginx ignores directive
  order). Snippet added to the bootstrap nginx loop (skipped on HTTP-only nodes).

missing_* flags are now gated on their splice anchors so the included snippet
neither attempts the main-conf-only patches nor logs warn-skips every boot.
Idempotent via the 'href="/' 'href="/app/fedimint/' marker.

Verified on .198 (both paths): fedimint app-icon 404 -> 200 image/jpeg; nginx -t
OK; containers survived restart (Quadlet); idempotent steady state, no warn spam.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 18:03:04 -04:00
archipelago
a50b6df21b fix(nginx): rewrite fedimint UI asset paths so CSS applies (B13, fresh-ISO)
Fedimint UI HTML/CSS reference absolute /assets/* paths; under /app/fedimint/
those hit the main SPA, not the fedimint container, so the UI renders
unstyled. Add the proven sub_filter asset-rewrite pattern (as indeedhub/
botfights use) to the /app/fedimint/ block in the nginx template + https
snippet (also rewrites url(...) for the CSS background image). Bootstrap
self-heal for already-deployed nodes is the documented resume point.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 16:52:30 -04:00
archipelago
8427e219ea docs(tracker): round-2 status (B15/B7 done, B13/B12/B16 deferred w/ plans)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 16:31:24 -04:00
archipelago
c0d41cf8cf fix(ui): faster bitcoin sync refresh + unstick ElectrumX loader (B15,B7)
B15: Home system stats (incl. bitcoin sync %) polled every 30s — too slow;
now 10s so sync progress tracks the actual block height more closely.

B7: the ElectrumX sync overlay was gated only on status!=='synced', so if
the status never flips to 'synced' (ElectrumX stale/disconnected) the loader
stuck on top forever. Now the overlay hides and the app iframe loads when
the sync status is stale (fail-open), while still showing during active
indexing. type-check EXIT 0.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 16:29:44 -04:00
archipelago
eb55c88e1a docs(tracker): B6/B7/B12/B13/B15/B16 root causes + fix plans
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 14:43:01 -04:00
archipelago
31fe91b99a docs(tracker): B13 fedimint CSS investigation progress
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 14:13:28 -04:00
archipelago
b9cc4bd780 docs(tracker): B14b FIPS reachability findings (dial-time, not npub/service)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 14:11:47 -04:00
archipelago
6c92eacba0 docs(tracker): add B22 (peer download/audio errors), B23 (group chat), B3 PASSED-http
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 14:09:31 -04:00
archipelago
602b9cd3df fix(nginx): route /api/peer-content/* to the backend for B3 streaming
The B3 streaming proxy endpoint existed in the backend but nginx had no
location for /api/peer-content/*, so the browser's requests fell through to
the SPA (200 text/html) and media still wouldn't play. Add an
NGINX_PEER_CONTENT_BLOCK that bootstrap patches into every server block
(forwards Cookie for session auth + Range, proxy_buffering off). Idempotent;
covers fresh-ISO nodes too since bootstrap runs on every startup.

Verified on .198: after restart the async nginx patch lands and
/api/peer-content/<onion>/<id> returns 401 (reaches backend, auth-gated)
instead of the SPA; nginx block present in both server blocks.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 14:07:39 -04:00
archipelago
5c8707432b fix(cloud): Range-streaming proxy for peer media so it plays/seeks (B3)
Peer media (music/video) wouldn't play: the frontend downloaded the whole
file via RPC as base64 and made a non-seekable Blob URL, so <video>/large
<audio> stalled and big files hit the RPC timeout.

Add GET /api/peer-content/<onion>/<id> — a same-origin, session-gated proxy
that forwards the browser's Range header to the peer's /content/<id> (which
already returns 206 Partial Content) and passes status + Content-Range +
Content-Type back. PeerFiles.playMedia() now points <video>/<audio> at this
streaming URL for free content instead of buffering a base64 blob, so the
player can seek and start immediately. Onion/id validated to prevent
SSRF/path traversal. (Paid preview keeps its existing flow.)

Verified: cargo build --release EXIT 0; vue-tsc --noEmit EXIT 0.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 13:46:51 -04:00
archipelago
4cac6bc835 docs(tracker): record B1/B2/B4/B14/B21 done + B14b; next B3
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 13:27:51 -04:00
archipelago
0801dd6632 feat(cloud): show Tor/FIPS transport pill on peer browse (B21)
content.browse-peer now returns the transport that actually reached the
peer (fips/tor/mesh/lan). PeerFiles shows it as a small coloured pill next
to the peer name (FIPS/Mesh green, LAN blue, Tor amber) and the loading
text no longer hardcodes "Connecting via Tor" (it was misleading when FIPS
was used). Pairs with B14 (transport recording).

Verified: cargo build --release EXIT 0; vue-tsc --noEmit EXIT 0.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 13:25:39 -04:00
archipelago
1c6dc153ce fix(content): use re-exported federation::record_peer_transport path (repair build)
The B14 commit referenced crate::federation::storage::record_peer_transport
but `storage` is a private module — record_peer_transport is re-exported at
crate::federation::. E0603 broke the build. Use the re-exported path (as
load_nodes/fips_npub_for_onion already do). Verified: cargo build --release
EXIT 0. Also logs B21 (Tor/FIPS pill) plan.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 13:15:01 -04:00
archipelago
f2e3710c28 fix(content): record peer transport on cloud browse/download/preview (B14)
The 4 content peer handlers (browse, download, download_paid, preview)
captured the transport returned by PeerRequest::send_get() but discarded
it, so the federation node's last_transport was never updated for cloud
activity — the UI showed Tor/none even when FIPS was used. Call
record_peer_transport() after each successful fetch (same as sync does).

Note: live data shows FIPS still reaches only some peers (many genuinely
fall back to Tor) — tracked separately as B14b (FIPS reachability).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 13:02:13 -04:00
archipelago
ed4931064b fix(federation,cloud): dedup trusted nodes + chat contacts by onion; guard cloud my-folders (B1,B2,B4)
B1/B2: the same physical node can linger in the federation list under two
dids (e.g. after a did/key change). An onion is a node's unique stable
identity, so two entries with the same onion are one node. This showed the
node twice in the trusted-node list (B1) and as two mesh chat contacts —
one by name+logo, one by raw did (B2).
- storage::load_nodes now collapses same-onion entries (keep first, merge
  fips_npub/name/last_state) so every consumer (list + chat seed + sync)
  sees one entry per node.
- federation::sync merge_transitive_peers also matches by onion (not just
  did) so new transitive hints don't re-add a known node under a new did.
- mesh::seed_federation_peers_into_mesh skips already-seeded onions (belt
  and suspenders).
- Unit tests for dedup_nodes_by_onion (collapse + onion-suffix handling).

B4: filebrowser-client.listDirectory only checked res.ok before res.json(),
so when File Browser is absent (nginx serves the SPA index.html, 200) or
down (502) the JSON parse threw the opaque "Unexpected token '<'". Now it
checks the content-type and throws a friendly "File Browser is not
available" the Cloud view already renders as an empty state.

Verified: dedup unit tests 2/2; live .198 (15 entries→13 distinct onions)
restarted healthy on new binary; B4 guard present in built bundle + deployed.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 12:29:12 -04:00
archipelago
1db720af13 fix(lnd): repair fleet-wide CORS on LND connect-wallet endpoints (B5)
The LND wallet UI (served on its own app port) fetches /lnd-connect-info
and /proxy/lnd/* cross-origin, so both need correct CORS headers.

(a) Older nginx configs add their own Access-Control-Allow-Origin in the
    /lnd-connect-info location on top of the one the backend sets, yielding
    a DUPLICATE header that browsers reject ("multiple values"). bootstrap
    now strips that redundant nginx add_header (backend owns CORS).
(b) /proxy/lnd/* returned a 401 with no CORS headers when the session
    check failed, so the browser saw an opaque CORS error instead of a
    readable 401. Add unauthorized_cors() and use it on that path.

Adds tests/production-quality/ (bug tracker + lnd-cors-test.sh harness).
Verified: harness 4/4 on .116, .198, .103.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 11:31:14 -04:00
archipelago
8c3c79543e chore: sync core/Cargo.lock to 1.7.96-alpha (release leftover)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 10:15:24 -04:00
archipelago
7aa1ca013f chore: release v1.7.96-alpha 2026-06-15 10:14:05 -04:00
archipelago
5af9a22b98 feat(fips): selectable TCP/UDP transport when adding a seed anchor
The add-anchor form previously hardcoded transport=udp. Expose a
TCP/UDP selector (default tcp) so public internet anchors and
local-network anchors can both be added. Includes changelog + What's
New entry for v1.7.96-alpha.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 10:12:23 -04:00
archipelago
786498a57a fix(kiosk): remove kiosk launcher grid, show normal app on the display
The kiosk attached-display showed a separate app-tile launcher grid
(Kiosk.vue at /kiosk) instead of the normal onboarding/login/dashboard.
The grid is auth-gated, so it only surfaced once the kiosk browser held a
persisted session; otherwise it bounced to login — masking the issue.

Remove the grid entirely. /kiosk now just persists kiosk mode + safe-area
insets and redirects to the root app. The launcher keeps pointing at
/kiosk (not directly at /) so the 'kiosk' localStorage flag is still set —
App.vue uses it to skip the remote relay, which would otherwise double
xdotool input on the kiosk display. Route made public so the auth guard
doesn't bounce it before the redirect runs.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 10:03:07 -04:00
archipelago
790ad154f3 chore: sync core/Cargo.lock to 1.7.95-alpha (release leftover)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 09:04:30 -04:00
archipelago
0c8991b519 test(multinode): assertion-based two-node E2E smoke suite
Adds tests/multinode/smoke.sh on the existing multinode.bash lib: an
assertion suite (pass/fail + non-zero exit) driving two real nodes through
login, onion + FIPS identity, FIPS anchor-connected, federation pairing
both directions, peer content browse over the mesh, and the removed-node
tombstone (with an optional 3rd node C for the transitive-reappear case).
Guards the v1.7.94/v1.7.95 fixes. Content-browse + tombstone checks
skip-with-note against peers older than v1.7.95.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 09:03:58 -04:00
archipelago
e2c2f942c2 chore: release v1.7.95-alpha 2026-06-15 08:48:22 -04:00
archipelago
937ba7e115 chore: sync core/Cargo.lock to 1.7.94-alpha (release leftover)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 08:09:55 -04:00
archipelago
e056c2477b fix(fips,federation,ui): mesh content browse, removed-node tombstones, modal sizing
FIPS peer content browse over the mesh was failing with "Peer returned
error: 404 Not Found" and never falling back to Tor. `is_peer_allowed_path`
only allowed `/content/<id>` (item fetches) — the catalog endpoint is
exactly `/content` (no trailing slash), so it 404'd over the FIPS peer
listener. A FIPS 404 was also treated as a successful response, so the dial
never retried Tor. Fixes: allow `/content` over the mesh; add
`fips_should_fall_back()` so a FIPS 404/5xx in Auto mode falls back to Tor
(handles version-skew peers reaching a different route). Also correct the
reconnect hint text — the public anchor is TCP/8443, not UDP/8668.

Federation: deleted nodes reappeared because transitive discovery
(`merge` of a peer's advertised trusted peers) re-added any unknown DID.
Add a tombstone store (`removed-nodes.json`): remove_node tombstones the
DID, transitive merge skips tombstoned DIDs, and a remote-triggered
peer-joined is ignored for a removed DID. Explicit local re-add (add_node)
clears the tombstone.

UI: the app credentials modal panel stretched edge-to-edge (height:100%,
max-width:none, items-stretch overlay). Constrain it to a centered card
(max-width 34rem, rounded, dimmed full-screen backdrop) matching the
AppIconGrid / wallet-receive modal.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 08:09:26 -04:00
archipelago
7bd22f1f80 chore: release v1.7.94-alpha 2026-06-15 07:09:58 -04:00
archipelago
cfb0e4735a chore: sync What's New modal for v1.7.94-alpha
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 06:43:20 -04:00
archipelago
95f9a805b1 feat(fips): connect to public mesh anchor over TCP + wire daemon updates
The whole fleet was silently never reaching the FIPS mesh: the default
public anchor was configured as fips.v0l.io:8668/udp, but the anchor only
answers on TCP/8443. Fix the default to 185.18.221.160:8443/tcp (IPv4
literal — the hostname resolves IPv6-first and the daemon binds v4-only,
which fails the handshake with EAFNOSUPPORT), and auto-seed it in
anchors::load() so every node dials it without operator action (removal
still persists). Proven live on .116: cold start → anchor_connected in
~400ms, anchor became mesh parent.

Wire fips::update::apply() against upstream GitHub releases (stable
channel only): resolve /releases/latest → SHA256-verify the .deb against
checksums-linux.txt → install → restart. dpkg runs via `systemd-run` to
escape archipelago's ProtectSystem=strict sandbox (else /var/lib/dpkg is
read-only), with --force-confold (archipelago manages /etc/fips conffiles)
and --force-downgrade (dev builds sort newer than the stable tag).
Validated live: .116 upgraded 0.3.0-dev -> stable v0.3.0.

Also: standalone fips-ui dashboard app (apps/fips-ui + docker/fips-ui,
static nginx proxying /rpc/v1 same-origin, copiable own-anchor address);
reserve UI port 8336; register fips/fips-ui as platform-managed. Includes
the Lightning wallet cross-origin (CORS) + LND proxy auth + nginx
self-healer fix so the wallet screen connects instead of "failed to fetch".

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-15 06:41:48 -04:00
archipelago
640dc87a5f chore: sync core/Cargo.lock to 1.7.93-alpha (release leftover)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 15:21:07 -04:00
archipelago
327a4e34dd chore: release v1.7.93-alpha 2026-06-14 15:18:34 -04:00
archipelago
bf2793be7b chore: sync What's New modal for v1.7.93-alpha
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 14:45:56 -04:00
archipelago
1973d76427 style: rustfmt lnd migrate_locked_wallet matches! call
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 14:41:40 -04:00
archipelago
403fa6eff3 docs: changelog for v1.7.93-alpha (LND wallet self-heal)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 14:38:57 -04:00
archipelago
3214d6aff3 fix(lnd): self-heal unrecoverable locked wallet via wipe+recreate
When an existing LND wallet is locked and none of the candidate passwords
(per-node secret, legacy constant) open it, the node can never auto-unlock
unattended. unlock_existing_wallet now returns Ok(false) for "all candidates
actively rejected" (vs Err for transient "LND not ready"), and
ensure_wallet_initialized responds by recreating the wallet:

  - mark the lnd container user-stopped so the health monitor won't
    re-launch it (and re-open the wallet) mid-wipe,
  - stop lnd, delete its wallet/chain/graph state as root,
  - start lnd, wait for NON_EXISTING, re-init a fresh wallet on the
    per-node secret, then clear the user-stopped flag.

LND runs as a plain bridge-network podman container (not a Quadlet unit),
so it is restarted via `systemd-run --user --scope podman`, matching the
orchestrator/health-monitor path.

Alpha nodes hold no funds and a wallet locked with an unknown password is
already inaccessible, so the wipe loses nothing reachable. Completes the
forward fix from 91adc281 for nodes whose wallet pre-dates the per-node
secret and whose password is unrecorded (e.g. .116/.228).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 14:08:33 -04:00
archipelago
459046b21c docs: resume notes for LND wallet fix (in-progress, branch lnd-wallet-password-fix)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 11:26:10 -04:00
archipelago
91adc281ca fix(lnd): per-node wallet password + locked-wallet self-heal on login
Replaces the fleet-wide hardcoded WALLET_PASSWORD='hellohello' that left wallets
LOCKED after OTA/reboot (auto-unlock used the wrong password fleet-wide).

Forward fix (both init paths unified, validated cargo check + LND REST mechanics
on a scratch wallet):
- Per-node random 256-bit secret in secrets/lnd-wallet-password (0600), mirroring
  secrets/bitcoin-rpc-password. read_wallet_password (no-gen) vs
  ensure_wallet_password (gen at init only).
- container/lnd.rs init AND api/rpc/lnd/wallet.rs seed-derived init both use the
  per-node secret (wallet.rs keeps recoverable derived entropy; password unified).
- Unlock tries [per-node secret, legacy 'hellohello']; single-attempt primitive
  distinguishes invalid-passphrase (fail fast, try next) from not-ready (retry),
  so a wrong password no longer hangs the boot path ~60s.

Migration (candidate-unlock + rotate, best-effort at login):
- change_wallet_password (WalletUnlocker.ChangePassword) + migrate_locked_wallet:
  if LOCKED, try candidates as current pw and ChangePassword onto the per-node
  secret so future boots auto-unlock. Hooked into auth.login (non-blocking) with
  the just-verified password as the candidate.

NOT YET: seed-recovery fallback for wallets where no candidate matches (e.g.
.116/.228) — destructive, needs entropy-source/funds-safety handling; next pass.
NOT shipped: pending end-to-end validation on a real node.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 11:19:56 -04:00
archipelago
a9c4e54023 chore: sync core/Cargo.lock to 1.7.92-alpha (release leftover)
create-release.sh bumps Cargo.toml but not the lock's archipelago version line;
the cargo build regenerates it post-commit. Same as the 1.7.91 leftover — worth
fixing create-release.sh to stage Cargo.lock, tracked separately.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 10:42:13 -04:00
archipelago
8c8e4d7a29 test: gate that LND wallet is unlocked after restart (catches fleet-wide lock)
A wrong/locked LND wallet password leaves the wallet LOCKED after every
restart/OTA, breaking all Bitcoin-receive + Lightning ops fleet-wide — and the
harness was blind to it: live-lnd-address-type treats 'wallet locked' as PASS,
os-audit treated lnd-unreachable as WARN, and the archipelago lnd.getinfo RPC
masks a locked wallet (returns all-zero success).

- tests/release/run.sh: new 'live-lnd-unlocked' stage polls LND's unauth
  /v1/state and FAILs if still LOCKED after a 60s grace window.
- tests/lifecycle/os-audit.sh: probe lnd.newaddress (the real receive path,
  which surfaces LND_WALLET_LOCKED) instead of lnd.getinfo; locked = hard FAIL,
  not-installed = WARN.

Proven on .116 (genuinely locked): os-audit now reports
'[FAIL] lnd wallet unlocked (lnd.newaddress) wallet LOCKED'.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 10:36:12 -04:00
archipelago
9d3347463a docs: record v1.7.91 + v1.7.92 published; What's New gate; .116 nginx fix
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 09:20:35 -04:00
archipelago
d462e44453 chore: release v1.7.92-alpha 2026-06-14 09:09:57 -04:00
archipelago
1af583e1ab docs: add third v1.7.92 changelog bullet (What's New backfill) + sync modal
create-release staging requires >=3 curated release-note bullets. The What's
New restoration is itself user-facing, so it's an honest third note; mirror it
into the modal's v1.7.92 block via sync-whats-new.py.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 09:03:18 -04:00
archipelago
2fac63e58c feat(release): gate that Settings 'What's New' modal stays in sync with CHANGELOG
The What's New modal (AccountInfoSection.vue) hardcodes one block per release
and had silently drifted: it sat at v1.7.84 while the fleet shipped through
v1.7.92, so eight releases of notes never reached users in Settings.

- scripts/sync-whats-new.py: renders a modal block from each CHANGELOG version
  that's missing one (curated bullets, dev-process 'Validation…' lines dropped),
  inserts newest-first; never touches older hand-written pre-CHANGELOG history.
  --check mode lists anything missing and exits non-zero.
- tests/release/run.sh: new 'whats-new-sync' static gate runs --check, so a
  release with an un-surfaced CHANGELOG entry fails before shipping.
- Backfilled the eight missing blocks (v1.7.85 … v1.7.92) into the modal.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 08:31:43 -04:00
archipelago
2999ab62ea docs: changelog for v1.7.92-alpha
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 08:04:13 -04:00
archipelago
5b052372b7 test(resilience): gate host-reboot batch on os-audit (L3 per-boot health)
batch_host_reboot previously asserted only container-set equality after the
reboot. Add the os-audit.sh per-boot health gate: after rpc_login succeeds
post-reboot, run os-audit against the target (ARCHY_LOCAL=0, https) and record
host_reboot_osaudit PASS/FAIL. This asserts the node is actually healthy after
a reboot — RPC up, OTA not wedged (FM12), every app reachable with valid launch
metadata, FM-guards green — not just that the right containers exist. Validated
green on .116 (11 pass / 0 fail / 0 warn).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 08:01:30 -04:00
archipelago
4232424b23 fix(ui): suppress app-unreachable overlay while ElectrumX sync screen shows
When ElectrumX is still building its index (or waiting on the Bitcoin node),
AppSessionFrame shows a sync 'pre UI'. The iframe-blocked fallback ('App not
reachable / retrying') was not gated on electrsSync, so it painted over the
sync screen and read as a hard connection error. Gate it on !electrsSync,
mirroring the iframe's own guard.

Also harden the lifecycle health probe: container_health used jq '// "unknown"',
which only catches null/false — an empty-string health (a brief window under
load) rendered as a blank 'bad health: X is '. Map empty to 'unknown' so the
retry loop keeps waiting instead of failing on a transient.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 07:58:24 -04:00
archipelago
60fe761def chore: sync core/Cargo.lock to 1.7.91-alpha (release leftover)
create-release.sh bumps Cargo.toml; the lock's archipelago version line is
regenerated by the subsequent cargo build and was left uncommitted after the
v1.7.91-alpha release commit. The shipped binary is built from the bumped
Cargo.toml, so this is bookkeeping only.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 07:58:03 -04:00
archipelago
9b9fa9cdee chore: release v1.7.91-alpha 2026-06-14 05:32:38 -04:00
archipelago
329e7811eb test(lifecycle): add os-audit OS-wide health gate; docs: v1.7.91 resume notes
os-audit.sh: one non-destructive scorecard tying backend/RPC health, the
all-apps lifecycle audit (delegates to remote-lifecycle.sh), and the FM-guards
(port-drift, secret-completeness, orphan-container sweep, OTA-wedge). The
per-boot building block for the reboot-survival loop. FM12 check uses jq has()
not // (// treats a legit false as empty). Section A validated all-PASS on .116.

docs: v1.7.91 release-pass resume notes + the bitcoinReceive blocker writeup.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 04:36:06 -04:00
archipelago
21aaacc8b4 fix(ui): guard receive-code index access — unblocks v1.7.91 frontend build
codeMatch[1] is string|undefined under noUncheckedIndexedAccess; using it
directly as an index into RECEIVE_CODE_MESSAGES failed vue-tsc (TS2538) and
aborted create-release.sh at the frontend build step. Bind to a const and
narrow before indexing.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 04:35:21 -04:00
archipelago
ab85827187 docs: changelog for v1.7.91-alpha
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 03:59:49 -04:00
archipelago
bea745047d docs: record F1 live validation on .116 (green)
Before/after on the live node confirms the launch_url_port fix:
jellyfin/btcpay/fedimint/gitea/portainer/botfights all went from
lan_address=None to a resolved http://localhost:PORT/ URL; harness
focused audit passed, exit 0. Also documents that archipelago.service
restarts are safe on .116 (containers run in the user-1000 slice, a
different cgroup, and survived the restart).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 03:55:58 -04:00
archipelago
a483fe4baa fix: derive launch port from URL authority, not naive rsplit
reachable_lan_address() parsed the launch port with url.rsplit(':')
which yields "8096/" for manifest interfaces.main URLs that carry a
path (http://localhost:8096/). That fails to parse and silently drops
a perfectly reachable launch URL, so apps like jellyfin, btcpay-server,
fedimint, gitea, nextcloud and portainer showed running with no launch
link in the UI. New launch_url_port() reads digits after the final
colon (mirroring port_from_url in the RPC layer) and tolerates a
trailing path. Adds regression tests.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 03:35:19 -04:00
archipelago
0ed892a412 fix: wallet receive reliability, bitcoin install self-heal, ElectrumX app tile
Fixes three Bitcoin/wallet failures observed across the fleet on v1.7.90-alpha
(all nodes were already on the latest build — these were live bugs, not stale
builds), plus the missing ElectrumX tile, and adds automated coverage so each
can't regress silently.

Receive address (".116 receive fails", ".228 false 'wallet is locked'"):
- LND publishes its REST API on a host port that can drift from the manifest
  (a container created when the mapping was 8080 kept publishing 8080 after the
  manifest moved to 18080). The in-process client connects to the manifest port,
  gets connection-refused, and wallet init fails forever while the container
  looks "Up". Add published-port drift detection to the reconciler
  (container_ports_drifted / host_port_bindings_drifted) that recreates a
  drifted backend even for restart-sensitive apps — a drifted container is
  already broken, so leaving it "untouched" only perpetuates the failure.
- Receive errors now carry a stable [CODE] token (REST_UNREACHABLE, WALLET_LOCKED,
  WALLET_UNINITIALIZED, SYNCING) and always start with "Bitcoin address" so they
  survive the RPC error sanitizer instead of collapsing to the generic
  "Operation failed". The UI maps the code instead of guessing wallet state from
  substrings — so an unreachable REST endpoint is no longer mislabelled "locked".

Bitcoin install (".198 bitcoin gone / reinstall just stops"):
- bitcoin-knots requires the secret bitcoin-rpc-txrelay-rpcauth, which was only
  generated by the tx-relay flow. Nodes that never used tx-relay lacked it, so
  secret resolution hard-failed and the whole Bitcoin stack cascaded. Generate
  it idempotently before bitcoin starts (ensure_app_secrets, reusing
  ensure_txrelay_credentials), and name the missing secret in the error so a
  genuine gap is actionable instead of a bare "IO error".

ElectrumX app tile missing on every node with it installed:
- The catalog generator dropped electrumx because the manifest had no
  interfaces.main block, so the tile had no launch URL and was hidden. Declare
  the companion UI port (50002) in the manifest, regenerate the catalog, and let
  an app with a known launch URL stay launchable while its backend is still
  "starting" (ElectrumX indexes for 10m+).

Test harness:
- New lifecycle bats suites: bitcoin-receive, port-drift, secret-completeness
  (validated live; port-drift catches the real .116 drift).
- Rust unit tests for drift detection, the receive reason-code classifier, and
  the named-missing-secret error; vitest for the UI code mapping.
- create-release.sh now runs tests/release/run.sh and aborts the release on
  failure — previously it ran no tests at all.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 03:12:56 -04:00
archipelago
bb808df89a chore: release v1.7.90-alpha 2026-06-13 05:05:14 -04:00
archipelago
c800293f1f fix: bitcoin receive, AIUI pointer input, electrs self-heal, OTA timeout
- LND wallet: request correct address type so receive-address generation
  no longer 400s
- AIUI/app session: on-screen pointer can click + type into app content
  (incl. app store search); "open in new tab" opens the phone browser;
  mobile credential modal centered instead of full-height
  (remote-relay.ts, AppSession.vue, AppSessionFrame.vue, AppIconGrid.vue,
  openExternal.ts, WebViewScreen.kt) + remote-relay tests
- health_monitor: electrs auto-recovers from a corrupt index and shows a
  percent/block-height progress screen while reindexing (useElectrsSync.ts)
- update.rs: drop retired tx1138 secondary mirror (one-time migration);
  longer download timeout for slow connections
- CHANGELOG: v1.7.90-alpha notes
- tests/release/run.sh: harness tweaks

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-13 04:49:32 -04:00
375 changed files with 36861 additions and 10237 deletions

51
.githooks/pre-push Executable file
View File

@ -0,0 +1,51 @@
#!/usr/bin/env bash
# Keep the served companion APK in sync with main on every push.
#
# When a push to main includes Android changes, rebuild the APK, refresh
# neode-ui/public/packages/archipelago-companion.apk, commit it, and ask
# you to push again (so the refreshed APK rides along in the same push).
#
# Enable once per clone: git config core.hooksPath .githooks
set -euo pipefail
ROOT="$(git rev-parse --show-toplevel)"
cd "$ROOT"
# ship-companion.sh already (re)published the APK for this push — don't redo it.
[ -n "${SHIP_COMPANION:-}" ] && exit 0
PUSH_MAIN=0; RANGE_OLD=""; RANGE_NEW=""
while read -r _local_ref local_sha remote_ref remote_sha; do
if [ "${remote_ref##*/}" = "main" ]; then
PUSH_MAIN=1; RANGE_OLD="$remote_sha"; RANGE_NEW="$local_sha"
fi
done
[ "$PUSH_MAIN" = "1" ] || exit 0
# Loop-break: if the tip is already the auto APK commit, let the push proceed.
case "$(git log -1 --pretty=%s)" in
*"companion APK"*) exit 0 ;;
esac
# Only rebuild when this push actually touches the Android app.
ZEROS="0000000000000000000000000000000000000000"
if [ -z "$RANGE_OLD" ] || [ "$RANGE_OLD" = "$ZEROS" ]; then
ANDROID_CHANGED=1
elif git diff --quiet "$RANGE_OLD" "$RANGE_NEW" -- Android/ 2>/dev/null; then
ANDROID_CHANGED=0
else
ANDROID_CHANGED=1
fi
[ "$ANDROID_CHANGED" = "1" ] || exit 0
bash scripts/publish-companion-apk.sh || exit 0
DEST="neode-ui/public/packages/archipelago-companion.apk"
if git diff --cached --quiet -- "$DEST"; then
exit 0 # APK unchanged — nothing to do
fi
git commit -q -m "chore(android): update companion APK download [skip ci]"
echo "" >&2
echo "▶ Companion APK rebuilt and committed. Run your push again to include it." >&2
exit 1

5
Android/.gitignore vendored
View File

@ -14,3 +14,8 @@ local.properties
*.aab
*.jks
*.keystore
# Exception: the repo-dedicated *debug* keystore is committed on purpose so every
# machine (and the published companion download) signs debug builds identically —
# updates then install over the top without an uninstall. Debug keys are not
# secret (well-known password "android"); never commit a real release keystore.
!/app/debug.keystore

View File

@ -0,0 +1,94 @@
# Companion App — Build, Ship & "App Not Installed" Runbook
Canonical procedure for releasing the Archipelago Companion Android app and for
debugging install failures. Read this before touching the companion release flow.
Hard lessons from 2026-06-26 are baked in below — don't relearn them.
## Ship the companion (the only sanctioned way)
```bash
./Android/ship-companion.sh
```
This calls `scripts/publish-companion-apk.sh` (the single source of truth, also
used by the `.githooks/pre-push` hook), which:
1. **Removes/rejects resource dirs whose names contain spaces.** Empty stray
`mipmap-* NNN` dirs (left by icon-export tools) break a *clean* build with
`Invalid resource directory name`. Incremental builds hide them — clean builds
don't.
2. **Always does a CLEAN build** (`:app:clean :app:assembleDebug`).
3. **Forces v1 + v2 + v3 signing** via `zipalign` + `apksigner`.
4. **Verifies all three schemes** (`apksigner verify --min-sdk-version 21`) and
**aborts** if any is missing.
5. Stages the signed APK at `neode-ui/public/packages/archipelago-companion.apk`,
commits, and pushes with `SHIP_COMPANION=1` (the sanctioned pre-push bypass).
**Never** hand-roll `gradlew assembleDebug` + `cp` to the served path. That path
skips the clean build and the signature enforcement and is exactly how a broken
APK shipped.
### Bump the version first
Edit `Android/app/build.gradle.kts``versionCode` (must strictly increase) and
`versionName`. The committed value can drift AHEAD of what's actually built into
the served APK, so verify the served APK's real version after shipping:
`aapt2 dump badging neode-ui/public/packages/archipelago-companion.apk | grep version`.
## Signing facts (important)
- Debug builds are signed with the **committed** `Android/app/debug.keystore`
(store/key pass `android`, alias `androiddebugkey`) so every machine and the
served download share ONE signing key. Cert SHA-256: `D6:22:E0:7E:…:66:4D`.
- **AGP silently ignores `enableV1Signing = true` for `minSdk ≥ 24`**, so a plain
gradle build produces a **v2-only** APK. The `apksigner` step in the publish
script is what actually guarantees v1+v2+v3 — do not remove it.
- **Changing the signing key forces every existing install to be uninstalled
once.** Android blocks in-place upgrades across different signatures. Treat the
keystore as permanent; never regenerate it casually.
## Debugging "App Not Installed" — DIAGNOSE FIRST
Do **not** theorize about signing schemes / OEM quirks. Get the real reason:
```bash
adb install ~/Desktop/archipelago-companion-<ver>.apk
# -> Failure [INSTALL_FAILED_<REASON>: ...]
```
Map the reason:
| `INSTALL_FAILED_*` | Cause | Fix |
|---|---|---|
| `UPDATE_INCOMPATIBLE … signatures do not match` | Old install signed with a **different key** (e.g. pre-shared-keystore per-machine key `58:31:12…`). | Uninstall the old package, then install. **One-time** per device after a key change. |
| `INVALID_APK` / parse error | Corrupt/incomplete download or bad signing. | Re-download; re-run the publish script. |
| `INSUFFICIENT_STORAGE` | Storage. | Free space. |
| `OLDER_SDK` | Device below `minSdk` (26 = Android 8.0). | Unsupported device. |
> A manual uninstall on the phone may NOT clear `UPDATE_INCOMPATIBLE` if the
> package is registered under another user/profile — `pm path <pkg>` under user 0
> can show nothing while the conflict persists. `adb uninstall <pkg>` clears it
> across all users.
## Phone / adb safety (non-negotiable)
When acting on the user's physical phone, be surgical — the user once had all
home-screen app layouts wiped by an over-broad action.
- Default to **read-only** adb (`devices`, `getprop`, `pm path/list`, `dumpsys`).
- Mutations (`adb install`, `adb uninstall com.archipelago.app.debug`) only with
explicit go-ahead and **scoped to our exact package** — echo it first.
- **Never** run launcher/system resets: no `pm clear` on launchers, no
`reset-permissions`, no factory wipe, no uninstalling apps you didn't build.
## Verify the published download after shipping
The download served to nodes is Gitea raw-on-main. Confirm the live bytes match
what you built and signed:
```bash
SERVED=neode-ui/public/packages/archipelago-companion.apk
URL=http://146.59.87.168:3000/lfg2025/archy/raw/branch/main/$SERVED
curl -sS -o /tmp/live.apk "$URL"
shasum -a 256 "$SERVED" /tmp/live.apk # must match
apksigner verify -v --min-sdk-version 21 /tmp/live.apk | grep -i "scheme" # v1/v2/v3 = true
```

View File

@ -11,15 +11,41 @@ android {
applicationId = "com.archipelago.app"
minSdk = 26
targetSdk = 35
versionCode = 6
versionName = "0.4.2"
versionCode = 16
versionName = "0.4.12"
vectorDrawables {
useSupportLibrary = true
}
}
signingConfigs {
// Repo-dedicated debug keystore (committed at app/debug.keystore) so every
// machine — and the published companion download — signs debug builds with
// the SAME key. Without this, Gradle falls back to each machine's
// ~/.android/debug.keystore, so a build from a different machine has a
// different signature and the phone rejects the update ("App not installed").
getByName("debug") {
storeFile = file("debug.keystore")
storePassword = "android"
keyAlias = "androiddebugkey"
keyPassword = "android"
// Force both legacy JAR (v1) and APK Signature Scheme v2. AGP drops v1
// for minSdk>=24, but some OEM package installers (e.g. Samsung) reject
// a v2-only sideload with "App not installed" — keep v1 for max compat.
enableV1Signing = true
enableV2Signing = true
}
}
buildTypes {
debug {
// Separate app ID so a debug/test build installs alongside the
// release app instead of colliding on signature.
applicationIdSuffix = ".debug"
versionNameSuffix = "-debug"
signingConfig = signingConfigs.getByName("debug")
}
release {
isMinifyEnabled = true
isShrinkResources = true

BIN
Android/app/debug.keystore Normal file

Binary file not shown.

View File

@ -18,7 +18,11 @@ data class ServerEntry(
val useHttps: Boolean,
val port: String = "",
val password: String = "",
val name: String = "",
) {
/** Label to show in lists — the user-given name, or the address if unnamed. */
fun displayName(): String = name.ifBlank { address }
fun toUrl(): String {
val scheme = if (useHttps) "https" else "http"
val portSuffix = if (port.isNotBlank()) ":$port" else ""
@ -31,7 +35,9 @@ data class ServerEntry(
return "$scheme://$address$portSuffix"
}
fun serialize(): String = "$address|$useHttps|$port|$password"
// name is the trailing field so entries saved before naming existed
// (4 fields) still deserialize, with name defaulting to "".
fun serialize(): String = "$address|$useHttps|$port|$password|$name"
companion object {
fun deserialize(raw: String): ServerEntry? {
@ -42,6 +48,7 @@ data class ServerEntry(
useHttps = parts[1].toBooleanStrictOrNull() ?: false,
port = parts.getOrElse(2) { "" },
password = parts.getOrElse(3) { "" },
name = parts.getOrElse(4) { "" },
)
}
}
@ -53,6 +60,7 @@ class ServerPreferences(private val context: Context) {
private val activeHttpsKey = booleanPreferencesKey("active_https")
private val activePortKey = stringPreferencesKey("active_port")
private val activePasswordKey = stringPreferencesKey("active_password")
private val activeNameKey = stringPreferencesKey("active_name")
private val savedServersKey = stringSetPreferencesKey("saved_servers")
private val introSeenKey = booleanPreferencesKey("intro_seen")
@ -63,6 +71,7 @@ class ServerPreferences(private val context: Context) {
useHttps = prefs[activeHttpsKey] ?: false,
port = prefs[activePortKey] ?: "",
password = prefs[activePasswordKey] ?: "",
name = prefs[activeNameKey] ?: "",
)
}
@ -81,6 +90,7 @@ class ServerPreferences(private val context: Context) {
prefs[activeHttpsKey] = server.useHttps
prefs[activePortKey] = server.port
prefs[activePasswordKey] = server.password
prefs[activeNameKey] = server.name
}
addSavedServer(server)
}
@ -91,6 +101,7 @@ class ServerPreferences(private val context: Context) {
prefs.remove(activeHttpsKey)
prefs.remove(activePortKey)
prefs.remove(activePasswordKey)
prefs.remove(activeNameKey)
}
}
@ -101,10 +112,50 @@ class ServerPreferences(private val context: Context) {
}
}
/**
* Replace a saved server in place. Matches the existing entry by connection
* identity (address/port/scheme) so edits that change the name or password
* or that touch a legacy 4-field entry still update the right record. If the
* edited server is also the active one, the active record is kept in sync.
*/
suspend fun updateSavedServer(original: ServerEntry, updated: ServerEntry) {
context.dataStore.edit { prefs ->
val current = prefs[savedServersKey] ?: emptySet()
val filtered = current.filterNot { raw ->
val e = ServerEntry.deserialize(raw)
e != null &&
e.address == original.address &&
e.port == original.port &&
e.useHttps == original.useHttps
}.toSet()
prefs[savedServersKey] = filtered + updated.serialize()
val isActive = prefs[activeAddressKey] == original.address &&
(prefs[activePortKey] ?: "") == original.port &&
(prefs[activeHttpsKey] ?: false) == original.useHttps
if (isActive) {
prefs[activeAddressKey] = updated.address
prefs[activeHttpsKey] = updated.useHttps
prefs[activePortKey] = updated.port
prefs[activePasswordKey] = updated.password
prefs[activeNameKey] = updated.name
}
}
}
suspend fun removeSavedServer(server: ServerEntry) {
context.dataStore.edit { prefs ->
val current = prefs[savedServersKey] ?: emptySet()
prefs[savedServersKey] = current - server.serialize()
// Match by connection identity (address/port/scheme) rather than the
// exact serialized string, so a rename — or the legacy 4-field format
// saved before names existed — still removes the right entry.
prefs[savedServersKey] = current.filterNot { raw ->
val e = ServerEntry.deserialize(raw)
e != null &&
e.address == server.address &&
e.port == server.port &&
e.useHttps == server.useHttps
}.toSet()
}
}

View File

@ -35,6 +35,13 @@ class InputWebSocket(
/** Player ID for arcade mode (0 = broadcast, 1 = P1, 2 = P2) */
var playerId: Int = 0
/**
* Invoked when the kiosk asks us to open a URL in the phone's default
* browser ({"t":"o","url":""}). "Open in external browser" apps can't be
* usefully opened on the kiosk, so the kiosk forwards them here.
*/
var onExternalOpen: ((String) -> Unit)? = null
private val _state = MutableStateFlow(ConnectionState.DISCONNECTED)
val state: StateFlow<ConnectionState> = _state
@ -127,6 +134,20 @@ class InputWebSocket(
reconnectAttempt = 0
}
override fun onMessage(webSocket: WebSocket, text: String) {
// The only inbound message we act on is an external-open request
// forwarded from the kiosk: {"t":"o","url":"https://…"}.
try {
val obj = org.json.JSONObject(text)
if (obj.optString("t") == "o") {
val url = obj.optString("url")
if (url.startsWith("http://") || url.startsWith("https://")) {
onExternalOpen?.invoke(url)
}
}
} catch (_: Exception) {}
}
override fun onFailure(webSocket: WebSocket, t: Throwable, response: Response?) {
_state.value = ConnectionState.ERROR
scheduleReconnect()

View File

@ -108,7 +108,9 @@ private fun Btn(icon: ImageVector, key: String, onDir: (String) -> Unit) {
.pointerInput(key) {
detectTapGestures(onPress = {
p = true; onDir(key)
job = scope.launch { delay(350); while (true) { onDir(key); delay(100) } }
// 500ms initial delay so a normal tap sends one key, not two
// (a touch tap often exceeds 350ms → doubled nav sound).
job = scope.launch { delay(500); while (true) { onDir(key); delay(100) } }
tryAwaitRelease(); p = false; job?.cancel()
})
},

View File

@ -83,13 +83,16 @@ val ClassicPalette = NESPalette(
inlayBg = Color(0xFF080808), inlayBorder = Color(0xFF999999),
)
// Glassmorphism-black (OS design): translucent dark surfaces so the backdrop
// shows through the controller, subtle white-alpha borders, translucent-white
// buttons. Accents come from each button's ring.
val DarkPalette = NESPalette(
body = NES.DarkBody, face = NES.DarkFace, ridge = NES.DarkRidge,
label = NES.DarkLabel, labelMuted = NES.DarkLabelMuted,
dpad = Color(0xFF080808), dpadHi = Color(0xFF141418),
btn = NES.DarkButtonMain, btnPress = NES.DarkButtonMainPress,
capsule = Color(0xFF121216), capsulePress = Color(0xFF0A0A0C),
inlayBg = Color(0xFF060608), inlayBorder = Color(0xFF444448),
body = Color(0xA6121216), face = Color(0x8C0E0E12), ridge = Color(0x14FFFFFF),
label = Color(0xFF9A9A9A), labelMuted = Color(0xFF777777),
dpad = Color(0xFF202024), dpadHi = Color(0xFF33333A),
btn = Color(0x14FFFFFF), btnPress = Color(0x0AFFFFFF),
capsule = Color(0x12FFFFFF), capsulePress = Color(0x08FFFFFF),
inlayBg = Color(0x990A0A0A), inlayBorder = Color(0x1FFFFFFF),
)
fun paletteFor(style: ControllerStyle) = if (style == ControllerStyle.CLASSIC) ClassicPalette else DarkPalette
@ -113,20 +116,10 @@ fun NESController(
Box(
modifier = modifier
.fillMaxSize()
.background(Color(0xFF0C0C0C)) // Slightly lighter than black for shadow visibility
.twoFingerHold(onMenu)
.padding(horizontal = 40.dp, vertical = 24.dp),
contentAlignment = Alignment.Center,
) {
// Shadow platform
Box(
modifier = Modifier
.fillMaxWidth(0.86f)
.aspectRatio(2.3f)
.padding(top = 6.dp)
.clip(RoundedCornerShape(18.dp))
.background(Color(0xFF000000)),
)
// Controller body
Box(
Modifier
@ -135,7 +128,7 @@ fun NESController(
.shadow(32.dp, RoundedCornerShape(16.dp), ambientColor = Color(0xFF000000), spotColor = Color(0xFF000000))
.clip(RoundedCornerShape(16.dp))
.background(
Brush.verticalGradient(listOf(c.body, c.body.copy(alpha = 0.95f)))
Brush.verticalGradient(listOf(c.body, c.body))
)
.border(1.dp, Color.White.copy(alpha = if (isClassic) 0.08f else 0.04f), RoundedCornerShape(16.dp)),
) {
@ -193,13 +186,13 @@ fun NESController(
horizontalAlignment = Alignment.CenterHorizontally,
verticalArrangement = Arrangement.Center,
) {
// C on top (white)
ColorBtn(Color(0xFF888888), Color(0xFFAAAAAA), 44.dp) { onKey("c") }
// C on top
GlassFaceBtn("C", Color(0xFFBBBBBB), 44.dp) { onKey("c") }
Spacer(Modifier.height(6.dp))
// B + A on bottom row
Row(horizontalArrangement = Arrangement.spacedBy(12.dp)) {
ColorBtn(Color(0xFF3B82F6), Color(0xFF60A5FA), 44.dp) { onKey("b") }
ColorBtn(Color(0xFFEA580C), Color(0xFFFB923C), 44.dp) { onKey("a") }
GlassFaceBtn("B", Color(0xFF60A5FA), 44.dp) { onKey("b") }
GlassFaceBtn("A", Color(0xFFF7931A), 44.dp) { onKey("a") }
}
}
}
@ -264,7 +257,9 @@ fun OnePointDPad(c: NESPalette, size: Dp, onDir: (String) -> Unit) {
}
activeDir = dir; onDir(dir)
job?.cancel()
job = scope.launch { delay(300); while (true) { onDir(dir); delay(90) } }
// 500ms initial delay so a normal tap sends one key, not
// two (a touch tap often exceeds 300ms → doubled nav sound).
job = scope.launch { delay(500); while (true) { onDir(dir); delay(90) } }
tryAwaitRelease()
job?.cancel(); activeDir = null
},
@ -375,6 +370,28 @@ fun ColorBtn(color: Color, pressColor: Color, sz: Dp = 48.dp, onClick: () -> Uni
}
}
/** Glass face button — dark translucent fill, colored ring + letter (OS style) */
@Composable
fun GlassFaceBtn(label: String, accent: Color, sz: Dp = 44.dp, onClick: () -> Unit) {
var p by remember { mutableStateOf(false) }
Box(
Modifier
.size(sz)
.clip(CircleShape)
.background(
Brush.verticalGradient(
if (p) listOf(Color.White.copy(alpha = 0.05f), Color.White.copy(alpha = 0.02f))
else listOf(Color.White.copy(alpha = 0.10f), Color.White.copy(alpha = 0.03f))
)
)
.border(1.5.dp, accent.copy(alpha = if (p) 0.95f else 0.55f), CircleShape)
.pointerInput(Unit) { detectTapGestures(onPress = { p = true; onClick(); tryAwaitRelease(); p = false }) },
contentAlignment = Alignment.Center,
) {
Text(label, color = accent.copy(alpha = if (p) 1f else 0.85f), fontSize = 16.sp, fontWeight = FontWeight.Bold)
}
}
/** START/SELECT capsule */
@Composable
fun CapsuleBtn(label: String, c: NESPalette, w: Dp = 64.dp, h: Dp = 28.dp, onClick: () -> Unit) {

View File

@ -3,6 +3,8 @@ package com.archipelago.app.ui.components
import androidx.compose.animation.AnimatedVisibility
import androidx.compose.animation.fadeIn
import androidx.compose.animation.fadeOut
import androidx.compose.animation.scaleIn
import androidx.compose.animation.scaleOut
import androidx.compose.foundation.background
import androidx.compose.foundation.border
import androidx.compose.foundation.clickable
@ -34,17 +36,35 @@ import androidx.compose.ui.Alignment
import androidx.compose.ui.Modifier
import androidx.compose.ui.draw.clip
import androidx.compose.ui.graphics.Color
import androidx.compose.ui.text.TextStyle
import androidx.compose.ui.text.font.FontWeight
import androidx.compose.ui.text.input.ImeAction
import androidx.compose.ui.text.input.KeyboardType
import androidx.compose.ui.text.input.PasswordVisualTransformation
import androidx.compose.ui.text.style.TextAlign
import androidx.compose.ui.unit.dp
import androidx.compose.ui.unit.sp
import com.archipelago.app.data.ServerEntry
import com.archipelago.app.ui.theme.BitcoinOrange
import com.archipelago.app.ui.theme.ControllerStyle
import com.archipelago.app.ui.theme.NES
import com.archipelago.app.ui.theme.SurfaceDark
import com.archipelago.app.ui.theme.TextMuted
import com.archipelago.app.ui.theme.TextPrimary
/** NES-styled modal menu — dark blue panel with white borders */
// Glassmorphism palette (OS design): near-black surfaces, subtle white borders,
// Bitcoin-orange accent.
private val PanelBg = SurfaceDark // #0A0A0A
private val PanelBorder = Color.White.copy(alpha = 0.12f)
private val RowBg = Color.White.copy(alpha = 0.05f)
private val RowBorder = Color.White.copy(alpha = 0.08f)
private val FieldBg = Color.White.copy(alpha = 0.04f)
private val PANEL_R = 20.dp
private val ROW_R = 14.dp
private val ROW_H = 54.dp
private val FIELD_H = 58.dp
/** Glassmorphism modal menu — #0A0A0A surface, subtle white borders. */
@Composable
fun NESMenu(
visible: Boolean,
@ -55,6 +75,7 @@ fun NESMenu(
onDismiss: () -> Unit,
onSelectServer: (ServerEntry) -> Unit,
onAddServer: (ServerEntry) -> Unit,
onEditServer: (ServerEntry, ServerEntry) -> Unit,
onRemoveServer: (ServerEntry) -> Unit,
onToggleMode: () -> Unit,
onToggleStyle: () -> Unit,
@ -66,7 +87,9 @@ fun NESMenu(
.clickable(indication = null, interactionSource = remember { MutableInteractionSource() }) { onDismiss() },
contentAlignment = Alignment.Center,
) {
MenuPanel(servers, activeServer, isGamepadMode, controllerStyle, onDismiss, onSelectServer, onAddServer, onRemoveServer, onToggleMode, onToggleStyle, onBackToWebView)
AnimatedVisibility(visible = visible, enter = fadeIn() + scaleIn(initialScale = 0.95f), exit = fadeOut() + scaleOut(targetScale = 0.95f)) {
MenuPanel(servers, activeServer, isGamepadMode, controllerStyle, onDismiss, onSelectServer, onAddServer, onEditServer, onRemoveServer, onToggleMode, onToggleStyle, onBackToWebView)
}
}
}
}
@ -80,105 +103,160 @@ private fun MenuPanel(
onDismiss: () -> Unit,
onSelectServer: (ServerEntry) -> Unit,
onAddServer: (ServerEntry) -> Unit,
onEditServer: (ServerEntry, ServerEntry) -> Unit,
onRemoveServer: (ServerEntry) -> Unit,
onToggleMode: () -> Unit,
onToggleStyle: () -> Unit,
onBackToWebView: (() -> Unit)?,
) {
var showAdd by remember { mutableStateOf(false) }
// The saved server being edited, or null when adding a new one.
var editing by remember { mutableStateOf<ServerEntry?>(null) }
var nm by remember { mutableStateOf("") }
var addr by remember { mutableStateOf("") }
var pwd by remember { mutableStateOf("") }
fun resetForm() {
nm = ""; addr = ""; pwd = ""; showAdd = false; editing = null
}
fun startEdit(server: ServerEntry) {
editing = server
nm = server.name; addr = server.address; pwd = server.password
showAdd = false
}
fun submit() {
if (addr.isBlank()) return
val orig = editing
if (orig != null) {
// Preserve fields the compact form doesn't expose (scheme, port).
onEditServer(orig, orig.copy(address = addr, password = pwd, name = nm))
} else {
onAddServer(ServerEntry(addr, false, password = pwd, name = nm))
}
resetForm()
}
Column(
modifier = Modifier
.widthIn(max = 360.dp)
.clip(RoundedCornerShape(4.dp))
.background(NES.MenuPanel)
.border(3.dp, NES.MenuBorder, RoundedCornerShape(4.dp))
.widthIn(max = 420.dp)
.padding(horizontal = 20.dp)
.clip(RoundedCornerShape(PANEL_R))
.background(PanelBg)
.border(1.dp, PanelBorder, RoundedCornerShape(PANEL_R))
.clickable(indication = null, interactionSource = remember { MutableInteractionSource() }) {}
.padding(16.dp),
verticalArrangement = Arrangement.spacedBy(6.dp),
.padding(22.dp),
verticalArrangement = Arrangement.spacedBy(10.dp),
) {
// Title
Text("- MENU -", color = NES.MenuText, fontSize = 14.sp, fontWeight = FontWeight.Bold, letterSpacing = 4.sp,
modifier = Modifier.fillMaxWidth(), textAlign = androidx.compose.ui.text.style.TextAlign.Center)
Spacer(Modifier.height(4.dp))
Text(
"Menu",
color = TextPrimary,
fontSize = 18.sp,
fontWeight = FontWeight.SemiBold,
letterSpacing = 2.sp,
modifier = Modifier.fillMaxWidth(),
textAlign = TextAlign.Center,
)
Spacer(Modifier.height(2.dp))
// Servers
servers.forEach { server ->
val active = server.serialize() == activeServer?.serialize()
MenuItem(
label = (if (active) "\u25B6 " else " ") + server.address,
label = server.displayName(),
selected = active,
onClick = { onSelectServer(server) },
onEdit = { startEdit(server) },
onRemove = { onRemoveServer(server) },
)
}
if (servers.isEmpty()) {
Text(" NO SERVERS", color = NES.MenuMuted, fontSize = 11.sp, modifier = Modifier.padding(vertical = 4.dp))
Text("No servers", color = TextMuted, fontSize = 14.sp, modifier = Modifier.padding(vertical = 4.dp))
}
// Add server
if (showAdd) {
// Add / edit server
if (showAdd || editing != null) {
Column(
Modifier.fillMaxWidth().background(Color.Black.copy(alpha = 0.3f)).padding(8.dp),
verticalArrangement = Arrangement.spacedBy(6.dp),
Modifier
.fillMaxWidth()
.clip(RoundedCornerShape(ROW_R))
.background(FieldBg)
.border(1.dp, RowBorder, RoundedCornerShape(ROW_R))
.padding(12.dp),
verticalArrangement = Arrangement.spacedBy(8.dp),
) {
OutlinedTextField(
value = addr, onValueChange = { addr = it.trim() },
placeholder = { Text("192.168.1.100", color = NES.MenuMuted, fontSize = 11.sp) },
modifier = Modifier.fillMaxWidth().height(48.dp), singleLine = true,
textStyle = androidx.compose.ui.text.TextStyle(color = NES.MenuText, fontSize = 12.sp),
colors = nesFieldColors(),
shape = RoundedCornerShape(2.dp),
Row(
Modifier.fillMaxWidth(),
verticalAlignment = Alignment.CenterVertically,
horizontalArrangement = Arrangement.SpaceBetween,
) {
Text(
if (editing != null) "Edit Server" else "Add Server",
color = TextMuted,
fontSize = 13.sp,
letterSpacing = 1.sp,
fontWeight = FontWeight.Medium,
)
Text(
"Cancel",
color = TextMuted,
fontSize = 13.sp,
modifier = Modifier.clickable { resetForm() }.padding(start = 8.dp),
)
}
GlassField(
value = nm, onValueChange = { nm = it },
placeholder = "Name (optional)",
keyboardOptions = KeyboardOptions(keyboardType = KeyboardType.Text, imeAction = ImeAction.Next),
)
Row(horizontalArrangement = Arrangement.spacedBy(6.dp), verticalAlignment = Alignment.CenterVertically) {
OutlinedTextField(
GlassField(
value = addr, onValueChange = { addr = it.trim() },
placeholder = "192.168.1.100",
keyboardOptions = KeyboardOptions(keyboardType = KeyboardType.Uri, imeAction = ImeAction.Next),
)
Row(horizontalArrangement = Arrangement.spacedBy(8.dp), verticalAlignment = Alignment.CenterVertically) {
GlassField(
value = pwd, onValueChange = { pwd = it },
placeholder = { Text("PASSWORD", color = NES.MenuMuted, fontSize = 11.sp) },
modifier = Modifier.weight(1f).height(48.dp), singleLine = true,
placeholder = "Password",
modifier = Modifier.weight(1f),
visualTransformation = PasswordVisualTransformation(),
keyboardOptions = KeyboardOptions(keyboardType = KeyboardType.Password, imeAction = ImeAction.Go),
keyboardActions = KeyboardActions(onGo = {
if (addr.isNotBlank()) { onAddServer(ServerEntry(addr, false, password = pwd)); addr = ""; pwd = ""; showAdd = false }
}),
textStyle = androidx.compose.ui.text.TextStyle(color = NES.MenuText, fontSize = 12.sp),
colors = nesFieldColors(),
shape = RoundedCornerShape(2.dp),
keyboardActions = KeyboardActions(onGo = { submit() }),
)
Box(
Modifier.size(48.dp).clip(RoundedCornerShape(2.dp)).background(NES.MenuSelected)
.clickable {
if (addr.isNotBlank()) { onAddServer(ServerEntry(addr, false, password = pwd)); addr = ""; pwd = ""; showAdd = false }
},
Modifier.size(FIELD_H).clip(RoundedCornerShape(12.dp)).background(BitcoinOrange.copy(alpha = 0.15f))
.border(1.dp, BitcoinOrange.copy(alpha = 0.4f), RoundedCornerShape(12.dp))
.clickable { submit() },
contentAlignment = Alignment.Center,
) { Text("OK", color = NES.MenuText, fontSize = 10.sp, fontWeight = FontWeight.Bold) }
) { Text("OK", color = BitcoinOrange, fontSize = 14.sp, fontWeight = FontWeight.Bold) }
}
}
} else {
MenuItem(label = " ADD SERVER", onClick = { showAdd = true })
MenuItem(label = "Add Server", labelColor = BitcoinOrange, onClick = { showAdd = true })
}
Spacer(Modifier.height(2.dp))
Box(Modifier.fillMaxWidth().height(1.dp).background(NES.MenuBorder.copy(alpha = 0.3f)))
Box(Modifier.fillMaxWidth().height(1.dp).background(PanelBorder))
Spacer(Modifier.height(2.dp))
// Mode toggle
MenuItem(
label = if (isGamepadMode) " SWITCH TO KEYBOARD" else " SWITCH TO GAMEPAD",
label = if (isGamepadMode) "Switch to Keyboard" else "Switch to Gamepad",
onClick = onToggleMode,
)
// Style toggle
MenuItem(
label = if (controllerStyle == ControllerStyle.CLASSIC) " STYLE: CLASSIC" else " STYLE: DARK",
label = if (controllerStyle == ControllerStyle.CLASSIC) "Style: Classic" else "Style: Dark",
onClick = onToggleStyle,
)
// Back to dashboard
if (onBackToWebView != null) {
MenuItem(label = " BACK TO DASHBOARD", onClick = onBackToWebView)
MenuItem(label = "Back to Dashboard", onClick = onBackToWebView)
}
}
}
@ -187,32 +265,79 @@ private fun MenuPanel(
private fun MenuItem(
label: String,
selected: Boolean = false,
labelColor: Color = TextPrimary,
onClick: () -> Unit,
onEdit: (() -> Unit)? = null,
onRemove: (() -> Unit)? = null,
) {
Row(
Modifier
.fillMaxWidth()
.height(32.dp)
.background(if (selected) NES.MenuSelected.copy(alpha = 0.15f) else Color.Transparent)
.height(ROW_H)
.clip(RoundedCornerShape(ROW_R))
.background(if (selected) BitcoinOrange.copy(alpha = 0.12f) else RowBg)
.border(1.dp, if (selected) BitcoinOrange.copy(alpha = 0.4f) else RowBorder, RoundedCornerShape(ROW_R))
.clickable { onClick() }
.padding(horizontal = 8.dp),
.padding(horizontal = 16.dp),
verticalAlignment = Alignment.CenterVertically,
horizontalArrangement = Arrangement.SpaceBetween,
) {
Text(label, color = if (selected) NES.MenuSelected else NES.MenuText, fontSize = 11.sp, fontWeight = FontWeight.Medium)
Text(
label,
color = if (selected) BitcoinOrange else labelColor,
fontSize = 16.sp,
fontWeight = FontWeight.Medium,
modifier = Modifier.weight(1f),
)
if (onEdit != null) {
Text(
"",
color = TextMuted,
fontSize = 16.sp,
modifier = Modifier.clickable { onEdit() }.padding(horizontal = 8.dp),
)
}
if (onRemove != null) {
Text("\u2715", color = NES.MenuMuted, fontSize = 10.sp,
modifier = Modifier.clickable { onRemove() }.padding(horizontal = 8.dp))
Text(
"",
color = TextMuted,
fontSize = 16.sp,
modifier = Modifier.clickable { onRemove() }.padding(horizontal = 8.dp),
)
}
}
}
/** Glass text field with centered input text. */
@Composable
private fun nesFieldColors() = OutlinedTextFieldDefaults.colors(
focusedBorderColor = NES.MenuBorder,
unfocusedBorderColor = NES.MenuMuted,
cursorColor = NES.MenuText,
focusedTextColor = NES.MenuText,
unfocusedTextColor = NES.MenuText,
)
private fun GlassField(
value: String,
onValueChange: (String) -> Unit,
placeholder: String,
modifier: Modifier = Modifier,
visualTransformation: androidx.compose.ui.text.input.VisualTransformation = androidx.compose.ui.text.input.VisualTransformation.None,
keyboardOptions: KeyboardOptions = KeyboardOptions.Default,
keyboardActions: KeyboardActions = KeyboardActions.Default,
) {
OutlinedTextField(
value = value,
onValueChange = onValueChange,
placeholder = {
Text(placeholder, color = TextMuted, fontSize = 15.sp, modifier = Modifier.fillMaxWidth(), textAlign = TextAlign.Center)
},
modifier = modifier.fillMaxWidth().height(FIELD_H),
singleLine = true,
visualTransformation = visualTransformation,
keyboardOptions = keyboardOptions,
keyboardActions = keyboardActions,
textStyle = TextStyle(color = TextPrimary, fontSize = 16.sp, textAlign = TextAlign.Center),
colors = OutlinedTextFieldDefaults.colors(
focusedBorderColor = Color.White.copy(alpha = 0.3f),
unfocusedBorderColor = Color.White.copy(alpha = 0.12f),
cursorColor = BitcoinOrange,
focusedTextColor = TextPrimary,
unfocusedTextColor = TextPrimary,
),
shape = RoundedCornerShape(12.dp),
)
}

View File

@ -50,7 +50,6 @@ fun NESPortraitController(
Box(
Modifier
.fillMaxSize()
.background(Color(0xFF0C0C0C))
.twoFingerHold(onMenu)
.padding(horizontal = 40.dp, vertical = 24.dp),
contentAlignment = Alignment.Center,
@ -62,7 +61,7 @@ fun NESPortraitController(
.fillMaxSize()
.shadow(28.dp, RoundedCornerShape(20.dp), ambientColor = Color.Black, spotColor = Color.Black)
.clip(RoundedCornerShape(20.dp))
.background(Brush.verticalGradient(listOf(c.body, c.body.copy(alpha = 0.95f))))
.background(Brush.verticalGradient(listOf(c.body, c.body)))
.border(1.dp, Color.White.copy(alpha = if (isClassic) 0.08f else 0.04f), RoundedCornerShape(20.dp)),
) {
// Top highlight
@ -119,11 +118,11 @@ fun NESPortraitController(
Modifier.fillMaxWidth().padding(horizontal = 12.dp, vertical = 8.dp),
horizontalAlignment = Alignment.CenterHorizontally,
) {
ColorBtn(Color(0xFF888888), Color(0xFFAAAAAA), 46.dp) { onKey("c") }
GlassFaceBtn("C", Color(0xFFBBBBBB), 46.dp) { onKey("c") }
Spacer(Modifier.height(6.dp))
Row(horizontalArrangement = Arrangement.spacedBy(14.dp)) {
ColorBtn(Color(0xFF3B82F6), Color(0xFF60A5FA), 46.dp) { onKey("b") }
ColorBtn(Color(0xFFEA580C), Color(0xFFFB923C), 46.dp) { onKey("a") }
GlassFaceBtn("B", Color(0xFF60A5FA), 46.dp) { onKey("b") }
GlassFaceBtn("A", Color(0xFFF7931A), 46.dp) { onKey("a") }
}
}
}

View File

@ -23,6 +23,7 @@ import androidx.compose.foundation.layout.fillMaxWidth
import androidx.compose.foundation.layout.height
import androidx.compose.foundation.layout.padding
import androidx.compose.foundation.layout.safeDrawing
import androidx.compose.foundation.layout.size
import androidx.compose.foundation.layout.windowInsetsPadding
import androidx.compose.foundation.shape.RoundedCornerShape
import androidx.compose.material3.MaterialTheme
@ -41,7 +42,7 @@ import androidx.compose.ui.geometry.Offset
import androidx.compose.ui.geometry.Size
import androidx.compose.ui.graphics.Brush
import androidx.compose.ui.graphics.Color
import androidx.compose.ui.graphics.ColorFilter
import androidx.compose.ui.layout.ContentScale
import androidx.compose.ui.res.painterResource
import androidx.compose.ui.res.stringResource
import androidx.compose.ui.text.style.TextAlign
@ -67,26 +68,45 @@ fun IntroScreen(onContinue: () -> Unit) {
Box(
modifier = Modifier
.fillMaxSize()
.background(SurfaceBlack)
.windowInsetsPadding(WindowInsets.safeDrawing),
contentAlignment = Alignment.Center,
.background(SurfaceBlack),
) {
// Reddish synthwave backdrop
Image(
painter = painterResource(id = R.drawable.bg_synthwave),
contentDescription = null,
modifier = Modifier.fillMaxSize(),
contentScale = ContentScale.Crop,
)
// Dark scrim so the title/buttons stay legible over the art
Box(
modifier = Modifier
.fillMaxSize()
.background(
Brush.verticalGradient(
colors = listOf(
Color.Black.copy(alpha = 0.55f),
Color.Black.copy(alpha = 0.35f),
Color.Black.copy(alpha = 0.75f),
),
)
),
)
Column(
modifier = Modifier
.align(Alignment.Center)
.fillMaxWidth()
.windowInsetsPadding(WindowInsets.safeDrawing)
.padding(horizontal = 32.dp),
horizontalAlignment = Alignment.CenterHorizontally,
verticalArrangement = Arrangement.Center,
) {
// Wide pixel-art logo
// Circular badge logo
Image(
painter = painterResource(id = R.drawable.ic_logo_wide),
painter = painterResource(id = R.drawable.ic_logo),
contentDescription = "Archipelago",
modifier = Modifier
.fillMaxWidth()
.padding(horizontal = 8.dp)
.size(160.dp)
.alpha(logoAlpha.value),
colorFilter = ColorFilter.tint(Color.White),
)
Spacer(modifier = Modifier.height(48.dp))
@ -102,7 +122,7 @@ fun IntroScreen(onContinue: () -> Unit) {
Text(
text = stringResource(R.string.welcome_title),
style = MaterialTheme.typography.headlineLarge,
color = TextPrimary,
color = Color(0xFFFAFAFA),
textAlign = TextAlign.Center,
)
@ -111,7 +131,7 @@ fun IntroScreen(onContinue: () -> Unit) {
Text(
text = stringResource(R.string.welcome_subtitle),
style = MaterialTheme.typography.bodyLarge,
color = TextMuted,
color = Color(0xFFFAFAFA),
textAlign = TextAlign.Center,
lineHeight = 26.sp,
)

View File

@ -2,6 +2,7 @@ package com.archipelago.app.ui.screens
import android.content.res.Configuration
import androidx.activity.compose.BackHandler
import androidx.compose.foundation.Image
import androidx.compose.foundation.background
import androidx.compose.foundation.layout.Box
import androidx.compose.foundation.layout.Column
@ -24,13 +25,17 @@ import androidx.compose.runtime.setValue
import androidx.compose.ui.Alignment
import androidx.compose.ui.Modifier
import androidx.compose.ui.draw.clip
import androidx.compose.ui.graphics.Brush
import androidx.compose.ui.graphics.Color
import androidx.compose.ui.layout.ContentScale
import androidx.compose.ui.platform.LocalConfiguration
import androidx.compose.ui.platform.LocalContext
import androidx.compose.ui.platform.LocalLifecycleOwner
import androidx.lifecycle.Lifecycle
import androidx.lifecycle.LifecycleEventObserver
import androidx.compose.ui.res.painterResource
import androidx.compose.ui.unit.dp
import com.archipelago.app.R
import com.archipelago.app.data.ServerPreferences
import com.archipelago.app.network.ConnectionState
import com.archipelago.app.network.InputWebSocket
@ -58,11 +63,26 @@ fun RemoteInputScreen(onBack: () -> Unit) {
var isGamepadMode by remember { mutableStateOf(true) }
var showModal by remember { mutableStateOf(false) }
var controllerStyle by remember { mutableStateOf(ControllerStyle.CLASSIC) }
var controllerStyle by remember { mutableStateOf(ControllerStyle.DARK) }
var playerId by remember { mutableStateOf(0) } // 0 = broadcast, 1 = P1, 2 = P2
val ws = remember { InputWebSocket(scope) }
// When the kiosk forwards an "open in external browser" app, launch it in
// the phone's default browser.
DisposableEffect(ws) {
ws.onExternalOpen = { url ->
try {
val intent = android.content.Intent(
android.content.Intent.ACTION_VIEW,
android.net.Uri.parse(url),
).apply { addFlags(android.content.Intent.FLAG_ACTIVITY_NEW_TASK) }
context.startActivity(intent)
} catch (_: Exception) {}
}
onDispose { ws.onExternalOpen = null }
}
fun togglePlayer() {
playerId = when (playerId) { 0 -> 1; 1 -> 2; else -> 0 }
ws.playerId = playerId
@ -98,9 +118,31 @@ fun RemoteInputScreen(onBack: () -> Unit) {
Box(
Modifier
.fillMaxSize()
.background(Color(0xFF0C0C0C))
.windowInsetsPadding(WindowInsets.safeDrawing),
.background(Color(0xFF0C0C0C)),
) {
// Reddish synthwave backdrop behind the controller
Image(
painter = painterResource(id = R.drawable.bg_synthwave),
contentDescription = null,
modifier = Modifier.fillMaxSize(),
contentScale = ContentScale.Crop,
)
// Light scrim — the controller body provides its own contrast, so keep
// this subtle and let the backdrop show through around it.
Box(
modifier = Modifier
.fillMaxSize()
.background(
Brush.verticalGradient(
colors = listOf(
Color.Black.copy(alpha = 0.4f),
Color.Black.copy(alpha = 0.25f),
Color.Black.copy(alpha = 0.45f),
),
)
),
)
Box(Modifier.fillMaxSize().windowInsetsPadding(WindowInsets.safeDrawing)) {
when {
isGamepadMode && isLandscape -> NESController(
style = controllerStyle,
@ -159,6 +201,7 @@ fun RemoteInputScreen(onBack: () -> Unit) {
}
),
)
}
NESMenu(
visible = showModal,
@ -173,7 +216,31 @@ fun RemoteInputScreen(onBack: () -> Unit) {
onAddServer = { server ->
scope.launch { prefs.addSavedServer(server); if (activeServer == null) prefs.setActiveServer(server) }
},
onRemoveServer = { server -> scope.launch { prefs.removeSavedServer(server) } },
onEditServer = { original, updated ->
scope.launch {
prefs.updateSavedServer(original, updated)
// If the edited server is the live one, reconnect with the new
// address/credentials so the change takes effect immediately.
if (original.serialize() == activeServer?.serialize()) {
ws.disconnect()
prefs.setActiveServer(updated)
}
}
},
onRemoveServer = { server ->
scope.launch {
prefs.removeSavedServer(server)
// Deleting the last server leaves nothing to control — drop the
// active server and return to the Connect screen.
val remaining = savedServers.count { it.serialize() != server.serialize() }
if (remaining == 0) {
ws.disconnect()
prefs.clearActiveServer()
showModal = false
onBack()
}
}
},
onToggleMode = { isGamepadMode = !isGamepadMode; showModal = false },
onToggleStyle = {
controllerStyle = if (controllerStyle == ControllerStyle.CLASSIC) ControllerStyle.DARK else ControllerStyle.CLASSIC

View File

@ -30,6 +30,7 @@ import androidx.compose.material.icons.filled.VisibilityOff
import androidx.compose.foundation.verticalScroll
import androidx.compose.material.icons.Icons
import androidx.compose.material.icons.filled.Close
import androidx.compose.material.icons.filled.Edit
import androidx.compose.material.icons.filled.Lock
import androidx.compose.material.icons.filled.LockOpen
import androidx.compose.material3.CircularProgressIndicator
@ -55,6 +56,7 @@ import androidx.compose.ui.draw.drawWithContent
import androidx.compose.ui.graphics.Brush
import androidx.compose.ui.graphics.Color
import androidx.compose.ui.graphics.ColorFilter
import androidx.compose.ui.layout.ContentScale
import androidx.compose.ui.platform.LocalContext
import androidx.compose.ui.platform.LocalSoftwareKeyboardController
import androidx.compose.ui.res.painterResource
@ -97,6 +99,7 @@ fun ServerConnectScreen(
val scope = rememberCoroutineScope()
val keyboard = LocalSoftwareKeyboardController.current
var name by remember { mutableStateOf("") }
var address by remember { mutableStateOf("") }
var port by remember { mutableStateOf("") }
var password by remember { mutableStateOf("") }
@ -104,9 +107,50 @@ fun ServerConnectScreen(
var useHttps by remember { mutableStateOf(false) }
var isConnecting by remember { mutableStateOf(false) }
var errorMessage by remember { mutableStateOf<String?>(null) }
// The saved server currently being edited, or null when adding/connecting.
var editingServer by remember { mutableStateOf<ServerEntry?>(null) }
val savedServers by prefs.savedServers.collectAsState(initial = emptyList())
fun clearForm() {
name = ""
address = ""
port = ""
password = ""
useHttps = false
passwordVisible = false
errorMessage = null
}
fun startEdit(server: ServerEntry) {
editingServer = server
name = server.name
address = server.address
port = server.port
password = server.password
useHttps = server.useHttps
passwordVisible = false
errorMessage = null
}
fun cancelEdit() {
editingServer = null
clearForm()
}
fun saveEdit() {
val original = editingServer ?: return
if (address.isBlank()) {
errorMessage = "Enter a server address"
return
}
val updated = ServerEntry(address, useHttps, port, password, name)
scope.launch {
prefs.updateSavedServer(original, updated)
cancelEdit()
}
}
fun connect(server: ServerEntry) {
if (isConnecting) return
if (server.address.isBlank()) {
@ -132,12 +176,33 @@ fun ServerConnectScreen(
Box(
modifier = Modifier
.fillMaxSize()
.background(SurfaceBlack)
.windowInsetsPadding(WindowInsets.safeDrawing),
.background(SurfaceBlack),
) {
// Reddish synthwave backdrop
Image(
painter = painterResource(id = R.drawable.bg_synthwave),
contentDescription = null,
modifier = Modifier.fillMaxSize(),
contentScale = ContentScale.Crop,
)
// Dark scrim so the form stays legible over the art
Box(
modifier = Modifier
.fillMaxSize()
.background(
Brush.verticalGradient(
colors = listOf(
Color.Black.copy(alpha = 0.6f),
Color.Black.copy(alpha = 0.45f),
Color.Black.copy(alpha = 0.8f),
),
)
),
)
Column(
modifier = Modifier
.fillMaxSize()
.windowInsetsPadding(WindowInsets.safeDrawing)
.verticalScroll(state = rememberScrollState())
.drawWithContent { drawContent() }
.padding(horizontal = 24.dp)
@ -145,20 +210,17 @@ fun ServerConnectScreen(
horizontalAlignment = Alignment.CenterHorizontally,
verticalArrangement = Arrangement.spacedBy(16.dp),
) {
// Wide logo
// Circular badge logo
Image(
painter = painterResource(id = R.drawable.ic_logo_wide),
painter = painterResource(id = R.drawable.ic_logo),
contentDescription = "Archipelago",
modifier = Modifier
.fillMaxWidth()
.padding(horizontal = 16.dp),
colorFilter = ColorFilter.tint(Color.White),
modifier = Modifier.size(96.dp),
)
Spacer(modifier = Modifier.height(4.dp))
Text(
text = "Connect to Server",
text = if (editingServer != null) stringResource(R.string.edit_server_title) else "Connect to Server",
style = MaterialTheme.typography.headlineMedium,
color = TextPrimary,
textAlign = TextAlign.Center,
@ -178,6 +240,7 @@ fun ServerConnectScreen(
modifier = Modifier
.fillMaxWidth()
.clip(RoundedCornerShape(16.dp))
.background(Color.Black.copy(alpha = 0.6f))
.background(
Brush.verticalGradient(
colors = listOf(
@ -190,6 +253,34 @@ fun ServerConnectScreen(
.padding(20.dp),
) {
Column {
OutlinedTextField(
value = name,
onValueChange = {
name = it
errorMessage = null
},
label = { Text(stringResource(R.string.server_name_label)) },
placeholder = { Text(stringResource(R.string.server_name_placeholder)) },
modifier = Modifier.fillMaxWidth(),
singleLine = true,
keyboardOptions = KeyboardOptions(
keyboardType = KeyboardType.Text,
imeAction = ImeAction.Next,
),
colors = OutlinedTextFieldDefaults.colors(
focusedBorderColor = Color.White.copy(alpha = 0.3f),
unfocusedBorderColor = Color.White.copy(alpha = 0.12f),
cursorColor = Color.White,
focusedLabelColor = Color.White.copy(alpha = 0.7f),
unfocusedLabelColor = TextMuted,
focusedTextColor = TextPrimary,
unfocusedTextColor = TextPrimary,
),
shape = RoundedCornerShape(12.dp),
)
Spacer(modifier = Modifier.height(12.dp))
OutlinedTextField(
value = address,
onValueChange = {
@ -275,7 +366,11 @@ fun ServerConnectScreen(
keyboardActions = KeyboardActions(
onGo = {
keyboard?.hide()
connect(ServerEntry(address, useHttps, port, password))
if (editingServer != null) {
saveEdit()
} else {
connect(ServerEntry(address, useHttps, port, password, name))
}
},
),
colors = OutlinedTextFieldDefaults.colors(
@ -340,15 +435,40 @@ fun ServerConnectScreen(
}
}
// Connect button — glass style
GlassButton(
text = if (isConnecting) stringResource(R.string.connecting) else stringResource(R.string.connect),
onClick = {
keyboard?.hide()
connect(ServerEntry(address, useHttps, port, password))
},
modifier = Modifier.fillMaxWidth().height(56.dp),
)
if (editingServer != null) {
// Save / Cancel while editing an existing saved server
Row(
modifier = Modifier.fillMaxWidth(),
horizontalArrangement = Arrangement.spacedBy(12.dp),
) {
GlassButton(
text = stringResource(R.string.cancel),
onClick = {
keyboard?.hide()
cancelEdit()
},
modifier = Modifier.weight(1f).height(56.dp),
)
GlassButton(
text = stringResource(R.string.save_changes),
onClick = {
keyboard?.hide()
saveEdit()
},
modifier = Modifier.weight(1f).height(56.dp),
)
}
} else {
// Connect button — glass style
GlassButton(
text = if (isConnecting) stringResource(R.string.connecting) else stringResource(R.string.connect),
onClick = {
keyboard?.hide()
connect(ServerEntry(address, useHttps, port, password, name))
},
modifier = Modifier.fillMaxWidth().height(56.dp),
)
}
if (isConnecting) {
CircularProgressIndicator(
@ -358,8 +478,8 @@ fun ServerConnectScreen(
)
}
// Saved servers
if (savedServers.isNotEmpty()) {
// Saved servers (hidden while editing one to keep focus on the form)
if (editingServer == null && savedServers.isNotEmpty()) {
Spacer(modifier = Modifier.height(8.dp))
Text(
text = stringResource(R.string.saved_servers),
@ -373,6 +493,7 @@ fun ServerConnectScreen(
SavedServerItem(
server = server,
onConnect = { connect(it) },
onEdit = { startEdit(it) },
onRemove = { scope.launch { prefs.removeSavedServer(it) } },
)
}
@ -385,12 +506,14 @@ fun ServerConnectScreen(
private fun SavedServerItem(
server: ServerEntry,
onConnect: (ServerEntry) -> Unit,
onEdit: (ServerEntry) -> Unit,
onRemove: (ServerEntry) -> Unit,
) {
Row(
modifier = Modifier
.fillMaxWidth()
.clip(RoundedCornerShape(12.dp))
.background(Color.Black.copy(alpha = 0.6f))
.background(
Brush.verticalGradient(
colors = listOf(
@ -414,12 +537,21 @@ private fun SavedServerItem(
)
Spacer(modifier = Modifier.width(12.dp))
Column {
Text(text = server.address, style = MaterialTheme.typography.bodyMedium, color = TextPrimary, maxLines = 1, overflow = TextOverflow.Ellipsis)
if (server.port.isNotBlank()) {
Text(text = "Port ${server.port}", style = MaterialTheme.typography.labelMedium, color = TextMuted)
Text(text = server.displayName(), style = MaterialTheme.typography.bodyMedium, color = TextPrimary, maxLines = 1, overflow = TextOverflow.Ellipsis)
val secondary = buildString {
if (server.name.isNotBlank()) append(server.address)
if (server.port.isNotBlank()) {
if (isNotEmpty()) append(":${server.port}") else append("Port ${server.port}")
}
}
if (secondary.isNotBlank()) {
Text(text = secondary, style = MaterialTheme.typography.labelMedium, color = TextMuted, maxLines = 1, overflow = TextOverflow.Ellipsis)
}
}
}
IconButton(onClick = { onEdit(server) }) {
Icon(imageVector = Icons.Default.Edit, contentDescription = stringResource(R.string.edit_server), modifier = Modifier.size(18.dp), tint = TextMuted)
}
IconButton(onClick = { onRemove(server) }) {
Icon(imageVector = Icons.Default.Close, contentDescription = stringResource(R.string.remove_server), modifier = Modifier.size(18.dp), tint = TextMuted)
}

View File

@ -2,6 +2,7 @@ package com.archipelago.app.ui.screens
import android.annotation.SuppressLint
import android.graphics.Bitmap
import android.graphics.BitmapFactory
import android.view.ViewGroup
import android.webkit.CookieManager
import android.webkit.WebChromeClient
@ -14,10 +15,12 @@ import androidx.activity.compose.BackHandler
import androidx.compose.animation.AnimatedVisibility
import androidx.compose.animation.fadeIn
import androidx.compose.animation.fadeOut
import androidx.compose.foundation.Image
import androidx.compose.foundation.background
import androidx.compose.foundation.layout.Arrangement
import androidx.compose.foundation.layout.Box
import androidx.compose.foundation.layout.Column
import androidx.compose.foundation.layout.Row
import androidx.compose.foundation.layout.Spacer
import androidx.compose.foundation.layout.WindowInsets
import androidx.compose.foundation.layout.fillMaxSize
@ -26,14 +29,24 @@ import androidx.compose.foundation.layout.height
import androidx.compose.foundation.layout.padding
import androidx.compose.foundation.layout.safeDrawing
import androidx.compose.foundation.layout.size
import androidx.compose.foundation.layout.width
import androidx.compose.foundation.layout.windowInsetsPadding
import androidx.compose.foundation.shape.RoundedCornerShape
import androidx.compose.material.icons.Icons
import androidx.compose.material.icons.automirrored.filled.ArrowBack
import androidx.compose.material.icons.automirrored.filled.ArrowForward
import androidx.compose.material.icons.filled.Close
import androidx.compose.material.icons.filled.CloudOff
import androidx.compose.material.icons.filled.OpenInBrowser
import androidx.compose.material.icons.filled.Refresh
import androidx.compose.material3.CircularProgressIndicator
import androidx.compose.material3.Icon
import androidx.compose.material3.IconButton
import androidx.compose.material3.LinearProgressIndicator
import androidx.compose.material3.MaterialTheme
import androidx.compose.material3.Text
import androidx.compose.runtime.Composable
import androidx.compose.runtime.LaunchedEffect
import androidx.compose.runtime.getValue
import androidx.compose.runtime.mutableIntStateOf
import androidx.compose.runtime.mutableStateOf
@ -41,8 +54,12 @@ import androidx.compose.runtime.remember
import androidx.compose.runtime.setValue
import androidx.compose.ui.Alignment
import androidx.compose.ui.Modifier
import androidx.compose.ui.draw.clip
import androidx.compose.ui.graphics.asImageBitmap
import androidx.compose.ui.platform.LocalContext
import androidx.compose.ui.res.stringResource
import androidx.compose.ui.text.style.TextAlign
import androidx.compose.ui.text.style.TextOverflow
import androidx.compose.ui.unit.dp
import androidx.compose.ui.viewinterop.AndroidView
import com.archipelago.app.R
@ -50,8 +67,70 @@ import com.archipelago.app.ui.theme.BitcoinOrange
import com.archipelago.app.ui.theme.SurfaceBlack
import com.archipelago.app.ui.theme.TextMuted
import com.archipelago.app.ui.theme.TextPrimary
import kotlinx.coroutines.Dispatchers
import kotlinx.coroutines.withContext
/** Open a URL in the phone's default browser (genuinely external links). */
private fun openExternalUrl(context: android.content.Context, url: String) {
try {
val intent = android.content.Intent(
android.content.Intent.ACTION_VIEW,
android.net.Uri.parse(url),
).apply {
// Required when launching from a non-Activity/binder thread
// (the JS bridge below can run off the UI thread).
addFlags(android.content.Intent.FLAG_ACTIVITY_NEW_TASK)
}
context.startActivity(intent)
} catch (_: Exception) {}
}
/** True when [url] points at the same host as the connected Archipelago node
* (ignoring port). Such URLs are node apps e.g. one that can't be iframed
* and should stay inside the app rather than bouncing out to the browser. */
private fun isSameHost(url: String, base: String): Boolean {
return try {
val a = android.net.Uri.parse(url).host ?: return false
val b = android.net.Uri.parse(base).host ?: return false
a.equals(b, ignoreCase = true)
} catch (_: Exception) {
false
}
}
/** Apply the WebView settings shared by the kiosk view and the in-app browser.
* These are tuned for SPA performance and parity with the mobile browser;
* none of them alter how a page renders visually. */
@SuppressLint("SetJavaScriptEnabled")
private fun WebView.applyArchipelagoSettings() {
// Pre-rasterize just outside the viewport so flinging the kiosk/app doesn't
// show blank checkerboarding — the single biggest scroll-smoothness win and
// a major part of the "feels slower than the browser" gap. (API 23+)
settings.setOffscreenPreRaster(true)
settings.apply {
javaScriptEnabled = true
domStorageEnabled = true
databaseEnabled = true
mediaPlaybackRequiresUserGesture = false
mixedContentMode = WebSettings.MIXED_CONTENT_COMPATIBILITY_MODE
useWideViewPort = true
loadWithOverviewMode = true
setSupportZoom(false)
builtInZoomControls = false
cacheMode = WebSettings.LOAD_DEFAULT
allowContentAccess = true
allowFileAccess = false
}
// chrome://inspect profiling on debuggable builds only — lets us measure the
// real in-page bottleneck rather than guess. No effect on release builds.
val debuggable = 0 != (context.applicationInfo.flags and
android.content.pm.ApplicationInfo.FLAG_DEBUGGABLE)
if (debuggable) WebView.setWebContentsDebuggingEnabled(true)
}
@SuppressLint("SetJavaScriptEnabled", "ClickableViewAccessibility")
@Composable
fun WebViewScreen(
serverUrl: String,
@ -63,7 +142,12 @@ fun WebViewScreen(
var hasError by remember { mutableStateOf(false) }
var webView by remember { mutableStateOf<WebView?>(null) }
BackHandler(enabled = webView?.canGoBack() == true) {
// A node app that refused iframing, opened in a local WebView overlay.
// null = no overlay. The kiosk WebView underneath stays alive (and warm)
// while this is shown, so closing it returns instantly with no reload.
var inAppUrl by remember { mutableStateOf<String?>(null) }
BackHandler(enabled = inAppUrl == null && webView?.canGoBack() == true) {
webView?.goBack()
}
@ -132,16 +216,6 @@ fun WebViewScreen(
AndroidView(
modifier = Modifier.fillMaxSize(),
factory = { context ->
fun openExternalUrl(url: String) {
try {
val intent = android.content.Intent(
android.content.Intent.ACTION_VIEW,
android.net.Uri.parse(url),
)
context.startActivity(intent)
} catch (_: Exception) {}
}
WebView(context).apply {
layoutParams = ViewGroup.LayoutParams(
ViewGroup.LayoutParams.MATCH_PARENT,
@ -155,22 +229,49 @@ fun WebViewScreen(
cookieManager.setAcceptCookie(true)
cookieManager.setAcceptThirdPartyCookies(this, true)
applyArchipelagoSettings()
settings.apply {
javaScriptEnabled = true
domStorageEnabled = true
databaseEnabled = true
mediaPlaybackRequiresUserGesture = false
mixedContentMode = WebSettings.MIXED_CONTENT_COMPATIBILITY_MODE
useWideViewPort = true
loadWithOverviewMode = true
setSupportZoom(false)
builtInZoomControls = false
cacheMode = WebSettings.LOAD_DEFAULT
allowContentAccess = true
allowFileAccess = false
setSupportMultipleWindows(true) // enables onCreateWindow for window.open
// Let JS open windows without a synchronous user-gesture
// chain; without this, window.open() from a Vue click
// handler silently no-ops and "Open in new tab" dies.
javaScriptCanOpenWindowsAutomatically = true
}
val webViewRef = this
// Decide where an outbound URL goes:
// - same host as the node → in-app WebView overlay
// (this is the "open in browser" target for apps the
// kiosk couldn't iframe — keep the user inside the app)
// - different host → the phone's real browser
fun routeOutbound(url: String) {
if (isSameHost(url, serverUrl)) {
inAppUrl = url
} else {
openExternalUrl(context, url)
}
}
// JS bridge. The web UI calls:
// window.ArchipelagoNative.openExternal(url) — host-routed
// window.ArchipelagoNative.openInApp(url) — force in-app
// Falls back to window.open in a plain mobile browser.
addJavascriptInterface(
object {
@android.webkit.JavascriptInterface
fun openExternal(url: String) {
webViewRef.post { routeOutbound(url) }
}
@android.webkit.JavascriptInterface
fun openInApp(url: String) {
webViewRef.post { inAppUrl = url }
}
},
"ArchipelagoNative",
)
webViewClient = object : WebViewClient() {
override fun onPageStarted(view: WebView?, url: String?, favicon: Bitmap?) {
isLoading = true
@ -222,15 +323,35 @@ fun WebViewScreen(
}
}
// Node apps (e.g. NetBird) terminate TLS with a
// self-signed cert — the dashboard needs a secure
// context for OIDC/window.crypto.subtle (#15). The
// WebView default is to CANCEL untrusted certs, so
// those apps render blank. The user explicitly trusts
// their own node, so proceed for same-host certs only;
// reject anything else (don't blanket-trust the web).
override fun onReceivedSslError(
view: WebView?,
handler: android.webkit.SslErrorHandler?,
error: android.net.http.SslError?,
) {
val u = error?.url
if (u != null && isSameHost(u, serverUrl)) {
handler?.proceed()
} else {
handler?.cancel()
}
}
override fun shouldOverrideUrlLoading(
view: WebView?,
request: WebResourceRequest?,
): Boolean {
val url = request?.url?.toString() ?: return false
// Keep navigation within the Archipelago server
// Keep kiosk navigation (same origin incl. port) in place
if (url.startsWith(serverUrl)) return false
// Open external URLs in the system browser
openExternalUrl(url)
// Same node (other port) → in-app; external → browser
routeOutbound(url)
return true
}
}
@ -240,7 +361,9 @@ fun WebViewScreen(
loadProgress = newProgress
}
// Handle window.open() — open in system browser
// window.open() — e.g. the kiosk's "Open in new tab"
// for an app that can't be iframed. Capture the target
// URL via a throwaway WebView and route it ourselves.
override fun onCreateWindow(
view: WebView?,
isDialog: Boolean,
@ -258,12 +381,12 @@ fun WebViewScreen(
request: WebResourceRequest?,
): Boolean {
val url = request?.url?.toString() ?: return true
openExternalUrl(url)
routeOutbound(url)
return true
}
override fun onPageStarted(view: WebView?, url: String?, favicon: Bitmap?) {
if (url != null) openExternalUrl(url)
if (url != null) routeOutbound(url)
view?.stopLoading()
}
}
@ -325,6 +448,255 @@ fun WebViewScreen(
)
}
// In-app browser overlay for non-iframeable node apps. Rendered last
// so it sits above the kiosk WebView, which stays alive underneath.
inAppUrl?.let { target ->
InAppBrowser(
url = target,
serverUrl = serverUrl,
onClose = { inAppUrl = null },
)
}
}
}
}
/** Best-effort fetch of the origin's /favicon.ico, so the launched app's icon
* can be shown on the loading screen before the WebView reports onReceivedIcon
* (which only fires once the page's <head> has parsed). Blocking call on IO. */
private fun fetchFavicon(pageUrl: String): Bitmap? {
return try {
val u = android.net.Uri.parse(pageUrl)
val scheme = u.scheme ?: return null
val host = u.host ?: return null
val portPart = if (u.port > 0) ":${u.port}" else ""
val conn = (java.net.URL("$scheme://$host$portPart/favicon.ico").openConnection()
as java.net.HttpURLConnection).apply {
connectTimeout = 4000
readTimeout = 4000
instanceFollowRedirects = true
}
conn.inputStream.use { BitmapFactory.decodeStream(it) }
} catch (_: Exception) {
null
}
}
/**
* Lightweight in-app browser used when the kiosk hands off an app that can't be
* shown in an iframe. Loads the app in a local WebView with a centered loading
* screen (app favicon + progress bar) and a BOTTOM control bar mirroring the
* web mobile-iframe footer (back / forward / reload / open-in-browser / close).
* Same-host navigation stays here; any genuinely external link escapes to the
* phone's browser.
*/
@SuppressLint("SetJavaScriptEnabled")
@Composable
private fun InAppBrowser(
url: String,
serverUrl: String,
onClose: () -> Unit,
) {
val context = LocalContext.current
var browser by remember { mutableStateOf<WebView?>(null) }
var title by remember { mutableStateOf(android.net.Uri.parse(url).host ?: url) }
var favicon by remember { mutableStateOf<Bitmap?>(null) }
var progress by remember { mutableIntStateOf(0) }
var loading by remember { mutableStateOf(true) }
var canGoBack by remember { mutableStateOf(false) }
var canGoForward by remember { mutableStateOf(false) }
// Seed the loading-screen icon immediately from a best-effort favicon
// pre-fetch (main's app-icon work), then onReceivedIcon upgrades it — so the
// loader shows an icon right away instead of staying blank until the page
// parses its <head> (which is what made the loader look stuck).
LaunchedEffect(url) {
val fetched = withContext(Dispatchers.IO) { fetchFavicon(url) }
if (fetched != null && favicon == null) favicon = fetched
}
// Back: walk the in-app history first, then close the overlay.
BackHandler {
val b = browser
if (b != null && b.canGoBack()) b.goBack() else onClose()
}
Column(
modifier = Modifier
.fillMaxSize()
.background(SurfaceBlack)
.windowInsetsPadding(WindowInsets.safeDrawing),
) {
// WebView + loading overlay fill the area above the bottom control bar.
Box(modifier = Modifier.weight(1f).fillMaxWidth()) {
AndroidView(
modifier = Modifier.fillMaxSize(),
factory = { ctx ->
WebView(ctx).apply {
layoutParams = ViewGroup.LayoutParams(
ViewGroup.LayoutParams.MATCH_PARENT,
ViewGroup.LayoutParams.MATCH_PARENT,
)
isVerticalScrollBarEnabled = false
isHorizontalScrollBarEnabled = false
CookieManager.getInstance().setAcceptThirdPartyCookies(this, true)
applyArchipelagoSettings()
webChromeClient = object : WebChromeClient() {
override fun onProgressChanged(view: WebView?, newProgress: Int) {
progress = newProgress
}
override fun onReceivedTitle(view: WebView?, t: String?) {
if (!t.isNullOrBlank()) title = t
}
override fun onReceivedIcon(view: WebView?, icon: Bitmap?) {
if (icon != null) favicon = icon
}
}
webViewClient = object : WebViewClient() {
override fun onPageStarted(view: WebView?, u: String?, favicon: Bitmap?) {
loading = true
}
override fun onPageFinished(view: WebView?, u: String?) {
loading = false
canGoBack = view?.canGoBack() == true
canGoForward = view?.canGoForward() == true
}
override fun doUpdateVisitedHistory(view: WebView?, u: String?, isReload: Boolean) {
canGoBack = view?.canGoBack() == true
canGoForward = view?.canGoForward() == true
}
// Self-signed TLS on the node's apps (e.g. NetBird on
// :8087) would otherwise be cancelled by the WebView
// and render blank. Proceed for the user's own node
// (same host); reject any other untrusted cert.
override fun onReceivedSslError(
view: WebView?,
handler: android.webkit.SslErrorHandler?,
error: android.net.http.SslError?,
) {
val u = error?.url
if (u != null && isSameHost(u, serverUrl)) {
handler?.proceed()
} else {
handler?.cancel()
}
}
override fun shouldOverrideUrlLoading(
view: WebView?,
request: WebResourceRequest?,
): Boolean {
val u = request?.url?.toString() ?: return false
// Stay in the overlay for same-node navigation;
// hand genuinely external links to the real browser.
if (isSameHost(u, serverUrl)) return false
openExternalUrl(ctx, u)
return true
}
}
browser = this
loadUrl(url)
}
},
)
// Centered loading screen — app favicon (or spinner) + title + bar.
if (loading) {
Column(
modifier = Modifier
.fillMaxSize()
.background(SurfaceBlack),
horizontalAlignment = Alignment.CenterHorizontally,
verticalArrangement = Arrangement.Center,
) {
Box(
modifier = Modifier.size(84.dp).clip(RoundedCornerShape(20.dp)),
contentAlignment = Alignment.Center,
) {
val fav = favicon
if (fav != null) {
Image(
bitmap = fav.asImageBitmap(),
contentDescription = title,
modifier = Modifier.fillMaxSize(),
)
} else {
CircularProgressIndicator(color = BitcoinOrange)
}
}
Spacer(modifier = Modifier.height(18.dp))
Text(
text = title,
style = MaterialTheme.typography.bodyLarge,
color = TextPrimary,
maxLines = 1,
overflow = TextOverflow.Ellipsis,
)
Spacer(modifier = Modifier.height(16.dp))
LinearProgressIndicator(
progress = { progress / 100f },
modifier = Modifier.width(220.dp),
color = BitcoinOrange,
trackColor = TextMuted.copy(alpha = 0.2f),
)
}
}
}
// Bottom control bar — mirrors the web mobile-iframe footer.
Row(
modifier = Modifier
.fillMaxWidth()
.height(56.dp)
.background(SurfaceBlack)
.padding(horizontal = 8.dp),
horizontalArrangement = Arrangement.SpaceAround,
verticalAlignment = Alignment.CenterVertically,
) {
IconButton(onClick = { browser?.goBack() }, enabled = canGoBack) {
Icon(
imageVector = Icons.AutoMirrored.Filled.ArrowBack,
contentDescription = "Back",
tint = if (canGoBack) TextPrimary else TextMuted.copy(alpha = 0.4f),
)
}
IconButton(onClick = { browser?.goForward() }, enabled = canGoForward) {
Icon(
imageVector = Icons.AutoMirrored.Filled.ArrowForward,
contentDescription = "Forward",
tint = if (canGoForward) TextPrimary else TextMuted.copy(alpha = 0.4f),
)
}
IconButton(onClick = { browser?.reload() }) {
Icon(
imageVector = Icons.Default.Refresh,
contentDescription = "Reload",
tint = TextPrimary,
)
}
IconButton(onClick = { openExternalUrl(context, browser?.url ?: url) }) {
Icon(
imageVector = Icons.Default.OpenInBrowser,
contentDescription = stringResource(R.string.open_in_browser),
tint = TextPrimary,
)
}
IconButton(onClick = onClose) {
Icon(
imageVector = Icons.Default.Close,
contentDescription = stringResource(R.string.close),
tint = TextPrimary,
)
}
}
}
}

Binary file not shown.

After

Width:  |  Height:  |  Size: 869 KiB

View File

@ -1,10 +1,53 @@
<?xml version="1.0" encoding="utf-8"?>
<!-- Whole badge lives here (background renders to the mask edge with no
safe-zone cropping, unlike the foreground): dark fill + metallic ring pulled
inward to ~0.88 so the mask can't clip it + grid at ~0.58. Matches the
locally-rendered preview. Foreground is transparent. -->
<vector xmlns:android="http://schemas.android.com/apk/res/android"
xmlns:aapt="http://schemas.android.com/aapt"
android:width="108dp"
android:height="108dp"
android:viewportWidth="108"
android:viewportHeight="108">
android:viewportWidth="752"
android:viewportHeight="752">
<path
android:fillColor="#030202"
android:pathData="M0,0h108v108H0z" />
android:fillColor="#0A0A0A"
android:pathData="M0,0h752v752H0z" />
<!-- Ring matching logo.svg's gradient (#000->#666). Scale 0.65 places it at
the home-screen's visible edge (calibrated from a device home screenshot;
launcher3 crops less than the Settings App-info view). -->
<group
android:pivotX="376"
android:pivotY="376"
android:scaleX="0.65"
android:scaleY="0.65">
<path
android:fillColor="#00000000"
android:strokeWidth="22.8834"
android:pathData="M11.441,375.669a364.227,364.227 0 1,0 728.454,0a364.227,364.227 0 1,0 -728.454,0z">
<aapt:attr name="android:strokeColor">
<gradient
android:type="linear"
android:startX="751.337"
android:startY="751.338"
android:endX="0"
android:endY="0.000976562">
<item android:offset="0" android:color="#FF000000" />
<item android:offset="1" android:color="#FF666666" />
</gradient>
</aapt:attr>
</path>
</group>
<!-- White Archipelago grid -->
<group
android:pivotX="376"
android:pivotY="376"
android:scaleX="0.55"
android:scaleY="0.55">
<path
android:fillColor="#FFFFFF"
android:pathData="M253.805,278.37V222.28H309.853V278.37H253.805ZM315.797,278.37V222.28H372.694V278.37H315.797ZM378.639,278.37V222.28H435.536V278.37H378.639ZM441.481,278.37V222.28H497.529V278.37H441.481ZM441.481,341.259V284.319H497.529V341.259H441.481ZM503.473,341.259V284.319H560.37V341.259H503.473ZM190.963,404.148V347.208H247.86V404.148H190.963ZM253.805,404.148V347.208H309.853V404.148H253.805ZM315.797,404.148V347.208H372.694V404.148H315.797ZM378.639,404.148V347.208H435.536V404.148H378.639ZM441.481,404.148V347.208H497.529V404.148H441.481ZM503.473,404.148V347.208H560.37V404.148H503.473ZM190.963,466.187V410.097H247.86V466.187H190.963ZM253.805,466.187V410.097H309.853V466.187H253.805ZM441.481,466.187V410.097H497.529V466.187H441.481ZM503.473,466.187V410.097H560.37V466.187H503.473ZM253.805,529.076V472.136H309.853V529.076H253.805ZM315.797,529.076V472.136H372.694V529.076H315.797ZM378.639,529.076V472.136H435.536V529.076H378.639ZM441.481,529.076V472.136H497.529V529.076H441.481Z" />
</group>
</vector>

View File

@ -1,45 +1,12 @@
<?xml version="1.0" encoding="utf-8"?>
<!-- Archipelago pixel-art "A" logo — scaled 90% and centered -->
<!-- Transparent — the whole badge (ring + grid) is in the background layer so it
renders to the mask edge without safe-zone cropping. -->
<vector xmlns:android="http://schemas.android.com/apk/res/android"
android:width="108dp"
android:height="108dp"
android:viewportWidth="1024"
android:viewportHeight="1024">
<group
android:pivotX="512"
android:pivotY="512"
android:scaleX="0.55"
android:scaleY="0.55">
<!-- Row 1: 4 blocks -->
<path android:fillColor="#FFFFFF" android:pathData="M357.614,318h71.007v70.936h-71.007z" />
<path android:fillColor="#FFFFFF" android:pathData="M436.152,318h72.082v70.936h-72.082z" />
<path android:fillColor="#FFFFFF" android:pathData="M515.766,318h72.082v70.936h-72.082z" />
<path android:fillColor="#FFFFFF" android:pathData="M595.379,318h71.007v70.936h-71.007z" />
<!-- Row 2: 2 blocks (right side) -->
<path android:fillColor="#FFFFFF" android:pathData="M595.379,396.46h71.007v72.011h-71.007z" />
<path android:fillColor="#FFFFFF" android:pathData="M673.917,396.46h72.083v72.011h-72.083z" />
<!-- Row 3: 6 blocks (full width) -->
<path android:fillColor="#FFFFFF" android:pathData="M278,475.994h72.083v72.012h-72.083z" />
<path android:fillColor="#FFFFFF" android:pathData="M357.614,475.994h71.007v72.012h-71.007z" />
<path android:fillColor="#FFFFFF" android:pathData="M436.152,475.994h72.082v72.012h-72.082z" />
<path android:fillColor="#FFFFFF" android:pathData="M515.766,475.994h72.082v72.012h-72.082z" />
<path android:fillColor="#FFFFFF" android:pathData="M595.379,475.994h71.007v72.012h-71.007z" />
<path android:fillColor="#FFFFFF" android:pathData="M673.917,475.994h72.083v72.012h-72.083z" />
<!-- Row 4: 4 blocks (sides only — the "A" gap) -->
<path android:fillColor="#FFFFFF" android:pathData="M278,555.529h72.083v70.936h-72.083z" />
<path android:fillColor="#FFFFFF" android:pathData="M357.614,555.529h71.007v70.936h-71.007z" />
<path android:fillColor="#FFFFFF" android:pathData="M595.379,555.529h71.007v70.936h-71.007z" />
<path android:fillColor="#FFFFFF" android:pathData="M673.917,555.529h72.083v70.936h-72.083z" />
<!-- Row 5: 4 blocks (bottom) -->
<path android:fillColor="#FFFFFF" android:pathData="M357.614,633.989h71.007v72.011h-71.007z" />
<path android:fillColor="#FFFFFF" android:pathData="M436.152,633.989h72.082v72.011h-72.082z" />
<path android:fillColor="#FFFFFF" android:pathData="M515.766,633.989h72.082v72.011h-72.082z" />
<path android:fillColor="#FFFFFF" android:pathData="M595.379,633.989h71.007v72.011h-71.007z" />
</group>
android:viewportWidth="108"
android:viewportHeight="108">
<path
android:fillColor="#00000000"
android:pathData="M0,0h108v108H0z" />
</vector>

View File

@ -0,0 +1,33 @@
<?xml version="1.0" encoding="utf-8"?>
<!-- Archipelago circular badge logo (from logo.svg):
dark circle with a black→grey gradient ring + white pixel-grid mark. -->
<vector xmlns:android="http://schemas.android.com/apk/res/android"
xmlns:aapt="http://schemas.android.com/aapt"
android:width="120dp"
android:height="120dp"
android:viewportWidth="752"
android:viewportHeight="752">
<!-- Ringed circle (circle converted to a path; stroke carries the gradient) -->
<path
android:fillColor="#0A0A0A"
android:strokeWidth="22.8834"
android:pathData="M11.441,375.669a364.227,364.227 0 1,0 728.454,0a364.227,364.227 0 1,0 -728.454,0z">
<aapt:attr name="android:strokeColor">
<gradient
android:type="linear"
android:startX="751.337"
android:startY="751.338"
android:endX="0"
android:endY="0">
<item android:offset="0" android:color="#FF000000" />
<item android:offset="1" android:color="#FF666666" />
</gradient>
</aapt:attr>
</path>
<!-- White Archipelago pixel grid -->
<path
android:fillColor="#FFFFFF"
android:pathData="M253.805,278.37V222.28H309.853V278.37H253.805ZM315.797,278.37V222.28H372.694V278.37H315.797ZM378.639,278.37V222.28H435.536V278.37H378.639ZM441.481,278.37V222.28H497.529V278.37H441.481ZM441.481,341.259V284.319H497.529V341.259H441.481ZM503.473,341.259V284.319H560.37V341.259H503.473ZM190.963,404.148V347.208H247.86V404.148H190.963ZM253.805,404.148V347.208H309.853V404.148H253.805ZM315.797,404.148V347.208H372.694V404.148H315.797ZM378.639,404.148V347.208H435.536V404.148H378.639ZM441.481,404.148V347.208H497.529V404.148H441.481ZM503.473,404.148V347.208H560.37V404.148H503.473ZM190.963,466.187V410.097H247.86V466.187H190.963ZM253.805,466.187V410.097H309.853V466.187H253.805ZM441.481,466.187V410.097H497.529V466.187H441.481ZM503.473,466.187V410.097H560.37V466.187H503.473ZM253.805,529.076V472.136H309.853V529.076H253.805ZM315.797,529.076V472.136H372.694V529.076H315.797ZM378.639,529.076V472.136H435.536V529.076H378.639ZM441.481,529.076V472.136H497.529V529.076H441.481Z" />
</vector>

View File

@ -0,0 +1,12 @@
<vector xmlns:android="http://schemas.android.com/apk/res/android"
android:width="24dp"
android:height="24dp"
android:viewportWidth="24"
android:viewportHeight="24">
<path
android:pathData="M15,19l-7,-7 7,-7"
android:strokeColor="#FFFFFF"
android:strokeWidth="2"
android:strokeLineCap="round"
android:strokeLineJoin="round" />
</vector>

View File

@ -0,0 +1,12 @@
<vector xmlns:android="http://schemas.android.com/apk/res/android"
android:width="24dp"
android:height="24dp"
android:viewportWidth="24"
android:viewportHeight="24">
<path
android:pathData="M6,18L18,6M6,6l12,12"
android:strokeColor="#FFFFFF"
android:strokeWidth="2"
android:strokeLineCap="round"
android:strokeLineJoin="round" />
</vector>

View File

@ -0,0 +1,12 @@
<vector xmlns:android="http://schemas.android.com/apk/res/android"
android:width="24dp"
android:height="24dp"
android:viewportWidth="24"
android:viewportHeight="24">
<path
android:pathData="M9,5l7,7 -7,7"
android:strokeColor="#FFFFFF"
android:strokeWidth="2"
android:strokeLineCap="round"
android:strokeLineJoin="round" />
</vector>

View File

@ -0,0 +1,12 @@
<vector xmlns:android="http://schemas.android.com/apk/res/android"
android:width="24dp"
android:height="24dp"
android:viewportWidth="24"
android:viewportHeight="24">
<path
android:pathData="M10,6H6a2,2 0,0 0,-2 2v10a2,2 0,0 0,2 2h10a2,2 0,0 0,2 -2v-4M14,4h6m0,0v6m0,-6L10,14"
android:strokeColor="#FFFFFF"
android:strokeWidth="2"
android:strokeLineCap="round"
android:strokeLineJoin="round" />
</vector>

View File

@ -0,0 +1,12 @@
<vector xmlns:android="http://schemas.android.com/apk/res/android"
android:width="24dp"
android:height="24dp"
android:viewportWidth="24"
android:viewportHeight="24">
<path
android:pathData="M4,4v6h6M20,20v-6h-6M5.64,15.36A8,8 0,0 0,18.36 18M18.36,8.64A8,8 0,0 0,5.64 6"
android:strokeColor="#FFFFFF"
android:strokeWidth="2"
android:strokeLineCap="round"
android:strokeLineJoin="round" />
</vector>

View File

@ -21,4 +21,15 @@
<string name="retry">Retry</string>
<string name="remote_input">Remote Control</string>
<string name="remote_input_hint">Use your phone as a keyboard and mouse for the kiosk</string>
<string name="close">Close</string>
<string name="open_in_browser">Open in browser</string>
<string name="back">Back</string>
<string name="forward">Forward</string>
<string name="refresh">Refresh</string>
<string name="server_name_label">Server Name (optional)</string>
<string name="server_name_placeholder">My Archipelago</string>
<string name="edit_server">Edit</string>
<string name="edit_server_title">Edit Server</string>
<string name="save_changes">Save Changes</string>
<string name="cancel">Cancel</string>
</resources>

10
Android/logo.svg Normal file
View File

@ -0,0 +1,10 @@
<svg width="752" height="752" viewBox="0 0 752 752" fill="none" xmlns="http://www.w3.org/2000/svg">
<circle cx="375.668" cy="375.669" r="364.227" fill="#0A0A0A" stroke="url(#paint0_linear_877_1990)" stroke-width="22.8834"/>
<path d="M253.805 278.37V222.28H309.853V278.37H253.805ZM315.797 278.37V222.28H372.694V278.37H315.797ZM378.639 278.37V222.28H435.536V278.37H378.639ZM441.481 278.37V222.28H497.529V278.37H441.481ZM441.481 341.259V284.319H497.529V341.259H441.481ZM503.473 341.259V284.319H560.37V341.259H503.473ZM190.963 404.148V347.208H247.86V404.148H190.963ZM253.805 404.148V347.208H309.853V404.148H253.805ZM315.797 404.148V347.208H372.694V404.148H315.797ZM378.639 404.148V347.208H435.536V404.148H378.639ZM441.481 404.148V347.208H497.529V404.148H441.481ZM503.473 404.148V347.208H560.37V404.148H503.473ZM190.963 466.187V410.097H247.86V466.187H190.963ZM253.805 466.187V410.097H309.853V466.187H253.805ZM441.481 466.187V410.097H497.529V466.187H441.481ZM503.473 466.187V410.097H560.37V466.187H503.473ZM253.805 529.076V472.136H309.853V529.076H253.805ZM315.797 529.076V472.136H372.694V529.076H315.797ZM378.639 529.076V472.136H435.536V529.076H378.639ZM441.481 529.076V472.136H497.529V529.076H441.481Z" fill="white"/>
<defs>
<linearGradient id="paint0_linear_877_1990" x1="751.337" y1="751.338" x2="0" y2="0.000976562" gradientUnits="userSpaceOnUse">
<stop/>
<stop offset="1" stop-color="#666666"/>
</linearGradient>
</defs>
</svg>

After

Width:  |  Height:  |  Size: 1.4 KiB

41
Android/ship-companion.sh Executable file
View File

@ -0,0 +1,41 @@
#!/usr/bin/env bash
#
# Build the Android companion app and publish it as the served download
# (neode-ui/public/packages/archipelago-companion.apk — a plain APK a phone can
# install straight from the link), then commit + push.
#
# Use this INSTEAD of `git push` when shipping the companion app, so the
# downloadable APK on the node always matches what's on main.
#
# ./Android/ship-companion.sh
#
# The actual build/sign/verify/stage is done by scripts/publish-companion-apk.sh
# (single source of truth, shared with the pre-push hook). It does a CLEAN build,
# forces v1+v2+v3 signing, and ABORTS if any signature scheme is missing — so a
# broken or v2-only APK can never be shipped.
set -euo pipefail
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
cd "$ROOT"
export JAVA_HOME="${JAVA_HOME:-/opt/homebrew/opt/openjdk@17}"
export ANDROID_HOME="${ANDROID_HOME:-$HOME/Library/Android/sdk}"
DEST="neode-ui/public/packages/archipelago-companion.apk"
echo "==> Building + signing + verifying companion APK"
bash scripts/publish-companion-apk.sh
[ -f "$DEST" ] || { echo "ERROR: served APK not found at $DEST" >&2; exit 1; }
if git diff --cached --quiet -- "$DEST"; then
echo "==> Nothing to commit (APK unchanged)"
else
git commit -q -m "chore(android): update companion apk download"
echo "==> Committed"
fi
echo "==> Pushing $(git branch --show-current)"
# SHIP_COMPANION lets the pre-push guard know the APK was just refreshed.
SHIP_COMPANION=1 git push origin "$(git branch --show-current)"
echo "==> Done — companion APK published and pushed."

View File

@ -1,5 +1,125 @@
# Changelog
## v1.8.00-alpha (2026-06-18)
Polishes the mesh AI assistant and Fedimint, on top of all the v1.7.99 features (kept listed below so you can still see what's new).
- The off-grid mesh radio no longer posts cryptic identity codes to the shared public channel. Your node was announcing a line starting with "ARCHY:" to the public channel about once a minute, which everyone else on that channel saw as spam; that broadcast has been removed.
- You can now use your node's AI assistant straight from a normal chat. Send "!ai <your question>" in a direct message to an AI-enabled node and the answer comes right back in the same conversation — whether your message travelled over the internet or the LoRa radio. Before, the reply could be sent on the wrong path and never arrive.
- The Mesh AI Assistant panel is easier to set up: pick the Claude model from a dropdown (Haiku, Sonnet, or Opus) instead of typing it, and add specific contacts to an "always allow" list so chosen people can use "!ai" even when the assistant is set to trusted-nodes-only.
- Fedimint federations show up in Wallet Settings again. The Fedimint client app wasn't starting because of a configuration error, so the federation your node auto-joins never appeared; the client is fixed and runs again.
- In Settings, "App Updates" and "App Registry" now sit directly under your Account section for quicker access.
- In Mesh chat, scrolling the conversation no longer also scrolls the contact list behind it.
- Mesh direct messages are now private and end-to-end encrypted to the recipient — they're sent as real radio DMs instead of being broadcast on the public channel, so other people on the mesh no longer see them, and the answer arrives intact (even on standard meshcore phone apps).
- You can now message standard meshcore apps (like the phone companion) and they can message you — text shows up readable on both sides, and your node's AI answers come back as a private reply rather than on the public channel.
- New contacts you hear on the radio are added automatically, so people show up in your Peers list without any extra steps.
- "Clear All" now actually removes contacts (rather than hiding them forever); a contact comes back on its own the next time it's in range. Each contact also shows a reachability dot so you can see who's currently reachable.
- The Peers list has a search box (with a clear button) to quickly filter your contacts by name, DID, npub, or key.
All the v1.7.99-alpha features are included as well:
- Your node can now hold Fedimint ecash as well as Cashu, with tabbed Wallet Settings for each and both balances shown side by side on the home wallet card.
- You can buy files shared by another node right from their cloud, paying from this node's ecash, your Lightning wallet, on-chain, or by scanning a Lightning QR with any outside wallet.
- Your node can act as an AI assistant on the off-grid mesh: peers ask by starting a message with "!ai" and get an answer back over the radio, with a panel to turn it on or off.
- You can view your node's 24-word recovery phrase any time from Settings, behind a password (and 2FA) confirmation and a tap-to-show blur.
- Setting up a brand-new node is smoother: it waits and retries quietly instead of flashing errors, and shows a gentle "securing your private connection…" status that turns to "ready" on its own.
- The NetBird VPN app now logs in (it's served over HTTPS and opens in a browser tab).
- Phone remote-control of a node's screen now supports two-finger scrolling inside apps, and external-browser apps open on your phone.
- You can choose whether your node shares Bitcoin block headers over the mesh, and your choices are remembered.
- Version numbers display cleanly everywhere (no more doubled "v"), and "Back" buttons look and behave consistently across desktop and mobile.
- For advanced testing, Settings includes an optional update & app source choice between the usual trusted origin and an experimental peer-to-peer (DHT swarm) mode, with the trusted origin remaining the default.
## v1.7.99-alpha (2026-06-17)
- Your node can now hold Fedimint ecash as well as Cashu. Wallet Settings now has tabbed sections for each: keep your list of trusted Cashu mints, or paste a Fedimint invite code to join a federation, and the home wallet card shows both your Cashu and Fedimint balances side by side. A new "Fedimint Client" app in the catalog powers the federation side.
- You can now buy files shared by another node, right from their cloud. When you open a peer's paid file you get a simple "Buy this file" picker with several ways to pay — instantly from this node's ecash balance, from your node's own Lightning wallet, on-chain from your node, or by scanning a Lightning QR code with any outside wallet. Once payment settles, the file downloads automatically.
- Your node can now act as an AI assistant on the off-grid mesh radio network. If your node has a local AI model available (via Ollama), other people on the mesh can ask it a question by starting their message with "!ai" and get an answer back over the radio — handy where there's no internet. A new Mesh assistant panel lets you turn this on or off and shows whether a local AI model was detected.
- You can now view your node's 24-word recovery phrase whenever you need it. Settings has a new "Recovery phrase" option that, after you confirm your password (and 2FA code if you use one), reveals the words behind a tap-to-show blur with a copy button — so you can write them down and store them safely offline.
- Setting up a brand-new node is smoother and less alarming. If the node is still starting up while you generate or confirm your recovery phrase, it now quietly waits and retries instead of flashing a scary error, and offers a clear "Try again" button only when something genuinely goes wrong. The final setup screen also shows a gentle "securing your private connection…" status that turns to "ready" on its own, so you can tell the encrypted transport is coming up rather than stuck.
- The NetBird VPN app now actually logs in. It was failing to reach its sign-in screen because the dashboard needs a secure (HTTPS) connection that wasn't being provided; the node now serves it over HTTPS and opens it in a browser tab, so the login flow completes.
- When you use your phone to remote-control a node's attached screen, two-finger scrolling now works inside apps and panels, not just the main page. And tapping an app that's meant to open in an external browser now hands the link to your phone to open there, instead of trying to open it on the (often unattended) attached display.
- You can now choose whether your node shares Bitcoin block headers over the mesh. The Mesh Bitcoin panel has new switches to announce headers to peers and to accept headers from them, and your choices are remembered.
- Version numbers now display cleanly everywhere. In a few places the interface was showing a doubled "v" (like "vv1.7.98"); it now always shows a single, tidy version label.
- The "Back" buttons throughout the cloud and other detail screens now look and behave consistently on both desktop and mobile, including when browsing another node's files.
- For advanced testing, Settings now includes an optional "update & app source" choice between the usual trusted origin and an experimental peer-to-peer (DHT swarm) mode that pulls updates and app content from other nodes first, falling back to the origin automatically. The trusted origin remains the default.
## v1.7.98-alpha (2026-06-16)
- Apps that crash now recover on their own. Multi-part apps like Immich and IndeedHub could have one of their pieces stop and stay stopped until the whole node was rebooted; the node now checks every couple of minutes and restarts any crashed piece automatically (while still leaving apps you deliberately stopped alone).
- The on-screen kiosk display can no longer slow the whole node down. On machines without a graphics chip the kiosk browser could spin a CPU core at full tilt, starving everything else (including the wallet, which then timed out); it's now capped and uses lighter rendering on those machines.
- If an update download fails, you're taken back to the Download button to retry, instead of being stranded on an Install button for an update that didn't actually finish downloading.
- Your node's identity is clearer and always visible: Settings now shows your Node DID on every node (it previously only appeared if your browser had cached it) plus your node's npub, both with copy buttons. There's also a terminal tool to cryptographically prove all your node's keys come from your one seed phrase.
- The "all nodes over Tor" group chat sends quickly now — the "sending" spinner clears as soon as the reachable nodes have the message, instead of hanging on a slow or offline node.
- Message notifications now have a close button and open the relevant chat when tapped.
- The encrypted mesh transport (FIPS) turns itself on automatically after setup — no button to press — and connects to peers more reliably (it retries and keeps connections warm), so node-to-node features use the fast path more often instead of falling back to Tor.
- Your chat history with other nodes is saved reliably and now encrypted on disk, so it survives restarts and updates and can't be read from a stolen drive (only clearing chat removes it).
- Peer media shows a "connecting" loader before a video or audio file plays, and audio errors are accurate instead of blaming File Browser.
- The Fedimint app now displays with its proper styling, and the Connected Nodes screen stays compact — it shows a few nodes and scrolls, you can tap a node to jump to it in Federation, or tap Message to open its chat.
- App updates can now arrive on their own without waiting for a full system release, so individual apps can be improved and shipped faster.
## v1.7.97-alpha (2026-06-16)
- The Bitcoin sync status on the home screen no longer disappears for a moment when it refreshes. If the node was briefly busy, the panel used to vanish and pop back; it now stays put and simply shows "Updating…" until the next reading arrives, while a genuinely stopped node still correctly shows as not running.
- Bitcoin sync progress on the home screen now updates more promptly, so the percentage and block height keep pace with the node instead of lagging behind.
- The Lightning wallet "connect your wallet" screen loads its details and QR code again across all nodes, instead of failing to fetch them.
- Your list of trusted nodes is now clean: the same node no longer appears several times under different names, and removed nodes stay removed. In chat, a node that previously showed up as two separate contacts now appears just once.
- Browsing another node's cloud is smoother: music and video files from a peer now preview and play properly (including seeking partway through), and the connection now shows a small badge telling you whether it's using the fast encrypted mesh or the slower Tor network.
- Opening "My Folders" in the cloud now shows a clear, friendly message when the file app isn't running, instead of a confusing error.
- The Electrum server app opens on its own once it's ready, instead of sometimes leaving a loading spinner stuck on top of the screen.
- The Fedimint app now displays with its proper styling and icons, instead of appearing unstyled with a missing image.
- The Mempool app now connects to your Bitcoin node whether the node is Bitcoin Core or Bitcoin Knots, instead of only working with one of them.
- Nodes start up cleanly after a reboot. On some boots the node's main service was trying to start before its data drive had finished mounting, so it failed and retried about twenty times over roughly five minutes — showing a wall of "Failed to start" messages — before finally coming up. It now waits for the data drive to be ready first, so it starts on the first try.
- The background images throughout the interface now load faster — they've been made significantly smaller with no loss of quality.
## v1.7.96-alpha (2026-06-15)
- The screen attached to your node now shows the normal Archipelago interface and your dashboard after you sign in, instead of a separate, stripped-down grid of app icons that could appear in its place. That extra screen has been removed so the attached display matches what you see everywhere else.
- On a brand-new node, the attached screen now walks through the same welcome and setup steps you'd see on a phone or laptop, and shows the normal sign-in screen once the node is set up — so the on-device display always matches the rest of the interface.
- When adding a FIPS network anchor, you can now choose whether it connects over TCP (for a public anchor reached across the internet) or UDP (for one on your local network), instead of it always assuming the local-network option.
- Behind the scenes, a new automated two-node test now exercises real node-to-node features — browsing another node's shared files and handling a removed node — against live nodes before each release, so node-to-node problems are caught earlier.
## v1.7.95-alpha (2026-06-15)
- Browsing another node's shared files now works over the fast encrypted mesh. Opening a peer's cloud could fail with a generic "Operation failed" message because the request for their file list wasn't permitted over the mesh and came back as "not found" — and it never retried over Tor. The mesh now serves the file list directly, and if a peer can't answer over the mesh the node automatically falls back to Tor instead of giving up.
- Nodes you remove from your federation now stay removed. Previously a deleted node could quietly come back the next time you synced with another node that still listed it. Removed nodes are now remembered as removed and won't reappear on their own — only if you add them back yourself.
- The app credentials pop-up now appears as a normal centred box with a dimmed background over the whole screen, instead of stretching to fill the entire screen.
## v1.7.94-alpha (2026-06-15)
- Your node now joins the private encrypted mesh network on its own. A wrong built-in setting meant nodes were quietly never reaching the shared mesh meeting point, so everything between nodes fell back to the slower Tor network. Every node now connects to the mesh automatically on startup, so node-to-node features like file sharing use the faster encrypted mesh first and only fall back to Tor when a peer is genuinely offline. (Confirmed live: a node with its mesh setting wiped re-connected to the mesh by itself within a second of starting.)
- You can now bring the mesh networking software up to the latest stable version straight from the node, with one action — it fetches the new version, checks it's genuine before installing, and restarts the mesh on its own. (Confirmed live end to end: a node on an older build was upgraded to the current stable release and rejoined the mesh automatically.)
- The Lightning wallet screen connects again on nodes where it was showing a "failed to fetch" error instead of your balance and channels. The wallet app and the node now talk to each other correctly, and the connection quietly repairs itself if its details drift after a restart.
## v1.7.93-alpha (2026-06-14)
- Receiving Bitcoin and Lightning works again on nodes where the Lightning wallet was stuck locked. After some updates the wallet could come back locked with a password the node no longer had, so "generate a receive address" kept failing with a "wallet is locked" message that nothing could clear. The node now detects this and repairs itself automatically.
- Each node now secures its Lightning wallet with its own unique, randomly generated password instead of a shared built-in one, and remembers it safely so the wallet unlocks on its own after every restart or update — no more getting stuck locked.
- If a wallet is found locked with an unrecoverable password, the node rebuilds it cleanly so Bitcoin and Lightning start working again. (On these early-access nodes the wallet holds no funds, so nothing is lost — a wallet locked with an unknown password was already inaccessible.)
- The self-repair was validated end to end on live nodes: a stuck, locked wallet was detected, rebuilt, and came back unlocked on its own, and stayed unlocked across restarts.
## v1.7.92-alpha (2026-06-14)
- The Electrum server app no longer flashes a "can't connect, try again" error over its loading screen while it's still catching up. If ElectrumX is building its index or waiting on the Bitcoin node, you now just see the sync progress, and the app opens on its own once it's ready.
- Behind the scenes, the reboot-survival test now confirms the whole system is genuinely healthy after a restart — every app reachable, updates not stuck, core services answering — instead of only checking that containers came back, so update-related problems are caught before shipping.
- Settings → What's New now lists the notes for every recent release again. The screen had quietly fallen several versions behind, so the last eight releases of changes weren't showing up there — they're all back now, and a release check keeps it from drifting again.
## v1.7.91-alpha (2026-06-14)
- Apps you've installed now reliably show their "Open" button again. Some apps — including Jellyfin, BTCPay Server, Fedimint, Gitea and Portainer — were running fine but their launch link sometimes went missing, so there was no way to open them from the home screen. They now open correctly.
- Receiving Bitcoin is more dependable: if the wallet's internal connection details drift after a restart, it now repairs them on its own, and any error it does hit is reported clearly instead of as a generic failure or a misleading "wallet locked" message.
- Installing Bitcoin now sets itself up correctly without manual help — a security credential that could previously be missing and stop Bitcoin from starting is created automatically before it launches.
- The Electrum server app is back on the home screen and can be launched again.
- Behind the scenes, the release now runs an expanded automated test suite before shipping, so these kinds of issues are caught earlier.
## v1.7.90-alpha (2026-06-13)
- Generating a Bitcoin receive address works again — the wallet now requests the correct address type, fixing the "400 Bad Request" error when creating an address.
- In the companion app, the on-screen pointer can now click into apps and type — including the app store search box — instead of clicks and keystrokes not reaching app content.
- "Open in a new tab" from the companion app now opens the app in your phone's browser, instead of doing nothing. The normal mobile browser keeps working as before.
- The login/credentials pop-up on phones is once again a centered, properly sized window rather than stretching the full height of the screen.
- The Electrum server now recovers on its own if its index ever gets corrupted, and shows a clear progress screen (with percent complete and block height) while it builds its index, instead of a blank or broken page.
- Software updates are more reliable on slow internet connections — downloads are given much more time to finish before giving up.
## v1.7.89-alpha (2026-06-12)
- The AI assistant looks the way it always did again: no extra back button or close button on phones, and the desktop view fills the whole screen without a gap at the bottom.

57
CLAUDE.md Normal file
View File

@ -0,0 +1,57 @@
# Archipelago — agent guide
## ✅ Single-node production gate is GREEN (2026-06-23)
`tests/lifecycle/run-gate.sh` is **5/5 on .228, 0 failures** — the single-node exit
criterion is met and the priority banner is demoted. Next exit-criteria: the
**multinode pass** (`docs/multinode-testing-plan.md`) and workstreams B/C/D.
**Read `docs/PRODUCTION-MASTER-PLAN.md` first** — it is still the authoritative plan
for the north star: a world-class, **developer-ready app platform** where every app
is manifest-driven, manifests ship via the **signed registry** (not OTA disk files),
and **third-party developers publish apps via an external/decentralized registry**
all rootless, secure, robust, and 100%-uptime-capable. It no longer overrides all
ad-hoc direction now that the gate is green, but it remains the source of truth for
sequencing the remaining workstreams.
Detailed sub-plans (all linked from the master):
- App platform / packaging phases + security model → `docs/APP-PACKAGING-MIGRATION-PLAN.md`
- Registry-distributed manifests (in progress) → `docs/registry-manifest-design.md`
- External/decentralized marketplace for devs → `docs/marketplace-protocol.md`
- Current per-app state → `docs/app-registry-status-2026-06-21.md`
- Production test gate (exit criterion) → `tests/lifecycle/TESTING.md`
## Invariants (never violate)
- **Rootless Podman only.** No rootful, no Docker-socket mounts, no privileged
containers unless explicitly approved.
- **No per-app Rust installers / no OS-level reliance.** Apps are declarative;
the orchestrator owns the lifecycle. `install_immich_stack` (hardcoded
`podman run` + `sudo chown`) is the anti-pattern being deleted, not a template.
- **Secrets are manifest-declared** (`generated_secrets`, materialised by
`container::secrets`, 0600/rootless) — never hardcoded, per-app, or logged.
- **Migrations never destroy data** — preserve `/var/lib/archipelago/<app>`,
secrets, credentials, ports, and adoption container names; keep a rollback path.
- **Verify on the real node .228 before any tag.** (Fleet-wide multinode
verification is a separate plan: `docs/multinode-testing-plan.md`.)
## Build / verify
- Rust workspace root is `core/` (no Cargo.toml at repo root). `cargo` from `core/`.
- If a `cargo test`/build hits `rust-lld: undefined hidden symbol`, it's
incremental-cache corruption — rebuild with `CARGO_INCREMENTAL=0`.
- Frontend: `neode-ui/``npm run build` outputs to `web/dist/neode-ui/`.
Grep the built bundle for new strings before shipping (build can silently no-op).
- App manifests load from disk on nodes at `/opt/archipelago/apps/*/manifest.yml`
(today); the goal is to distribute them via the signed catalog instead.
## Production test gate (definition of done)
`tests/lifecycle/run-gate.sh` green across install / UI / stop / start / restart /
reinstall / reboot-survive / archipelago-restart-survive / uninstall — **5× on
.228** (`ARCHY_ITERATIONS=5`). **Run the gate ON the node** (it uses local podman/systemctl/bitcoin
probes), not via RPC from another host. **✅ GREEN 2026-06-23 (5/5, 0 not-ok)** — keep it
green (re-run after orchestrator/lifecycle changes); regressions are top priority again.
**Multinode testing (.198 + the rest of the fleet) is a SEPARATE plan** —
`docs/multinode-testing-plan.md` — not part of this single-node gate criterion, and is
the next exit criterion now that single-node is green.

View File

@ -73,7 +73,7 @@
"author": "Mempool",
"category": "money",
"tier": "core",
"dockerImage": "146.59.87.168:3000/lfg2025/mempool-frontend:v3.0.0",
"dockerImage": "146.59.87.168:3000/lfg2025/mempool-frontend:v3.0.1",
"repoUrl": "https://github.com/mempool/mempool",
"requires": [
"bitcoin-knots",
@ -281,7 +281,7 @@
},
{
"id": "fedimint",
"title": "Fedimint",
"title": "Fedimint Guardian",
"version": "0.10.0",
"description": "Federated Bitcoin minting service with built-in Guardian UI. Privacy-preserving Bitcoin custody.",
"icon": "/assets/img/app-icons/fedimint.png",
@ -290,6 +290,18 @@
"dockerImage": "146.59.87.168:3000/lfg2025/fedimintd:v0.10.0",
"repoUrl": "https://github.com/fedimint/fedimint"
},
{
"id": "fedimint-clientd",
"title": "Fedimint Client",
"version": "0.8.0",
"description": "Fedimint ecash client daemon (fmcd). Lets your node hold Fedimint ecash and join federations; the wallet talks to it over a local REST API.",
"icon": "/assets/img/app-icons/fedimint.png",
"author": "Fedimint",
"category": "money",
"tier": "core",
"dockerImage": "146.59.87.168:3000/lfg2025/fmcd:0.8.0",
"repoUrl": "https://github.com/minmoto/fmcd"
},
{
"id": "fedimint-gateway",
"title": "Fedimint Gateway",

View File

@ -1,12 +1,12 @@
app:
id: archy-mempool-web
name: Mempool Web
version: 3.0.0
version: 3.0.1
description: Frontend web UI for mempool explorer.
container_name: mempool
container:
image: git.tx1138.com/lfg2025/mempool-frontend:v3.0.0
image: 146.59.87.168:3000/lfg2025/mempool-frontend:v3.0.1
pull_policy: if-not-present
network: archy-net

View File

@ -51,6 +51,20 @@ app:
- CACHE_MB=1024
- MAX_SEND=10000000
# The ElectrumX dashboard tile is served by the host-networked companion UI
# (archy-electrs-ui) on port 50002, NOT by this container. Declaring it here
# lets the catalog generator emit electrumx -> 50002 into GENERATED_APP_PORTS
# so the tile resolves a launch URL without relying on the hand-maintained
# override in appSessionConfig.ts (which the generator can clobber). The
# backend only validates this block — it does not proxy/health-check it.
interfaces:
main:
name: Web UI
description: ElectrumX server status and connection details
type: ui
port: 50002
protocol: http
health_check:
type: tcp
endpoint: localhost:50001

View File

@ -0,0 +1,95 @@
app:
id: fedimint-clientd
name: Fedimint Client
version: 0.8.0
description: Fedimint ecash client daemon (fmcd). Lets the node hold Fedimint ecash and join federations; the wallet talks to it over a local REST API.
container:
# fmcd built from source (github.com/minmoto/fmcd v0.8.0, fedimint-client
# 0.8.2 — iroh-capable). No usable upstream image exists, so we build + push
# this to the node registry. Pin the tag to match the REST shapes coded in
# core/archipelago/src/wallet/fedimint_client.rs (validated against 0.8.2).
image: 146.59.87.168:3000/lfg2025/fmcd:0.8.0
pull_policy: if-not-present
network: archy-net
# No entrypoint override: the image's resilient `fmcd-run` launcher loops
# fmcd and retries on join failure (fmcd needs >=1 federation to boot), so an
# unreachable default never crash-loops. All config comes from FMCD_* env
# below. Nodes can join more federations via wallet.fedimint-join.
# Auto-generated on first install (random hex, 0600, rootless-owned) so the
# app needs no host provisioning. The wallet bridge reads the same file.
generated_secrets:
- name: fmcd-password
kind: hex16
secret_env:
- key: FMCD_PASSWORD
secret_file: fmcd-password
data_uid: "1000:1000"
# NOTE: this is a CLIENT, not the guardian — it does not require the local
# `fedimint` app. It joins external federations (default below), so it can be
# bundled standalone on every node.
dependencies:
- storage: 2Gi
resources:
cpu_limit: 1
memory_limit: 1Gi
disk_limit: 2Gi
security:
# fmcd's `fmcd-run` launcher chowns its /data (existing federation DB) on
# every start. With the default `cap_drop: ALL` and no caps added back, that
# chown fails and fmcd dies "Operation not permitted (os error 1)" — but ONLY
# once /data holds a joined federation (a fresh/empty dir needs no chown, so
# it appeared to work). Restore the standard container capability set so the
# startup chown succeeds (#7). Verified by bisection on .116: these caps make
# fmcd boot + serve /v2/*; DAC_OVERRIDE or SETUID/SETGID alone do NOT.
capabilities: ["CHOWN", "DAC_OVERRIDE", "FOWNER", "SETUID", "SETGID"]
readonly_root: true
# NOT isolated: fmcd needs outbound UDP + Mainline DHT (port 6881) + iroh
# relays to reach iroh-transport federations. `bridge` gives NAT'd outbound
# (UDP/DHT/iroh hole-punch all work) plus the published 8178→8080 port the
# wallet bridge targets. ("open" is not a valid policy — it made the loader
# skip this whole manifest, so fmcd never ran and federations never joined.)
# Lock down once the default federation's reachability model is finalized.
network_policy: bridge
ports:
# fmcd REST bound to 8080 in-container; 8080 collides with LND REST on the
# host, so map to 8178. The Rust bridge targets http://127.0.0.1:8178.
- host: 8178
container: 8080
protocol: tcp
volumes:
# Same dir the first-boot bundled path uses + where the wallet bridge reads
# the password (/var/lib/archipelago/fmcd/password) — keep install paths aligned.
- type: bind
source: /var/lib/archipelago/fmcd
target: /data
options: [rw]
environment:
- FMCD_ADDR=0.0.0.0:8080
- FMCD_MODE=rest
- FMCD_DATA_DIR=/data
# Default federation joined out-of-the-box (guardian on .116, iroh
# transport; validated to join with fmcd 0.8.2). iroh does NAT traversal so
# it's reachable fleet-wide. Keep in sync with DEFAULT_FEDERATION_INVITE in
# core/.../wallet/fedimint_client.rs. CAVEAT: iroh is experimental — validate
# join reliability from a real second node before relying on auto-bundle.
- FMCD_INVITE_CODE=fed11qgqyj3mfwfhksw309uuxywtxxfjrjc35xuexverpxdsnxcnrxucxvenzveskgc3kvvun2c34xp3k2ep38yunzdpexcekxe3hvd3rvvmx8pnrvdenx5mnzvtzqqqjqt0t6pc3s5z0ynqjw9s4njf6svwgu59kweawc0vvrddcjeemw6yyn4pcdp
# fmcd serves only authenticated /v2/* routes — there is no unauthenticated
# /health endpoint, so an http probe to /health 404s forever and pins the
# container in "(starting)". fmcd's own image also ships neither curl nor wget.
# Use a TCP probe: the Quadlet renderer skips it (no HealthCmd emitted) and the
# host-side lifecycle layer verifies reachability, so the container reports
# "running" instead of a perpetual false-negative "(starting)".
health_check:
type: tcp
endpoint: localhost:8080
interval: 30s
timeout: 5s
retries: 3

View File

@ -16,6 +16,14 @@ app:
else
exec gatewayd --data-dir /data --listen 0.0.0.0:8176 --bcrypt-password-hash "$FEDI_HASH" --network bitcoin --bitcoind-url http://host.archipelago:8332 --bitcoind-username "$FM_BITCOIND_USERNAME" --bitcoind-password "$FM_BITCOIND_PASSWORD" ldk --ldk-lightning-port 9737 --ldk-alias archipelago-gateway;
fi
# The gateway's admin API is gated by a bcrypt password hash. Generate it on
# first install (random password + its bcrypt hash, both 0600 rootless-owned)
# so the app installs from its manifest alone — `fedimint-gateway-hash` holds
# the hash passed to gatewayd, `fedimint-gateway-hash.pw` the plaintext for
# any client that must authenticate. Self-heals a wrongly root-owned hash.
generated_secrets:
- name: fedimint-gateway-hash
kind: bcrypt
secret_env:
- key: FM_BITCOIND_PASSWORD
secret_file: bitcoin-rpc-password

View File

@ -1,6 +1,6 @@
app:
id: fedimint
name: Fedimint
name: Fedimint Guardian
version: 0.10.0
description: Federated Bitcoin minting service with built-in Guardian UI. Privacy-preserving Bitcoin custody.

42
apps/fips-ui/manifest.yml Normal file
View File

@ -0,0 +1,42 @@
app:
id: fips-ui
name: FIPS Mesh
version: 1.0.0
description: |
Archipelago-native dashboard for the FIPS mesh transport. Runs nginx
inside a container with host networking, serves a static dashboard on
:8336, and reverse-proxies /rpc/v1 to the archipelago backend on
127.0.0.1:5678. All FIPS controls (status, seed anchors, reconnect,
restart, and stable-channel daemon updates) go through the existing
fips.* RPC methods, authenticated by the browser's own archipelago
session — there is no separate secret to manage.
container:
build:
context: /opt/archipelago/docker/fips-ui
dockerfile: Dockerfile
tag: localhost/fips-ui:local
resources:
memory_limit: 128Mi
security:
readonly_root: false
network_policy: host
# Host networking: nginx listens on 8336 directly on the host IP and
# proxies to 127.0.0.1:5678 (the archipelago RPC). `ports:` is
# intentionally empty because host networking bypasses port mapping.
ports: []
volumes: []
environment: []
health_check:
type: http
endpoint: http://127.0.0.1:8336
path: /
interval: 30s
timeout: 5s
retries: 3

View File

@ -0,0 +1,58 @@
app:
id: immich-postgres
name: Immich Postgres
version: "14-vectorchord0.4.3-pgvectors0.2.0"
description: Postgres (pgvecto.rs / vectorchord) backend for Immich.
# Container named immich_postgres (underscore) to match the runtime's existing
# per-app references (lifecycle/health/crash-recovery/config) and serve as the
# server's DB_HOSTNAME alias. Top-level key → serde(flatten) → extensions →
# compute_container_name.
container_name: immich_postgres
container:
image: 146.59.87.168:3000/lfg2025/immich-postgres:14-vectorchord0.4.3-pgvectors0.2.0
pull_policy: if-not-present
network: archy-net
# postgres drops to its own uid (container 999 → host 100998 under rootless),
# so the data dir must be owned by that mapped uid — mirrors archy-btcpay-db.
# Verified on .228: the live immich-db is owned 100998. Without this a FRESH
# install's dir would be service-user-owned and postgres would EACCES.
data_uid: "100998:100998"
generated_secrets:
- name: immich-db-password
kind: hex32
secret_env:
- key: POSTGRES_PASSWORD
secret_file: immich-db-password
dependencies:
- storage: 40Gi
resources:
memory_limit: 2Gi
disk_limit: 40Gi
security:
capabilities: [CHOWN, DAC_OVERRIDE, FOWNER, SETGID, SETUID]
readonly_root: false
network_policy: isolated
ports: []
volumes:
- type: bind
source: /var/lib/archipelago/immich-db
target: /var/lib/postgresql/data
options: [rw]
environment:
- POSTGRES_USER=postgres
- POSTGRES_DB=immich
health_check:
type: tcp
endpoint: localhost:5432
interval: 30s
timeout: 5s
retries: 3

View File

@ -0,0 +1,37 @@
app:
id: immich-redis
name: Immich Redis
version: "7-alpine"
description: Valkey (Redis-compatible) cache for Immich.
# Container named immich_redis (underscore) to match runtime per-app references
# and serve as the server's REDIS_HOSTNAME alias on archy-net.
container_name: immich_redis
container:
image: 146.59.87.168:3000/lfg2025/valkey:7-alpine
pull_policy: if-not-present
network: archy-net
dependencies: []
resources:
memory_limit: 128Mi
security:
capabilities: [SETGID, SETUID]
readonly_root: false
network_policy: isolated
ports: []
volumes: []
environment: []
health_check:
type: tcp
endpoint: localhost:6379
interval: 30s
timeout: 5s
retries: 3

74
apps/immich/manifest.yml Normal file
View File

@ -0,0 +1,74 @@
app:
id: immich
name: Immich
version: "2.7.4"
description: Self-hosted photo and video backup with mobile apps and search.
# app_id "immich" = the user-facing launcher (matches the catalog entry's title
# + icon). The container is named "immich_server" so it matches the runtime's
# existing per-app container references (lifecycle/health/crash-recovery/ports);
# `container_name` is a top-level app key (captured by serde(flatten) into
# extensions, read by compute_container_name). It reaches its backends by their
# underscore aliases on archy-net (DB_HOSTNAME / REDIS_HOSTNAME below).
container_name: immich_server
container:
image: 146.59.87.168:3000/lfg2025/immich-server:release
pull_policy: if-not-present
network: archy-net
secret_env:
- key: DB_PASSWORD
secret_file: immich-db-password
dependencies:
- app_id: immich-postgres
- app_id: immich-redis
- storage: 200Gi
resources:
memory_limit: 2Gi
disk_limit: 200Gi
security:
capabilities: []
readonly_root: false
network_policy: isolated
ports:
- host: 2283
container: 2283
protocol: tcp
volumes:
- type: bind
source: /var/lib/archipelago/immich
target: /usr/src/app/upload
options: [rw]
environment:
- DB_HOSTNAME=immich_postgres
- DB_USERNAME=postgres
- DB_DATABASE_NAME=immich
- REDIS_HOSTNAME=immich_redis
- UPLOAD_LOCATION=/usr/src/app/upload
health_check:
type: http
endpoint: http://localhost:2283
path: /api/server/ping
interval: 30s
timeout: 5s
retries: 20
interfaces:
main:
name: Web UI
description: Immich photo library
type: ui
port: 2283
protocol: http
path: /
metadata:
launch:
open_in_new_tab: true

View File

@ -0,0 +1,77 @@
app:
id: indeedhub-api
name: IndeedHub API
version: "1.0.0"
description: IndeedHub backend API (Nostr auth, media, payments).
category: community
# Hyphen name matches runtime references + the live container (adoption);
# alias `api` is the short hostname the frontend nginx proxies to
# (http://api:4000). Reaches its backends by their short aliases
# (postgres/redis/minio) on indeedhub-net — unchanged from the legacy installer.
container_name: indeedhub-api
container:
image: 146.59.87.168:3000/lfg2025/indeedhub-api:1.0.0
pull_policy: if-not-present
network: indeedhub-net
network_aliases: [api]
# The JWT signing secret is owned here (no backend container owns it); the
# db + minio passwords are owned by indeedhub-postgres / indeedhub-minio and
# only consumed here. ensure_generated_secrets no-ops when a file already
# exists, so live values on .228 are preserved (postgres pw is fixed at
# PGDATA init — regenerating would lock the API out).
generated_secrets:
- name: indeedhub-jwt
kind: hex32
secret_env:
- key: DATABASE_PASSWORD
secret_file: indeedhub-db-password
- key: AWS_SECRET_KEY
secret_file: indeedhub-minio-password
- key: NOSTR_JWT_SECRET
secret_file: indeedhub-jwt
dependencies:
- app_id: indeedhub-postgres
- app_id: indeedhub-redis
- app_id: indeedhub-minio
resources:
memory_limit: 2Gi
security:
capabilities: []
readonly_root: false
network_policy: isolated
ports: []
volumes: []
environment:
- PORT=4000
- DATABASE_HOST=postgres
- DATABASE_PORT=5432
- DATABASE_USER=indeedhub
- DATABASE_NAME=indeedhub
- QUEUE_HOST=redis
- QUEUE_PORT=6379
- S3_ENDPOINT=http://minio:9000
- AWS_REGION=us-east-1
- AWS_ACCESS_KEY=indeeadmin
- S3_PUBLIC_BUCKET_NAME=indeedhub-public
- S3_PRIVATE_BUCKET_NAME=indeedhub-private
- S3_PUBLIC_BUCKET_URL=/storage
- NOSTR_JWT_EXPIRES_IN=7d
# Fixed across the fleet (envelope-encryption master key baked by the legacy
# installer); not node-specific, so a plain env literal, not a secret.
- AES_MASTER_SECRET=0123456789abcdef0123456789abcdef
- ENVIRONMENT=production
health_check:
type: tcp
endpoint: localhost:4000
interval: 30s
timeout: 5s
retries: 10

View File

@ -0,0 +1,51 @@
app:
id: indeedhub-ffmpeg
name: IndeedHub FFmpeg Worker
version: "1.0.0"
description: IndeedHub background media transcoding worker.
category: community
# Hyphen name matches runtime references + the live container (adoption). No
# network_alias: nothing connects TO the worker — it only dials out to
# postgres/redis/minio (resolved by their aliases on indeedhub-net).
container_name: indeedhub-ffmpeg
container:
image: 146.59.87.168:3000/lfg2025/indeedhub-ffmpeg:1.0.0
pull_policy: if-not-present
network: indeedhub-net
secret_env:
- key: DATABASE_PASSWORD
secret_file: indeedhub-db-password
- key: AWS_SECRET_KEY
secret_file: indeedhub-minio-password
dependencies:
- app_id: indeedhub-api
resources:
memory_limit: 4Gi
security:
capabilities: []
readonly_root: false
network_policy: isolated
ports: []
volumes: []
environment:
- DATABASE_HOST=postgres
- DATABASE_PORT=5432
- DATABASE_USER=indeedhub
- DATABASE_NAME=indeedhub
- QUEUE_HOST=redis
- QUEUE_PORT=6379
- S3_ENDPOINT=http://minio:9000
- AWS_REGION=us-east-1
- AWS_ACCESS_KEY=indeeadmin
- S3_PUBLIC_BUCKET_NAME=indeedhub-public
- S3_PRIVATE_BUCKET_NAME=indeedhub-private
- ENVIRONMENT=production
- AES_MASTER_SECRET=0123456789abcdef0123456789abcdef

View File

@ -0,0 +1,60 @@
app:
id: indeedhub-minio
name: IndeedHub MinIO
version: "RELEASE.2024-11-07T00-52-20Z"
description: MinIO S3-compatible object storage for IndeedHub media.
category: community
# Hyphen name matches runtime references + the live container (adoption);
# alias `minio` is the short hostname the api/ffmpeg use (S3_ENDPOINT=
# http://minio:9000) AND the frontend nginx proxies to (http://minio:9000).
container_name: indeedhub-minio
container:
image: 146.59.87.168:3000/lfg2025/minio:RELEASE.2024-11-07T00-52-20Z
pull_policy: if-not-present
network: indeedhub-net
network_aliases: [minio]
# `server /data` — the minio entrypoint args from the legacy installer.
custom_args: [server, /data]
generated_secrets:
- name: indeedhub-minio-password
kind: hex32
secret_env:
- key: MINIO_ROOT_PASSWORD
secret_file: indeedhub-minio-password
dependencies:
- storage: 50Gi
resources:
memory_limit: 1Gi
disk_limit: 50Gi
security:
capabilities: []
readonly_root: false
network_policy: isolated
ports: []
# Named volume matches the live indeedhub-minio-data volume on .228.
volumes:
- type: volume
source: indeedhub-minio-data
target: /data
options: [rw]
# MINIO_ROOT_USER "indeeadmin" is the fixed admin identity baked by the legacy
# installer (api/ffmpeg use it as AWS_ACCESS_KEY); the password is the
# generated secret above. Not secret, so it stays a plain env value.
environment:
- MINIO_ROOT_USER=indeeadmin
health_check:
type: http
endpoint: http://localhost:9000
path: /minio/health/live
interval: 30s
timeout: 5s
retries: 5

View File

@ -0,0 +1,59 @@
app:
id: indeedhub-postgres
name: IndeedHub Postgres
version: "16.13-alpine"
description: Postgres database backend for IndeedHub.
category: community
# Container named indeedhub-postgres (hyphen) to match the runtime's existing
# per-app references (health_monitor tiers/deps, crash_recovery) and the live
# .228 install, so the orchestrator ADOPTS the running container instead of
# recreating it. `network_aliases: [postgres]` keeps the short hostname the
# api/ffmpeg/relay reach by (DATABASE_HOST=postgres) resolvable on
# indeedhub-net, reproducing the legacy `--network-alias postgres`.
container_name: indeedhub-postgres
container:
image: 146.59.87.168:3000/lfg2025/postgres:16.13-alpine
pull_policy: if-not-present
network: indeedhub-net
network_aliases: [postgres]
generated_secrets:
- name: indeedhub-db-password
kind: hex32
secret_env:
- key: POSTGRES_PASSWORD
secret_file: indeedhub-db-password
dependencies:
- storage: 10Gi
resources:
memory_limit: 1Gi
disk_limit: 10Gi
security:
capabilities: [CHOWN, DAC_OVERRIDE, FOWNER, SETGID, SETUID]
readonly_root: false
network_policy: isolated
ports: []
# Named podman volume (matches the live indeedhub-postgres-data volume on .228);
# preserves all existing database content across the migration.
volumes:
- type: volume
source: indeedhub-postgres-data
target: /var/lib/postgresql/data
options: [rw]
environment:
- POSTGRES_USER=indeedhub
- POSTGRES_DB=indeedhub
health_check:
type: tcp
endpoint: localhost:5432
interval: 30s
timeout: 5s
retries: 3

View File

@ -0,0 +1,45 @@
app:
id: indeedhub-redis
name: IndeedHub Redis
version: "7.4.8-alpine"
description: Redis queue/cache backend for IndeedHub.
category: community
# Hyphen name matches runtime references + the live container (adoption);
# alias `redis` is the short hostname the api/ffmpeg reach (QUEUE_HOST=redis).
container_name: indeedhub-redis
container:
image: 146.59.87.168:3000/lfg2025/redis:7.4.8-alpine
pull_policy: if-not-present
network: indeedhub-net
network_aliases: [redis]
dependencies:
- storage: 1Gi
resources:
memory_limit: 256Mi
security:
capabilities: [SETGID, SETUID]
readonly_root: false
network_policy: isolated
ports: []
# Named volume matches the live indeedhub-redis-data volume on .228.
volumes:
- type: volume
source: indeedhub-redis-data
target: /data
options: [rw]
environment: []
health_check:
type: tcp
endpoint: localhost:6379
interval: 30s
timeout: 5s
retries: 3

View File

@ -0,0 +1,47 @@
app:
id: indeedhub-relay
name: IndeedHub Nostr Relay
version: "0.9.0"
description: nostr-rs-relay backing IndeedHub's Nostr identity + comments.
category: community
# Hyphen name matches runtime references + the live container (adoption);
# alias `relay` is the short hostname the frontend nginx proxies to
# (http://relay:8080 for the /relay websocket).
container_name: indeedhub-relay
container:
image: 146.59.87.168:3000/lfg2025/nostr-rs-relay:0.9.0
pull_policy: if-not-present
network: indeedhub-net
network_aliases: [relay]
dependencies:
- storage: 2Gi
resources:
memory_limit: 256Mi
disk_limit: 2Gi
security:
capabilities: []
readonly_root: false
network_policy: isolated
ports: []
# Named volume matches the live indeedhub-relay-data volume on .228.
volumes:
- type: volume
source: indeedhub-relay-data
target: /usr/src/app/db
options: [rw]
environment: []
health_check:
type: tcp
endpoint: localhost:8080
interval: 30s
timeout: 5s
retries: 3

View File

@ -1,63 +1,84 @@
app:
id: indeedhub
name: IndeeHub
version: 1.0.0
version: "1.0.0"
description: Bitcoin documentary streaming platform featuring God Bless Bitcoin and other educational content about Bitcoin, sovereignty, and decentralized technology. Sign in with your Nostr identity.
category: community
# The user-facing launcher (app_id "indeedhub"). Container is named "indeedhub"
# (matches the runtime's per-app references + the live container, so the
# orchestrator adopts it). Its nginx (listen 7777) proxies to the backends by
# their short aliases on indeedhub-net: api:4000, minio:9000, relay:8080.
container_name: indeedhub
container:
image: 146.59.87.168:3000/lfg2025/indeedhub:1.0.0
pull_policy: always # Pull from registry; falls back to local build
pull_policy: if-not-present
network: indeedhub-net
dependencies:
- app_id: indeedhub-api
- storage: 1Gi
resources:
cpu_limit: 2
memory_limit: 512Mi
disk_limit: 1Gi
security:
capabilities: []
readonly_root: true
no_new_privileges: true
user: 1001
seccomp_profile: default
network_policy: bridge
apparmor_profile: default
# nginx master runs as root and drops workers to the nginx user (uid/gid
# 101) — needs SET{UID,GID}; CHOWN + DAC_OVERRIDE let it own + write the
# proxy cache under the tmpfs /var/cache/nginx. The orchestrator does
# --cap-drop=ALL, so (unlike the legacy `podman run` default caps) these
# must be declared or nginx workers die with "setgid(101) failed".
capabilities: [CHOWN, DAC_OVERRIDE, SETGID, SETUID]
readonly_root: false
network_policy: isolated
ports:
- host: 7778
container: 7777
protocol: tcp # Web UI. Port 7777 on the host is reserved for Nostr relay.
protocol: tcp # Web UI. Port 7777 on the host is reserved for the Nostr relay.
# Writable scratch the baked nginx needs; matches the legacy installer's
# --tmpfs /run + /var/cache/nginx.
volumes:
- type: tmpfs
target: /tmp
options: [rw,noexec,nosuid,size=64m]
- type: tmpfs
target: /app/.next/cache
options: [rw,noexec,nosuid,size=128m]
- type: tmpfs
target: /run
options: [rw,nosuid,nodev,size=16m]
options: [rw, nosuid, nodev, size=16m]
- type: tmpfs
target: /var/cache/nginx
options: [rw,nosuid,nodev,size=32m]
options: [rw, nosuid, nodev, size=32m]
environment:
- NODE_ENV=production
- NEXT_TELEMETRY_DISABLED=1
environment: []
# Defensive + idempotent. The current indeedhub:1.0.0 image already bakes the
# iframe-friendly nginx (X-Frame-Options omitted, nostr-provider.js present +
# <script> injected), so these are mostly no-ops on that tag — but they keep
# the app iframe-loadable + the provider script fresh for any image build that
# predates the bake. copy_from_host pulls /opt/archipelago/web-ui/nostr-provider.js
# (kept current by frontend OTA releases). Replaces the legacy hardcoded
# patch_indeedhub_nostr_provider() Rust hook.
hooks:
post_install:
- exec: ["sed", "-i", "/X-Frame-Options/d", "/etc/nginx/conf.d/default.conf"]
- copy_from_host:
src: "web-ui/nostr-provider.js"
dest: "/usr/share/nginx/html/nostr-provider.js"
- exec: ["sh", "-c", "grep -q nostr-provider /etc/nginx/conf.d/default.conf || sed -i 's#</head>#<script src=\"/nostr-provider.js\"></script></head>#' /etc/nginx/conf.d/default.conf"]
- exec: ["nginx", "-s", "reload"]
# TCP liveness on the nginx port, NOT an http GET of /. nginx binds 7777 at
# startup (before workers), so this passes immediately and stays green under
# load. An http check of / runs the SPA + sub_filter and false-fails when the
# node is busy → the reconciler then treats the frontend as wedged and
# recreates it in a loop (observed churning the frontend on the loaded .198).
health_check:
type: http
endpoint: http://localhost:3000
path: /
type: tcp
endpoint: localhost:7777
interval: 30s
timeout: 10s
retries: 3
start_period: 40s
timeout: 5s
retries: 5
start_period: 30s
interfaces:
main:

View File

@ -8,6 +8,12 @@ app:
image: git.tx1138.com/lfg2025/mempool-backend:v3.0.0
pull_policy: if-not-present
network: archy-net
# CORE_RPC_HOST must follow the node's actual Bitcoin container — Knots or
# Core — resolved at apply time from host facts (B12). Hardcoding either
# breaks mempool's RPC connection on the other.
derived_env:
- key: CORE_RPC_HOST
template: "{{BITCOIN_HOST}}"
secret_env:
- key: CORE_RPC_PASSWORD
secret_file: bitcoin-rpc-password
@ -47,7 +53,6 @@ app:
- ELECTRUM_HOST=electrumx
- ELECTRUM_PORT=50001
- ELECTRUM_TLS_ENABLED=false
- CORE_RPC_HOST=bitcoin-knots
- CORE_RPC_PORT=8332
- CORE_RPC_USERNAME=archipelago
- DATABASE_ENABLED=true

View File

@ -5,7 +5,7 @@ app:
description: Bitcoin mempool and blockchain explorer. Real-time transaction and block visualization.
container:
image: 146.59.87.168:3000/lfg2025/mempool-frontend:v3.0.0
image: 146.59.87.168:3000/lfg2025/mempool-frontend:v3.0.1
image_signature: cosign://...
pull_policy: if-not-present

View File

@ -1,5 +0,0 @@
# Meshtastic - uses official image
FROM meshtastic/meshtastic:latest
# Default configuration is in the image
# No additional setup needed

View File

@ -1,69 +0,0 @@
app:
id: meshtastic
name: Meshtastic
version: 2-daily-alpine
description: Open-source mesh networking for LoRa radios. Create decentralized communication networks.
container:
image: docker.io/meshtastic/meshtasticd:daily-alpine
pull_policy: if-not-present
dependencies:
- storage: 1Gi
resources:
cpu_limit: 1
memory_limit: 512Mi
disk_limit: 1Gi
security:
capabilities: [NET_ADMIN, SYS_ADMIN] # Required for LoRa radio access
readonly_root: false # Needs write access for device management
no_new_privileges: true
user: 1000
seccomp_profile: default
network_policy: host # Requires host network for radio access
apparmor_profile: meshtastic
ports:
- host: 4403
container: 4403
protocol: tcp # Meshtastic TCP API
devices:
- /dev/ttyUSB0 # LoRa radio device (if connected)
volumes:
- type: bind
source: /var/lib/archipelago/meshtastic
target: /var/lib/meshtasticd
options: [rw]
files:
- path: /var/lib/archipelago/meshtastic/config.yaml
content: |
General:
MACAddress: AA:BB:CC:DD:EE:01
Webserver:
Port: 4403
environment:
- MESHTASTIC_PORT=/dev/ttyUSB0
- MESHTASTIC_SERIAL=true
health_check:
type: cmd
endpoint: test -f /var/lib/meshtasticd/config.yaml
interval: 30s
timeout: 30s
retries: 5
networking:
mesh_enabled: true
local_network_access: true
metadata:
icon: /assets/img/app-icons/meshcore.svg
category: networking
tier: recommended
repo: https://github.com/meshtastic/firmware

View File

@ -0,0 +1,77 @@
app:
id: netbird-dashboard
name: NetBird Dashboard
version: "2.38.0"
description: NetBird management dashboard (SPA). Internal stack member served through the netbird proxy.
category: networking
# Hyphen name matches runtime references + the live container (adoption).
# Alias `netbird-dashboard` is the short hostname the proxy's nginx proxies to.
container_name: netbird-dashboard
container:
image: docker.io/netbirdio/dashboard:v2.38.0
pull_policy: if-not-present
network: netbird-net
network_aliases: [netbird-dashboard]
# The dashboard SPA bakes its API/OIDC base URL from these at container
# start. They must point at the proxy's public HTTPS origin (8087) so the
# browser uses a secure context (window.crypto.subtle / OIDC PKCE, #15).
# {{HOST_IP}} is the node's primary host IP, resolved at apply time.
derived_env:
- key: NETBIRD_MGMT_API_ENDPOINT
template: "https://{{HOST_IP}}:8087"
- key: NETBIRD_MGMT_GRPC_API_ENDPOINT
template: "https://{{HOST_IP}}:8087"
- key: AUTH_AUTHORITY
template: "https://{{HOST_IP}}:8087/oauth2"
dependencies:
- app_id: netbird-server
resources:
memory_limit: 256Mi
security:
# cap-drop=ALL is applied by the orchestrator. The dashboard image runs
# nginx (master as root, drops workers) binding :80 — needs the worker-drop
# caps + NET_BIND_SERVICE for the privileged port.
capabilities: [CHOWN, DAC_OVERRIDE, SETGID, SETUID, NET_BIND_SERVICE]
readonly_root: false
network_policy: isolated
# Internal only — reached container-to-container by the proxy via netbird-net.
ports: []
volumes: []
environment:
- AUTH_AUDIENCE=netbird-dashboard
- AUTH_CLIENT_ID=netbird-dashboard
- AUTH_CLIENT_SECRET=
- USE_AUTH0=false
- AUTH_SUPPORTED_SCOPES=openid profile email groups
- AUTH_REDIRECT_URI=/nb-auth
- AUTH_SILENT_REDIRECT_URI=/nb-silent-auth
- NETBIRD_TOKEN_SOURCE=idToken
- NGINX_SSL_PORT=443
- LETSENCRYPT_DOMAIN=none
health_check:
type: tcp
endpoint: localhost:80
interval: 30s
timeout: 5s
retries: 5
start_period: 20s
metadata:
author: NetBird
icon: /assets/img/app-icons/netbird.svg
website: https://netbird.io
repo: https://github.com/netbirdio/dashboard
license: BSD-3-Clause
tags:
- networking
- vpn
- dashboard

View File

@ -0,0 +1,122 @@
app:
id: netbird-server
name: NetBird Server
version: "0.71.2"
description: NetBird combined management / signal / relay server with an embedded identity provider and STUN. Backend for the self-hosted NetBird mesh VPN.
category: networking
# Hyphen name matches the runtime references (crash_recovery / dependencies /
# config startup order) + the live container, so on an existing node the
# orchestrator ADOPTS the running server rather than recreating it (data +
# the sqlite store under /var/lib/netbird preserved). Alias `netbird-server`
# is the short hostname the proxy's nginx proxies/grpc-passes to.
container_name: netbird-server
container:
image: docker.io/netbirdio/netbird-server:0.71.2
pull_policy: if-not-present
network: netbird-net
network_aliases: [netbird-server]
# The relay authSecret and the sqlite store encryptionKey are base64 keys
# (the server base64-decodes them to recover raw bytes — hex would decode to
# the wrong value). Generated once and reused: ensure_generated_secrets
# no-ops when the file already exists, so a re-render of config.yaml on an
# adopted node keeps the same keys (regenerating would orphan the store).
generated_secrets:
- name: netbird-relay-auth-secret
kind: base64
- name: netbird-store-encryption-key
kind: base64
# Pass the rendered config explicitly, mirroring the legacy `--config` arg.
custom_args: ["--config", "/etc/netbird/config.yaml"]
dependencies:
- storage: 1Gi
resources:
memory_limit: 1Gi
security:
# cap-drop=ALL is applied by the orchestrator. The server binds :80
# (management/signal/relay HTTP + gRPC) inside the container — a privileged
# port — so it needs NET_BIND_SERVICE. STUN is 3478/udp (unprivileged).
capabilities: [NET_BIND_SERVICE]
readonly_root: false
network_policy: isolated
ports:
- host: 8086
container: 80
protocol: tcp # management API + embedded OIDC issuer (/oauth2)
- host: 3478
container: 3478
protocol: udp # STUN — must be UDP; tcp here breaks relay discovery
volumes:
- type: bind
source: /var/lib/archipelago/netbird/data
target: /var/lib/netbird
options: [rw]
# The rendered config.yaml, read-only. Re-rendered on every reconcile from
# host facts + the base64 secrets; idempotent (stable bytes → no restart).
- type: bind
source: /var/lib/archipelago/netbird/config.yaml
target: /etc/netbird/config.yaml
options: [ro]
environment: []
# The server's config. {{HOST_IP}} is the node's primary host IP (the proxy's
# public origin is https on 8087 — the dashboard needs a secure context for
# OIDC PKCE, issue #15). {{secret:...}} are read 0600 from the secrets dir.
files:
- path: /var/lib/archipelago/netbird/config.yaml
overwrite: true
content: |
server:
listenAddress: ":80"
exposedAddress: "https://{{HOST_IP}}:8087"
stunPorts:
- 3478
metricsPort: 9090
healthcheckAddress: ":9000"
logLevel: "info"
logFile: "console"
authSecret: "{{secret:netbird-relay-auth-secret}}"
dataDir: "/var/lib/netbird"
auth:
issuer: "https://{{HOST_IP}}:8087/oauth2"
localAuthDisabled: false
signKeyRefreshEnabled: false
dashboardRedirectURIs:
- "https://{{HOST_IP}}:8087/nb-auth"
- "https://{{HOST_IP}}:8087/nb-silent-auth"
dashboardPostLogoutRedirectURIs:
- "https://{{HOST_IP}}:8087/"
cliRedirectURIs:
- "http://localhost:53000/"
store:
engine: "sqlite"
encryptionKey: "{{secret:netbird-store-encryption-key}}"
# TCP liveness on the management port. Binds at startup, stays green; an http
# check of /oauth2 would false-fail while the issuer warms up.
health_check:
type: tcp
endpoint: localhost:80
interval: 30s
timeout: 5s
retries: 10
start_period: 30s
metadata:
author: NetBird
icon: /assets/img/app-icons/netbird.svg
website: https://netbird.io
repo: https://github.com/netbirdio/netbird
license: BSD-3-Clause
tags:
- networking
- vpn
- wireguard
- mesh

182
apps/netbird/manifest.yml Normal file
View File

@ -0,0 +1,182 @@
app:
id: netbird
name: NetBird
version: "2.38.0"
description: Self-hosted WireGuard mesh VPN control plane with dashboard, embedded identity provider, management API, signal, relay, and STUN. The user-facing entry point — a TLS proxy in front of the dashboard + server.
category: networking
# The user-facing launcher (app_id + container both "netbird", matching the
# runtime references + the live container so the orchestrator adopts it). This
# is the nginx that terminates TLS on 8087 and fans out to the dashboard +
# server by their short aliases on netbird-net.
container_name: netbird
container:
image: docker.io/library/nginx:1.27-alpine
pull_policy: if-not-present
network: netbird-net
# Self-signed TLS cert materialised before create — the dashboard needs a
# secure context (window.crypto.subtle / OIDC PKCE, issue #15), so the proxy
# serves HTTPS. Idempotent: kept as-is when crt+key already exist (a user
# accepts it once). SAN defaults to the host IP + 127.0.0.1 + localhost.
generated_certs:
- crt: /var/lib/archipelago/netbird/tls.crt
key: /var/lib/archipelago/netbird/tls.key
dependencies:
- app_id: netbird-server
- app_id: netbird-dashboard
- storage: 1Gi
resources:
memory_limit: 256Mi
security:
# cap-drop=ALL is applied by the orchestrator. nginx (master as root, drops
# workers) binds :443 — needs the worker-drop caps + NET_BIND_SERVICE.
capabilities: [CHOWN, DAC_OVERRIDE, SETGID, SETUID, NET_BIND_SERVICE]
readonly_root: false
network_policy: isolated
ports:
# 8087 publishes the TLS listener (container :443). HTTPS is required for the
# dashboard's secure context (issue #15).
- host: 8087
container: 443
protocol: tcp
volumes:
- type: bind
source: /var/lib/archipelago/netbird/nginx.conf
target: /etc/nginx/conf.d/default.conf
options: [ro]
- type: bind
source: /var/lib/archipelago/netbird/tls.crt
target: /etc/nginx/tls.crt
options: [ro]
- type: bind
source: /var/lib/archipelago/netbird/tls.key
target: /etc/nginx/tls.key
options: [ro]
environment: []
# The proxy config. {{NETWORK_GATEWAY}} is the netbird-net bridge gateway =
# Podman's aardvark DNS. nginx uses it as an explicit `resolver` with VARIABLE
# upstreams so it re-resolves container names per request — without it nginx
# pins a container IP at startup and 502s forever once that IP moves on a
# restart/reboot (issue #15, observed live on .198). Every #15 fix below
# (CORS $http_origin reflect, grpc pass, nb-auth/nb-silent-auth rewrite to
# index.html, /relay websocket) is preserved verbatim from the legacy config.
files:
- path: /var/lib/archipelago/netbird/nginx.conf
overwrite: true
content: |
server {
listen 443 ssl;
server_name _;
# netbird's dashboard needs a secure context (window.crypto.subtle for
# OIDC PKCE), so the proxy terminates TLS with a self-signed cert (#15).
ssl_certificate /etc/nginx/tls.crt;
ssl_certificate_key /etc/nginx/tls.key;
# Rootless Podman can hand a container a new IP across restarts/reboots.
# nginx resolves a literal upstream name ONCE at startup and caches it,
# so after the IP moves every request 502s with "host unreachable"
# (issue #15, observed live on .198: nginx pinned to a dead
# netbird-dashboard IP). Fix: point `resolver` at the netbird-net
# gateway (Podman's aardvark DNS) and use VARIABLE upstreams, which
# forces nginx to re-resolve the container names at request time.
resolver {{NETWORK_GATEWAY}} valid=10s ipv6=off;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
proxy_http_version 1.1;
location ~ ^/(relay|ws-proxy/) {
set $nb_server netbird-server;
proxy_pass http://$nb_server:80;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
proxy_read_timeout 1d;
}
location ~ ^/(api|oauth2)(/|$) {
# The dashboard is a SPA whose API/OIDC base URL is baked at build
# time to one host:port. A single box is reached via several
# addresses, so those fetches are cross-origin and the browser
# blocks them with no Access-Control-Allow-Origin (#15, live on
# .198). Reflect the caller's Origin and answer the CORS preflight.
if ($request_method = OPTIONS) {
add_header Access-Control-Allow-Origin $http_origin always;
add_header Access-Control-Allow-Credentials true always;
add_header Access-Control-Allow-Methods "GET, POST, PUT, PATCH, DELETE, OPTIONS" always;
add_header Access-Control-Allow-Headers "Authorization, Content-Type, Accept" always;
add_header Access-Control-Max-Age 86400 always;
add_header Content-Length 0;
return 204;
}
add_header Access-Control-Allow-Origin $http_origin always;
add_header Access-Control-Allow-Credentials true always;
add_header Access-Control-Allow-Methods "GET, POST, PUT, PATCH, DELETE, OPTIONS" always;
add_header Access-Control-Allow-Headers "Authorization, Content-Type, Accept" always;
set $nb_server netbird-server;
proxy_pass http://$nb_server:80;
}
location ~ ^/(signalexchange\.SignalExchange|management\.ManagementService|management\.ProxyService)/ {
set $nb_server netbird-server;
grpc_pass grpc://$nb_server:80;
grpc_read_timeout 1d;
grpc_send_timeout 1d;
}
# OIDC callback routes are client-side SPA routes with NO prebuilt page
# in the dashboard bundle, so proxying them straight through 404s —
# which crashes the dashboard's auth init and shows "Unauthenticated"
# with dead buttons (#15, live on .198: /nb-auth + /nb-silent-auth
# returned 404). Serve index.html at these paths (URL unchanged) so
# react-oidc boots and completes the login / silent-SSO.
location ~ ^/(nb-auth|nb-silent-auth) {
set $nb_dashboard netbird-dashboard;
rewrite ^.*$ /index.html break;
proxy_pass http://$nb_dashboard:80;
}
location / {
set $nb_dashboard netbird-dashboard;
proxy_pass http://$nb_dashboard:80;
}
}
health_check:
type: tcp
endpoint: localhost:443
interval: 30s
timeout: 5s
retries: 5
start_period: 20s
interfaces:
main:
name: Dashboard
description: Manage your self-hosted NetBird mesh VPN
type: ui
port: 8087
protocol: https
path: /
metadata:
author: NetBird
icon: /assets/img/app-icons/netbird.svg
website: https://netbird.io
repo: https://github.com/netbirdio/netbird
license: BSD-3-Clause
tags:
- networking
- vpn
- wireguard
- mesh

3168
core/Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@ -1,6 +1,6 @@
[package]
name = "archipelago"
version = "1.7.89-alpha"
version = "1.7.99-alpha"
edition = "2021"
description = "Archipelago Bitcoin Node OS - Native backend"
authors = ["Archipelago Team"]
@ -9,6 +9,16 @@ authors = ["Archipelago Team"]
name = "archipelago"
path = "src/main.rs"
[features]
default = []
# DHT Phase 2: iroh-blobs peer swarm engine. OFF by default — it pulls a heavy
# QUIC dependency tree, so it ships behind a flag for PoC/measurement on a
# scratch node before any fleet rollout. With the flag off, swarm::providers()
# is empty and every fetch goes straight to the origin HTTP path (today's
# behaviour). Attach the optional iroh / iroh-blobs deps to this feature when
# wiring the IrohProvider.
iroh-swarm = ["dep:iroh", "dep:iroh-blobs"]
[dependencies]
# Core dependencies
tokio = { version = "1", features = ["full"] }
@ -42,6 +52,7 @@ archipelago-performance = { path = "../performance" }
# Authentication
bcrypt = "0.15"
sha2 = "0.10.9"
blake3 = "1"
hmac = "0.12.1"
uuid = { version = "1.0", features = ["v4"] }
regex = "1.10"
@ -64,7 +75,7 @@ serde_yaml = "0.9"
# HTTP client (for LND REST proxy, Tor SOCKS for peer messaging)
# Uses rustls-tls for cross-compilation (no OpenSSL dependency)
reqwest = { version = "0.11", default-features = false, features = ["json", "socks", "rustls-tls"] }
reqwest = { version = "0.11", default-features = false, features = ["json", "socks", "rustls-tls", "stream"] }
# Nostr (node discovery + NIP-44 encrypted peer handshake)
nostr-sdk = { version = "0.44", features = ["nip04", "nip44"] }
@ -106,6 +117,12 @@ sd-notify = "0.4"
# Trait objects for async methods (container orchestrator trait, Step 4)
async-trait = "0.1"
# DHT Phase 2: iroh-blobs peer swarm engine. OPTIONAL — only pulled in by the
# `iroh-swarm` feature (off by default). Heavy QUIC dep tree; kept behind the
# flag so the default fleet build is unaffected until the PoC is measured.
iroh = { version = "1", optional = true }
iroh-blobs = { version = "0.103", optional = true }
[dev-dependencies]
tokio-test = "0.4"
tempfile = "3.10"

View File

@ -66,6 +66,21 @@ impl ApiHandler {
.and_then(|v| v.to_str().ok())
.map(|s| s.to_string());
// Extract a paid-entitlement gate token from X-Invoice-Hash (Lightning)
// or X-Onchain-Address (on-chain) — both authorize the download if this
// node issued+settled them, and both resolve against the same shared
// entitlement store keyed by the token string (#46).
let invoice_hash = headers
.get("x-invoice-hash")
.and_then(|v| v.to_str().ok())
.map(|s| s.to_string())
.or_else(|| {
headers
.get("x-onchain-address")
.and_then(|v| v.to_str().ok())
.map(|s| s.to_string())
});
// Extract federation peer DID from X-Federation-DID header
let peer_did = headers
.get("x-federation-did")
@ -82,6 +97,7 @@ impl ApiHandler {
&config.data_dir,
content_id,
payment_token.as_deref(),
invoice_hash.as_deref(),
peer_did.as_deref(),
range,
)
@ -130,7 +146,9 @@ impl ApiHandler {
Ok(content_server::ServeResult::Forbidden) => Ok(build_response(
StatusCode::FORBIDDEN,
"application/json",
hyper::Body::from(r#"{"error":"Access denied — federation peer required"}"#),
hyper::Body::from(
r#"{"error":"This file is shared with the host's federation peers only. Federate with that node (exchange invites) so it recognizes you, then try again."}"#,
),
)),
Ok(content_server::ServeResult::NotFound) | Err(_) => Ok(build_response(
StatusCode::NOT_FOUND,
@ -140,6 +158,259 @@ impl ApiHandler {
}
}
/// Seller side (#46): mint a Lightning invoice for a paid catalog item so a
/// buyer can pay from any external wallet. Path: GET /content/{id}/invoice.
/// Records a pending entitlement keyed by the invoice's payment hash.
pub(super) async fn handle_content_invoice(&self, path: &str) -> Result<Response<hyper::Body>> {
let content_id = path
.strip_prefix("/content/")
.and_then(|s| s.strip_suffix("/invoice"))
.unwrap_or("");
if content_id.is_empty() || !is_valid_app_id(content_id) {
return Ok(build_response(
StatusCode::BAD_REQUEST,
"text/plain",
hyper::Body::from("Invalid content ID"),
));
}
let catalog = content_server::load_catalog(&self.config.data_dir)
.await
.unwrap_or_default();
let item = match catalog.items.iter().find(|i| i.id == content_id) {
Some(i) => i,
None => {
return Ok(build_response(
StatusCode::NOT_FOUND,
"text/plain",
hyper::Body::from("Content not found"),
))
}
};
let price_sats = match &item.access {
content_server::AccessControl::Paid { price_sats } => *price_sats,
_ => {
// Not a paid item — no invoice to issue.
return Ok(build_response(
StatusCode::BAD_REQUEST,
"application/json",
hyper::Body::from(r#"{"error":"Item is not paid"}"#),
));
}
};
let memo = format!("Archipelago peer file {content_id}");
match self
.rpc_handler
.create_invoice(price_sats as i64, &memo)
.await
{
Ok((bolt11, payment_hash)) if !payment_hash.is_empty() => {
crate::content_invoice::record_pending(&payment_hash, content_id, price_sats).await;
let body = serde_json::json!({
"bolt11": bolt11,
"payment_hash": payment_hash,
"price_sats": price_sats,
});
Ok(build_response(
StatusCode::OK,
"application/json",
hyper::Body::from(serde_json::to_vec(&body).unwrap_or_default()),
))
}
Ok(_) => Ok(build_response(
StatusCode::INTERNAL_SERVER_ERROR,
"application/json",
hyper::Body::from(r#"{"error":"Invoice missing payment hash"}"#),
)),
Err(e) => {
// Surface the FULL error chain ({:#}) — the generic top-level
// message hid the real cause (e.g. the LND REST connection
// failing), which made this 503 undiagnosable.
tracing::warn!("content invoice creation failed: {e:#}");
let body = serde_json::json!({
"error": format!("Could not create invoice: {e:#}")
});
Ok(build_response(
StatusCode::SERVICE_UNAVAILABLE,
"application/json",
hyper::Body::from(serde_json::to_vec(&body).unwrap_or_default()),
))
}
}
}
/// Seller side (#46): report whether a previously-issued invoice has settled.
/// Path: GET /content/{id}/invoice-status/{payment_hash}. On settlement the
/// entitlement is marked paid so the buyer can then download the file.
pub(super) async fn handle_content_invoice_status(
&self,
path: &str,
) -> Result<Response<hyper::Body>> {
let rest = path.strip_prefix("/content/").unwrap_or("");
let (content_id, payment_hash) = match rest.split_once("/invoice-status/") {
Some((id, hash)) => (id, hash),
None => {
return Ok(build_response(
StatusCode::BAD_REQUEST,
"text/plain",
hyper::Body::from("Invalid request"),
))
}
};
if content_id.is_empty() || !is_valid_app_id(content_id) || payment_hash.is_empty() {
return Ok(build_response(
StatusCode::BAD_REQUEST,
"text/plain",
hyper::Body::from("Invalid request"),
));
}
// The hash must be one we issued for exactly this content item.
match crate::content_invoice::lookup(payment_hash).await {
Some((cid, _)) if cid == content_id => {}
_ => {
return Ok(build_response(
StatusCode::NOT_FOUND,
"application/json",
hyper::Body::from(r#"{"error":"Unknown invoice"}"#),
))
}
}
// Already paid? Otherwise ask our LND and persist the result.
let mut paid = crate::content_invoice::is_paid_for(payment_hash, content_id).await;
if !paid {
if let Ok(true) = self.rpc_handler.invoice_is_settled(payment_hash).await {
crate::content_invoice::mark_paid(payment_hash).await;
paid = true;
}
}
let body = serde_json::json!({ "paid": paid });
Ok(build_response(
StatusCode::OK,
"application/json",
hyper::Body::from(serde_json::to_vec(&body).unwrap_or_default()),
))
}
/// Seller side (#46): issue a fresh on-chain address for a paid catalog item
/// so a buyer can pay on-chain. Path: GET /content/{id}/onchain. Records a
/// pending entitlement keyed by the address; price doubles as expected amount.
pub(super) async fn handle_content_onchain(&self, path: &str) -> Result<Response<hyper::Body>> {
let content_id = path
.strip_prefix("/content/")
.and_then(|s| s.strip_suffix("/onchain"))
.unwrap_or("");
if content_id.is_empty() || !is_valid_app_id(content_id) {
return Ok(build_response(
StatusCode::BAD_REQUEST,
"text/plain",
hyper::Body::from("Invalid content ID"),
));
}
let catalog = content_server::load_catalog(&self.config.data_dir)
.await
.unwrap_or_default();
let price_sats = match catalog.items.iter().find(|i| i.id == content_id) {
Some(i) => match &i.access {
content_server::AccessControl::Paid { price_sats } => *price_sats,
_ => {
return Ok(build_response(
StatusCode::BAD_REQUEST,
"application/json",
hyper::Body::from(r#"{"error":"Item is not paid"}"#),
))
}
},
None => {
return Ok(build_response(
StatusCode::NOT_FOUND,
"text/plain",
hyper::Body::from("Content not found"),
))
}
};
match self.rpc_handler.new_onchain_address().await {
Ok(address) if !address.is_empty() => {
crate::content_invoice::record_pending(&address, content_id, price_sats).await;
let body = serde_json::json!({
"address": address,
"amount_sats": price_sats,
});
Ok(build_response(
StatusCode::OK,
"application/json",
hyper::Body::from(serde_json::to_vec(&body).unwrap_or_default()),
))
}
_ => {
let body = serde_json::json!({
"error": "Could not generate an on-chain address (is the wallet ready?)"
});
Ok(build_response(
StatusCode::SERVICE_UNAVAILABLE,
"application/json",
hyper::Body::from(serde_json::to_vec(&body).unwrap_or_default()),
))
}
}
}
/// Seller side (#46): report whether an on-chain payment to a previously-
/// issued address has arrived (>= price, >= 1 conf). Path:
/// GET /content/{id}/onchain-status/{address}. Marks the entitlement paid.
pub(super) async fn handle_content_onchain_status(
&self,
path: &str,
) -> Result<Response<hyper::Body>> {
let rest = path.strip_prefix("/content/").unwrap_or("");
let (content_id, address) = match rest.split_once("/onchain-status/") {
Some((id, addr)) => (id, addr),
None => {
return Ok(build_response(
StatusCode::BAD_REQUEST,
"text/plain",
hyper::Body::from("Invalid request"),
))
}
};
if content_id.is_empty() || !is_valid_app_id(content_id) || address.is_empty() {
return Ok(build_response(
StatusCode::BAD_REQUEST,
"text/plain",
hyper::Body::from("Invalid request"),
));
}
// The address must be one we issued for exactly this content item.
let price = match crate::content_invoice::lookup(address).await {
Some((cid, price)) if cid == content_id => price,
_ => {
return Ok(build_response(
StatusCode::NOT_FOUND,
"application/json",
hyper::Body::from(r#"{"error":"Unknown address"}"#),
))
}
};
let mut paid = crate::content_invoice::is_paid_for(address, content_id).await;
if !paid {
if let Ok(true) = self.rpc_handler.onchain_received(address, price).await {
crate::content_invoice::mark_paid(address).await;
paid = true;
}
}
let body = serde_json::json!({ "paid": paid });
Ok(build_response(
StatusCode::OK,
"application/json",
hyper::Body::from(serde_json::to_vec(&body).unwrap_or_default()),
))
}
/// Serve a degraded preview of paid content (blurred image or first 2% of video).
pub(super) async fn handle_content_preview(
path: &str,
@ -190,6 +461,14 @@ impl ApiHandler {
.body(hyper::Body::from(bytes))
.unwrap())
}
Ok(content_server::PreviewResult::PreviewUnavailable) => Ok(Response::builder()
.status(StatusCode::UNSUPPORTED_MEDIA_TYPE)
.header("Content-Type", "text/plain")
.header("X-Content-Preview", "unavailable")
.body(hyper::Body::from(
"Preview unavailable for this media (needs re-encoding)",
))
.unwrap()),
Ok(content_server::PreviewResult::NotFound) | Err(_) => Ok(build_response(
StatusCode::NOT_FOUND,
"text/plain",

View File

@ -44,6 +44,11 @@ pub struct ApiHandler {
session_store: SessionStore,
/// Broadcast channel for relaying companion app input to remote browsers.
input_relay_tx: broadcast::Sender<String>,
/// Reverse broadcast channel: the kiosk browser publishes "open this URL
/// externally" requests here, and the companion (phone) socket forwards them
/// to the phone's default browser. Lets "open in external browser" apps —
/// which the kiosk can't usefully open itself — launch on the controller.
external_open_tx: broadcast::Sender<String>,
/// Content-addressed blob store for attachments shared over mesh/federation.
blob_store: Arc<BlobStore>,
/// Our own node pubkey (hex) — used to self-sign debug/test capabilities.
@ -71,6 +76,7 @@ impl ApiHandler {
.await?,
);
let (input_relay_tx, _) = broadcast::channel(64);
let (external_open_tx, _) = broadcast::channel(16);
// Derive a blob-store capability key from the node's Ed25519 signing
// key. SHA-256 domain-separated so rotating the identity rotates
@ -100,6 +106,7 @@ impl ApiHandler {
metrics_store,
session_store,
input_relay_tx,
external_open_tx,
blob_store,
self_pubkey_hex,
})
@ -202,6 +209,27 @@ impl ApiHandler {
.unwrap()
}
/// A 401 that still carries CORS headers, for endpoints fetched
/// cross-origin by same-node app UIs (e.g. the LND wallet UI on its own
/// port). Without the ACAO header the browser surfaces an opaque CORS
/// error instead of the 401, so the app can't tell it just needs auth.
/// `origin` is the already-validated reflect value from `app_cors_origin`
/// (empty string when the origin isn't allowed → no CORS header added).
fn unauthorized_cors(origin: &str) -> Response<hyper::Body> {
let body = serde_json::json!({ "error": "Unauthorized" });
let body_bytes = serde_json::to_vec(&body).unwrap_or_default();
let mut builder = Response::builder()
.status(StatusCode::UNAUTHORIZED)
.header("Content-Type", "application/json")
.header("Vary", "Origin");
if !origin.is_empty() {
builder = builder
.header("Access-Control-Allow-Origin", origin)
.header("Access-Control-Allow-Credentials", "true");
}
builder.body(hyper::Body::from(body_bytes)).unwrap()
}
/// Allowed CORS origins derived from the config host IP.
fn allowed_origins(&self) -> Vec<String> {
let mut origins = vec![
@ -256,6 +284,45 @@ impl ApiHandler {
}
}
/// CORS origin to echo for same-node app → backend calls (e.g. the LND
/// wallet UI, served on its own APP_PORTS port). Such apps share the node's
/// host but use a different port, so the strict allowlist (`host_ip`, no
/// port) rejects them and the browser gets no `Access-Control-Allow-Origin`
/// header ("blocked by CORS policy"). Reflect the Origin when its host
/// matches the request's own `Host` header — i.e. the app lives on the same
/// address the node is being reached by, which transparently covers the LAN
/// IP, the Tailscale IP, localhost, and the `.onion` address without needing
/// to enumerate them. Auth is still enforced by the session cookie; this
/// only authorizes the browser to *read* the reply. Returns "" (no echoed
/// origin) when there is no match.
fn app_cors_origin(&self, headers: &hyper::HeaderMap) -> String {
if let Some(origin) = self.validate_origin(headers) {
return origin;
}
let Some(origin) = headers.get("origin").and_then(|v| v.to_str().ok()) else {
return String::new();
};
// host portion (no scheme, no port) of an `scheme://host[:port]` value
let host_of = |s: &str| -> Option<String> {
let after_scheme = s.split_once("://").map(|(_, r)| r).unwrap_or(s);
let host_port = after_scheme.split('/').next().unwrap_or(after_scheme);
let host = host_port
.rsplit_once(':')
.map(|(h, _)| h)
.unwrap_or(host_port);
(!host.is_empty()).then(|| host.to_string())
};
let origin_host = host_of(origin);
let req_host = headers
.get(hyper::header::HOST)
.and_then(|v| v.to_str().ok())
.and_then(host_of);
match (origin_host, req_host) {
(Some(o), Some(r)) if o == r => origin.to_string(),
_ => String::new(),
}
}
pub async fn handle_request(&self, req: Request<hyper::Body>) -> Result<Response<hyper::Body>> {
let path = req.uri().path().to_string();
let method = req.method().clone();
@ -265,9 +332,10 @@ impl ApiHandler {
let mut builder = Response::builder()
.status(StatusCode::NO_CONTENT)
.header("Vary", "Origin");
if let Some(origin) = self.validate_origin(req.headers()) {
let preflight_origin = self.app_cors_origin(req.headers());
if !preflight_origin.is_empty() {
builder = builder
.header("Access-Control-Allow-Origin", &origin)
.header("Access-Control-Allow-Origin", &preflight_origin)
.header("Access-Control-Allow-Methods", "GET, POST, OPTIONS")
.header("Access-Control-Allow-Headers", "Content-Type, X-CSRF-Token")
.header("Access-Control-Allow-Credentials", "true");
@ -295,7 +363,12 @@ impl ApiHandler {
tracing::warn!("401 WebSocket /ws/remote-input — session invalid or missing");
return Ok(Self::unauthorized());
}
return Self::handle_remote_input(req, self.input_relay_tx.clone()).await;
return Self::handle_remote_input(
req,
self.input_relay_tx.clone(),
self.external_open_tx.subscribe(),
)
.await;
}
// Remote relay WebSocket — browser receives companion input events
@ -304,7 +377,12 @@ impl ApiHandler {
tracing::warn!("401 WebSocket /ws/remote-relay — session invalid or missing");
return Ok(Self::unauthorized());
}
return Self::handle_remote_relay(req, self.input_relay_tx.subscribe()).await;
return Self::handle_remote_relay(
req,
self.input_relay_tx.subscribe(),
self.external_open_tx.clone(),
)
.await;
}
// Convert body to bytes for non-WS routes
@ -419,6 +497,22 @@ impl ApiHandler {
Self::handle_content_preview(p, &self.config).await
}
// Lightning-invoice peer-file sale (#46): mint invoice / poll settlement
(Method::GET, p) if p.starts_with("/content/") && p.ends_with("/invoice") => {
self.handle_content_invoice(p).await
}
(Method::GET, p) if p.starts_with("/content/") && p.contains("/invoice-status/") => {
self.handle_content_invoice_status(p).await
}
// On-chain peer-file sale (#46): issue address / poll for payment
(Method::GET, p) if p.starts_with("/content/") && p.contains("/onchain-status/") => {
self.handle_content_onchain_status(p).await
}
(Method::GET, p) if p.starts_with("/content/") && p.ends_with("/onchain") => {
self.handle_content_onchain(p).await
}
// Content serving — peers access shared content over Tor (no session auth)
(Method::GET, p) if p.starts_with("/content/") => {
Self::handle_content_request(p, &headers, &self.config).await
@ -448,7 +542,8 @@ impl ApiHandler {
// No backend auth check here because the LND UI iframe fetches this
// endpoint and the session cookie flow is validated at the nginx layer.
(Method::GET, "/lnd-connect-info") => {
Self::handle_lnd_connect_info(self.rpc_handler.clone()).await
let origin = self.app_cors_origin(&headers);
Self::handle_lnd_connect_info(self.rpc_handler.clone(), &origin).await
}
// Container logs — requires session
@ -460,13 +555,26 @@ impl ApiHandler {
Self::handle_container_logs_http(self.rpc_handler.clone(), path, &origin).await
}
// LND proxy — requires session
(Method::GET, path) if path.starts_with("/proxy/lnd/") => {
// Peer content streaming proxy — Range-streams a peer's media file
// so <video>/<audio> can seek/play (B3). Same-origin, session-gated.
(Method::GET, p) if p.starts_with("/api/peer-content/") => {
if !self.is_authenticated(&headers).await {
return Ok(Self::unauthorized());
}
let origin = self.validate_origin(&headers).unwrap_or_default();
Self::handle_lnd_proxy(path, &origin).await
self.handle_peer_content_stream(p, &headers).await
}
// LND proxy — requires session. The LND wallet UI calls this
// cross-origin from its own app port, so even the 401 must carry
// CORS headers; otherwise the browser reports a bare CORS failure
// ("No 'Access-Control-Allow-Origin' header") instead of a
// readable 401 the UI can act on.
(Method::GET, path) if path.starts_with("/proxy/lnd/") => {
let origin = self.app_cors_origin(&headers);
if !self.is_authenticated(&headers).await {
return Ok(Self::unauthorized_cors(&origin));
}
Self::handle_lnd_proxy(self.rpc_handler.clone(), path, &origin).await
}
// DWN health — unauthenticated

View File

@ -19,6 +19,8 @@ impl ApiHandler {
signature: Option<String>,
#[serde(default)]
encrypted: bool,
#[serde(default)]
msg_id: Option<String>,
}
let incoming: Incoming = serde_json::from_slice(&body).unwrap_or(Incoming {
from_pubkey: None,
@ -26,6 +28,7 @@ impl ApiHandler {
message: None,
signature: None,
encrypted: false,
msg_id: None,
});
if let (Some(from), Some(msg)) = (incoming.from_pubkey.as_ref(), incoming.message.as_ref())
{
@ -152,7 +155,13 @@ impl ApiHandler {
let clean_from = sanitize_html(from);
let clean_msg = sanitize_html(&plaintext);
let clean_name = incoming.from_name.as_deref().map(sanitize_html);
node_msg::store_received(&clean_from, &clean_msg, clean_name.as_deref()).await;
node_msg::store_received(
&clean_from,
&clean_msg,
clean_name.as_deref(),
incoming.msg_id.as_deref(),
)
.await;
}
Ok(build_response(
StatusCode::OK,

View File

@ -99,33 +99,61 @@ impl ApiHandler {
pub(super) async fn handle_lnd_connect_info(
rpc: std::sync::Arc<super::super::rpc::RpcHandler>,
cors_origin: &str,
) -> Result<Response<hyper::Body>> {
// The LND wallet UI is served on its own APP_PORTS origin and fetches
// this cross-origin, so it needs the CORS headers echoed back.
let cors = |builder: hyper::http::response::Builder| {
builder
.header("Access-Control-Allow-Origin", cors_origin)
.header("Access-Control-Allow-Credentials", "true")
.header("Vary", "Origin")
};
match rpc.handle_lnd_connect_info().await {
Ok(val) => {
let body = serde_json::to_vec(&val).unwrap_or_default();
Ok(build_response(
StatusCode::OK,
"application/json",
hyper::Body::from(body),
))
Ok(cors(
Response::builder()
.status(StatusCode::OK)
.header("Content-Type", "application/json"),
)
.body(hyper::Body::from(body))
.unwrap_or_else(|_| Response::new(hyper::Body::from("{}"))))
}
Err(e) => Ok(Response::builder()
.status(StatusCode::INTERNAL_SERVER_ERROR)
.header("Content-Type", "application/json")
.body(hyper::Body::from(
serde_json::json!({"error": e.to_string()}).to_string(),
))
.unwrap()),
Err(e) => Ok(cors(
Response::builder()
.status(StatusCode::INTERNAL_SERVER_ERROR)
.header("Content-Type", "application/json"),
)
.body(hyper::Body::from(
serde_json::json!({"error": e.to_string()}).to_string(),
))
.unwrap()),
}
}
pub(super) async fn handle_lnd_proxy(
rpc: Arc<RpcHandler>,
path: &str,
cors_origin: &str,
) -> Result<Response<hyper::Body>> {
let suffix = path.strip_prefix("/proxy/lnd").unwrap_or("/");
let url = format!("{LND_REST_BASE_URL}{suffix}");
match reqwest::get(&url).await {
// LND REST serves a self-signed cert and requires the admin macaroon.
// A bare reqwest::get() uses the default client, which rejects the
// self-signed cert (TLS verify error -> 502 "failing to fetch") and
// sends no macaroon. Use the shared authenticated client instead — the
// same one lnd.getinfo and the wallet RPCs use.
let request = match rpc.lnd_client().await {
Ok((client, macaroon_hex)) => client
.get(&url)
.header("Grpc-Metadata-macaroon", &macaroon_hex)
.send()
.await
.map_err(anyhow::Error::from),
Err(e) => Err(e),
};
match request {
Ok(resp) => {
let status = resp.status().as_u16();
let headers = resp.headers().clone();
@ -157,4 +185,84 @@ impl ApiHandler {
}
}
}
/// Range-streaming proxy for a peer's content file (B3). The browser's
/// `<video>`/`<audio>` element makes Range requests; we forward the Range
/// header to the peer's `/content/<id>` (which already returns 206 Partial
/// Content) and pass the bytes + Content-Range/Content-Type straight back.
/// This replaces the old path of downloading the whole file as base64 into
/// a non-seekable Blob URL, which broke playback/seeking for video and
/// large audio. Same-origin + session-authenticated (checked by caller).
/// Path: `/api/peer-content/<onion>/<content_id>`.
pub(super) async fn handle_peer_content_stream(
&self,
path: &str,
headers: &hyper::HeaderMap,
) -> Result<Response<hyper::Body>> {
let bad = |msg: &str| {
Ok(build_response(
StatusCode::BAD_REQUEST,
"application/json",
hyper::Body::from(serde_json::json!({ "error": msg }).to_string()),
))
};
let rest = path.strip_prefix("/api/peer-content/").unwrap_or("");
let (onion, content_id) = match rest.split_once('/') {
Some((o, c)) if !o.is_empty() && !c.is_empty() => (o, c),
_ => return bad("expected /api/peer-content/<onion>/<content_id>"),
};
// Validate to prevent SSRF / path traversal.
let onion_norm = onion.trim_end_matches(".onion");
let onion_ok = onion_norm.len() == 56
&& onion_norm
.bytes()
.all(|b| b.is_ascii_lowercase() || b.is_ascii_digit());
let id_ok = !content_id.contains("..")
&& content_id
.bytes()
.all(|b| b.is_ascii_alphanumeric() || matches!(b, b'-' | b'_' | b'.'));
if !onion_ok || !id_ok {
return bad("invalid onion or content id");
}
let fips_npub = crate::federation::fips_npub_for_onion(&self.config.data_dir, onion).await;
let peer_path = format!("/content/{}", content_id);
// Generous overall timeout: this endpoint serves both seek/Range
// playback (small, finishes fast) and full-file downloads of large
// media (#38). 60s was too tight for a multi-hundred-MB transfer over
// Tor and aborted the download mid-stream.
let mut req = crate::fips::dial::PeerRequest::new(fips_npub.as_deref(), onion, &peer_path)
.service(crate::settings::transport::PeerService::PeerFiles)
.timeout(std::time::Duration::from_secs(900));
if let Some(r) = headers.get("range").and_then(|v| v.to_str().ok()) {
req = req.header("Range", r.to_string());
}
match req.send_get().await {
Ok((resp, _transport)) => {
let status = resp.status().as_u16();
let rh = resp.headers().clone();
let mut builder = Response::builder()
.status(status)
.header("Accept-Ranges", "bytes");
for h in ["content-type", "content-range", "content-length"] {
if let Some(v) = rh.get(h).and_then(|v| v.to_str().ok()) {
builder = builder.header(h, v);
}
}
// Stream the peer's body straight through instead of buffering
// the whole file into memory (#38). For a 178MB download the old
// `resp.bytes().await` allocated the entire file on the node
// before sending a byte; `wrap_stream` forwards chunks as they
// arrive, with constant memory.
Ok(builder
.body(hyper::Body::wrap_stream(resp.bytes_stream()))
.unwrap_or_else(|_| Response::new(hyper::Body::empty())))
}
Err(e) => Ok(build_response(
StatusCode::BAD_GATEWAY,
"application/json",
hyper::Body::from(serde_json::json!({ "error": e.to_string() }).to_string()),
)),
}
}
}

View File

@ -211,6 +211,7 @@ impl ApiHandler {
pub(super) async fn handle_remote_input(
req: Request<hyper::Body>,
relay_tx: broadcast::Sender<String>,
mut external_open_rx: broadcast::Receiver<String>,
) -> Result<Response<hyper::Body>> {
// Extract optional player ID from query string: /ws/remote-input?p=1
let player_id: Option<u8> = req
@ -266,6 +267,19 @@ impl ApiHandler {
break;
}
}
// Forward kiosk "open this URL externally" requests down to
// the companion so the link opens in the phone's browser.
ext = external_open_rx.recv() => {
match ext {
Ok(text) => {
if tx.send(Message::Text(text)).await.is_err() {
break;
}
}
Err(broadcast::error::RecvError::Lagged(_)) => {}
Err(broadcast::error::RecvError::Closed) => {}
}
}
msg = rx.next() => {
match msg {
Some(Ok(Message::Text(text))) => {

View File

@ -11,9 +11,16 @@ use super::ApiHandler;
impl ApiHandler {
/// WebSocket endpoint for browser clients to receive relayed companion input.
/// The browser's remote-relay.ts dispatches these as DOM keyboard/mouse events.
///
/// The kiosk also uses this socket in the *reverse* direction: when an "open
/// in external browser" app is launched, the kiosk can't usefully open it
/// itself, so it sends `{"t":"o","url":"https://…"}` here. We validate the
/// URL and publish it on `external_open_tx`, which the companion (phone)
/// socket forwards so the link opens in the phone's default browser.
pub(super) async fn handle_remote_relay(
req: Request<hyper::Body>,
mut relay_rx: broadcast::Receiver<String>,
external_open_tx: broadcast::Sender<String>,
) -> Result<Response<hyper::Body>> {
let (response, ws_fut_opt) = hyper_ws_listener::create_ws(req)
.map_err(|e| anyhow::anyhow!("WebSocket upgrade failed: {}", e))?;
@ -63,10 +70,20 @@ impl ApiHandler {
Err(broadcast::error::RecvError::Closed) => break,
}
}
// Handle client-side messages (pong, close)
// Handle client-side messages (pong, close, open-url requests)
client_msg = rx.next() => {
match client_msg {
Some(Ok(Message::Pong(_))) | Some(Ok(Message::Ping(_))) => {}
Some(Ok(Message::Text(text))) => {
// The only kiosk→server message we accept is an
// external-open request: {"t":"o","url":"https://…"}.
if let Some(url) = parse_open_url(&text) {
debug!("Relaying external-open to companion: {}", url);
let _ = external_open_tx.send(
format!(r#"{{"t":"o","url":{}}}"#, json_string(&url))
);
}
}
Some(Ok(Message::Close(_))) | None => break,
_ => {}
}
@ -81,3 +98,29 @@ impl ApiHandler {
Ok(response)
}
}
/// Parse a kiosk `{"t":"o","url":"…"}` external-open request, returning the URL
/// only if it's a well-formed http(s) URL. Anything else (other message tags,
/// non-http schemes like `javascript:`/`file:`, malformed JSON) is rejected so a
/// compromised kiosk page can't push arbitrary URIs to the phone.
fn parse_open_url(text: &str) -> Option<String> {
let v: serde_json::Value = serde_json::from_str(text).ok()?;
if v.get("t").and_then(|t| t.as_str()) != Some("o") {
return None;
}
let url = v.get("url").and_then(|u| u.as_str())?.trim();
if url.len() > 2048 {
return None;
}
let lower = url.to_ascii_lowercase();
if lower.starts_with("http://") || lower.starts_with("https://") {
Some(url.to_string())
} else {
None
}
}
/// Serialize a string as a JSON string literal (with surrounding quotes).
fn json_string(s: &str) -> String {
serde_json::Value::String(s.to_string()).to_string()
}

View File

@ -1,4 +1,4 @@
mod handler;
mod rpc;
pub(crate) mod rpc;
pub use handler::ApiHandler;

View File

@ -33,6 +33,19 @@ impl RpcHandler {
tracing::info!("[onboarding] login successful");
// Best-effort: heal a LOCKED LND wallet created with an unknown/legacy
// password by rotating it onto the per-node secret, using the password
// the user just authenticated with as a candidate. Non-blocking so login
// is never slowed or broken when LND isn't installed / already unlocked.
let candidate = password.to_string();
tokio::spawn(async move {
match crate::container::lnd::migrate_locked_wallet(&[candidate]).await {
Ok(true) => tracing::info!("[login] LND wallet healed / auto-unlocked"),
Ok(false) => {} // not locked, or seed-recovery required
Err(e) => tracing::debug!("[login] LND wallet migration skipped: {e}"),
}
});
// Ensure NostrVPN config exists — covers the case where onboardingComplete
// was never called (e.g., user took the "already set up" shortcut).
let data_dir = self.config.data_dir.clone();

View File

@ -107,7 +107,7 @@ struct TrustedRelayPeer {
}
#[derive(Debug, Clone)]
struct TxRelayCredentials {
pub(crate) struct TxRelayCredentials {
username: String,
password: String,
}
@ -648,7 +648,13 @@ async fn txrelay_credentials_available(data_dir: &Path) -> bool {
&& fs::metadata(&client_env_path).await.is_ok()
}
async fn ensure_txrelay_credentials(data_dir: &Path) -> Result<TxRelayCredentials> {
/// Idempotently ensure the tx-relay credential trio exists in the secrets dir:
/// the random password, its derived `rpcauth` line, and the client env file.
/// Bitcoin backend manifests reference `bitcoin-rpc-txrelay-rpcauth` as a
/// required `secret_env`, so this must run before bitcoind starts — otherwise
/// secret resolution hard-fails and the whole Bitcoin stack cascades (the .198
/// failure). Safe to call repeatedly; it only writes what's missing or stale.
pub(crate) async fn ensure_txrelay_credentials(data_dir: &Path) -> Result<TxRelayCredentials> {
let (password_path, rpcauth_path, client_env_path) = txrelay_secret_paths(data_dir);
let password = match read_trimmed(&password_path).await {
Some(value) => value,

View File

@ -171,6 +171,13 @@ impl RpcHandler {
// than the WebSocket-delivered package_data, which caused apps to flicker
// between "installed" and "not-installed" in the UI.
let (data, _) = self.state_manager.get_snapshot().await;
// Apps the user explicitly stopped must read as "stopped" even though a
// UI companion (electrs-ui, bitcoin-ui, …) keeps serving the launch port:
// launch_port_reachable() below would otherwise upgrade an exited backend
// back to "running". The reconcile guard keeps these backends down, so the
// marker is authoritative here.
let user_stopped =
crate::crash_recovery::load_user_stopped(&self.config.data_dir).await;
if data.server_info.status_info.containers_scanned && !data.package_data.is_empty() {
let mut containers = Vec::with_capacity(data.package_data.len());
for (id, pkg) in &data.package_data {
@ -202,7 +209,11 @@ impl RpcHandler {
// Scanner backoff preserves cached package_data. Refresh stable
// states so callers do not see stale `running`/`exited` after
// health-monitor recovery or Quadlet --rm container removal.
if state == "running" && requires_launch_port_for_health(id) {
if user_stopped.contains(id) {
// User stopped it → authoritative "stopped". Do NOT let a
// still-running UI companion's launch port mark it running.
state = "stopped".to_string();
} else if state == "running" && requires_launch_port_for_health(id) {
if !self.cached_reachable_health(id).await?.is_some() {
state = live_state_for_app(id)
.await

View File

@ -19,6 +19,29 @@ fn is_valid_v3_onion(addr: &str) -> bool {
const FILE_CATALOG_PROTOCOL: &str = "https://archipelago.dev/protocols/file-catalog/v1";
/// Best-effort reclaim of an ecash payment token that was minted but the sale
/// didn't complete (seller unreachable or couldn't redeem it), so the buyer
/// doesn't lose the value. For Fedimint the spender can reissue its own
/// un-redeemed notes; for Cashu the proofs are received back. Fails silently if
/// the seller already claimed the token (then the value is genuinely gone).
async fn reclaim_spent_ecash(data_dir: &std::path::Path, token: &str, backend: &str) {
let res = match backend {
"fedimint" => crate::wallet::fedimint_client::reissue_into_any(data_dir, token)
.await
.map(|(sats, _fed)| sats),
_ => ecash::receive_token(data_dir, token).await,
};
match res {
Ok(sats) => tracing::info!(
"paid download: reclaimed {sats} sats of unspent {backend} ecash after a failed sale"
),
Err(e) => tracing::warn!(
"paid download: could not reclaim {backend} ecash (the peer may have already \
claimed it): {e:#}"
),
}
}
impl RpcHandler {
/// List content I'm sharing.
pub(super) async fn handle_content_list_mine(&self) -> Result<serde_json::Value> {
@ -234,7 +257,7 @@ impl RpcHandler {
let fips_npub = crate::federation::fips_npub_for_onion(&self.config.data_dir, onion).await;
let path = format!("/content/{}", content_id);
let (response, _transport) =
let (response, transport) =
crate::fips::dial::PeerRequest::new(fips_npub.as_deref(), onion, &path)
.service(crate::settings::transport::PeerService::PeerFiles)
.header("X-Federation-DID", local_did)
@ -242,6 +265,15 @@ impl RpcHandler {
.send_get()
.await
.context("Failed to connect to peer")?;
// Record which transport actually reached the peer (B14) so the UI
// reflects FIPS vs Tor truthfully instead of always showing Tor/none.
let _ = crate::federation::record_peer_transport(
&self.config.data_dir,
None,
Some(onion),
&transport.to_string(),
)
.await;
if response.status() == reqwest::StatusCode::PAYMENT_REQUIRED {
let body: serde_json::Value = response.json().await.unwrap_or_default();
@ -251,6 +283,20 @@ impl RpcHandler {
}));
}
// A 403 carries an actionable reason in its JSON body (e.g. "shared with
// the host's federation peers only — federate first"). Surface that to
// the user instead of a bare "Peer returned: 403 Forbidden".
if response.status() == reqwest::StatusCode::FORBIDDEN {
let status = response.status();
let body: serde_json::Value = response.json().await.unwrap_or_default();
let msg = body
.get("error")
.and_then(|v| v.as_str())
.map(|s| s.to_string())
.unwrap_or_else(|| format!("Peer returned: {status}"));
return Err(anyhow::anyhow!(msg));
}
if !response.status().is_success() {
return Err(anyhow::anyhow!("Peer returned: {}", response.status()));
}
@ -294,13 +340,21 @@ impl RpcHandler {
fips_npub.is_some()
);
let (response, _transport) =
let (response, transport) =
crate::fips::dial::PeerRequest::new(fips_npub.as_deref(), onion, "/content")
.service(crate::settings::transport::PeerService::PeerFiles)
.timeout(std::time::Duration::from_secs(30))
.send_get()
.await
.context("Failed to connect to peer")?;
// Record which transport actually reached the peer (B14).
let _ = crate::federation::record_peer_transport(
&self.config.data_dir,
None,
Some(onion),
&transport.to_string(),
)
.await;
if !response.status().is_success() {
return Err(anyhow::anyhow!(
@ -309,11 +363,20 @@ impl RpcHandler {
));
}
let body: serde_json::Value = response
let mut body: serde_json::Value = response
.json()
.await
.context("Failed to parse peer catalog")?;
// Surface the transport that actually reached the peer so the cloud
// browse UI can show a FIPS/Tor pill instead of always assuming Tor (B21).
if let Some(obj) = body.as_object_mut() {
obj.insert(
"transport".to_string(),
serde_json::Value::String(transport.to_string()),
);
}
Ok(body)
}
@ -343,49 +406,573 @@ impl RpcHandler {
return Err(anyhow::anyhow!("Invalid v3 onion address"));
}
// Mint ecash payment token
let token_str = ecash::send_token(&self.config.data_dir, price_sats)
.await
.context("Failed to create ecash payment token — check wallet balance")?;
// `method` pins the backend the user confirmed in the UI ("cashu" |
// "fedimint"); absent = auto (Cashu first, then Fedimint). The seller's
// verify_payment_token accepts either, so a node whose balance lives in
// one system can still pay (#3).
let method = params.get("method").and_then(|v| v.as_str());
let mint_cashu = || ecash::send_token(&self.config.data_dir, price_sats);
let mint_fedimint =
|| crate::wallet::fedimint_client::spend_from_any(&self.config.data_dir, price_sats);
let (token_str, used_backend) = match method {
Some("cashu") => match mint_cashu().await {
Ok(t) => (t, "cashu"),
Err(e) => {
tracing::warn!("paid download: cashu mint failed for {price_sats} sats: {e:#}");
return Ok(serde_json::json!({ "error": format!(
"Couldn't pay {price_sats} sats from your Cashu wallet: {e}. \
Fund it, or choose Fedimint."
) }));
}
},
Some("fedimint") => match mint_fedimint().await {
Ok((notes, fed)) => {
tracing::info!("paid download: spending {price_sats} sats Fedimint notes from {fed}");
(notes, "fedimint")
}
Err(e) => {
tracing::warn!("paid download: fedimint spend failed for {price_sats} sats: {e:#}");
return Ok(serde_json::json!({ "error": format!(
"Couldn't pay {price_sats} sats from your Fedimint wallet: {e}. \
Fund it, or choose Cashu."
) }));
}
},
_ => match mint_cashu().await {
Ok(t) => (t, "cashu"),
Err(cashu_err) => match mint_fedimint().await {
Ok((notes, _fed)) => (notes, "fedimint"),
Err(fedi_err) => {
tracing::warn!(
"paid download: no ecash backend could pay {price_sats} sats \
(cashu: {cashu_err:#}; fedimint: {fedi_err:#})"
);
return Ok(serde_json::json!({ "error": format!(
"Couldn't pay {price_sats} sats from your ecash wallet \
(Cashu or Fedimint). Fund either wallet and try again."
) }));
}
},
},
};
tracing::info!("paid download: paying {price_sats} sats to {onion} via {used_backend} ecash");
let (data, _) = self.state_manager.get_snapshot().await;
let local_did = crate::identity::did_key_from_pubkey_hex(&data.server_info.pubkey)?;
let fips_npub = crate::federation::fips_npub_for_onion(&self.config.data_dir, onion).await;
let path = format!("/content/{}", content_id);
let (response, _transport) =
crate::fips::dial::PeerRequest::new(fips_npub.as_deref(), onion, &path)
.service(crate::settings::transport::PeerService::PeerFiles)
.header("X-Federation-DID", local_did)
.header("X-Payment-Token", token_str)
.timeout(std::time::Duration::from_secs(120))
.send_get()
.await
.context("Failed to connect to peer")?;
// Surface a real reason instead of the generic sanitized error (#30):
// the dial already tries FIPS/mesh then falls back to Tor, so a failure
// here means the peer is genuinely unreachable on both transports.
let (response, transport) = match crate::fips::dial::PeerRequest::new(
fips_npub.as_deref(),
onion,
&path,
)
.service(crate::settings::transport::PeerService::PeerFiles)
.header("X-Federation-DID", local_did)
.header("X-Payment-Token", token_str.clone())
.timeout(std::time::Duration::from_secs(900))
.send_get()
.await
{
Ok(v) => v,
Err(e) => {
tracing::warn!("paid peer download dial failed for {}: {:#}", onion, e);
// The token was already minted/spent — reclaim it so the buyer
// doesn't lose the value when the seller was simply unreachable.
reclaim_spent_ecash(&self.config.data_dir, &token_str, used_backend).await;
return Ok(serde_json::json!({
"error": "Could not reach the peer over mesh or Tor — it may be offline. Your ecash was refunded to your wallet. Please try again."
}));
}
};
// Record which transport actually reached the peer (B14).
let _ = crate::federation::record_peer_transport(
&self.config.data_dir,
None,
Some(onion),
&transport.to_string(),
)
.await;
if response.status() == reqwest::StatusCode::PAYMENT_REQUIRED {
// Payment was rejected — token is spent but content not received
return Err(anyhow::anyhow!(
"Payment rejected by peer — token may have been insufficient or invalid"
));
// Payment was rejected by the seller. Surface the most likely cause
// per backend — for ecash both sides must share a redemption network
// (a Cashu mint, or a Fedimint federation).
let body = response.text().await.unwrap_or_default();
tracing::warn!(
"paid download: seller {onion} rejected {used_backend} payment of {price_sats} sats: {body}"
);
// Seller couldn't redeem the token — reclaim it so the buyer keeps
// their funds (the spent-but-unredeemed-notes case the user hit).
reclaim_spent_ecash(&self.config.data_dir, &token_str, used_backend).await;
let hint = match used_backend {
"fedimint" => "the seller isn't in the same Fedimint federation as you",
_ => "the seller doesn't accept your Cashu mint",
};
return Ok(serde_json::json!({
"error": format!(
"Payment rejected by the seller — {hint}. Your ecash was refunded to \
your wallet. Try the other ecash type, or use a shared mint/federation."
)
}));
}
if !response.status().is_success() {
return Err(anyhow::anyhow!("Peer returned: {}", response.status()));
let status = response.status();
let body = response.text().await.unwrap_or_default();
tracing::warn!("paid download: seller {onion} returned {status}: {body}");
reclaim_spent_ecash(&self.config.data_dir, &token_str, used_backend).await;
return Ok(serde_json::json!({
"error": format!("Peer returned an error ({status}). Your ecash was refunded to your wallet.")
}));
}
// Capture the content type BEFORE consuming the body so the local cache
// can render the right viewer (image vs video) later.
let mime_type = response
.headers()
.get(reqwest::header::CONTENT_TYPE)
.and_then(|v| v.to_str().ok())
.map(|s| s.split(';').next().unwrap_or(s).trim().to_string())
.filter(|s| !s.is_empty())
.unwrap_or_else(|| "application/octet-stream".to_string());
let bytes = response
.bytes()
.await
.context("Failed to read response body")?;
// Persist the purchase so it "stays unlocked" for this buyer: cache the
// bytes + metadata keyed by (onion, content_id). The gallery then renders
// it unblurred and views it in-app from this cache — no re-payment and no
// reliance on a browser download (which silently fails on the mobile
// companion, the original "paid but never unlocked" report). Best-effort:
// a cache-write failure must not fail an already-paid download.
let filename = params
.get("filename")
.and_then(|v| v.as_str())
.unwrap_or(content_id)
.to_string();
let purchased_at = chrono::Utc::now().to_rfc3339();
if let Err(e) = crate::content_owned::record_purchase(
&self.config.data_dir,
onion,
content_id,
&filename,
&mime_type,
&bytes,
price_sats,
used_backend,
&purchased_at,
)
.await
{
tracing::warn!("paid download: failed to cache purchased content (non-fatal): {e:#}");
}
use base64::Engine;
let encoded = base64::engine::general_purpose::STANDARD.encode(&bytes);
tracing::info!("paid download: received {} bytes from {onion} (paid {price_sats} sats via {used_backend})", bytes.len());
Ok(serde_json::json!({
"data": encoded,
"size": bytes.len(),
"paid_sats": price_sats,
"ecash_backend": used_backend,
"mime_type": mime_type,
"owned": true,
}))
}
/// Buyer side (#46): ask the selling node to mint a Lightning invoice for a
/// paid item so the buyer can pay from any external wallet. Returns the
/// bolt11 invoice + payment hash to render as a QR and poll for settlement.
pub(super) async fn handle_content_request_invoice(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let params = params.ok_or_else(|| anyhow::anyhow!("Missing params"))?;
let onion = params
.get("onion")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing onion address"))?;
let content_id = params
.get("content_id")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing content_id"))?;
if !is_valid_v3_onion(onion) {
return Err(anyhow::anyhow!("Invalid v3 onion address"));
}
let (data, _) = self.state_manager.get_snapshot().await;
let local_did = crate::identity::did_key_from_pubkey_hex(&data.server_info.pubkey)?;
let fips_npub = crate::federation::fips_npub_for_onion(&self.config.data_dir, onion).await;
// Minting a bolt11 is a tiny request/response — keep it snappy. Cap the
// FIPS attempt hard so a cold overlay can't burn the whole budget, and
// give Tor a short-but-real window (onion circuits need a few seconds).
let path = format!("/content/{}/invoice", content_id);
let (response, _transport) =
match crate::fips::dial::PeerRequest::new(fips_npub.as_deref(), onion, &path)
.service(crate::settings::transport::PeerService::PeerFiles)
.header("X-Federation-DID", local_did)
.timeout(std::time::Duration::from_secs(25))
.fips_timeout(std::time::Duration::from_secs(6))
.send_get()
.await
{
Ok(v) => v,
Err(e) => {
tracing::warn!("request-invoice dial failed for {}: {:#}", onion, e);
return Ok(serde_json::json!({
"error": "Could not reach the peer over mesh or Tor — it may be offline."
}));
}
};
if !response.status().is_success() {
return Ok(serde_json::json!({
"error": format!("Seller could not create an invoice ({}).", response.status())
}));
}
let body: serde_json::Value = response
.json()
.await
.context("Failed to parse invoice response")?;
Ok(body)
}
/// Buyer side (#46): poll the selling node for invoice settlement.
pub(super) async fn handle_content_invoice_status(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let params = params.ok_or_else(|| anyhow::anyhow!("Missing params"))?;
let onion = params
.get("onion")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing onion address"))?;
let content_id = params
.get("content_id")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing content_id"))?;
let payment_hash = params
.get("payment_hash")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing payment_hash"))?;
if !is_valid_v3_onion(onion) {
return Err(anyhow::anyhow!("Invalid v3 onion address"));
}
// Payment hash is hex from the seller; keep it strictly hex so it's safe
// to interpolate into the request path.
if payment_hash.is_empty()
|| payment_hash.len() > 128
|| !payment_hash.chars().all(|c| c.is_ascii_hexdigit())
{
return Err(anyhow::anyhow!("Invalid payment_hash"));
}
let fips_npub = crate::federation::fips_npub_for_onion(&self.config.data_dir, onion).await;
// Settlement poll — runs repeatedly, so each call must be quick. Fast-fail
// FIPS and keep a short Tor window; an unreachable peer just reads as
// "not yet paid" and the UI polls again.
let path = format!("/content/{}/invoice-status/{}", content_id, payment_hash);
let (response, _transport) =
match crate::fips::dial::PeerRequest::new(fips_npub.as_deref(), onion, &path)
.service(crate::settings::transport::PeerService::PeerFiles)
.timeout(std::time::Duration::from_secs(15))
.fips_timeout(std::time::Duration::from_secs(6))
.send_get()
.await
{
Ok(v) => v,
Err(_) => {
// Treat an unreachable peer as "not yet paid" so the UI keeps polling.
return Ok(serde_json::json!({ "paid": false, "unreachable": true }));
}
};
if !response.status().is_success() {
return Ok(serde_json::json!({ "paid": false }));
}
let body: serde_json::Value = response
.json()
.await
.context("Failed to parse invoice-status response")?;
Ok(body)
}
/// Buyer side (#46): download a paid item after the invoice settled, passing
/// the payment hash so the seller's content gate releases the file.
pub(super) async fn handle_content_download_peer_invoice(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let params = params.ok_or_else(|| anyhow::anyhow!("Missing params"))?;
let onion = params
.get("onion")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing onion address"))?;
let content_id = params
.get("content_id")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing content_id"))?;
let payment_hash = params
.get("payment_hash")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing payment_hash"))?;
if !is_valid_v3_onion(onion) {
return Err(anyhow::anyhow!("Invalid v3 onion address"));
}
if payment_hash.is_empty() || !payment_hash.chars().all(|c| c.is_ascii_hexdigit()) {
return Err(anyhow::anyhow!("Invalid payment_hash"));
}
let (data, _) = self.state_manager.get_snapshot().await;
let local_did = crate::identity::did_key_from_pubkey_hex(&data.server_info.pubkey)?;
let fips_npub = crate::federation::fips_npub_for_onion(&self.config.data_dir, onion).await;
let path = format!("/content/{}", content_id);
let (response, transport) = match crate::fips::dial::PeerRequest::new(
fips_npub.as_deref(),
onion,
&path,
)
.service(crate::settings::transport::PeerService::PeerFiles)
.header("X-Federation-DID", local_did)
.header("X-Invoice-Hash", payment_hash.to_string())
.timeout(std::time::Duration::from_secs(900))
.send_get()
.await
{
Ok(v) => v,
Err(e) => {
tracing::warn!("invoice download dial failed for {}: {:#}", onion, e);
return Ok(serde_json::json!({
"error": "Could not reach the peer over mesh or Tor — it may be offline. Please try again."
}));
}
};
let _ = crate::federation::record_peer_transport(
&self.config.data_dir,
None,
Some(onion),
&transport.to_string(),
)
.await;
if response.status() == reqwest::StatusCode::PAYMENT_REQUIRED {
return Ok(serde_json::json!({
"error": "Seller has not registered this payment yet — wait for settlement and retry."
}));
}
if !response.status().is_success() {
return Ok(serde_json::json!({
"error": format!("Peer returned an error ({}).", response.status())
}));
}
let bytes = response
.bytes()
.await
.context("Failed to read response body")?;
use base64::Engine;
let encoded = base64::engine::general_purpose::STANDARD.encode(&bytes);
Ok(serde_json::json!({
"data": encoded,
"size": bytes.len(),
}))
}
/// Buyer side (#46): ask the seller for a fresh on-chain address to pay.
pub(super) async fn handle_content_request_onchain(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let params = params.ok_or_else(|| anyhow::anyhow!("Missing params"))?;
let onion = params
.get("onion")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing onion address"))?;
let content_id = params
.get("content_id")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing content_id"))?;
if !is_valid_v3_onion(onion) {
return Err(anyhow::anyhow!("Invalid v3 onion address"));
}
let (data, _) = self.state_manager.get_snapshot().await;
let local_did = crate::identity::did_key_from_pubkey_hex(&data.server_info.pubkey)?;
let fips_npub = crate::federation::fips_npub_for_onion(&self.config.data_dir, onion).await;
// Issuing an address is a tiny request/response — fast-fail FIPS, short
// Tor window (same budget shape as the invoice path, #6).
let path = format!("/content/{}/onchain", content_id);
let (response, _transport) =
match crate::fips::dial::PeerRequest::new(fips_npub.as_deref(), onion, &path)
.service(crate::settings::transport::PeerService::PeerFiles)
.header("X-Federation-DID", local_did)
.timeout(std::time::Duration::from_secs(25))
.fips_timeout(std::time::Duration::from_secs(6))
.send_get()
.await
{
Ok(v) => v,
Err(e) => {
tracing::warn!("request-onchain dial failed for {}: {:#}", onion, e);
return Ok(serde_json::json!({
"error": "Could not reach the peer over mesh or Tor — it may be offline."
}));
}
};
if !response.status().is_success() {
return Ok(serde_json::json!({
"error": format!("Seller could not provide an address ({}).", response.status())
}));
}
let body: serde_json::Value = response
.json()
.await
.context("Failed to parse onchain response")?;
Ok(body)
}
/// Buyer side (#46): poll the selling node for on-chain payment detection.
pub(super) async fn handle_content_onchain_status(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let params = params.ok_or_else(|| anyhow::anyhow!("Missing params"))?;
let onion = params
.get("onion")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing onion address"))?;
let content_id = params
.get("content_id")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing content_id"))?;
let address = params
.get("address")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing address"))?;
if !is_valid_v3_onion(onion) {
return Err(anyhow::anyhow!("Invalid v3 onion address"));
}
// Bitcoin addresses are alphanumeric; keep strictly so for safe path use.
if address.is_empty()
|| address.len() > 100
|| !address.chars().all(|c| c.is_ascii_alphanumeric())
{
return Err(anyhow::anyhow!("Invalid address"));
}
let fips_npub = crate::federation::fips_npub_for_onion(&self.config.data_dir, onion).await;
let path = format!("/content/{}/onchain-status/{}", content_id, address);
let (response, _transport) =
match crate::fips::dial::PeerRequest::new(fips_npub.as_deref(), onion, &path)
.service(crate::settings::transport::PeerService::PeerFiles)
.timeout(std::time::Duration::from_secs(15))
.fips_timeout(std::time::Duration::from_secs(6))
.send_get()
.await
{
Ok(v) => v,
Err(_) => return Ok(serde_json::json!({ "paid": false, "unreachable": true })),
};
if !response.status().is_success() {
return Ok(serde_json::json!({ "paid": false }));
}
let body: serde_json::Value = response
.json()
.await
.context("Failed to parse onchain-status response")?;
Ok(body)
}
/// Buyer side (#46): download a paid item after the on-chain payment was
/// detected, passing the address so the seller's content gate releases it.
pub(super) async fn handle_content_download_peer_onchain(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let params = params.ok_or_else(|| anyhow::anyhow!("Missing params"))?;
let onion = params
.get("onion")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing onion address"))?;
let content_id = params
.get("content_id")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing content_id"))?;
let address = params
.get("address")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing address"))?;
if !is_valid_v3_onion(onion) {
return Err(anyhow::anyhow!("Invalid v3 onion address"));
}
if address.is_empty() || !address.chars().all(|c| c.is_ascii_alphanumeric()) {
return Err(anyhow::anyhow!("Invalid address"));
}
let (data, _) = self.state_manager.get_snapshot().await;
let local_did = crate::identity::did_key_from_pubkey_hex(&data.server_info.pubkey)?;
let fips_npub = crate::federation::fips_npub_for_onion(&self.config.data_dir, onion).await;
let path = format!("/content/{}", content_id);
let (response, transport) = match crate::fips::dial::PeerRequest::new(
fips_npub.as_deref(),
onion,
&path,
)
.service(crate::settings::transport::PeerService::PeerFiles)
.header("X-Federation-DID", local_did)
.header("X-Onchain-Address", address.to_string())
.timeout(std::time::Duration::from_secs(900))
.send_get()
.await
{
Ok(v) => v,
Err(e) => {
tracing::warn!("onchain download dial failed for {}: {:#}", onion, e);
return Ok(serde_json::json!({
"error": "Could not reach the peer over mesh or Tor — it may be offline. Please try again."
}));
}
};
let _ = crate::federation::record_peer_transport(
&self.config.data_dir,
None,
Some(onion),
&transport.to_string(),
)
.await;
if response.status() == reqwest::StatusCode::PAYMENT_REQUIRED {
return Ok(serde_json::json!({
"error": "Seller has not registered this payment yet — wait for confirmation and retry."
}));
}
if !response.status().is_success() {
return Ok(serde_json::json!({
"error": format!("Peer returned an error ({}).", response.status())
}));
}
let bytes = response
.bytes()
.await
.context("Failed to read response body")?;
use base64::Engine;
let encoded = base64::engine::general_purpose::STANDARD.encode(&bytes);
Ok(serde_json::json!({
"data": encoded,
"size": bytes.len(),
}))
}
@ -418,13 +1005,21 @@ impl RpcHandler {
fips_npub.is_some()
);
let (response, _transport) =
let (response, transport) =
crate::fips::dial::PeerRequest::new(fips_npub.as_deref(), onion, &path)
.service(crate::settings::transport::PeerService::PeerFiles)
.timeout(std::time::Duration::from_secs(30))
.send_get()
.await
.context("Failed to connect to peer for preview")?;
// Record which transport actually reached the peer (B14).
let _ = crate::federation::record_peer_transport(
&self.config.data_dir,
None,
Some(onion),
&transport.to_string(),
)
.await;
if !response.status().is_success() {
return Err(anyhow::anyhow!(
@ -462,4 +1057,43 @@ impl RpcHandler {
"preview_mode": is_preview,
}))
}
/// `content.owned-list` — every paid item this node has purchased, so the
/// gallery can render owned items unblurred/viewable without re-payment.
pub(super) async fn handle_content_owned_list(&self) -> Result<serde_json::Value> {
let items = crate::content_owned::list_owned(&self.config.data_dir).await;
Ok(serde_json::json!({ "items": items }))
}
/// `content.owned-get` — return a purchased item's bytes (base64) from the
/// local cache for in-app viewing/saving. No network, no re-payment.
pub(super) async fn handle_content_owned_get(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let params = params.ok_or_else(|| anyhow::anyhow!("Missing params"))?;
let onion = params
.get("onion")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing onion address"))?;
let content_id = params
.get("content_id")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing content_id"))?;
match crate::content_owned::read_owned(&self.config.data_dir, onion, content_id).await {
Some((mime_type, bytes)) => {
use base64::Engine;
let encoded = base64::engine::general_purpose::STANDARD.encode(&bytes);
Ok(serde_json::json!({
"data": encoded,
"size": bytes.len(),
"mime_type": mime_type,
}))
}
None => Ok(serde_json::json!({
"error": "You don't own this item yet, or its cached copy is missing."
})),
}
}
}

View File

@ -33,6 +33,7 @@ impl RpcHandler {
"seed.restore" => self.handle_seed_restore(params).await,
"seed.save-encrypted" => self.handle_seed_save_encrypted(params).await,
"seed.status" => self.handle_seed_status().await,
"seed.reveal" => self.handle_seed_reveal(params).await,
// Container orchestration (for Archipelago-managed containers)
"container-install" => self.handle_container_install(params).await,
@ -55,6 +56,7 @@ impl RpcHandler {
"package.restart" => self.handle_package_restart(params).await,
"package.uninstall" => self.clone().spawn_package_uninstall(params).await,
"package.update" => self.clone().spawn_package_update(params).await,
"package.check-updates" => self.handle_package_check_updates(params).await,
"package.credentials" => self.handle_package_credentials(params).await,
"app.filebrowser-token" => self.handle_filebrowser_token().await,
@ -236,6 +238,11 @@ impl RpcHandler {
"wallet.ecash-receive" => self.handle_wallet_ecash_receive(params).await,
"wallet.ecash-history" => self.handle_wallet_ecash_history().await,
"wallet.networking-profits" => self.handle_wallet_networking_profits().await,
// Fedimint ecash (via fedimint-clientd sidecar)
"wallet.fedimint-list" => self.handle_wallet_fedimint_list().await,
"wallet.fedimint-join" => self.handle_wallet_fedimint_join(params).await,
"wallet.fedimint-leave" => self.handle_wallet_fedimint_leave(params).await,
"wallet.fedimint-balance" => self.handle_wallet_fedimint_balance().await,
// Container registries
"registry.list" => self.handle_registry_list().await,
@ -249,6 +256,7 @@ impl RpcHandler {
"streaming.configure-service" => self.handle_streaming_configure_service(params).await,
"streaming.toggle-service" => self.handle_streaming_toggle_service(params).await,
"streaming.pay" => self.handle_streaming_pay(params).await,
"streaming.prepare-payment" => self.handle_streaming_prepare_payment(params).await,
"streaming.discover" => self.handle_streaming_discover().await,
"streaming.usage" => self.handle_streaming_usage(params).await,
"streaming.session" => self.handle_streaming_session(params).await,
@ -268,6 +276,18 @@ impl RpcHandler {
"content.browse-peer" => self.handle_content_browse_peer(params).await,
"content.download-peer" => self.handle_content_download_peer(params).await,
"content.download-peer-paid" => self.handle_content_download_peer_paid(params).await,
"content.owned-list" => self.handle_content_owned_list().await,
"content.owned-get" => self.handle_content_owned_get(params).await,
"content.request-invoice" => self.handle_content_request_invoice(params).await,
"content.invoice-status" => self.handle_content_invoice_status(params).await,
"content.download-peer-invoice" => {
self.handle_content_download_peer_invoice(params).await
}
"content.request-onchain" => self.handle_content_request_onchain(params).await,
"content.onchain-status" => self.handle_content_onchain_status(params).await,
"content.download-peer-onchain" => {
self.handle_content_download_peer_onchain(params).await
}
"content.preview-peer" => self.handle_content_preview_peer(params).await,
// DWN (Decentralized Web Node)
@ -379,6 +399,11 @@ impl RpcHandler {
"mesh.deadman-status" => self.handle_mesh_deadman_status().await,
"mesh.deadman-configure" => self.handle_mesh_deadman_configure(params).await,
"mesh.deadman-checkin" => self.handle_mesh_deadman_checkin().await,
"mesh.assistant-status" => self.handle_mesh_assistant_status().await,
"mesh.assistant-configure" => self.handle_mesh_assistant_configure(params).await,
"mesh.schedule-message" => self.handle_mesh_schedule_message(params).await,
"mesh.list-scheduled" => self.handle_mesh_list_scheduled().await,
"mesh.cancel-scheduled" => self.handle_mesh_cancel_scheduled(params).await,
"mesh.test-send" => self.handle_mesh_test_send(params).await,
// Transport layer (unified routing)
@ -470,6 +495,11 @@ impl RpcHandler {
let p = params.unwrap_or(serde_json::json!({}));
self.handle_update_test_mirror(&p).await
}
"update.get-source" => self.handle_update_get_source().await,
"update.set-source" => {
let p = params.unwrap_or(serde_json::json!({}));
self.handle_update_set_source(&p).await
}
"update.apply" => self.handle_update_apply().await,
"update.git-apply" => self.handle_update_git_apply().await,
"update.rollback" => self.handle_update_rollback().await,

View File

@ -30,6 +30,25 @@ impl RpcHandler {
mesh::upsert_federation_peer(&svc.shared_state(), pubkey_hex, did, name).await;
}
}
/// Re-seed every federation node from disk into the mesh peer table so the
/// chat list reflects what the latest federation sync learned — display
/// names (landed in `nodes.json` by `update_node_state` when a peer
/// announces its name) and transitively-discovered peers (merged by
/// `merge_transitive_peers`) — WITHOUT waiting for a mesh restart.
///
/// Without this, a peer accepted via invite (seeded with `name = None`)
/// stays "Archipelago <pubkey8>" in chat until the next restart even after
/// sync has learned its real name, and transitive peers never appear as
/// chat contacts at all. `seed_federation_peers_into_mesh` is idempotent
/// and dedups by onion, so calling it after each sync is safe.
/// Best-effort: silently no-ops when mesh is off.
pub(crate) async fn refresh_federation_mesh_peers(&self) {
let svc = self.mesh_service.read().await;
if let Some(svc) = svc.as_ref() {
mesh::seed_federation_peers_into_mesh(&svc.shared_state(), &self.config.data_dir).await;
}
}
}
impl RpcHandler {
@ -243,9 +262,31 @@ impl RpcHandler {
.ok_or_else(|| anyhow::anyhow!("Missing 'did' parameter"))?;
validate_did(did)?;
// Capture the node's pubkey before removal so we can also purge its
// synthetic mesh contact/thread (#2) — remove_node only touches
// nodes.json, which would otherwise leave a stale chat contact behind.
let removed_pubkey = federation::load_nodes(&self.config.data_dir)
.await
.ok()
.and_then(|nodes| nodes.into_iter().find(|n| n.did == did).map(|n| n.pubkey));
let nodes = federation::remove_node(&self.config.data_dir, did).await?;
info!(did = %did, "Removed node from federation");
if let Some(pubkey) = removed_pubkey.filter(|p| !p.is_empty()) {
let svc = self.mesh_service.read().await;
if let Some(svc) = svc.as_ref() {
let contact_id = mesh::federation_peer_contact_id(&pubkey);
mesh::purge_federation_peer(
&svc.shared_state(),
contact_id,
&pubkey,
&self.config.data_dir,
)
.await;
}
}
Ok(serde_json::json!({
"removed": true,
"nodes_remaining": nodes.len(),
@ -341,6 +382,10 @@ impl RpcHandler {
}
}
// Push any names/roster the sync just learned into the live mesh peer
// table so the chat list updates without a restart (#42).
self.refresh_federation_mesh_peers().await;
Ok(serde_json::json!({
"synced": synced,
"failed": failed,
@ -533,6 +578,19 @@ impl RpcHandler {
return Ok(serde_json::json!({ "accepted": true, "already_known": true }));
}
// Respect operator removal: a peer the operator deleted must not
// silently re-join via a stale invite. The tombstone is only cleared
// by an explicit local action (manually adding the node or accepting
// an incoming invite) — not by a remote-triggered join.
if federation::load_removed_dids(&self.config.data_dir)
.await
.unwrap_or_default()
.contains(did)
{
info!(peer_did = %did, "Ignoring peer-joined for a removed (tombstoned) DID");
return Ok(serde_json::json!({ "accepted": false, "removed": true }));
}
let node = FederatedNode {
did: did.to_string(),
pubkey: pubkey.to_string(),

View File

@ -0,0 +1,131 @@
//! Fedimint ecash RPCs — bridge to the `fedimint-clientd` sidecar.
//!
//! Companion to the Cashu wallet RPCs in [`super::wallet`]. Joining/holding
//! Fedimint ecash is delegated to the clientd container via
//! [`crate::wallet::fedimint_client::FedimintClient`]; here we expose the
//! node's JSON-RPC surface and keep a local registry of joined federations so
//! the list survives clientd being temporarily unreachable.
//!
//! See `docs/dual-ecash-design.md`.
use super::RpcHandler;
use crate::wallet::fedimint_client::{self, FedimintClient, JoinedFederation};
use anyhow::Result;
impl RpcHandler {
/// `wallet.fedimint-list` — joined federations with live balances.
pub(super) async fn handle_wallet_fedimint_list(&self) -> Result<serde_json::Value> {
// Best-effort: make sure the default federation is joined/tracked.
let _ = fedimint_client::ensure_default_federation(&self.config.data_dir).await;
let reg = fedimint_client::load_registry(&self.config.data_dir).await?;
// Live balances are best-effort: if clientd is down we still return the
// tracked federations (with 0 balance) rather than failing the call.
let info = match FedimintClient::from_node(&self.config.data_dir).await {
Ok(client) => client.info().await.ok(),
Err(_) => None,
};
let federations: Vec<serde_json::Value> = reg
.federations
.iter()
.map(|f| {
let balance_sats = info
.as_ref()
.and_then(|i| i.get(&f.federation_id))
.and_then(|e| {
e.get("totalAmountMsat")
.or_else(|| e.get("totalMsat"))
.and_then(|v| v.as_u64())
})
.map(|msat| msat / 1000)
.unwrap_or(0);
serde_json::json!({
"federation_id": f.federation_id,
"name": f.name,
"balance_sats": balance_sats,
})
})
.collect();
Ok(serde_json::json!({ "federations": federations }))
}
/// `wallet.fedimint-join` — join a federation by invite code.
pub(super) async fn handle_wallet_fedimint_join(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let params = params.ok_or_else(|| anyhow::anyhow!("Missing params"))?;
let invite_code = params
.get("invite_code")
.and_then(|v| v.as_str())
.map(str::trim)
.filter(|s| !s.is_empty())
.ok_or_else(|| anyhow::anyhow!("Missing invite_code"))?;
let client = FedimintClient::from_node(&self.config.data_dir).await?;
let federation_id = client.join(invite_code).await?;
// Try to label it from the federation meta (best-effort).
let name = client.info().await.ok().and_then(|i| {
i.get(&federation_id)
.and_then(|e| e.get("meta"))
.and_then(|m| {
m.get("federation_name")
.or_else(|| m.get("federation_expiry_timestamp"))
})
.and_then(|v| v.as_str())
.map(|s| s.to_string())
});
let mut reg = fedimint_client::load_registry(&self.config.data_dir).await?;
if !reg
.federations
.iter()
.any(|f| f.federation_id == federation_id)
{
reg.federations.push(JoinedFederation {
federation_id: federation_id.clone(),
name,
});
fedimint_client::save_registry(&self.config.data_dir, &reg).await?;
}
Ok(serde_json::json!({ "federation_id": federation_id }))
}
/// `wallet.fedimint-leave` — stop tracking a federation locally.
pub(super) async fn handle_wallet_fedimint_leave(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let params = params.ok_or_else(|| anyhow::anyhow!("Missing params"))?;
let federation_id = params
.get("federation_id")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("Missing federation_id"))?;
let mut reg = fedimint_client::load_registry(&self.config.data_dir).await?;
let before = reg.federations.len();
reg.federations.retain(|f| f.federation_id != federation_id);
let removed = reg.federations.len() != before;
if removed {
fedimint_client::save_registry(&self.config.data_dir, &reg).await?;
}
Ok(serde_json::json!({ "removed": removed }))
}
/// `wallet.fedimint-balance` — total sats across all joined federations.
pub(super) async fn handle_wallet_fedimint_balance(&self) -> Result<serde_json::Value> {
// Soft-fail to zero when clientd isn't installed/running, so the unified
// wallet balance still renders from the Cashu side.
let balance_sats = match FedimintClient::from_node(&self.config.data_dir).await {
Ok(client) => client.total_balance_sats().await.unwrap_or(0),
Err(_) => 0,
};
Ok(serde_json::json!({ "balance_sats": balance_sats }))
}
}

View File

@ -115,10 +115,12 @@ impl RpcHandler {
} else if !after.key_present {
"no_seed_key"
} else if after.authenticated_peer_count == 0 {
// Daemon is up with a key but hasn't authenticated any
// peers — almost always outbound UDP/8668 dropped by the
// local firewall/router, or the anchor itself being down.
"no_outbound_udp_or_anchor_down"
// Daemon is up with a key but hasn't authenticated any peers —
// almost always the outbound connection to the anchor being
// dropped by the local firewall/router, or the anchor itself
// being down. The public anchor is reached over TCP/8443 (not
// UDP/8668 — that endpoint is dead).
"no_outbound_or_anchor_down"
} else {
"peers_but_no_anchor"
};
@ -126,8 +128,8 @@ impl RpcHandler {
"connected" => "An anchor is reachable.",
"daemon_down" => "The FIPS daemon didn't come back up — check the FIPS service on this host.",
"no_seed_key" => "No seed-derived FIPS key on disk. Re-run the onboarding unlock step.",
"no_outbound_udp_or_anchor_down" =>
"Daemon is running but no peers handshook. Your router / ISP might be blocking outbound UDP 8668, or every configured anchor could be down. Add a reachable peer in Seed Anchors.",
"no_outbound_or_anchor_down" =>
"Daemon is running but no peers handshook. Your router or ISP may be blocking the outbound connection to the mesh anchor (TCP port 8443), or every configured anchor is down. The public anchor is added automatically — if it still won't connect, add another reachable peer in Seed Anchors.",
"peers_but_no_anchor" =>
"Mesh has peers but none of them are anchors we recognise. Add your cluster's anchor in Seed Anchors.",
_ => "",

View File

@ -14,10 +14,39 @@ impl RpcHandler {
let manager = IdentityManager::new(&self.config.data_dir).await?;
let (identities, default_id) = manager.list().await?;
// #49: The canonical node Nostr key is the node-level HKDF key
// (`derive_node_nostr_key`) that Settings and Nostr discovery both use
// via `node.nostr-pubkey`. The mirrored "Node" identity stores
// nostr=None, and seed identities use a different BIP-32 NIP-06 key, so
// the "Node" entry in Web5 > Identities disagreed with Settings. Resolve
// the node-level key once and override it onto whichever identity record
// is the node's own (its ed25519 matches `server_info.pubkey`), so both
// surfaces always show the same npub. Display-only — no key is rewritten.
let identity_dir = self.config.data_dir.join("identity");
let node_nostr_hex = crate::nostr_discovery::get_nostr_pubkey(&identity_dir)
.await
.ok();
let node_nostr_npub = node_nostr_hex.as_ref().and_then(|h| {
nostr_sdk::PublicKey::from_hex(h)
.ok()
.and_then(|pk| pk.to_bech32().ok())
});
let (snapshot, _) = self.state_manager.get_snapshot().await;
let node_pubkey_hex = snapshot.server_info.pubkey.clone();
let items: Vec<serde_json::Value> = identities
.into_iter()
.map(|id| {
let is_default = default_id.as_deref() == Some(&id.id);
let is_node = !node_pubkey_hex.is_empty() && id.pubkey_hex == node_pubkey_hex;
let (nostr_pubkey, nostr_npub) = if is_node {
(
node_nostr_hex.clone().or(id.nostr_pubkey),
node_nostr_npub.clone().or(id.nostr_npub),
)
} else {
(id.nostr_pubkey, id.nostr_npub)
};
serde_json::json!({
"id": id.id,
"name": id.name,
@ -26,8 +55,8 @@ impl RpcHandler {
"did": id.did,
"created_at": id.created_at,
"is_default": is_default,
"nostr_pubkey": id.nostr_pubkey,
"nostr_npub": id.nostr_npub,
"nostr_pubkey": nostr_pubkey,
"nostr_npub": nostr_npub,
"profile": id.profile,
})
})

View File

@ -9,21 +9,44 @@ use super::LND_REST_BASE_URL;
impl RpcHandler {
/// Generate a new on-chain Bitcoin address.
pub(in crate::api::rpc) async fn handle_lnd_newaddress(&self) -> Result<serde_json::Value> {
let (client, macaroon_hex) = self.lnd_client().await?;
let (client, macaroon_hex) = self.lnd_client().await.map_err(|e| {
tracing::warn!(error = %format!("{e:#}"), "LND newaddress: client/macaroon unavailable");
receive_error(
RECEIVE_WALLET_UNINITIALIZED,
"The Lightning wallet isn't set up on this node yet. Finish wallet setup, then try again.",
)
})?;
let resp = client
let resp = match client
.get(format!("{LND_REST_BASE_URL}/v1/newaddress"))
.query(&[("type", "p2wkh")])
// LND's REST gateway parses `type` as the AddressType enum by its
// proto name (or integer), NOT the lncli aliases. "p2wkh" is not a
// valid enum value and returns 400 "parsing field type"; the native
// SegWit (bech32) variant is WITNESS_PUBKEY_HASH (= 0).
.query(&[("type", "WITNESS_PUBKEY_HASH")])
.header("Grpc-Metadata-macaroon", &macaroon_hex)
.send()
.await
.context("LND REST connection failed")?;
{
Ok(resp) => resp,
Err(e) => {
// The .116 case: LND container is up but its REST endpoint isn't
// reachable on the expected port (e.g. published-port drift), so
// the connection is refused. This is NOT a locked wallet — emit a
// distinct code so the UI stops mislabelling it.
tracing::warn!(error = %format!("{e:#}"), "LND newaddress: REST connection failed");
return Err(receive_error(
RECEIVE_REST_UNREACHABLE,
"The Lightning wallet service isn't reachable yet. It may be starting up or recovering — please try again in a moment.",
));
}
};
let status = resp.status();
let raw_body = resp
.text()
.await
.context("LND address response could not be read")?;
.context("Bitcoin address response could not be read")?;
let body: serde_json::Value = serde_json::from_str(&raw_body).unwrap_or_else(|_| {
serde_json::json!({
"raw": raw_body,
@ -32,11 +55,9 @@ impl RpcHandler {
if !status.is_success() {
let message = lnd_error_message(&body);
anyhow::bail!(
"Bitcoin address generation failed ({}): {}",
status,
message
);
let code = classify_lnd_address_error(&message);
tracing::warn!(%status, lnd_message = %message, code, "LND newaddress returned an error");
return Err(receive_error(code, default_receive_detail(code)));
}
if let Some(error) = body
@ -44,14 +65,21 @@ impl RpcHandler {
.or_else(|| body.get("message"))
.and_then(|v| v.as_str())
{
anyhow::bail!("Bitcoin address generation failed: {}", error);
let code = classify_lnd_address_error(error);
tracing::warn!(lnd_message = %error, code, "LND newaddress returned an error body");
return Err(receive_error(code, default_receive_detail(code)));
}
let address = body
.get("address")
.and_then(|v| v.as_str())
.filter(|addr| !addr.trim().is_empty())
.ok_or_else(|| anyhow::anyhow!("Bitcoin address generation failed: LND did not return a Bitcoin address. The wallet may still be locked, uninitialized, or waiting for Bitcoin to sync."))?
.ok_or_else(|| {
receive_error(
RECEIVE_WALLET_UNINITIALIZED,
"The wallet didn't return an address yet. It may still be unlocking or waiting for Bitcoin to sync — please try again shortly.",
)
})?
.to_string();
Ok(serde_json::json!({ "address": address }))
@ -123,6 +151,250 @@ impl RpcHandler {
}
/// Create a Lightning invoice.
/// Create a Lightning invoice and return `(bolt11, payment_hash_hex)`.
///
/// Shared helper used by both the `lnd.createinvoice` RPC and the seller-side
/// peer-file invoice flow (#46). LND returns `r_hash` as base64; we re-encode
/// it as hex so it can be used as a stable lookup key and passed in URLs.
/// Whether LND reports it's synced to its Bitcoin chain backend. Used to
/// fail invoice minting FAST with a clear reason while the node's Bitcoin
/// backend is still in initial block download — otherwise the `/v1/invoices`
/// POST hangs for the full client timeout (×3 retries ≈ 45s) and surfaces as
/// an opaque failure. `getinfo` answers in ~2s even mid-IBD. Returns
/// `Some(false)` only when LND is reachable AND explicitly not synced;
/// `None` when we couldn't tell (let the mint attempt proceed and report its
/// own error rather than guess "syncing").
pub(crate) async fn lnd_chain_synced(&self) -> Option<bool> {
let (client, macaroon_hex) = self.lnd_client().await.ok()?;
let resp = client
.get(format!("{LND_REST_BASE_URL}/v1/getinfo"))
.header("Grpc-Metadata-macaroon", &macaroon_hex)
.send()
.await
.ok()?;
let body: serde_json::Value = resp.json().await.ok()?;
body.get("synced_to_chain").and_then(|v| v.as_bool())
}
/// Error returned when the node can't mint a Lightning invoice because its
/// Bitcoin backend is still syncing. Kept as one string so every invoice
/// entry point surfaces the same clear, user-facing reason.
fn syncing_invoice_err() -> anyhow::Error {
anyhow::anyhow!(
"Your Bitcoin node is still syncing — Lightning invoices are unavailable until it finishes. Try again once the node is fully synced."
)
}
pub(crate) async fn create_invoice(
&self,
amount_sats: i64,
memo: &str,
) -> Result<(String, String)> {
if amount_sats < 0 {
return Err(anyhow::anyhow!("Amount must be non-negative"));
}
if memo.len() > 639 {
return Err(anyhow::anyhow!("Memo too long (max 639 bytes)"));
}
let (client, macaroon_hex) = self.lnd_client().await?;
let invoice_body = serde_json::json!({
"value": amount_sats.to_string(),
"memo": memo,
});
// LND's REST endpoint can briefly drop/reset connections under load
// (swap pressure, just-restarted, TLS handshake races), which used to
// hard-fail the buy-file invoice with an opaque 503. Retry on a
// CONNECTION error with short backoff so a transient blip doesn't
// surface as a payment failure. A *timeout* is NOT retried: it means LND
// accepted the connection but isn't answering the mint (e.g. a degraded
// node), and retrying just multiplies the wait (3×15s ≈ 45s) — fail
// after the first hang and let the caller surface the real reason.
let mut last_err: Option<anyhow::Error> = None;
let mut resp = None;
for attempt in 0..3u32 {
match client
.post(format!("{LND_REST_BASE_URL}/v1/invoices"))
.header("Grpc-Metadata-macaroon", &macaroon_hex)
.json(&invoice_body)
.send()
.await
{
Ok(r) => {
resp = Some(r);
break;
}
Err(e) => {
let timed_out = e.is_timeout();
last_err = Some(anyhow::anyhow!(
"LND REST send failed (attempt {}): {e}",
attempt + 1
));
if timed_out {
break;
}
tokio::time::sleep(std::time::Duration::from_millis(400)).await;
}
}
}
let resp = match resp {
Some(r) => r,
None => {
// If LND is reachable but explicitly not synced to chain, say so —
// it's the most common reason a just-restored/syncing node can't
// mint. Otherwise surface the underlying transport error.
if self.lnd_chain_synced().await == Some(false) {
return Err(Self::syncing_invoice_err());
}
return Err(last_err.unwrap_or_else(|| {
anyhow::anyhow!("Failed to reach LND REST to create invoice")
}));
}
};
let status = resp.status();
let body: serde_json::Value = resp
.json()
.await
.context("Failed to parse invoice response")?;
if !status.is_success() {
let msg = body
.get("message")
.and_then(|v| v.as_str())
.unwrap_or("Unknown error");
return Err(anyhow::anyhow!("Failed to create invoice: {}", msg));
}
let payment_request = body
.get("payment_request")
.and_then(|v| v.as_str())
.unwrap_or("")
.to_string();
// r_hash is base64 in LND's REST response — convert to hex.
use base64::Engine;
let payment_hash_hex = body
.get("r_hash")
.and_then(|v| v.as_str())
.and_then(|b64| base64::engine::general_purpose::STANDARD.decode(b64).ok())
.map(hex::encode)
.unwrap_or_default();
Ok((payment_request, payment_hash_hex))
}
/// Look up an invoice by hex payment hash; true if it has settled.
pub(crate) async fn invoice_is_settled(&self, payment_hash_hex: &str) -> Result<bool> {
if payment_hash_hex.is_empty() || hex::decode(payment_hash_hex).is_err() {
return Err(anyhow::anyhow!("Invalid payment hash"));
}
let (client, macaroon_hex) = self.lnd_client().await?;
// LND REST: GET /v1/invoice/{r_hash_str} where r_hash_str is hex.
let resp = client
.get(format!("{LND_REST_BASE_URL}/v1/invoice/{payment_hash_hex}"))
.header("Grpc-Metadata-macaroon", &macaroon_hex)
.send()
.await
.context("Failed to look up invoice")?;
if !resp.status().is_success() {
return Ok(false);
}
let body: serde_json::Value = resp
.json()
.await
.context("Failed to parse invoice lookup response")?;
let settled = body
.get("settled")
.and_then(|v| v.as_bool())
.unwrap_or(false)
|| body.get("state").and_then(|v| v.as_str()) == Some("SETTLED");
Ok(settled)
}
/// Generate a fresh on-chain receive address (seller side, #46).
pub(crate) async fn new_onchain_address(&self) -> Result<String> {
let (client, macaroon_hex) = self.lnd_client().await?;
let resp = client
.get(format!("{LND_REST_BASE_URL}/v1/newaddress"))
.header("Grpc-Metadata-macaroon", &macaroon_hex)
.send()
.await
.context("Failed to get new address")?;
if !resp.status().is_success() {
return Err(anyhow::anyhow!("LND newaddress failed: {}", resp.status()));
}
let body: serde_json::Value = resp
.json()
.await
.context("Failed to parse newaddress response")?;
body.get("address")
.and_then(|v| v.as_str())
.filter(|s| !s.is_empty())
.map(|s| s.to_string())
.ok_or_else(|| anyhow::anyhow!("LND newaddress returned no address"))
}
/// True if an on-chain payment of >= `min_sats` to `address` has been seen
/// with at least one confirmation (seller side, #46). Conservative on
/// purpose: requires a confirmation + exact-address + sufficient-amount so a
/// file sale is never released on an unconfirmed (reorg-able) tx.
pub(crate) async fn onchain_received(&self, address: &str, min_sats: u64) -> Result<bool> {
if address.is_empty() {
return Err(anyhow::anyhow!("Empty address"));
}
let (client, macaroon_hex) = self.lnd_client().await?;
let resp = client
.get(format!("{LND_REST_BASE_URL}/v1/transactions"))
.header("Grpc-Metadata-macaroon", &macaroon_hex)
.send()
.await
.context("Failed to list transactions")?;
if !resp.status().is_success() {
return Ok(false);
}
let body: serde_json::Value = resp
.json()
.await
.context("Failed to parse transactions response")?;
let i64_field = |tx: &serde_json::Value, k: &str| -> i64 {
tx.get(k)
.and_then(|v| v.as_str())
.and_then(|s| s.parse::<i64>().ok())
.or_else(|| tx.get(k).and_then(|v| v.as_i64()))
.unwrap_or(0)
};
let txs = body
.get("transactions")
.and_then(|v| v.as_array())
.cloned()
.unwrap_or_default();
for tx in &txs {
if i64_field(tx, "num_confirmations") < 1 {
continue;
}
if i64_field(tx, "amount") < min_sats as i64 {
continue;
}
let pays_addr = tx
.get("dest_addresses")
.and_then(|v| v.as_array())
.map(|arr| arr.iter().any(|a| a.as_str() == Some(address)))
.unwrap_or(false)
|| tx
.get("output_details")
.and_then(|v| v.as_array())
.map(|arr| {
arr.iter()
.any(|o| o.get("address").and_then(|a| a.as_str()) == Some(address))
})
.unwrap_or(false);
if pays_addr {
return Ok(true);
}
}
Ok(false)
}
pub(in crate::api::rpc) async fn handle_lnd_createinvoice(
&self,
params: Option<serde_json::Value>,
@ -155,13 +427,23 @@ impl RpcHandler {
"memo": memo,
});
let resp = client
let resp = match client
.post(format!("{LND_REST_BASE_URL}/v1/invoices"))
.header("Grpc-Metadata-macaroon", &macaroon_hex)
.json(&invoice_body)
.send()
.await
.context("Failed to create invoice")?;
{
Ok(r) => r,
Err(e) => {
// A hung/failed mint while LND is explicitly not synced to chain
// gets a clear, user-facing reason instead of an opaque error.
if self.lnd_chain_synced().await == Some(false) {
return Err(Self::syncing_invoice_err());
}
return Err(anyhow::anyhow!(e).context("Failed to create invoice"));
}
};
let status = resp.status();
let body: serde_json::Value = resp
@ -524,8 +806,15 @@ impl RpcHandler {
let entropy_b64 = base64::engine::general_purpose::STANDARD.encode(entropy);
entropy.zeroize();
// Use the per-node secret as the LND wallet password (NOT the
// caller-supplied one) so the unattended boot path can auto-unlock this
// wallet. The wallet stays recoverable from the Archipelago seed via the
// derived entropy above. This unifies both init paths on one password
// source — the divergence here is what left wallets locked fleet-wide.
let _ = wallet_password; // accepted for API compat; superseded by the per-node secret
let node_wallet_pw = crate::container::lnd::ensure_wallet_password().await?;
let wallet_password_b64 =
base64::engine::general_purpose::STANDARD.encode(wallet_password.as_bytes());
base64::engine::general_purpose::STANDARD.encode(node_wallet_pw.as_bytes());
// Call LND REST API to initialize wallet with derived entropy.
// LND must be running but NOT yet initialized (no existing wallet).
@ -579,9 +868,75 @@ fn lnd_error_message(body: &serde_json::Value) -> String {
.to_string()
}
// Stable, machine-readable reason codes for receive-address failures. They are
// embedded in the error message as a `[CODE]` token so the frontend
// (neode-ui/src/utils/bitcoinReceive.ts) can show an accurate explanation
// instead of guessing wallet state by substring-matching — which is what made
// .228 report "wallet is locked" when LND's REST was merely unreachable.
//
// Every receive error string starts with "Bitcoin address" so it survives the
// RPC error sanitizer (api/rpc/middleware.rs) unchanged rather than being
// flattened to the generic "Operation failed" message (the .116 symptom).
pub(crate) const RECEIVE_REST_UNREACHABLE: &str = "LND_REST_UNREACHABLE";
pub(crate) const RECEIVE_WALLET_LOCKED: &str = "LND_WALLET_LOCKED";
pub(crate) const RECEIVE_WALLET_UNINITIALIZED: &str = "LND_WALLET_UNINITIALIZED";
pub(crate) const RECEIVE_SYNCING: &str = "LND_SYNCING";
pub(crate) const RECEIVE_LND_ERROR: &str = "LND_ERROR";
/// Build a receive-address error carrying a reason code the UI can map.
fn receive_error(code: &str, detail: &str) -> anyhow::Error {
anyhow::anyhow!("Bitcoin address unavailable [{code}]: {detail}")
}
/// A sensible default human message per code (used for non-UI callers and logs;
/// the frontend renders its own copy from the code).
fn default_receive_detail(code: &str) -> &'static str {
match code {
RECEIVE_REST_UNREACHABLE => {
"The Lightning wallet service isn't reachable yet. It may be starting up or recovering — please try again in a moment."
}
RECEIVE_WALLET_LOCKED => {
"The Lightning wallet is locked. Unlock it (or finish wallet setup), then try again."
}
RECEIVE_WALLET_UNINITIALIZED => {
"The Lightning wallet isn't set up yet. Finish wallet setup, then try again."
}
RECEIVE_SYNCING => {
"The wallet is still syncing with the Bitcoin network. Please try again once it has caught up."
}
_ => "Couldn't generate a Bitcoin address right now. Please try again shortly.",
}
}
/// Classify a non-2xx LND error body/message into a reason code. The wording of
/// LND's REST errors is stable enough to bucket: a locked wallet, an
/// uninitialized wallet, a syncing chain, or some other failure.
fn classify_lnd_address_error(message: &str) -> &'static str {
let m = message.to_lowercase();
if m.contains("locked") || m.contains("unlock") {
RECEIVE_WALLET_LOCKED
} else if m.contains("synchroniz")
|| m.contains("syncing")
|| m.contains("not yet ready")
|| m.contains("in the process of starting")
{
RECEIVE_SYNCING
} else if m.contains("wallet not found")
|| m.contains("not exist")
|| m.contains("uninitialized")
|| m.contains("not initialized")
|| m.contains("create a wallet")
|| m.contains("no wallet")
{
RECEIVE_WALLET_UNINITIALIZED
} else {
RECEIVE_LND_ERROR
}
}
#[cfg(test)]
mod tests {
use super::lnd_error_message;
use super::*;
#[test]
fn lnd_error_message_prefers_message_field() {
@ -600,4 +955,46 @@ mod tests {
"unknown LND error"
);
}
#[test]
fn classify_locked_wallet() {
assert_eq!(
classify_lnd_address_error("wallet locked, please unlock"),
RECEIVE_WALLET_LOCKED
);
}
#[test]
fn classify_uninitialized_wallet() {
assert_eq!(
classify_lnd_address_error("wallet not found, create a wallet first"),
RECEIVE_WALLET_UNINITIALIZED
);
}
#[test]
fn classify_syncing() {
assert_eq!(
classify_lnd_address_error("server is still in the process of starting"),
RECEIVE_SYNCING
);
}
#[test]
fn classify_unknown_is_generic_error() {
assert_eq!(
classify_lnd_address_error("some other failure"),
RECEIVE_LND_ERROR
);
}
#[test]
fn receive_error_starts_with_sanitizer_safe_prefix_and_embeds_code() {
// Must start with "Bitcoin address" (survives the RPC error sanitizer)
// and carry the [CODE] token the frontend parses.
let err = receive_error(RECEIVE_REST_UNREACHABLE, "unreachable");
let s = format!("{err}");
assert!(s.starts_with("Bitcoin address"), "got: {s}");
assert!(s.contains("[LND_REST_UNREACHABLE]"), "got: {s}");
}
}

View File

@ -0,0 +1,189 @@
//! Mesh-AI assistant RPCs (issue #50): read/update the local assistant config
//! and report whether a local Ollama is available (for the install deep-link).
use super::super::RpcHandler;
use anyhow::Result;
use std::time::Duration;
/// Default model when the node hasn't picked one (kept in sync with the mesh
/// assistant handler's `DEFAULT_MODEL`).
const DEFAULT_MODEL: &str = "qwen2.5-coder";
impl RpcHandler {
/// mesh.assistant-status — current settings + local Ollama availability.
pub(in crate::api::rpc) async fn handle_mesh_assistant_status(
&self,
) -> Result<serde_json::Value> {
let (cfg, denied_askers) = {
let service = self.mesh_service.read().await;
let svc = service
.as_ref()
.ok_or_else(|| anyhow::anyhow!("Mesh service not running"))?;
(svc.assistant_config().await, svc.assistant_denied_askers().await)
};
let (ollama_detected, models) = detect_ollama().await;
let claude_available =
tokio::fs::metadata(self.config.data_dir.join("secrets/claude-api-key"))
.await
.is_ok();
Ok(serde_json::json!({
"enabled": cfg.enabled,
"model": cfg.model,
"trusted_only": cfg.trusted_only,
"backend": cfg.backend,
"allowed_contacts": cfg.allowed_contacts,
"default_model": DEFAULT_MODEL,
"ollama_detected": ollama_detected,
"claude_available": claude_available,
"models": models,
"denied_askers": denied_askers,
}))
}
/// mesh.assistant-configure — update assistant settings live.
/// Params: `enabled?: bool`, `trusted_only?: bool`,
/// `model?: string|null` (string sets, null clears to default, absent leaves).
pub(in crate::api::rpc) async fn handle_mesh_assistant_configure(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let params = params.unwrap_or_default();
let service = self.mesh_service.read().await;
let svc = service
.as_ref()
.ok_or_else(|| anyhow::anyhow!("Mesh service not running"))?;
let enabled = params.get("enabled").and_then(|v| v.as_bool());
let trusted_only = params.get("trusted_only").and_then(|v| v.as_bool());
let backend = params
.get("backend")
.and_then(|v| v.as_str())
.map(|s| s.to_string());
// model: key present + string => set; present + null => clear; absent => leave
let model = if let Some(v) = params.get("model") {
Some(v.as_str().map(|s| s.to_string()))
} else {
None
};
// allowed_contacts: present + array => replace the allowlist (pubkey hex
// strings); absent => leave unchanged.
let allowed_contacts = params
.get("allowed_contacts")
.and_then(|v| v.as_array())
.map(|arr| {
arr.iter()
.filter_map(|e| e.as_str().map(|s| s.to_string()))
.collect::<Vec<String>>()
});
svc.configure_assistant(enabled, model, trusted_only, backend, allowed_contacts)
.await?;
let cfg = svc.assistant_config().await;
Ok(serde_json::json!({
"enabled": cfg.enabled,
"model": cfg.model,
"trusted_only": cfg.trusted_only,
"backend": cfg.backend,
"allowed_contacts": cfg.allowed_contacts,
}))
}
/// mesh.schedule-message — queue a message to send at a future time.
/// Params: `body: string`, `fire_at: i64` (unix secs), and one of
/// `contact_id: u32` (DM) or `channel: u8` (broadcast).
pub(in crate::api::rpc) async fn handle_mesh_schedule_message(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let p = params.ok_or_else(|| anyhow::anyhow!("Missing params"))?;
let body = p
.get("body")
.and_then(|v| v.as_str())
.ok_or_else(|| anyhow::anyhow!("body is required"))?
.to_string();
let fire_at = p
.get("fire_at")
.and_then(|v| v.as_i64())
.ok_or_else(|| anyhow::anyhow!("fire_at (unix seconds) is required"))?;
let contact_id = p
.get("contact_id")
.and_then(|v| v.as_u64())
.map(|v| v as u32);
let channel = p.get("channel").and_then(|v| v.as_u64()).map(|v| v as u8);
if contact_id.is_none() && channel.is_none() {
anyhow::bail!("either contact_id or channel is required");
}
let service = self.mesh_service.read().await;
let svc = service
.as_ref()
.ok_or_else(|| anyhow::anyhow!("Mesh service not running"))?;
let msg = svc
.scheduler
.add(contact_id, channel, body, fire_at)
.await?;
Ok(serde_json::to_value(msg)?)
}
/// mesh.list-scheduled — list queued messages (sorted by fire time).
pub(in crate::api::rpc) async fn handle_mesh_list_scheduled(
&self,
) -> Result<serde_json::Value> {
let service = self.mesh_service.read().await;
let svc = service
.as_ref()
.ok_or_else(|| anyhow::anyhow!("Mesh service not running"))?;
let messages = svc.scheduler.list().await;
Ok(serde_json::json!({ "messages": messages }))
}
/// mesh.cancel-scheduled — remove a queued message by id.
pub(in crate::api::rpc) async fn handle_mesh_cancel_scheduled(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let id = params
.as_ref()
.and_then(|p| p.get("id"))
.and_then(|v| v.as_u64())
.ok_or_else(|| anyhow::anyhow!("id is required"))?;
let service = self.mesh_service.read().await;
let svc = service
.as_ref()
.ok_or_else(|| anyhow::anyhow!("Mesh service not running"))?;
let cancelled = svc.scheduler.cancel(id).await?;
Ok(serde_json::json!({ "cancelled": cancelled }))
}
}
/// Probe the local Ollama HTTP API; return (detected, model_names).
async fn detect_ollama() -> (bool, Vec<String>) {
let client = match reqwest::Client::builder()
.timeout(Duration::from_secs(2))
.build()
{
Ok(c) => c,
Err(_) => return (false, Vec::new()),
};
match client.get("http://localhost:11434/api/tags").send().await {
Ok(resp) if resp.status().is_success() => {
let json: serde_json::Value = resp.json().await.unwrap_or_default();
let models = json
.get("models")
.and_then(|m| m.as_array())
.map(|arr| {
arr.iter()
.filter_map(|m| {
m.get("name")
.and_then(|n| n.as_str())
.map(|s| s.to_string())
})
.collect()
})
.unwrap_or_default();
(true, models)
}
_ => (false, Vec::new()),
}
}

View File

@ -110,6 +110,18 @@ impl RpcHandler {
if let Some(name) = params.get("advert_name").and_then(|v| v.as_str()) {
config.advert_name = Some(name.to_string());
}
if let Some(announce) = params
.get("announce_block_headers")
.and_then(|v| v.as_bool())
{
config.announce_block_headers = announce;
}
if let Some(receive) = params
.get("receive_block_headers")
.and_then(|v| v.as_bool())
{
config.receive_block_headers = receive;
}
mesh::save_config(&self.config.data_dir, &config).await?;
@ -124,6 +136,8 @@ impl RpcHandler {
"configured": true,
"enabled": config.enabled,
"device_path": config.device_path,
"announce_block_headers": config.announce_block_headers,
"receive_block_headers": config.receive_block_headers,
}))
}
}

View File

@ -1,3 +1,4 @@
mod assistant;
mod bitcoin_ops;
mod messaging;
mod safety;

View File

@ -5,26 +5,39 @@ use anyhow::Result;
impl RpcHandler {
/// mesh.status — Get mesh radio status, device info, and peer count.
pub(in crate::api::rpc) async fn handle_mesh_status(&self) -> Result<serde_json::Value> {
// Block-header send/receive prefs live in MeshConfig; surface them in
// status so the UI toggles (issue #28) can show the persisted state.
let config = mesh::load_config(&self.config.data_dir).await?;
let service = self.mesh_service.read().await;
if let Some(svc) = service.as_ref() {
let mut value = if let Some(svc) = service.as_ref() {
let status = svc.status().await;
Ok(serde_json::to_value(status)?)
serde_json::to_value(status)?
} else {
// No service running — return basic config + device detection
let config = mesh::load_config(&self.config.data_dir).await?;
let devices = mesh::detect_devices().await;
Ok(serde_json::json!({
serde_json::json!({
"enabled": config.enabled,
"device_connected": false,
"device_type": "unknown",
"device_path": config.device_path,
"channel_name": config.channel_name.unwrap_or_else(|| "archipelago".to_string()),
"channel_name": config.channel_name.clone().unwrap_or_else(|| "archipelago".to_string()),
"detected_devices": devices,
"peer_count": 0,
"messages_sent": 0,
"messages_received": 0,
}))
})
};
if let Some(obj) = value.as_object_mut() {
obj.insert(
"announce_block_headers".into(),
config.announce_block_headers.into(),
);
obj.insert(
"receive_block_headers".into(),
config.receive_block_headers.into(),
);
}
Ok(value)
}
/// mesh.peers — List discovered mesh peers.
@ -82,12 +95,17 @@ impl RpcHandler {
if let Some(svc) = service.as_ref() {
let peers = svc.peers().await;
let messages = svc.messages(None).await;
// Per-peer last message.
for peer in &peers {
// Collapse radio/federation twins into one conversation per identity
// so a node reachable both ways shows once, with its messages unioned
// across both twin contact_ids (#12).
let groups = mesh::group_peer_twins(&peers);
for group in &groups {
let peer = &group.canonical;
// Newest message across ALL twin contact_ids in this group.
let last = messages
.iter()
.rev()
.find(|m| m.peer_contact_id == peer.contact_id);
.find(|m| group.contact_ids.contains(&m.peer_contact_id));
let is_federation = peer.contact_id & 0x8000_0000 != 0;
conversations.push(serde_json::json!({
"id": format!("{}:{}", if is_federation { "federation" } else { "mesh" }, peer.contact_id),
@ -150,8 +168,16 @@ impl RpcHandler {
let filtered: Vec<_> = match kind {
"mesh" | "federation" => {
let contact_id: u32 = rest.parse().unwrap_or(0);
// Resolve this id's twin group and union messages across all of
// its contact_ids, so opening either twin shows the full thread
// (federation-injected + radio messages) (#12).
let ids: Vec<u32> = mesh::group_peer_twins(&svc.peers().await)
.into_iter()
.find(|g| g.contact_ids.contains(&contact_id))
.map(|g| g.contact_ids)
.unwrap_or_else(|| vec![contact_id]);
all.into_iter()
.filter(|m| m.peer_contact_id == contact_id)
.filter(|m| ids.contains(&m.peer_contact_id))
.collect()
}
"channel" => {
@ -245,43 +271,45 @@ impl RpcHandler {
if let Some(svc) = service.as_ref() {
let state = svc.state();
// Snapshot the firmware pubkeys we currently know about, then
// add them to the radio-contact blocklist. MeshCore's on-device
// contact table is persistent and reads back stale rows on the
// next refresh_contacts, so without this step `clear-all` only
// wipes the app view for a few seconds before the old entries
// reappear. The blocklist is also saved to disk so the filter
// survives a restart.
let firmware_pubkeys: Vec<String> = state
// NOTE: `clear-all` intentionally does NOT build a radio-contact
// blocklist. Permanently ignoring firmware contacts meant a cleared
// peer could never return even when it re-advertised (it also broke
// re-pairing a phone after a clear). Real per-contact blocking will
// be a separate, explicit feature. Here we just wipe the app-side
// view and ALSO clear any blocklist left over from older builds, so
// previously-hidden contacts can re-appear when next heard. The
// firmware's own contact table is the source of truth on refresh.
{
let mut set = state.radio_contact_blocklist.write().await;
set.clear();
}
let _ = crate::mesh::save_ignored_radio_contacts(&data_dir, &[]).await;
// Actually DELETE each radio contact from the firmware table (via
// CMD_REMOVE_CONTACT) so wiped peers don't just reappear on the next
// refresh. They come back only when they re-advertise (reachable).
// Federation-synthetic peers (high contact_id bit) aren't firmware
// contacts, so skip those.
let firmware_pubkeys: Vec<[u8; 32]> = state
.peers
.read()
.await
.values()
.filter_map(|p| {
// Federation-synthetic peers have their contact_id in the
// high half of u32 and carry the archipelago key — those
// aren't firmware contacts and must not go on the list.
if p.contact_id & 0x8000_0000 != 0 {
None
} else {
p.pubkey_hex.clone()
}
.filter(|p| p.contact_id & 0x8000_0000 == 0)
.filter_map(|p| p.pubkey_hex.as_deref())
.filter_map(|h| hex::decode(h).ok())
.filter(|b| b.len() == 32)
.map(|b| {
let mut k = [0u8; 32];
k.copy_from_slice(&b);
k
})
.collect();
{
let mut set = state.radio_contact_blocklist.write().await;
for pk in &firmware_pubkeys {
set.insert(pk.clone());
}
for pk in firmware_pubkeys {
let _ = state
.send_cmd(crate::mesh::listener::MeshCommand::RemoveContact { pubkey: pk })
.await;
}
let persisted: Vec<String> = state
.radio_contact_blocklist
.read()
.await
.iter()
.cloned()
.collect();
let _ = crate::mesh::save_ignored_radio_contacts(&data_dir, &persisted).await;
state.peers.write().await.clear();
state.messages.write().await.clear();

View File

@ -1133,9 +1133,13 @@ impl RpcHandler {
.ok_or_else(|| anyhow::anyhow!("Mesh service not running"))?;
let state = svc.shared_state();
let contacts = state.contacts.read().await;
let peers = state.peers.read().await;
let peer_vec: Vec<_> = state.peers.read().await.values().cloned().collect();
// Collapse radio/federation twins so a node reachable both ways shows as
// one contact instead of two (#12).
let groups = crate::mesh::group_peer_twins(&peer_vec);
let mut out: Vec<serde_json::Value> = Vec::new();
for peer in peers.values() {
for group in &groups {
let peer = &group.canonical;
if let Some(pk) = peer.pubkey_hex.as_ref() {
let entry = contacts.get(pk).cloned().unwrap_or_default();
out.push(serde_json::json!({
@ -1184,6 +1188,12 @@ impl RpcHandler {
entry.pinned = p;
}
let saved = entry.clone();
let snapshot = contacts.clone();
drop(contacts);
// Persist (encrypted, atomic) so the customisation survives restarts.
if let Err(e) = crate::mesh::save_mesh_contacts(&self.config.data_dir, &snapshot).await {
tracing::warn!("failed to persist mesh contacts: {e}");
}
Ok(serde_json::json!({
"saved": true,
"pubkey": pubkey,
@ -1215,6 +1225,11 @@ impl RpcHandler {
let mut contacts = state.contacts.write().await;
let entry = contacts.entry(pubkey.clone()).or_default();
entry.blocked = blocked;
let snapshot = contacts.clone();
drop(contacts);
if let Err(e) = crate::mesh::save_mesh_contacts(&self.config.data_dir, &snapshot).await {
tracing::warn!("failed to persist mesh contacts: {e}");
}
Ok(serde_json::json!({ "pubkey": pubkey, "blocked": blocked }))
}

View File

@ -9,6 +9,7 @@ mod credentials;
mod dispatcher;
mod dwn;
mod federation;
mod fedimint;
mod fips;
mod handshake;
mod identity;

View File

@ -32,6 +32,8 @@ fn is_platform_managed_app(app_id: &str) -> bool {
| "fedimint-gateway"
| "indeedhub"
| "immich"
| "fips"
| "fips-ui"
)
}
@ -347,13 +349,37 @@ fn http_probe_cmd(url: &'static str) -> &'static str {
}
}
/// Bitcoin UTXO cache (`-dbcache`) in MB, sized to host RAM.
///
/// A fixed large dbcache on a small box pushes bitcoind + the ~20 app
/// containers past physical RAM and triggers system-wide swap thrash: the
/// disk saturates, bitcoind can't answer its own RPC, and the dashboard
/// backend's sqlite reads stall — surfacing as /rpc/v1 502s and a blank
/// Bitcoin UI. Budget ~1/16 of RAM for the cache (floor 300 MB — bitcoind's
/// own default is 450 — cap 4096 MB), mirroring scripts/container-specs.sh.
pub(super) fn bitcoin_dbcache_mb() -> u64 {
let total_mb = std::fs::read_to_string("/proc/meminfo")
.ok()
.and_then(|c| {
c.lines()
.find_map(|l| l.strip_prefix("MemTotal:"))
.and_then(|v| v.split_whitespace().next())
.and_then(|kb| kb.parse::<u64>().ok())
})
.map(|kb| kb / 1024)
.unwrap_or(16000); // assume a comfortable host if /proc/meminfo is unreadable
(total_mb / 16).clamp(300, 4096)
}
/// Get per-app memory limit.
pub(super) fn get_memory_limit(app_id: &str) -> &'static str {
match app_id {
// Heavy apps. Bitcoin: dbcache uses ~4GB; the daemon also needs
// headroom for mempool + connection buffers + script-verifier
// memory + I/O. 4g caused OOM-cascades during IBD. 8g is the
// floor; ideally this would be host-RAM aware (next pass).
// Heavy apps. Bitcoin: dbcache is now host-RAM-aware (see
// bitcoin_dbcache_mb), so the daemon's footprint scales with the box.
// This cgroup cap is an upper bound for mempool + connection buffers +
// script-verifier memory + I/O; a tight cap (4g) previously caused
// OOM-cascades during IBD, so keep 8g as a generous ceiling rather
// than a tight limit — swap thrash is prevented at the dbcache layer.
"bitcoin" | "bitcoin-core" | "bitcoin-knots" => "8g",
// ElectrumX indexing spikes above its cache size due Python,
// RocksDB, socket buffers, and reorg/history work. Keep cache
@ -672,9 +698,10 @@ pub(super) async fn get_app_config(
// RPC is reachable from the bitcoin-ui companion container.
//
// Sync-speed flags:
// -dbcache=4096 — UTXO set cache; 4GB is the sweet spot before
// diminishing returns. Container has --memory=8g now so
// there's headroom for mempool + connections.
// -dbcache — UTXO set cache, sized to host RAM via
// bitcoin_dbcache_mb() (see there). A fixed 4GB cache swap-
// thrashed small nodes into fleet-wide 502s; ~1/16 of RAM
// keeps headroom for mempool + connections + the app stack.
// -par=0 — use all available cores for script
// verification (defaults to NCPU-1 capped at 16). Was
// effectively pinned at 2 by --cpus=2 (now removed).
@ -687,7 +714,7 @@ pub(super) async fn get_app_config(
"-rpcport=8332".to_string(),
"-printtoconsole=1".to_string(),
"-datadir=/home/bitcoin/.bitcoin".to_string(),
"-dbcache=4096".to_string(),
format!("-dbcache={}", bitcoin_dbcache_mb()),
"-par=0".to_string(),
"-maxconnections=125".to_string(),
]),
@ -750,27 +777,33 @@ pub(super) async fn get_app_config(
None,
None,
),
"mempool-api" => (
vec!["8999:8999".to_string()],
vec!["/var/lib/archipelago/mempool:/data".to_string()],
vec![
"MEMPOOL_BACKEND=electrum".to_string(),
"ELECTRUM_HOST=electrumx".to_string(),
"ELECTRUM_PORT=50001".to_string(),
"ELECTRUM_TLS_ENABLED=false".to_string(),
"CORE_RPC_HOST=bitcoin-knots".to_string(),
"CORE_RPC_PORT=8332".to_string(),
"CORE_RPC_USERNAME=archipelago".to_string(),
format!("CORE_RPC_PASSWORD={}", rpc_pass),
"DATABASE_ENABLED=true".to_string(),
"DATABASE_HOST=archy-mempool-db".to_string(),
"DATABASE_DATABASE=mempool".to_string(),
"DATABASE_USERNAME=mempool".to_string(),
format!("DATABASE_PASSWORD={}", read_secret("mempool-db-password", "mempoolpass")),
],
None,
None,
),
"mempool-api" => {
// CORE_RPC_HOST must resolve to the actual Bitcoin node container —
// bitcoin-knots OR bitcoin-core — else mempool-api can't reach RPC
// on a Core node (B12). Falls back to bitcoin-knots if undetected.
let bitcoin_rpc_host = super::dependencies::detect_bitcoin_rpc_host().await;
(
vec!["8999:8999".to_string()],
vec!["/var/lib/archipelago/mempool:/data".to_string()],
vec![
"MEMPOOL_BACKEND=electrum".to_string(),
"ELECTRUM_HOST=electrumx".to_string(),
"ELECTRUM_PORT=50001".to_string(),
"ELECTRUM_TLS_ENABLED=false".to_string(),
format!("CORE_RPC_HOST={}", bitcoin_rpc_host),
"CORE_RPC_PORT=8332".to_string(),
"CORE_RPC_USERNAME=archipelago".to_string(),
format!("CORE_RPC_PASSWORD={}", rpc_pass),
"DATABASE_ENABLED=true".to_string(),
"DATABASE_HOST=archy-mempool-db".to_string(),
"DATABASE_DATABASE=mempool".to_string(),
"DATABASE_USERNAME=mempool".to_string(),
format!("DATABASE_PASSWORD={}", read_secret("mempool-db-password", "mempoolpass")),
],
None,
None,
)
}
"electrumx" | "mempool-electrs" | "electrs" => {
(
vec!["50001:50001".to_string()],

View File

@ -84,6 +84,78 @@ pub(super) async fn detect_running_deps() -> Result<RunningDeps> {
})
}
/// Detect the container name of the running Bitcoin node so dependent stacks
/// (mempool) can point CORE_RPC_HOST at the right host. Bitcoin Knots and Bitcoin
/// Core are both reachable on archy-net by their container name — only the name
/// differs (`bitcoin-knots` vs `bitcoin-core`), so hardcoding one breaks the
/// other. Returns the first running BITCOIN_NAMES match; falls back to the
/// default `bitcoin-knots` if none is detected (callers gate on has_bitcoin).
pub(super) async fn detect_bitcoin_rpc_host() -> String {
let out = tokio::time::timeout(
std::time::Duration::from_secs(15),
tokio::process::Command::new("podman")
.args(["ps", "--format", "{{.Names}}"])
.output(),
)
.await;
if let Ok(Ok(o)) = out {
if o.status.success() {
let running = String::from_utf8_lossy(&o.stdout);
if let Some(name) = pick_bitcoin_host(&running) {
return name;
}
}
}
"bitcoin-knots".to_string()
}
/// Pure host-selection step of [`detect_bitcoin_rpc_host`], split out so it can
/// be unit-tested without a podman runtime. Returns the first `podman ps` line
/// whose trimmed name is one of [`BITCOIN_NAMES`]. (The Quadlet orchestrator
/// mirrors this in `prod_orchestrator::bitcoin_host`.)
fn pick_bitcoin_host(podman_names: &str) -> Option<String> {
podman_names
.lines()
.map(|l| l.trim())
.find(|name| BITCOIN_NAMES.contains(name))
.map(|name| name.to_string())
}
#[cfg(test)]
mod bitcoin_host_tests {
use super::pick_bitcoin_host;
#[test]
fn picks_knots() {
let ps = "electrumx\nbitcoin-knots\narchy-mempool-db\n";
assert_eq!(pick_bitcoin_host(ps).as_deref(), Some("bitcoin-knots"));
}
#[test]
fn picks_core() {
let ps = "lnd\nbitcoin-core\nelectrumx\n";
assert_eq!(pick_bitcoin_host(ps).as_deref(), Some("bitcoin-core"));
}
#[test]
fn picks_plain_bitcoin() {
assert_eq!(pick_bitcoin_host("bitcoin\n").as_deref(), Some("bitcoin"));
}
#[test]
fn none_when_no_bitcoin_node() {
let ps = "electrumx\nlnd\narchy-mempool-db\n";
assert_eq!(pick_bitcoin_host(ps), None);
}
#[test]
fn ignores_substring_matches() {
// A companion UI container must NOT be mistaken for the node itself.
let ps = "archy-bitcoin-ui\nbitcoin-knots-foo\n";
assert_eq!(pick_bitcoin_host(ps), None);
}
}
/// Verify that required dependency services are running before installing an app.
/// Returns an error with a user-friendly message if dependencies are missing.
pub(super) fn check_install_deps(package_id: &str, deps: &RunningDeps) -> Result<()> {
@ -304,16 +376,31 @@ pub(super) fn startup_order(package_id: &str) -> &'static [&'static str] {
/// order for the given app. Unknown containers sort to the end.
pub(super) async fn ordered_containers_for_start(package_id: &str) -> Result<Vec<String>> {
let containers = get_containers_for_app(package_id).await?;
Ok(order_present_containers(package_id, containers))
}
/// Order the *actually-present* containers of an app by its dependency-aware
/// startup order. Containers whose name is unknown to the order list sort to
/// the end, preserving their relative input order.
///
/// This deliberately does NOT inject order entries that aren't live
/// containers. `startup_order` is a union of container-name variants across
/// install generations (e.g. `mysql-mempool` vs `archy-mempool-db`), so any
/// single install only ever has a subset of those names. Injecting a phantom
/// name makes the start path fail on a "no such object" inspect — and because
/// `do_orchestrator_package_start` propagates the unknown-app-id fallback
/// error via `?`, every later member (the api + frontend) is then skipped,
/// leaving the stack down until the health monitor recovers it minutes later.
/// That was the source of mempool gate flakes #73 (frontend) / #74 (api).
fn order_present_containers(package_id: &str, containers: Vec<String>) -> Vec<String> {
if containers.is_empty() {
// Nothing is live under any known name. Fall back to the package id so
// a single-container app whose container matches its id still gets one
// start attempt; multi-container stacks with no live members are
// surfaced as "no containers" by the caller's emptiness check.
return vec![package_id.to_string()];
}
let order = startup_order(package_id);
if order.is_empty() && containers.is_empty() {
return Ok(vec![package_id.to_string()]);
}
let mut sorted = containers;
for required in order {
if !sorted.iter().any(|name| name == required) {
sorted.push((*required).to_string());
}
}
// If no special order is defined, fall back to mempool order for legacy
// multi-container names that may still be returned by config lookups.
let effective_order: &[&str] = if order.is_empty() {
@ -321,8 +408,14 @@ pub(super) async fn ordered_containers_for_start(package_id: &str) -> Result<Vec
} else {
order
};
sorted.sort_by_key(|c| effective_order.iter().position(|o| *o == c).unwrap_or(99));
Ok(sorted)
let mut sorted = containers;
sorted.sort_by_key(|c| {
effective_order
.iter()
.position(|o| *o == c)
.unwrap_or(usize::MAX)
});
sorted
}
/// Configure Fedimint Gateway to use LND instead of LDK.
@ -380,7 +473,48 @@ pub(super) fn configure_fedimint_lnd(
#[cfg(test)]
mod tests {
use super::{requires_unpruned_bitcoin, startup_order};
use super::{order_present_containers, requires_unpruned_bitcoin, startup_order};
#[test]
fn order_present_containers_never_injects_phantom_stack_members() {
// The live mempool stack on a node: db + api + frontend. These are the
// only real container names; the startup_order list also contains
// variant/legacy names (mysql-mempool, archy-mempool-api, ...) that are
// NOT live here and must never appear in the result — a phantom name in
// the start list aborts the orchestrator start mid-sequence (gate
// #73/#74).
let present = vec![
"mempool".to_string(),
"mempool-api".to_string(),
"archy-mempool-db".to_string(),
];
let ordered = order_present_containers("mempool", present);
// Dependency order: db -> api -> frontend.
assert_eq!(ordered, vec!["archy-mempool-db", "mempool-api", "mempool"]);
// No phantom variants leaked in.
for phantom in ["mysql-mempool", "archy-mempool-api", "archy-mempool-web"] {
assert!(
!ordered.iter().any(|c| c == phantom),
"phantom {phantom} must not be injected"
);
}
}
#[test]
fn order_present_containers_orders_known_before_unknown() {
let present = vec!["mempool".to_string(), "some-sidecar".to_string()];
let ordered = order_present_containers("mempool", present);
// The known frontend sorts ahead of an unknown sidecar.
assert_eq!(ordered, vec!["mempool", "some-sidecar"]);
}
#[test]
fn order_present_containers_empty_falls_back_to_package_id() {
assert_eq!(
order_present_containers("mempool", vec![]),
vec!["mempool".to_string()]
);
}
#[test]
fn btcpay_start_order_includes_required_stack_members() {

View File

@ -22,6 +22,11 @@ const PODMAN_LOG_TIMEOUT: Duration = Duration::from_secs(15);
/// Per-container graceful shutdown timeout in seconds.
/// Bitcoin Core needs 600s to flush UTXO set, LND 330s for channel state,
/// indexers 300s for index flush, databases 120s for WAL/transaction commit.
///
/// MIRRORS `archipelago_container::runtime::stop_grace_secs_for` (which returns
/// `u64` and is the canonical table used by the orchestrator stop path). This
/// `&str` variant exists for the legacy `podman stop -t <s>` call sites here —
/// keep the two tables in sync until those are migrated to the orchestrator.
pub fn stop_timeout_secs(container_name: &str) -> &'static str {
let id = container_name
.strip_prefix("archy-")
@ -307,7 +312,16 @@ impl RpcHandler {
let mut stopped = 0u32;
let mut removed = 0u32;
let mut errors = Vec::new();
// Two distinct failure classes, kept separate so they don't get
// conflated (the old single `errors` vec did, which caused the "ghost in
// My Apps" bug): `container_errors` means a container could NOT be
// removed (force-rm failed too) — the app is genuinely still present, so
// we keep its state entry and surface a hard error. `cleanup_errors`
// means volume/network/data-dir teardown left residue — the containers
// are already gone, so the app IS uninstalled and MUST disappear from My
// Apps; the residue is logged but never ghosts the app.
let mut container_errors: Vec<String> = Vec::new();
let mut cleanup_errors: Vec<String> = Vec::new();
self.set_uninstall_stage(
package_id,
@ -365,7 +379,7 @@ impl RpcHandler {
let msg =
format!("Failed to remove {}: {}; {}", name, stderr.trim(), e);
tracing::error!("Uninstall {}: {}", package_id, msg);
errors.push(msg);
container_errors.push(msg);
}
}
}
@ -374,12 +388,35 @@ impl RpcHandler {
Err(force_err) => {
let msg = format!("Failed to remove {}: {}; {}", name, e, force_err);
tracing::error!("Uninstall {}: {}", package_id, msg);
errors.push(msg);
container_errors.push(msg);
}
},
}
}
// A container that survived even force-remove means the app is NOT
// actually uninstalled — keep its state entry and fail so the spawned
// task reverts it to its prior state (and the user can retry), rather
// than orphaning a live container that's missing from My Apps.
if !container_errors.is_empty() {
tracing::error!(
"Uninstall {}: containers could not be removed: {:?}",
package_id,
container_errors
);
return Err(anyhow::anyhow!(
"Uninstall {} failed: {}",
package_id,
container_errors.join("; ")
));
}
// Containers are gone → the app is uninstalled. Remove its state entry
// NOW, before the (possibly slow, possibly fallible) volume/data
// teardown below, so My Apps updates immediately and a residue failure
// can never leave a ghost. Reinstall/scan no longer see a stale entry.
self.remove_package_state_entry(package_id).await;
self.set_uninstall_stage(package_id, "Cleaning up volumes")
.await;
// Avoid global Podman volume prune on production nodes: store-wide
@ -427,70 +464,73 @@ impl RpcHandler {
let stderr = String::from_utf8_lossy(&o.stderr);
let msg = format!("Failed to remove data {}: {}", dir, stderr.trim());
tracing::error!("Uninstall {}: {}", package_id, msg);
errors.push(msg);
cleanup_errors.push(msg);
}
Err(e) => {
let msg = format!("Failed to remove data {}: {}", dir, e);
tracing::error!("Uninstall {}: {}", package_id, msg);
errors.push(msg);
cleanup_errors.push(msg);
}
_ => {}
}
}
}
if !errors.is_empty() {
// The app is already gone from My Apps (entry removed above). Residual
// volume/data cleanup failures are logged but NEVER ghost the app — a
// reinstall and the next uninstall both tolerate leftover dirs.
if !cleanup_errors.is_empty() {
tracing::error!(
"Uninstall {} completed with errors: {:?}",
"Uninstall {} removed but left cleanup residue: {:?}",
package_id,
errors
cleanup_errors
);
return Err(anyhow::anyhow!(
"Uninstall {} partially failed: {}",
package_id,
errors.join("; ")
));
}
tracing::info!(
"Uninstall {} complete: stopped={}, removed={}",
"Uninstall {} complete: stopped={}, removed={}, cleanup_errors={}",
package_id,
stopped,
removed
removed,
cleanup_errors.len()
);
// Immediately remove from in-memory state so the UI updates without
// waiting for the scanner's absence threshold (3 scans × 60s each).
{
let (mut data, _rev) = self.state_manager.get_snapshot().await;
let before = data.package_data.len();
data.package_data.remove(package_id);
// Also remove any alias keys (e.g. "bitcoin-knots" vs "bitcoin")
let aliases: Vec<String> = data
.package_data
.keys()
.filter(|k| {
super::config::all_container_names(package_id)
.iter()
.any(|c| c.strip_prefix("archy-").unwrap_or(c) == k.as_str())
})
.cloned()
.collect();
for alias in &aliases {
data.package_data.remove(alias);
}
if data.package_data.len() < before {
self.state_manager.update_data(data).await;
}
}
Ok(serde_json::json!({
"status": "uninstalled",
"stopped": stopped,
"removed": removed,
"cleanup_warnings": cleanup_errors,
}))
}
/// Remove a package's entry (and any alias keys) from persisted state so it
/// disappears from My Apps immediately, without waiting for the scanner's
/// absence threshold (3 scans × 60s). Called as soon as an uninstall has
/// removed the app's containers — before the slower volume/data teardown —
/// so a residue failure can never leave a ghost entry behind.
async fn remove_package_state_entry(&self, package_id: &str) {
let (mut data, _rev) = self.state_manager.get_snapshot().await;
let before = data.package_data.len();
data.package_data.remove(package_id);
// Also remove any alias keys (e.g. "bitcoin-knots" vs "bitcoin").
let aliases: Vec<String> = data
.package_data
.keys()
.filter(|k| {
super::config::all_container_names(package_id)
.iter()
.any(|c| c.strip_prefix("archy-").unwrap_or(c) == k.as_str())
})
.cloned()
.collect();
for alias in &aliases {
data.package_data.remove(alias);
}
if data.package_data.len() < before {
self.state_manager.update_data(data).await;
}
}
/// Start a bundled app (create container from pre-loaded image if needed).
pub(in crate::api::rpc) async fn handle_bundled_app_start(
&self,

View File

@ -6,7 +6,6 @@
use crate::api::rpc::RpcHandler;
use crate::data_model::InstallPhase;
use anyhow::{Context, Result};
use base64::Engine;
use std::process::Output;
use std::time::Duration;
use tracing::info;
@ -434,6 +433,13 @@ async fn wait_for_stack_containers(
containers: &[&str],
timeout_secs: u64,
) -> Result<()> {
// A container can exit on its first start because a dependency (db, redis,
// the bitcoin node) was not quite ready — a transient crash, not a broken
// install. Restart each exited container a bounded number of times before
// declaring the install failed (#25). The runtime supervisor keeps it alive
// afterwards, but we want a healthy state by the time install returns.
const MAX_RESTARTS: u32 = 3;
let mut restarts: std::collections::HashMap<String, u32> = std::collections::HashMap::new();
let deadline = std::time::Instant::now() + std::time::Duration::from_secs(timeout_secs);
loop {
let mut pending = Vec::new();
@ -449,20 +455,41 @@ async fn wait_for_stack_containers(
match state.as_str() {
"running" => {}
"exited" | "dead" => {
let logs = stack_container_logs(container, 40).await;
install_log(&format!(
"INSTALL CRASH: {} - container {} exited. Logs:\n{}",
stack_name,
container,
logs.chars().take(1000).collect::<String>()
))
.await;
return Err(anyhow::anyhow!(
"{} container {} exited after install. Logs: {}",
stack_name,
container,
logs.chars().take(500).collect::<String>()
));
let attempts = restarts.entry(container.to_string()).or_insert(0);
if *attempts < MAX_RESTARTS {
*attempts += 1;
install_log(&format!(
"INSTALL RESTART: {} - container {} exited, restart attempt {}/{}",
stack_name, container, *attempts, MAX_RESTARTS
))
.await;
let _ = podman_stack_output(
&["start", container],
PODMAN_STACK_PROBE_TIMEOUT,
)
.await;
pending.push(format!(
"{}=restarting({}/{})",
container, *attempts, MAX_RESTARTS
));
} else {
let logs = stack_container_logs(container, 40).await;
install_log(&format!(
"INSTALL CRASH: {} - container {} exited after {} restarts. Logs:\n{}",
stack_name,
container,
MAX_RESTARTS,
logs.chars().take(1000).collect::<String>()
))
.await;
return Err(anyhow::anyhow!(
"{} container {} exited after install ({} restarts). Logs: {}",
stack_name,
container,
MAX_RESTARTS,
logs.chars().take(500).collect::<String>()
));
}
}
other => pending.push(format!("{}={}", container, other)),
}
@ -592,16 +619,25 @@ async fn install_stack_via_orchestrator(
))
.await;
let mut installed = 0usize;
for app_id in app_ids {
match orchestrator.install(app_id).await {
Ok(container_name) => {
installed += 1;
install_log(&format!(
"INSTALL ORCH: {} stack — app {} installed as {}",
stack_name, app_id, container_name
))
.await;
}
Err(e) if e.to_string().contains("unknown app_id") => {
Err(e) if e.to_string().contains("unknown app_id") && installed == 0 => {
// None of the stack's manifests are known — the orchestrator
// can't render this stack at all, so defer to the legacy
// installer. Only safe when NOTHING was installed yet: once an
// earlier member is up, falling back would let the legacy path
// double-create containers on the same data dir (observed
// corrupting an immich postgres cluster — two postmasters, one
// PGDATA). A partial set means a deploy bug, not a legacy node.
install_log(&format!(
"INSTALL ORCH SKIP: {} stack — app {} unknown, falling back to legacy stack installer",
stack_name, app_id
@ -609,6 +645,17 @@ async fn install_stack_via_orchestrator(
.await;
return Ok(None);
}
Err(e) if e.to_string().contains("unknown app_id") => {
install_log(&format!(
"INSTALL ORCH FAIL: {} stack — app {} unknown AFTER {} installed; refusing legacy fallback (would double-create on shared data)",
stack_name, app_id, installed
))
.await;
return Err(e.context(format!(
"orchestrator stack install {} aborted: app {} has no manifest but {} member(s) already installed — deploy all stack manifests",
stack_name, app_id, installed
)));
}
Err(e) => {
install_log(&format!(
"INSTALL ORCH FAIL: {} stack — app {} failed: {}",
@ -640,11 +687,42 @@ fn mempool_stack_app_ids() -> &'static [&'static str] {
&["archy-mempool-db", "mempool-api", "archy-mempool-web"]
}
const REGISTRY: &str = "146.59.87.168:3000/lfg2025";
fn immich_stack_app_ids() -> &'static [&'static str] {
// Install order = dependency order: db + cache before the server. The server
// app_id is the user-facing "immich" (canonical name + icon); its install is
// handled here (not recursively) since orchestrator.install bypasses the
// package.install routing that maps "immich" → this stack installer.
&["immich-postgres", "immich-redis", "immich"]
}
const NETBIRD_DASHBOARD_IMAGE: &str = "docker.io/netbirdio/dashboard:v2.38.0";
const NETBIRD_SERVER_IMAGE: &str = "docker.io/netbirdio/netbird-server:0.71.2";
const NETBIRD_PROXY_IMAGE: &str = "docker.io/library/nginx:1.27-alpine";
fn netbird_stack_app_ids() -> &'static [&'static str] {
// Dependency/startup order: the combined management/signal/relay server
// first (it owns the base64 relay/store secrets + the sqlite store, and is
// the OIDC issuer the others point at), then the dashboard SPA, then the
// user-facing TLS proxy ("netbird", which carries the self-signed cert +
// the templated nginx.conf and is the launcher). Mirrors the netbird
// startup_order in dependencies.rs.
&["netbird-server", "netbird-dashboard", "netbird"]
}
fn indeedhub_stack_app_ids() -> &'static [&'static str] {
// Dependency order: backends + their generated secrets first, then the api
// (owns indeedhub-jwt; reads the db/minio secrets the backends materialised),
// then the ffmpeg worker, then the user-facing frontend ("indeedhub", which
// carries the post_install nginx hook). The frontend's nginx reaches the
// backends by their short network_aliases (api/minio/relay) on indeedhub-net.
&[
"indeedhub-postgres",
"indeedhub-redis",
"indeedhub-minio",
"indeedhub-relay",
"indeedhub-api",
"indeedhub-ffmpeg",
"indeedhub",
]
}
const REGISTRY: &str = "146.59.87.168:3000/lfg2025";
/// Pull an image with retry and exponential backoff (3 attempts).
async fn pull_image_with_retry(image: &str) -> Result<()> {
@ -706,6 +784,17 @@ async fn pull_image_with_retry(image: &str) -> Result<()> {
impl RpcHandler {
/// Install Immich stack (postgres + redis + server).
pub(super) async fn install_immich_stack(&self) -> Result<serde_json::Value> {
// Manifest-driven path (workstream B/C): render the stack from
// apps/immich-*/manifest.yml via the orchestrator (rootless Quadlet
// units, generated_secrets, reboot-survivable). Falls back to the legacy
// installer below only when the orchestrator doesn't know these app_ids
// (manifests not yet deployed). See docs/PRODUCTION-MASTER-PLAN.md.
if let Some(orchestrated) =
install_stack_via_orchestrator(self, "immich", immich_stack_app_ids()).await?
{
return Ok(orchestrated);
}
if let Some(adopted) = adopt_stack_if_exists(
"immich_server",
"immich",
@ -1152,6 +1241,9 @@ impl RpcHandler {
let deps = super::dependencies::detect_running_deps().await?;
super::dependencies::check_install_deps("mempool", &deps)?;
let (_, rpc_pass) = crate::bitcoin_rpc::bitcoin_rpc_credentials().await;
// CORE_RPC_HOST must match the actual Bitcoin node container name —
// bitcoin-knots OR bitcoin-core — else mempool-api can't reach RPC (B12).
let bitcoin_rpc_host = super::dependencies::detect_bitcoin_rpc_host().await;
install_log("INSTALL START: mempool (stack: mariadb + mempool-api + mempool-web)").await;
@ -1275,7 +1367,7 @@ impl RpcHandler {
"-e",
"ELECTRUM_TLS_ENABLED=false",
"-e",
"CORE_RPC_HOST=bitcoin-knots",
&format!("CORE_RPC_HOST={}", bitcoin_rpc_host),
"-e",
"CORE_RPC_PORT=8332",
"-e",
@ -1352,6 +1444,20 @@ impl RpcHandler {
/// Install the IndeedHub multi-container stack.
pub(super) async fn install_indeedhub_stack(&self) -> Result<serde_json::Value> {
// Manifest-driven path (#20 phase 3): render the 7-member stack from
// apps/indeedhub-*/manifest.yml via the orchestrator (dedicated
// indeedhub-net + network_aliases, generated_secrets, the frontend's
// post_install nginx hook, reboot-survivable). The manifests use the exact
// live container names / named volumes, so on an existing node this ADOPTS
// the running stack rather than recreating it (data preserved). Falls back
// to the legacy installer below only when the orchestrator doesn't know
// these app_ids (manifests not yet deployed). See PRODUCTION-MASTER-PLAN.md.
if let Some(orchestrated) =
install_stack_via_orchestrator(self, "indeedhub", indeedhub_stack_app_ids()).await?
{
return Ok(orchestrated);
}
let registry = crate::container::registry::load_registries(&self.config.data_dir)
.await
.unwrap_or_default()
@ -1727,6 +1833,27 @@ impl RpcHandler {
/// Install self-hosted NetBird (dashboard + combined management/signal/relay server).
pub(super) async fn install_netbird_stack(&self) -> Result<serde_json::Value> {
// Manifest-driven path (#20 phase 4): render the 3-member stack from
// apps/netbird-*/manifest.yml via the orchestrator — dedicated
// netbird-net + network_aliases, base64 generated_secrets, a self-signed
// TLS cert (generated_certs) so the dashboard gets a secure context for
// OIDC PKCE (#15), and templated config.yaml/nginx.conf rendered from
// host facts + the netbird-net gateway. The manifests use the exact live
// container names, so on an existing node this ADOPTS the running stack
// rather than recreating it (the sqlite store + base64 keys are
// preserved — ensure_generated_secrets no-ops on existing files).
//
// #20 ph4: the legacy hardcoded `podman run` installer was DELETED — the
// signed catalog always ships apps/netbird-*/manifest.yml, so there is no
// in-Rust fallback. If the orchestrator doesn't know these app_ids and no
// running stack exists to adopt, install errors rather than silently
// diverging from the manifest contract.
if let Some(orchestrated) =
install_stack_via_orchestrator(self, "netbird", netbird_stack_app_ids()).await?
{
return Ok(orchestrated);
}
if let Some(adopted) = adopt_stack_if_exists(
"netbird",
"netbird",
@ -1737,271 +1864,12 @@ impl RpcHandler {
return Ok(adopted);
}
install_log("INSTALL START: netbird stack (dashboard + server)").await;
info!("Installing self-hosted NetBird stack");
self.set_install_phase("netbird", InstallPhase::PullingImage)
.await;
for (i, image) in [
NETBIRD_DASHBOARD_IMAGE,
NETBIRD_SERVER_IMAGE,
NETBIRD_PROXY_IMAGE,
]
.iter()
.enumerate()
{
self.set_install_progress("netbird", i as u64, 3).await;
pull_image_with_retry(image)
.await
.with_context(|| format!("Failed to pull NetBird image: {}", image))?;
}
self.set_install_progress("netbird", 3, 3).await;
for name in ["netbird", "netbird-dashboard", "netbird-server"] {
let _ = podman_stack_status(&["rm", "-f", name], PODMAN_STACK_PROBE_TIMEOUT).await;
}
let _ = podman_stack_status(
&["network", "rm", "-f", "netbird-net"],
PODMAN_STACK_PROBE_TIMEOUT,
anyhow::bail!(
"netbird manifests not available on this node — the signed catalog must provide apps/netbird-*/manifest.yml (legacy hardcoded installer removed in #20 ph4)"
)
.await;
self.set_install_phase("netbird", InstallPhase::CreatingContainer)
.await;
tokio::fs::create_dir_all("/var/lib/archipelago/netbird/data")
.await
.context("Failed to create NetBird data directory")?;
let host_ip = detect_netbird_public_host_ip()
.await
.unwrap_or_else(|| self.config.host_ip.clone());
write_netbird_config_files(&host_ip).await?;
let _ = podman_stack_status(
&["network", "create", "netbird-net"],
PODMAN_STACK_PROBE_TIMEOUT,
)
.await;
let mut server_cmd = tokio::process::Command::new("podman");
server_cmd.args([
"run",
"-d",
"--name",
"netbird-server",
"--network",
"netbird-net",
"--network-alias",
"netbird-server",
"--restart=unless-stopped",
"-p",
"8086:80",
"-p",
"3478:3478/udp",
"-v",
"/var/lib/archipelago/netbird/data:/var/lib/netbird",
"-v",
"/var/lib/archipelago/netbird/config.yaml:/etc/netbird/config.yaml:ro",
NETBIRD_SERVER_IMAGE,
"--config",
"/etc/netbird/config.yaml",
]);
run_required_stack_command("netbird", "create server", &mut server_cmd).await?;
self.set_install_phase("netbird", InstallPhase::StartingContainer)
.await;
tokio::time::sleep(std::time::Duration::from_secs(5)).await;
let mut dashboard_cmd = tokio::process::Command::new("podman");
dashboard_cmd.args([
"run",
"-d",
"--name",
"netbird-dashboard",
"--network",
"netbird-net",
"--restart=unless-stopped",
"--env-file",
"/var/lib/archipelago/netbird/dashboard.env",
NETBIRD_DASHBOARD_IMAGE,
]);
run_required_stack_command("netbird", "create dashboard", &mut dashboard_cmd).await?;
let mut proxy_cmd = tokio::process::Command::new("podman");
proxy_cmd.args([
"run",
"-d",
"--name",
"netbird",
"--network",
"netbird-net",
"--restart=unless-stopped",
"-p",
"8087:80",
"-v",
"/var/lib/archipelago/netbird/nginx.conf:/etc/nginx/conf.d/default.conf:ro",
NETBIRD_PROXY_IMAGE,
]);
run_required_stack_command("netbird", "create unified proxy", &mut proxy_cmd).await?;
wait_for_stack_containers(
"netbird",
&["netbird-server", "netbird-dashboard", "netbird"],
60,
)
.await?;
self.set_install_phase("netbird", InstallPhase::WaitingHealthy)
.await;
self.set_install_phase("netbird", InstallPhase::PostInstall)
.await;
self.set_install_phase("netbird", InstallPhase::Done).await;
self.clear_install_progress("netbird").await;
install_log("INSTALL OK: netbird stack").await;
info!("NetBird stack installed");
Ok(serde_json::json!({
"success": true,
"package_id": "netbird",
"message": "NetBird self-hosted stack installed",
}))
}
}
async fn read_or_generate_b64_secret(name: &str) -> String {
let path = format!("/var/lib/archipelago/secrets/{}", name);
if let Ok(val) = tokio::fs::read_to_string(&path).await {
let trimmed = val.trim().to_string();
if !trimmed.is_empty() {
return trimmed;
}
}
let mut buf = [0u8; 32];
rand::RngCore::fill_bytes(&mut rand::rngs::OsRng, &mut buf);
let secret = base64::engine::general_purpose::STANDARD.encode(buf);
let _ = tokio::fs::create_dir_all("/var/lib/archipelago/secrets").await;
let _ = tokio::fs::write(&path, &secret).await;
secret
}
async fn write_netbird_config_files(host_ip: &str) -> Result<()> {
let public_origin = format!("http://{}:8087", host_ip);
let server_origin = format!("http://{}:8086", host_ip);
let relay_secret = read_or_generate_b64_secret("netbird-relay-auth-secret").await;
let encryption_key = read_or_generate_b64_secret("netbird-store-encryption-key").await;
let config = format!(
r#"server:
listenAddress: ":80"
exposedAddress: "{public_origin}"
stunPorts:
- 3478
metricsPort: 9090
healthcheckAddress: ":9000"
logLevel: "info"
logFile: "console"
authSecret: "{relay_secret}"
dataDir: "/var/lib/netbird"
auth:
issuer: "{public_origin}/oauth2"
localAuthDisabled: false
signKeyRefreshEnabled: false
dashboardRedirectURIs:
- "{public_origin}/nb-auth"
- "{public_origin}/nb-silent-auth"
dashboardPostLogoutRedirectURIs:
- "{public_origin}/"
cliRedirectURIs:
- "http://localhost:53000/"
store:
engine: "sqlite"
encryptionKey: "{encryption_key}"
"#
);
tokio::fs::write("/var/lib/archipelago/netbird/config.yaml", config)
.await
.context("Failed to write NetBird config.yaml")?;
let dashboard_env = format!(
r#"NETBIRD_MGMT_API_ENDPOINT={public_origin}
NETBIRD_MGMT_GRPC_API_ENDPOINT={public_origin}
AUTH_AUDIENCE=netbird-dashboard
AUTH_CLIENT_ID=netbird-dashboard
AUTH_CLIENT_SECRET=
AUTH_AUTHORITY={public_origin}/oauth2
USE_AUTH0=false
AUTH_SUPPORTED_SCOPES=openid profile email groups
AUTH_REDIRECT_URI=/nb-auth
AUTH_SILENT_REDIRECT_URI=/nb-silent-auth
NETBIRD_TOKEN_SOURCE=idToken
NGINX_SSL_PORT=443
LETSENCRYPT_DOMAIN=none
"#
);
tokio::fs::write("/var/lib/archipelago/netbird/dashboard.env", dashboard_env)
.await
.context("Failed to write NetBird dashboard.env")?;
let nginx_conf = format!(
r#"server {{
listen 80;
server_name _;
# Route browser API/auth through the host-published server port. Rootless
# Podman can give netbird-server a new container IP on restart while nginx
# keeps an old resolved address, which breaks login with 502s.
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
proxy_http_version 1.1;
location ~ ^/(relay|ws-proxy/) {{
proxy_pass http://host.containers.internal:8086;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
proxy_read_timeout 1d;
}}
location ~ ^/(api|oauth2)(/|$) {{
proxy_pass http://host.containers.internal:8086;
}}
location ~ ^/(signalexchange\.SignalExchange|management\.ManagementService|management\.ProxyService)/ {{
grpc_pass grpc://netbird-server:80;
grpc_read_timeout 1d;
grpc_send_timeout 1d;
}}
location / {{
proxy_pass http://netbird-dashboard:80;
}}
}}
# Direct server remains available for diagnostics at {server_origin}.
"#
);
tokio::fs::write("/var/lib/archipelago/netbird/nginx.conf", nginx_conf)
.await
.context("Failed to write NetBird nginx.conf")?;
Ok(())
}
async fn detect_netbird_public_host_ip() -> Option<String> {
let output = tokio::process::Command::new("hostname")
.args(["-I"])
.output()
.await
.ok()?;
let stdout = String::from_utf8_lossy(&output.stdout);
stdout
.split_whitespace()
.find(|ip| ip.starts_with("100.") && ip.contains('.'))
.map(str::to_string)
}
#[cfg(test)]
mod tests {
use super::{btcpay_stack_app_ids, mempool_stack_app_ids};

View File

@ -32,8 +32,11 @@ impl RpcHandler {
.ok_or_else(|| anyhow::anyhow!("Missing package id"))?;
validate_app_id(package_id)?;
// Verify an update is actually available
let pinned = image_versions::pinned_image_for_app(package_id)
// Verify an update is actually available. Prefer the remote app catalog
// (decoupled from the binary OTA), falling back to the image-versions.sh
// pin when the catalog is absent or doesn't cover this app.
let pinned = crate::container::app_catalog::catalog_primary_image(package_id)
.or_else(|| image_versions::pinned_image_for_app(package_id))
.ok_or_else(|| anyhow::anyhow!("No pinned image found for {}", package_id))?;
// Note: the `already updating` guard lives in `spawn_package_update`
@ -149,6 +152,28 @@ impl RpcHandler {
}
}
/// Manual "check for updates": refresh the remote app catalog now. The
/// package scanner recomputes each app's `available-update` from the fresh
/// catalog on its next cycle and pushes it to the UI. Best-effort — a fetch
/// failure leaves the cached catalog in place and reports `refreshed: false`.
pub(in crate::api::rpc) async fn handle_package_check_updates(
&self,
_params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
match crate::container::app_catalog::refresh_catalog(&self.config.data_dir).await {
Ok(count) => Ok(serde_json::json!({
"status": "ok",
"refreshed": true,
"catalog_apps": count,
})),
Err(e) => Ok(serde_json::json!({
"status": "ok",
"refreshed": false,
"error": e.to_string(),
})),
}
}
/// Core update execution: stop → pull → remove → recreate → verify.
async fn execute_update(
&self,
@ -385,13 +410,24 @@ impl RpcHandler {
package_id: &str,
pinned_primary: &str,
) -> Vec<(String, String)> {
let stack_images = image_versions::pinned_images_for_stack(package_id);
let mut stack_images = image_versions::pinned_images_for_stack(package_id);
if stack_images.is_empty() {
// Single container app
vec![(package_id.to_string(), pinned_primary.to_string())]
} else {
stack_images
// Single container app — pinned_primary already prefers the catalog.
return vec![(package_id.to_string(), pinned_primary.to_string())];
}
// Stack app: override per-container images with the catalog where it
// provides them; components the catalog omits keep the image-versions.sh
// pin. This lets a single component (e.g. the IndeeHub frontend) be
// bumped without touching the rest of the stack.
let catalog_images = crate::container::app_catalog::catalog_stack_images(package_id);
if !catalog_images.is_empty() {
for (name, image) in stack_images.iter_mut() {
if let Some(catalog_image) = catalog_images.get(name) {
*image = catalog_image.clone();
}
}
}
stack_images
}
/// Rollback: restart old containers if they still exist.

View File

@ -60,6 +60,30 @@ impl RpcHandler {
/// Generate a new 24-word BIP-39 mnemonic, derive and persist node keys.
/// Returns the words for the user to write down.
pub(in crate::api::rpc) async fn handle_seed_generate(&self) -> Result<serde_json::Value> {
// Serialize concurrent / retried generate calls. The web client aborts
// at 15s and retries internally (up to 3x), and the onboarding view
// re-fires every 4s while the server is still booting on slow first-boot
// hardware. Without this guard each hit would mint a brand-new seed and
// overwrite the node keys mid-flight, leaving the words shown to the user
// out of sync with what `seed.verify` expects — the classic "error at the
// DID-creation screen". Holding the lock across the whole op fully
// serializes them.
let mut state = ONBOARDING_MNEMONIC.lock().await;
// Idempotent fast-path: a fresh pending mnemonic already exists, so the
// node keys are already on disk. Return the SAME words rather than
// regenerating, so every retry yields a consistent result.
if let Some(existing) = state.as_ref() {
if existing.created_at.elapsed() < MNEMONIC_TTL {
let words: Vec<String> = existing
.words
.split_whitespace()
.map(str::to_string)
.collect();
return Ok(serde_json::json!({ "words": words }));
}
}
let (mnemonic, seed) = crate::seed::MasterSeed::generate()?;
// Derive and write node Ed25519 key.
@ -89,16 +113,14 @@ impl RpcHandler {
// the onboarding RPC returns immediately.
spawn_post_onboarding_fips_activate(self.config.data_dir.clone());
let words: Vec<&str> = mnemonic.words().collect();
let words: Vec<String> = mnemonic.words().map(str::to_string).collect();
// Hold mnemonic in memory for the verify step.
{
let mut state = ONBOARDING_MNEMONIC.lock().await;
*state = Some(OnboardingMnemonicState {
words: mnemonic.to_string(),
created_at: std::time::Instant::now(),
});
}
// Hold mnemonic in memory for the verify step. We already own the lock
// guard (`state`) from the top of the function, so just write through it.
*state = Some(OnboardingMnemonicState {
words: mnemonic.to_string(),
created_at: std::time::Instant::now(),
});
Ok(serde_json::json!({
"words": words,
@ -149,11 +171,13 @@ impl RpcHandler {
let nostr_keys = crate::seed::derive_node_nostr_key(&seed)?;
let nostr_npub = nostr_keys.public_key().to_bech32().unwrap_or_default();
// Clear mnemonic from memory now that it's verified.
{
let mut state = ONBOARDING_MNEMONIC.lock().await;
*state = None;
}
// Intentionally DO NOT clear the mnemonic here. The web client aborts
// slow requests at 15s and retries internally; if we wiped it on the
// first (successful) verify, a retried request would fail with
// "No pending seed generation or session expired" even though the user
// did everything right. The mnemonic is bounded by MNEMONIC_TTL (10 min)
// and is overwritten on the next generate, so leaving it makes verify
// idempotent without meaningfully widening the in-memory window.
// Save the encrypted seed for convenience backup.
// Use empty passphrase placeholder — the real encrypted save happens via seed.save-encrypted.
@ -290,4 +314,101 @@ impl RpcHandler {
"next_index": next_index,
}))
}
/// Reveal the node's 24-word recovery phrase after onboarding. Heavily
/// gated, because this is the keys to the whole node:
/// - requires a full authenticated session (enforced upstream: this
/// method is NOT in the public auth whitelist),
/// - re-verifies the login password,
/// - requires a valid TOTP code when 2FA is enabled (replay-protected),
/// - decrypts `identity/master_seed.enc` with the backup passphrase
/// (defaults to the login password when the user used the same value).
/// The words are returned to the caller only and never logged.
pub(in crate::api::rpc) async fn handle_seed_reveal(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let params = params.unwrap_or_default();
let mut password = params
.get("password")
.and_then(|v| v.as_str())
.unwrap_or("")
.to_string();
if password.is_empty() {
anyhow::bail!("Password is required to reveal the recovery phrase");
}
// Nothing to reveal if this node never stored an encrypted seed.
if !crate::seed::seed_exists(&self.config.data_dir) {
anyhow::bail!(
"This node has no encrypted seed backup, so the recovery phrase \
cannot be shown. It was only displayed once during setup."
);
}
// 1) Re-authenticate with the login password.
if !self.auth_manager.verify_password(&password).await? {
password.zeroize();
anyhow::bail!("Incorrect password");
}
// 2) Require a valid 2FA code when TOTP is enabled (replay-protected).
if self.auth_manager.is_totp_enabled().await.unwrap_or(false) {
let code = params
.get("code")
.and_then(|v| v.as_str())
.unwrap_or("")
.to_string();
if code.is_empty() {
password.zeroize();
anyhow::bail!("A 2FA code is required to reveal the recovery phrase");
}
let totp_data = self
.auth_manager
.get_totp_data()
.await?
.ok_or_else(|| anyhow::anyhow!("2FA is enabled but no TOTP data found"))?;
let secret = crate::totp::decrypt_secret(&totp_data, &password)
.context("Could not unlock 2FA with this password")?;
match crate::totp::verify_code(&secret, &code, &totp_data.used_steps)? {
Some(step) => {
// Record the used step for replay protection, pruning old ones.
let mut data = totp_data;
data.used_steps.push(step);
let now = std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.unwrap_or_default()
.as_secs() as i64;
let cutoff = (now / 30) - 10; // ~5 minutes
data.used_steps.retain(|s| *s > cutoff);
let _ = self.auth_manager.update_totp(data).await;
}
None => {
password.zeroize();
anyhow::bail!("Invalid 2FA code");
}
}
}
// 3) Decrypt the stored seed. The backup passphrase may differ from the
// login password, so accept an explicit one and fall back to the
// password when the user used the same value for both.
let passphrase = params
.get("passphrase")
.and_then(|v| v.as_str())
.map(|s| s.to_string());
let secret_phrase = passphrase.unwrap_or_else(|| password.clone());
let reveal = crate::seed::load_seed_encrypted(&self.config.data_dir, &secret_phrase).await;
password.zeroize();
let mnemonic = reveal.map_err(|_| {
anyhow::anyhow!(
"Could not decrypt the saved seed. If you set a separate backup \
passphrase during setup, enter that passphrase."
)
})?;
let words: Vec<String> = mnemonic.words().map(|w| w.to_string()).collect();
let word_count = words.len();
Ok(serde_json::json!({ "words": words, "word_count": word_count }))
}
}

View File

@ -205,6 +205,64 @@ impl RpcHandler {
}
}
/// Build a payment token for a remote seeder (payer side, cross-mint aware).
///
/// Given the seeder's advertised `accepted_mints` and `price_sats`, builds a
/// `cashuA` token denominated in one of those mints — paying directly if we
/// already hold the right mint, else auto-swapping into a trusted accepted
/// mint (within `max_fee_sats`). If the price is over `budget_sats`, the
/// wallet can't cover it, or the swap is too costly, returns `declined` so
/// the caller falls back to the free origin (origin always wins).
pub(super) async fn handle_streaming_prepare_payment(
&self,
params: Option<serde_json::Value>,
) -> Result<serde_json::Value> {
let params = params.ok_or_else(|| anyhow::anyhow!("Missing params"))?;
let accepted_mints: Vec<String> = params
.get("accepted_mints")
.and_then(|v| v.as_array())
.map(|arr| {
arr.iter()
.filter_map(|v| v.as_str().map(|s| s.to_string()))
.collect()
})
.unwrap_or_default();
let price_sats = params
.get("price_sats")
.or_else(|| params.get("amount_sats"))
.and_then(|v| v.as_u64())
.ok_or_else(|| anyhow::anyhow!("Missing price_sats"))?;
// Default budget = the asked price (willing to pay exactly what's quoted).
let budget_sats = params
.get("budget_sats")
.and_then(|v| v.as_u64())
.unwrap_or(price_sats);
let max_fee_sats = params
.get("max_fee_sats")
.and_then(|v| v.as_u64())
.unwrap_or(0);
let policy = crate::swarm::payment::PaymentPolicy::with_budget(budget_sats, max_fee_sats);
match crate::swarm::payment::auto_pay_token(
&self.config.data_dir,
&policy,
&accepted_mints,
price_sats,
)
.await?
{
Some(token) => Ok(serde_json::json!({
"status": "ready",
"token": token,
"paid_sats": price_sats,
})),
None => Ok(serde_json::json!({
"status": "declined",
"message": "payment declined (over budget, unpayable, or swap too costly) — use free origin",
})),
}
}
/// Discover available streaming services (pricing info).
/// This is the unauthenticated discovery endpoint.
pub(super) async fn handle_streaming_discover(&self) -> Result<serde_json::Value> {

View File

@ -253,6 +253,54 @@ impl RpcHandler {
Ok(serde_json::json!({ "mirrors": list }))
}
/// Report the node's swarm prefs (fetch source + whether it provides to the
/// swarm) plus swarm capability, so the UI can show whether DHT mode is
/// actually usable on this build.
pub(super) async fn handle_update_get_source(&self) -> Result<serde_json::Value> {
let source = update::load_update_source(&self.config.data_dir).await;
let provide_dht = update::load_provide_dht(&self.config.data_dir).await;
let source_str = match source {
update::UpdateSource::Origin => "origin",
update::UpdateSource::Swarm => "swarm",
};
Ok(serde_json::json!({
"source": source_str,
// Whether this node seeds/serves blobs to peers (default true).
"provide_dht": provide_dht,
// Compiled with the iroh swarm engine? If false, "swarm" mode has no
// peers and silently behaves like origin.
"swarm_available": cfg!(feature = "iroh-swarm"),
// Runtime swarm-assist gate from config (ARCHIPELAGO_SWARM_ENABLED).
"swarm_enabled": self.config.swarm_enabled,
}))
}
/// Update the node's swarm prefs. Params (both optional, at least one):
/// `{ source?: "origin" | "swarm", provide?: bool }`.
pub(super) async fn handle_update_set_source(
&self,
params: &serde_json::Value,
) -> Result<serde_json::Value> {
let mut touched = false;
if let Some(s) = params.get("source").and_then(|v| v.as_str()) {
let source = match s {
"origin" => update::UpdateSource::Origin,
"swarm" => update::UpdateSource::Swarm,
_ => anyhow::bail!("source must be \"origin\" or \"swarm\""),
};
update::save_update_source(&self.config.data_dir, source).await?;
touched = true;
}
if let Some(provide) = params.get("provide").and_then(|v| v.as_bool()) {
update::save_provide_dht(&self.config.data_dir, provide).await?;
touched = true;
}
if !touched {
anyhow::bail!("expected \"source\" and/or \"provide\"");
}
self.handle_update_get_source().await
}
/// Add a mirror to the end of the list. Params: `{ url, label? }`.
/// Duplicates (same URL) are replaced rather than added twice.
pub(super) async fn handle_update_add_mirror(

View File

@ -1,12 +1,34 @@
use super::RpcHandler;
use crate::wallet::{ecash, profits};
use crate::wallet::{ecash, fedimint_client, profits};
use anyhow::Result;
/// A Cashu token (NUT-00 `cashuA`/`cashuB`, or our legacy `cashuSend_` form)
/// always starts with `cashu`. Fedimint ecash notes never do, so a non-`cashu`
/// string is routed to the Fedimint reissue path.
fn is_cashu_token(token: &str) -> bool {
token.trim_start().starts_with("cashu")
}
impl RpcHandler {
pub(super) async fn handle_wallet_ecash_balance(&self) -> Result<serde_json::Value> {
let wallet = ecash::load_wallet(&self.config.data_dir).await?;
let cashu_sats = wallet.balance();
// Spendable Fedimint balance too, so callers (e.g. the pay-for-file
// pre-check) see funds available across BOTH backends (#3). Best-effort:
// if fmcd isn't installed/joined this is just 0, never an error.
let fedimint_sats = match fedimint_client::FedimintClient::from_node(&self.config.data_dir)
.await
{
Ok(client) => client.total_balance_sats().await.unwrap_or(0),
Err(_) => 0,
};
Ok(serde_json::json!({
"balance_sats": wallet.balance(),
// `balance_sats` stays Cashu-only for back-compat; `total_sats` is the
// spendable amount across Cashu + Fedimint.
"balance_sats": cashu_sats,
"cashu_sats": cashu_sats,
"fedimint_sats": fedimint_sats,
"total_sats": cashu_sats + fedimint_sats,
"proof_count": wallet.proofs.iter().filter(|p| !p.spent && !p.reserved).count(),
"mint_url": wallet.mint_url,
}))
@ -129,18 +151,42 @@ impl RpcHandler {
let token = params
.get("token")
.and_then(|v| v.as_str())
.map(str::trim)
.filter(|s| !s.is_empty())
.ok_or_else(|| anyhow::anyhow!("Missing token"))?;
let amount = ecash::receive_token(&self.config.data_dir, token).await?;
// Dual-ecash: one "Receive ecash" box accepts either a Cashu token
// (redeemed at the mint) or Fedimint notes (reissued via the fmcd
// sidecar). Detect by prefix and route accordingly.
if is_cashu_token(token) {
let amount = ecash::receive_token(&self.config.data_dir, token).await?;
return Ok(serde_json::json!({
"received_sats": amount,
"kind": "cashu",
}));
}
let (amount, federation_id) =
fedimint_client::reissue_into_any(&self.config.data_dir, token).await?;
Ok(serde_json::json!({
"received_sats": amount,
"kind": "fedimint",
"federation_id": federation_id,
}))
}
pub(super) async fn handle_wallet_ecash_history(&self) -> Result<serde_json::Value> {
// Unified history: Cashu transactions (tagged kind="cashu") + the local
// Fedimint transaction log (kind="fedimint"), newest first. Previously
// only Cashu was returned, so a Fedimint receive showed up nowhere.
let wallet = ecash::load_wallet(&self.config.data_dir).await?;
let mut transactions = wallet.transactions;
transactions.extend(fedimint_client::load_fedimint_txs(&self.config.data_dir).await);
// Sort by RFC-3339 timestamp descending (string compare is valid for
// same-offset RFC-3339), newest first.
transactions.sort_by(|a, b| b.timestamp.cmp(&a.timestamp));
Ok(serde_json::json!({
"transactions": wallet.transactions,
"transactions": transactions,
}))
}

View File

@ -13,14 +13,32 @@ use std::time::{Duration, SystemTime, UNIX_EPOCH};
use tokio::sync::RwLock;
use tracing::{debug, warn};
const CACHE_REFRESH_SECS: u64 = 10;
const CACHE_ERROR_BACKOFF_SECS: u64 = 15;
// Poll frequently and recover fast so the cached snapshot tracks bitcoind's
// responsive windows during IBD. During heavy block-connection, getblockchaininfo
// can block briefly; a slow 10s/15s/20s cadence let one missed poll age the
// snapshot past the UI's 30s "stale" threshold, so the UI dwelled on
// "reconnecting…" long after bitcoind was answering again. Tight cadence + short
// timeout keeps last-known state fresh and clears the stale banner promptly.
const CACHE_REFRESH_SECS: u64 = 5;
const CACHE_ERROR_BACKOFF_SECS: u64 = 5;
// Grace window before a failing poll marks the snapshot "stale" for the UI.
// On a busy / swap-thrashing node (e.g. .198) getblockchaininfo intermittently
// exceeds the RPC timeout, so a single missed poll is normal and must NOT flip
// the UI to "reconnecting…". Only after the cached snapshot is genuinely old —
// several polls failed in a row — do we surface the banner.
const STALE_GRACE_MS: u64 = 20_000;
#[derive(Debug, Clone, Serialize)]
pub struct BitcoinNodeStatus {
pub ok: bool,
pub stale: bool,
pub updated_at_ms: u64,
// Server-computed age of the snapshot, filled in at serve time. The browser
// must not derive this itself (Date.now() - updated_at_ms) because that
// compares the browser clock against this node's clock — any skew made a
// fresh snapshot look stale and the "reconnecting…" banner never cleared.
pub age_ms: u64,
pub error: Option<String>,
pub blockchain_info: Option<serde_json::Value>,
pub network_info: Option<serde_json::Value>,
@ -34,6 +52,7 @@ impl Default for BitcoinNodeStatus {
ok: false,
stale: false,
updated_at_ms: 0,
age_ms: 0,
error: Some("Connecting to Bitcoin node...".to_string()),
blockchain_info: None,
network_info: None,
@ -122,7 +141,11 @@ pub fn spawn_status_cache() {
if cached.blockchain_info.is_some() {
cached.ok = false;
cached.stale = true;
// Only flip to "stale" once the last good snapshot is older
// than the grace window. A brief RPC gap on a busy node keeps
// showing last-known state silently instead of a banner flicker.
let snapshot_age_ms = now_ms().saturating_sub(cached.updated_at_ms);
cached.stale = snapshot_age_ms > STALE_GRACE_MS;
cached.error = Some(friendly_transient_error(true, &err_msg));
} else {
*cached = BitcoinNodeStatus {
@ -142,40 +165,46 @@ pub fn spawn_status_cache() {
}
pub async fn get_bitcoin_status() -> BitcoinNodeStatus {
cache().read().await.clone()
let mut status = cache().read().await.clone();
// Compute age here (server clock only) so the browser never has to subtract
// across clocks. A successful snapshot serves age_ms ≈ 0 → the UI clears the
// "reconnecting…" banner on its very next poll regardless of browser-clock skew.
if status.updated_at_ms > 0 {
status.age_ms = now_ms().saturating_sub(status.updated_at_ms);
}
status
}
async fn fetch_bitcoin_status() -> Result<BitcoinNodeStatus> {
// 12s (not 8s): on a swap-thrashing node getblockchaininfo can answer slowly
// but correctly; too tight a timeout turned working-but-slow polls into
// failures and tripped the "reconnecting…" banner. Stays under STALE_GRACE_MS.
let client = reqwest::Client::builder()
.timeout(Duration::from_secs(20))
.timeout(Duration::from_secs(12))
.build()
.context("build Bitcoin status HTTP client")?;
let blockchain_info = bitcoin_rpc_call(&client, "getblockchaininfo", serde_json::json!([]))
.await
.context("getblockchaininfo")?;
let network_info = bitcoin_rpc_call(&client, "getnetworkinfo", serde_json::json!([]))
.await
.context("getnetworkinfo")
.ok();
let index_info = bitcoin_rpc_call(&client, "getindexinfo", serde_json::json!([]))
.await
.context("getindexinfo")
.ok();
let zmq_notifications = bitcoin_rpc_call(&client, "getzmqnotifications", serde_json::json!([]))
.await
.context("getzmqnotifications")
.ok();
// Fetch all four calls concurrently: getblockchaininfo gates freshness, so a
// slow auxiliary call (network/index/zmq) must not delay the snapshot or block
// the next refresh. Only getblockchaininfo failing marks the status stale.
let (blockchain_info, network_info, index_info, zmq_notifications) = tokio::join!(
bitcoin_rpc_call(&client, "getblockchaininfo", serde_json::json!([])),
bitcoin_rpc_call(&client, "getnetworkinfo", serde_json::json!([])),
bitcoin_rpc_call(&client, "getindexinfo", serde_json::json!([])),
bitcoin_rpc_call(&client, "getzmqnotifications", serde_json::json!([])),
);
let blockchain_info = blockchain_info.context("getblockchaininfo")?;
Ok(BitcoinNodeStatus {
ok: true,
stale: false,
updated_at_ms: now_ms(),
age_ms: 0,
error: None,
blockchain_info: Some(blockchain_info),
network_info,
index_info,
zmq_notifications,
network_info: network_info.ok(),
index_info: index_info.ok(),
zmq_notifications: zmq_notifications.ok(),
})
}

View File

@ -25,6 +25,12 @@ pub const MAX_BLOB_SIZE: u64 = 64 * 1024 * 1024;
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct BlobMeta {
pub cid: String,
/// DHT Phase 1: BLAKE3 hash of the content (iroh-native swarm address).
/// The on-disk path stays SHA-256-keyed (`cid`) for back-compat; this
/// advertises the hash a peer swarm can fetch/range-verify by. Absent in
/// legacy metadata written before Phase 1.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub blake3: Option<String>,
pub size: u64,
pub mime: String,
#[serde(default, skip_serializing_if = "Option::is_none")]
@ -88,6 +94,7 @@ impl BlobStore {
let cid = hex::encode(hasher.finalize());
let meta = BlobMeta {
cid: cid.clone(),
blake3: Some(crate::content_hash::blake3_hex(bytes)),
size: bytes.len() as u64,
mime: mime.to_string(),
filename,

View File

@ -30,8 +30,22 @@ const DOCTOR_SH_PATH: &str = "/home/archipelago/archy/scripts/container-doctor.s
const DOCTOR_SERVICE_PATH: &str = "/etc/systemd/system/archipelago-doctor.service";
const DOCTOR_TIMER_PATH: &str = "/etc/systemd/system/archipelago-doctor.timer";
// Kiosk hardening (#36): keep the deployed unit + launcher in sync with the
// repo so the CPU/memory cap and the GPU-vs-headless flag selection reach
// already-installed nodes via OTA, not just fresh ISOs.
const KIOSK_SERVICE: &str = include_str!("../../../image-recipe/configs/archipelago-kiosk.service");
const KIOSK_LAUNCHER: &str =
include_str!("../../../image-recipe/configs/archipelago-kiosk-launcher.sh");
const KIOSK_SERVICE_PATH: &str = "/etc/systemd/system/archipelago-kiosk.service";
const KIOSK_LAUNCHER_PATH: &str = "/usr/local/bin/archipelago-kiosk-launcher";
const NGINX_CONF_PATH: &str = "/etc/nginx/sites-available/archipelago";
const NGINX_ENABLED_CONF_PATH: &str = "/etc/nginx/sites-enabled/archipelago";
/// Per-app proxy snippet included by the HTTPS (:443) server block. Carries its
/// own `/app/fedimint/` location, so it needs the same B13 asset-rewrite heal as
/// the main conf — browsers reach fedimint over HTTPS via this snippet. Absent on
/// HTTP-only nodes, in which case the bootstrap loop skips it.
const NGINX_HTTPS_SNIPPET_PATH: &str = "/etc/nginx/snippets/archipelago-https-app-proxies.conf";
const RUNTIME_ASSETS_DIR: &str = "/opt/archipelago/web-ui/archipelago-runtime";
/// Inserted into every server block of the nginx config that lacks the
@ -41,6 +55,41 @@ const NGINX_APP_CATALOG_BLOCK: &str = "\n # App Store catalog proxy — backe
const NGINX_BITCOIN_STATUS_BLOCK: &str = "\n location /bitcoin-status {\n proxy_pass http://127.0.0.1:5678/bitcoin-status;\n proxy_http_version 1.1;\n proxy_set_header Host $host;\n proxy_connect_timeout 10s;\n proxy_read_timeout 10s;\n proxy_send_timeout 5s;\n error_page 502 503 = @backend_unavailable;\n error_page 504 = @backend_timeout;\n }\n";
/// Inserted into every server block that lacks the `/proxy/lnd/` proxy. Nodes
/// flashed before 2026-04-10 shipped an nginx config without this block, so the
/// browser's wallet fetches to `/proxy/lnd/*` fell through to the SPA
/// index.html and got HTML back instead of JSON ("failing to fetch"). Kept in
/// sync with the canonical block in image-recipe/configs/nginx-archipelago.conf.
const NGINX_LND_PROXY_BLOCK: &str = "\n # LND REST proxy — backend handles auth + CORS\n location /proxy/lnd/ {\n proxy_pass http://127.0.0.1:5678;\n proxy_http_version 1.1;\n proxy_set_header Host $host;\n proxy_set_header Cookie $http_cookie;\n proxy_set_header X-Real-IP $remote_addr;\n proxy_connect_timeout 10s;\n proxy_read_timeout 10s;\n proxy_send_timeout 5s;\n error_page 502 503 = @backend_unavailable;\n error_page 504 = @backend_timeout;\n }\n";
/// Inserted into every server block lacking the peer-content streaming proxy.
/// Without it, the browser's `<video>`/`<audio>` Range requests to
/// `/api/peer-content/*` fall through to the SPA index.html (HTML, no Range)
/// and peer media won't play (B3). Forwards Cookie (session auth) + Range and
/// disables buffering so streaming works. Kept in sync with the canonical
/// block in image-recipe/configs/nginx-archipelago.conf.
const NGINX_PEER_CONTENT_BLOCK: &str = "\n # Peer content streaming proxy (B3) — Range-streams a peer's media file.\n # Long read timeout: this path also serves full-file downloads of large\n # media (#38), which can take minutes over Tor; 120s aborted them.\n location /api/peer-content/ {\n proxy_pass http://127.0.0.1:5678;\n proxy_http_version 1.1;\n proxy_set_header Host $host;\n proxy_set_header Cookie $http_cookie;\n proxy_set_header Range $http_range;\n proxy_buffering off;\n proxy_connect_timeout 10s;\n proxy_read_timeout 900s;\n error_page 502 503 = @backend_unavailable;\n error_page 504 = @backend_timeout;\n }\n";
/// B13 — Fedimint UI asset rewrite. Pre-fix nodes proxy /app/fedimint/ with only
/// the nostr-provider injection (`sub_filter_once on`), so the UI's root-rooted
/// CSS/JS asset URLs (href="/…", url("/…")) miss the proxy and load the SPA shell
/// → unstyled UI. We swap that single sub_filter for the full rewrite set that
/// reroots every asset URL under /app/fedimint/. NEW matches the canonical block
/// in image-recipe/configs/nginx-archipelago.conf byte-for-byte so self-healed
/// nodes converge to the same config fresh ISOs ship with.
const NGINX_FEDIMINT_OLD: &str = " sub_filter_once on;\n sub_filter '</head>' '<script src=\"/nostr-provider.js\"></script></head>';\n }\n location /app/fedimint-gateway/ {";
const NGINX_FEDIMINT_NEW: &str = " sub_filter_types text/css application/javascript application/json;\n sub_filter_once off;\n sub_filter 'href=\"/' 'href=\"/app/fedimint/';\n sub_filter 'src=\"/' 'src=\"/app/fedimint/';\n sub_filter \"href='/\" \"href='/app/fedimint/\";\n sub_filter \"src='/\" \"src='/app/fedimint/\";\n sub_filter 'url(\"/' 'url(\"/app/fedimint/';\n sub_filter \"url('/\" \"url('/app/fedimint/\";\n sub_filter '</head>' '<script src=\"/nostr-provider.js\"></script></head>';\n }\n location /app/fedimint-gateway/ {";
/// B13 Style B — the HTTPS app-proxy snippet's fedimint block has NO sub_filter
/// at all (older than the main conf's), and the directive that follows it varies
/// per node (fedimint-gateway vs tailscale), so a full-block match is unreliable.
/// Instead we anchor on the unique :8175 proxy_pass (fedimint is the only block
/// proxying there) and insert the reroot set right after it — directive order
/// inside a location block is irrelevant to nginx. Idempotent via the same
/// `href="/app/fedimint/` marker the main-conf heal leaves behind.
const NGINX_FEDIMINT_SNIPPET_ANCHOR: &str = "proxy_pass http://127.0.0.1:8175/;";
const NGINX_FEDIMINT_SNIPPET_INSERT: &str = "proxy_pass http://127.0.0.1:8175/;\n proxy_set_header Accept-Encoding \"\";\n sub_filter_types text/css application/javascript application/json;\n sub_filter_once off;\n sub_filter 'href=\"/' 'href=\"/app/fedimint/';\n sub_filter 'src=\"/' 'src=\"/app/fedimint/';\n sub_filter \"href='/\" \"href='/app/fedimint/\";\n sub_filter \"src='/\" \"src='/app/fedimint/\";\n sub_filter 'url(\"/' 'url(\"/app/fedimint/';\n sub_filter \"url('/\" \"url('/app/fedimint/\";\n sub_filter '</head>' '<script src=\"/nostr-provider.js\"></script></head>';";
/// Entry point called from main startup. Never returns an error to the caller —
/// failing to bootstrap host artifacts must not prevent the backend from serving.
pub async fn ensure_doctor_installed() {
@ -476,6 +525,92 @@ async fn write_root_if_needed(path: &str, content: &str) -> Result<bool> {
Ok(true)
}
const ARCHIPELAGO_SERVICE_PATH: &str = "/etc/systemd/system/archipelago.service";
const MOUNT_REQUIRE_LINE: &str = "RequiresMountsFor=/var/lib/archipelago";
/// B17 self-heal: ensure the installed archipelago.service waits for the data
/// volume to mount before it starts. On production nodes `/var/lib/archipelago`
/// (the app data dir AND podman's graphroot) is a separate device-mapper volume;
/// without a mount dependency the service can start before `var-lib-archipelago.mount`,
/// write to the bare mountpoint on rootfs, fail every podman call, exit, and be
/// restarted every 5s until the volume mounts (~5 min of "[FAILED] Failed to start"
/// on cold boots). Fresh ISOs already ship the directive; this heals already-deployed
/// nodes. The change is boot-ordering only — it takes effect on the NEXT reboot, so we
/// never restart the running service here. Idempotent; no-op if the unit is absent
/// (dev runs) or already patched. Harmless when the data dir is on rootfs (systemd maps
/// the requirement to the always-mounted root).
pub async fn ensure_archipelago_mount_ordering() {
let current = match fs::read_to_string(ARCHIPELAGO_SERVICE_PATH).await {
Ok(c) => c,
Err(e) => {
tracing::debug!(
"mount-ordering self-heal: {} not readable ({}) — skipping",
ARCHIPELAGO_SERVICE_PATH,
e
);
return;
}
};
if current.contains(MOUNT_REQUIRE_LINE) {
return; // already healed
}
// Insert the directive into the [Unit] section, immediately before [Service].
let Some(idx) = current.find("\n[Service]") else {
tracing::warn!(
"mount-ordering self-heal: no [Service] section in {} — skipping",
ARCHIPELAGO_SERVICE_PATH
);
return;
};
let mut patched = String::with_capacity(current.len() + MOUNT_REQUIRE_LINE.len() + 96);
patched.push_str(&current[..idx]);
patched.push_str("\n# B17: start only after the data volume (+ podman graphroot) is mounted\n");
patched.push_str(MOUNT_REQUIRE_LINE);
patched.push_str(&current[idx..]);
match write_root_if_needed(ARCHIPELAGO_SERVICE_PATH, &patched).await {
Ok(true) => {
info!(
"B17: added '{}' to archipelago.service (effective next reboot)",
MOUNT_REQUIRE_LINE
);
if let Err(e) = host_sudo(&["systemctl", "daemon-reload"]).await {
tracing::warn!("B17 self-heal: daemon-reload failed: {:#}", e);
}
}
Ok(false) => {}
Err(e) => tracing::warn!("B17 mount-ordering self-heal failed: {:#}", e),
}
}
/// #36 self-heal: keep the kiosk unit + launcher current on already-deployed
/// nodes so the CPU/memory cap (a runaway chromium was saturating the node and
/// starving the backend) and the GPU-vs-headless flag selection arrive via OTA.
/// No-op on nodes without the kiosk installed; only restarts the kiosk if it's
/// actually running (so it never re-enables an operator-disabled kiosk).
pub async fn ensure_kiosk_hardened() {
if fs::metadata(KIOSK_SERVICE_PATH).await.is_err() {
return; // kiosk not installed on this node
}
let svc_changed = write_root_if_needed(KIOSK_SERVICE_PATH, KIOSK_SERVICE)
.await
.unwrap_or(false);
let launcher_changed = write_root_if_needed(KIOSK_LAUNCHER_PATH, KIOSK_LAUNCHER)
.await
.unwrap_or(false);
if launcher_changed {
let _ = host_sudo(&["chmod", "+x", KIOSK_LAUNCHER_PATH]).await;
}
if svc_changed || launcher_changed {
if let Err(e) = host_sudo(&["systemctl", "daemon-reload"]).await {
warn!("kiosk hardening: daemon-reload failed: {:#}", e);
}
// try-restart only restarts a currently-active unit — leaves a stopped/
// disabled kiosk alone.
let _ = host_sudo(&["systemctl", "try-restart", "archipelago-kiosk.service"]).await;
info!("kiosk: applied resource cap + GPU-flag hardening (#36)");
}
}
/// Patch the nginx site config to add missing backend proxy blocks. Older ISO
/// configs shipped individual per-endpoint `location` blocks, so missing
/// endpoints silently fell through to the SPA `index.html` and the frontend
@ -496,7 +631,11 @@ async fn run_nginx() -> Result<bool> {
let mut changed = false;
let mut patched_paths = Vec::<PathBuf>::new();
for path in [NGINX_CONF_PATH, NGINX_ENABLED_CONF_PATH] {
for path in [
NGINX_CONF_PATH,
NGINX_ENABLED_CONF_PATH,
NGINX_HTTPS_SNIPPET_PATH,
] {
let candidate = Path::new(path);
if !candidate.exists() {
debug!("{} missing — skipping nginx bootstrap", path);
@ -514,18 +653,100 @@ async fn run_nginx() -> Result<bool> {
Ok(changed)
}
/// Reflective CORS add_headers that older configs placed inside the
/// `/lnd-connect-info` location. The backend now sets a validated
/// `Access-Control-Allow-Origin` for that endpoint (api/handler/proxy.rs), so
/// leaving these in nginx emits a DUPLICATE header ("contains multiple values
/// … but only one is allowed") and the LND wallet UI's cross-origin fetch is
/// rejected. Stripped during nginx bootstrap so the backend solely owns CORS.
const NGINX_LND_DUP_CORS: &str = " add_header Access-Control-Allow-Origin $http_origin always;\n add_header Access-Control-Allow-Credentials \"true\" always;\n";
async fn patch_nginx_conf(path: &str) -> Result<bool> {
let content = fs::read_to_string(path)
.await
.with_context(|| format!("read {}", path))?;
let missing_app_catalog = !content.contains("location /api/app-catalog");
let missing_bitcoin_status = !content.contains("location /bitcoin-status");
if !missing_app_catalog && !missing_bitcoin_status {
// Each "missing" flag is gated on the splice anchor actually being present,
// so an included snippet that legitimately has none of these endpoints (the
// HTTPS app-proxy snippet) neither tries to patch them nor logs warn-skips on
// every boot — it falls through to the fedimint heal alone.
let has_lnd_anchor = content.contains(" location /lnd-connect-info {")
|| content.contains(" location /electrs-status {");
let missing_app_catalog = content
.contains(" # DWN endpoints — peer access over Tor (no auth)")
&& !content.contains("location /api/app-catalog");
let missing_bitcoin_status = content.contains(" location /electrs-status {")
&& !content.contains("location /bitcoin-status");
let missing_lnd_proxy = has_lnd_anchor && !content.contains("location /proxy/lnd/");
let missing_peer_content = has_lnd_anchor && !content.contains("location /api/peer-content");
let has_lnd_dup_cors = content.contains(NGINX_LND_DUP_CORS);
// B13: fedimint block present but lacking the asset-rewrite sub_filters.
let needs_fedimint_css = content.contains("location /app/fedimint/")
&& !content.contains("'href=\"/' 'href=\"/app/fedimint/'");
if !missing_app_catalog
&& !missing_bitcoin_status
&& !missing_lnd_proxy
&& !missing_peer_content
&& !has_lnd_dup_cors
&& !needs_fedimint_css
{
return Ok(false);
}
let mut patched = content.clone();
if has_lnd_dup_cors {
// Drop the redundant nginx-side CORS headers so the backend's single
// validated Access-Control-Allow-Origin is the only one returned.
patched = patched.replace(NGINX_LND_DUP_CORS, "");
}
if needs_fedimint_css {
// Style A (main conf): the block already injects nostr-provider, so swap
// its single-sub_filter tail for the full asset-rewrite set. No-op if the
// node's fedimint block doesn't match OLD.
patched = patched.replace(NGINX_FEDIMINT_OLD, NGINX_FEDIMINT_NEW);
// Style B (HTTPS app-proxy snippet): the block has no sub_filter to swap,
// so insert the reroot set after the unique :8175 proxy_pass. Guarded on
// the marker so it can never double-apply after Style A already healed.
if !patched.contains("'href=\"/' 'href=\"/app/fedimint/'") {
patched = patched.replace(NGINX_FEDIMINT_SNIPPET_ANCHOR, NGINX_FEDIMINT_SNIPPET_INSERT);
}
}
if missing_lnd_proxy {
// Prefer the `/lnd-connect-info` anchor (present since 2026-03-17); fall
// back to `/electrs-status` (since 2026-03-08) for even older configs.
// Both appear once per archipelago server block, so the block is added
// to every server block that proxies to the backend.
let anchor = if patched.contains(" location /lnd-connect-info {") {
" location /lnd-connect-info {"
} else {
" location /electrs-status {"
};
if !patched.contains(anchor) {
warn!("nginx conf missing lnd-connect-info/electrs-status anchor — skipping /proxy/lnd patch");
} else {
let replacement = format!("{}{}", NGINX_LND_PROXY_BLOCK, anchor);
patched = patched.replace(anchor, &replacement);
}
}
if missing_peer_content {
// Same anchoring as the LND proxy: prepend the block to every server
// block so /api/peer-content/* reaches the backend instead of the SPA.
let anchor = if patched.contains(" location /lnd-connect-info {") {
" location /lnd-connect-info {"
} else {
" location /electrs-status {"
};
if patched.contains(anchor) {
let replacement = format!("{}{}", NGINX_PEER_CONTENT_BLOCK, anchor);
patched = patched.replace(anchor, &replacement);
} else {
warn!("nginx conf missing anchor — skipping /api/peer-content patch");
}
}
if missing_bitcoin_status {
let anchor = " location /electrs-status {";
if !patched.contains(anchor) {

View File

@ -0,0 +1,141 @@
//! Release-root signing ceremony — the publisher-side counterpart to
//! `trust::anchor`. Run as a subcommand of the same binary so it reuses the
//! exact key derivation (`seed::derive_release_root_ed25519`) and canonical
//! signing (`trust::signed_doc::sign_detached`) the fleet verifies against.
//!
//! Usage (the mnemonic is read from the `RELEASE_MASTER_MNEMONIC` env var or
//! stdin — never an argv so it stays out of shell history / `ps`):
//!
//! ```text
//! archipelago ceremony gen
//! Generate a fresh 24-word release master mnemonic and print it plus the
//! derived release-root pubkey + did. Back the mnemonic up OFFLINE.
//!
//! RELEASE_MASTER_MNEMONIC="word1 …" archipelago ceremony pubkey
//! Print the release-root pubkey hex (for ARCHY_RELEASE_ROOT_PUBKEY /
//! trust::anchor::RELEASE_ROOT_PUBKEY_HEX) and the signer did:key.
//!
//! RELEASE_MASTER_MNEMONIC="word1 …" archipelago ceremony sign <file.json>
//! Sign a JSON document (e.g. releases/app-catalog.json) in place: insert
//! `signature` + `signed_by` over the canonical form, matching exactly
//! what `trust::verify_detached` recomputes on every node.
//! ```
use anyhow::{bail, Context, Result};
use ed25519_dalek::SigningKey;
use crate::seed::{self, MasterSeed};
use crate::trust::{did, signed_doc};
const ENV_MNEMONIC: &str = "RELEASE_MASTER_MNEMONIC";
/// True if argv selects the ceremony subcommand. Checked before any server init.
pub fn is_ceremony_invocation() -> bool {
std::env::args().nth(1).as_deref() == Some("ceremony")
}
/// Entry point for `archipelago ceremony …`. Returns Ok(()) on success; the
/// caller (main) should exit without starting the server.
pub fn run() -> Result<()> {
let sub = std::env::args().nth(2).unwrap_or_default();
match sub.as_str() {
"gen" => cmd_gen(),
"pubkey" => cmd_pubkey(),
"sign" => {
let file = std::env::args()
.nth(3)
.context("usage: archipelago ceremony sign <file.json>")?;
cmd_sign(&file)
}
other => {
bail!(
"unknown ceremony subcommand {:?}; expected gen | pubkey | sign <file>",
other
)
}
}
}
fn cmd_gen() -> Result<()> {
let (mnemonic, seed) = MasterSeed::generate().context("generate mnemonic")?;
let key = seed::derive_release_root_ed25519(&seed).context("derive release-root")?;
eprintln!("⚠ Back this mnemonic up OFFLINE. It is the ONLY way to re-derive");
eprintln!(" the release-root signing key. Anyone with it can sign for the fleet.\n");
println!("RELEASE_MASTER_MNEMONIC=\"{}\"", mnemonic);
print_key(&key);
Ok(())
}
fn cmd_pubkey() -> Result<()> {
let key = load_release_root_key()?;
print_key(&key);
Ok(())
}
fn cmd_sign(path: &str) -> Result<()> {
let key = load_release_root_key()?;
let body = std::fs::read_to_string(path).with_context(|| format!("read {path}"))?;
let mut value: serde_json::Value =
serde_json::from_str(&body).with_context(|| format!("parse {path} as JSON"))?;
{
let obj = value
.as_object_mut()
.context("document root must be a JSON object")?;
// Re-sign cleanly: drop any prior signature so the preimage matches.
obj.remove("signature");
obj.remove("signed_by");
}
let (signature, signed_by) =
signed_doc::sign_detached(&key, &value).context("sign document")?;
let obj = value.as_object_mut().expect("checked above");
obj.insert("signature".into(), serde_json::Value::String(signature));
obj.insert(
"signed_by".into(),
serde_json::Value::String(signed_by.clone()),
);
let pretty = serde_json::to_string_pretty(&value).context("serialize signed document")?;
let tmp = format!("{path}.tmp");
std::fs::write(&tmp, format!("{pretty}\n")).with_context(|| format!("write {tmp}"))?;
std::fs::rename(&tmp, path).with_context(|| format!("rename {tmp} -> {path}"))?;
eprintln!("✓ signed {path}");
eprintln!(" signed_by: {signed_by}");
Ok(())
}
/// Derive the release-root signing key from the mnemonic in env/stdin.
fn load_release_root_key() -> Result<SigningKey> {
let phrase = read_mnemonic()?;
let (_mnemonic, seed) = MasterSeed::from_mnemonic_words(phrase.trim())
.context("invalid release master mnemonic")?;
seed::derive_release_root_ed25519(&seed).context("derive release-root")
}
/// Read the mnemonic from `RELEASE_MASTER_MNEMONIC` or, if unset, stdin.
fn read_mnemonic() -> Result<String> {
if let Ok(v) = std::env::var(ENV_MNEMONIC) {
if !v.trim().is_empty() {
return Ok(v);
}
}
use std::io::Read;
eprintln!("Paste the release master mnemonic, then Ctrl-D:");
let mut buf = String::new();
std::io::stdin()
.read_to_string(&mut buf)
.context("read mnemonic from stdin")?;
if buf.trim().is_empty() {
bail!("no mnemonic provided (set {ENV_MNEMONIC} or pipe it on stdin)");
}
Ok(buf)
}
fn print_key(key: &SigningKey) {
let vk = key.verifying_key();
println!("RELEASE_ROOT_PUBKEY_HEX={}", hex::encode(vk.to_bytes()));
println!("signed_by_did={}", did::did_key_for_ed25519(&vk));
}

View File

@ -66,10 +66,17 @@ pub struct Config {
/// through Quadlet (`.container` units in ~/.config/containers/systemd
/// + systemctl --user start) instead of `podman create + start`. Default
/// off so the legacy path stays the production path until the harness
/// at tests/lifecycle/run-20x.sh has gone green against the new path
/// at tests/lifecycle/run-gate.sh has gone green against the new path
/// on .228 + .198. See `project_v1_7_52_phase3_quadlet_design`.
#[serde(default)]
pub use_quadlet_backends: bool,
/// DHT swarm-assist (Phase 3): when true AND the binary was built with the
/// `iroh-swarm` feature, stand up an iroh-blobs provider that fetches release
/// blobs peer-to-peer (origin always wins) and seeds them via signed Nostr
/// adverts. Off by default; with the feature absent this is inert. Reuses
/// `nostr_relays` + `nostr_tor_proxy` for discovery transport.
#[serde(default)]
pub swarm_enabled: bool,
}
impl Config {
@ -182,6 +189,12 @@ impl Config {
config.nostr_tor_proxy = if s.is_empty() { None } else { Some(s) };
}
// DHT swarm-assist (Phase 3). Opt-in: only takes effect when the binary
// was also built with the `iroh-swarm` feature; otherwise inert.
if let Ok(v) = std::env::var("ARCHIPELAGO_SWARM_ENABLED") {
config.swarm_enabled = parse_truthy_env(&v);
}
// Phase 3.2 of v1.7.52. Truthy values (1, true, yes, on — case-insensitive)
// route backend installs through the Quadlet path without requiring a
// config.json edit + archipelago.service restart (which would trigger
@ -241,6 +254,7 @@ impl Default for Config {
],
nostr_tor_proxy: Some("127.0.0.1:9050".into()),
use_quadlet_backends: false,
swarm_enabled: false,
}
}
}
@ -473,7 +487,7 @@ mod tests {
#[test]
fn test_config_use_quadlet_backends_defaults_off() {
// Phase 3.2 of v1.7.52 — the new path stays gated until the 20×
// Phase 3.2 of v1.7.52 — the new path stays gated until the 5×
// harness goes green on .228 and .198. Flipping this default
// ahead of that would route every backend install through code
// we haven't fleet-validated yet.

View File

@ -0,0 +1,417 @@
//! Remote app version catalog — DECOUPLES per-app updates from the binary OTA.
//!
//! Background: `image_versions.rs` reads the pinned image tags from
//! `image-versions.sh`, which is deployed *with the archipelago binary*. That
//! coupled every app update to a full node release. This module adds a remote
//! catalog (`app-catalog.json`) fetched over HTTP from the same origin as the
//! OTA manifest, refreshed periodically and on demand. Bumping an app's version
//! is then a JSON edit + push — no binary release.
//!
//! Resolution order (origin-always-wins, matching the DHT design's posture):
//! 1. Remote catalog (this module) — the live source of "available update".
//! 2. `image-versions.sh` pin — offline/baseline fallback when the catalog is
//! missing or doesn't cover the app.
//!
//! ## Forward-compatibility with the DHT distribution plan
//! (`docs/dht-distribution-design.md`)
//! This catalog IS the "discovery / authenticity" layer of that plan. The schema
//! is deliberately extensible so the later phases bolt on WITHOUT a breaking
//! change:
//! - `signature` / `signed_by` (top level) — Phase 0 seed-derived release-root
//! signature over the canonical JSON. Absent today; verified when present.
//! - per-image `digest` / `size` — BLAKE3/SHA-256 content address + length, so
//! the iroh swarm can fetch images by hash with the registry as origin.
//! Unknown fields are ignored (no `deny_unknown_fields`), so adding fields on the
//! publisher side never breaks older nodes.
use serde::{Deserialize, Serialize};
use std::collections::HashMap;
use std::path::{Path, PathBuf};
use std::sync::Mutex;
use std::time::SystemTime;
use tracing::{debug, info, warn};
/// Filename for both the published catalog and the on-node cache.
pub const APP_CATALOG_FILE: &str = "app-catalog.json";
/// Cache of the parsed catalog, invalidated when the cache file mtime changes.
static CACHE: Mutex<Option<CacheEntry>> = Mutex::new(None);
struct CacheEntry {
mtime: SystemTime,
catalog: AppCatalog,
}
/// Top-level catalog document.
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct AppCatalog {
/// Schema version. 1 = current. Bump only on incompatible changes.
#[serde(default)]
pub schema: u32,
/// Publish date (RFC 3339 or YYYY-MM-DD). Informational.
#[serde(default)]
pub updated: String,
/// app_id -> entry.
#[serde(default)]
pub apps: HashMap<String, AppCatalogEntry>,
/// DHT-plan forward-compat: detached signature over the canonical JSON,
/// produced by the seed-derived release-root key. Absent today.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub signature: Option<String>,
/// DHT-plan forward-compat: publisher identity (did:key / npub).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub signed_by: Option<String>,
}
/// Per-app catalog entry.
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct AppCatalogEntry {
/// User-facing version string (drives the "Update available" badge text).
pub version: String,
/// Primary single-container image reference (`registry/repo:tag`). For stack
/// apps this is the primary container's image (the one whose version the
/// badge tracks — e.g. the IndeeHub frontend).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub image: Option<String>,
/// Stack apps only: container_name -> image reference. Components omitted here
/// fall back to the `image-versions.sh` pin during an update.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub images: Option<HashMap<String, String>>,
/// DHT-plan forward-compat: content address of the primary image (unused now).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub digest: Option<String>,
/// DHT-plan forward-compat: size in bytes of the primary image (unused now).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub size: Option<u64>,
/// Optional human-readable changelog lines for this version.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub changelog: Vec<String>,
/// Full app manifest, embedded so the app installs from the registry alone —
/// no OTA-shipped `apps/<id>/manifest.yml`. Carried as the raw value the
/// publisher signed (so it stays part of the verified preimage) and
/// deserialized into an `AppManifest` by the orchestrator at load time, where
/// it overrides the disk manifest (origin-wins). Absent during the migration
/// window => the node falls back to the disk manifest. See
/// `docs/registry-manifest-design.md`.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub manifest: Option<serde_json::Value>,
}
/// Read-side cache file search order. Mirrors `image_versions.rs`: the running
/// daemon's data dir first (via env for dev), then the canonical runtime path.
fn cache_paths() -> Vec<PathBuf> {
let mut paths = Vec::new();
if let Ok(dir) = std::env::var("ARCHIPELAGO_DATA_DIR") {
paths.push(Path::new(&dir).join(APP_CATALOG_FILE));
}
paths.push(Path::new("/var/lib/archipelago").join(APP_CATALOG_FILE));
paths
}
fn find_cache_file() -> Option<(PathBuf, SystemTime)> {
for p in cache_paths() {
if let Ok(meta) = p.metadata() {
if let Ok(mtime) = meta.modified() {
return Some((p, mtime));
}
}
}
None
}
/// Load and cache the on-node catalog. Returns an empty catalog when absent —
/// callers then fall back to `image-versions.sh`.
fn load_catalog() -> AppCatalog {
let (path, mtime) = match find_cache_file() {
Some(v) => v,
None => return AppCatalog::default(),
};
{
let cache = CACHE.lock().unwrap();
if let Some(ref entry) = *cache {
if entry.mtime == mtime {
return entry.catalog.clone();
}
}
}
let content = match std::fs::read_to_string(&path) {
Ok(c) => c,
Err(e) => {
debug!("app-catalog: failed to read {}: {}", path.display(), e);
return AppCatalog::default();
}
};
let catalog: AppCatalog = match serde_json::from_str(&content) {
Ok(c) => c,
Err(e) => {
warn!("app-catalog: invalid JSON at {}: {}", path.display(), e);
return AppCatalog::default();
}
};
{
let mut cache = CACHE.lock().unwrap();
*cache = Some(CacheEntry {
mtime,
catalog: catalog.clone(),
});
}
catalog
}
fn entry_for(app_id: &str) -> Option<AppCatalogEntry> {
load_catalog().apps.get(app_id).cloned()
}
/// Primary image for an app per the remote catalog, if covered.
pub fn catalog_primary_image(app_id: &str) -> Option<String> {
entry_for(app_id).and_then(|e| e.image)
}
/// Per-container stack image overrides from the catalog (container_name -> image).
pub fn catalog_stack_images(app_id: &str) -> HashMap<String, String> {
entry_for(app_id).and_then(|e| e.images).unwrap_or_default()
}
/// All `(app_id, manifest-value)` pairs the registry catalog carries. The
/// orchestrator deserializes + validates each into an `AppManifest` and prefers
/// it over the disk manifest (origin-wins); disk remains the migration fallback.
/// Empty when the catalog is absent or no entry embeds a manifest.
pub fn catalog_manifest_values() -> Vec<(String, serde_json::Value)> {
load_catalog()
.apps
.into_iter()
.filter_map(|(id, e)| e.manifest.map(|m| (id, m)))
.collect()
}
/// Image override for the orchestrator's install/upgrade path. Returns the
/// catalog's primary image for `app_id` ONLY when it refers to the same
/// repository as the manifest's current image — a guard so a catalog typo can
/// never redirect an app to an unrelated image. `None` means "use the manifest
/// image as-is" (catalog absent, app uncovered, or repo mismatch).
pub fn catalog_image_override(app_id: &str, manifest_image: &str) -> Option<String> {
let candidate = catalog_primary_image(app_id)?;
let same_repo = crate::container::image_versions::image_without_registry_or_tag(&candidate)
== crate::container::image_versions::image_without_registry_or_tag(manifest_image);
if same_repo {
Some(candidate)
} else {
warn!(
"app-catalog: ignoring image for {} — repo mismatch (catalog={}, manifest={})",
app_id, candidate, manifest_image
);
None
}
}
/// Decoupled "available update" check for ALL apps.
///
/// Prefers the remote catalog; when the catalog covers the app, its verdict is
/// authoritative (so we never advertise a stale `image-versions.sh` pin over a
/// newer catalog, nor vice-versa). Falls back to the deployed pin only when the
/// catalog is missing or doesn't cover the app.
pub fn available_update_for_app(app_id: &str, running_image: &str) -> Option<String> {
if let Some(catalog_image) = catalog_primary_image(app_id) {
// Catalog covers this app with a concrete image -> authoritative.
return crate::container::image_versions::available_update_for_images(
&catalog_image,
running_image,
);
}
// Not covered by the catalog -> baseline pin from image-versions.sh.
crate::container::image_versions::available_update_for_app(app_id, running_image)
}
/// Derive candidate catalog URLs from the OTA mirror list by swapping the
/// manifest filename for the catalog filename. Falls back to the default
/// manifest origin when no mirrors are configured.
fn catalog_urls_from_mirrors(mirrors: &[crate::update::UpdateMirror]) -> Vec<String> {
let mut urls: Vec<String> = mirrors
.iter()
.filter_map(|m| {
// mirror.url ends with ".../releases/manifest.json"
if m.url.ends_with("manifest.json") {
Some(m.url.replace("manifest.json", APP_CATALOG_FILE))
} else {
None
}
})
.collect();
urls.dedup();
urls
}
/// Fetch the catalog from the first reachable mirror and atomically write it to
/// `<data_dir>/app-catalog.json`. Returns the number of apps in the catalog on
/// success. Best-effort: a fetch failure leaves the existing cache untouched
/// (origin-always-wins; updates simply aren't refreshed this cycle).
pub async fn refresh_catalog(data_dir: &Path) -> anyhow::Result<usize> {
let mirrors = crate::update::load_mirrors(data_dir)
.await
.unwrap_or_default();
let urls = catalog_urls_from_mirrors(&mirrors);
if urls.is_empty() {
debug!("app-catalog: no mirror-derived URLs to fetch from");
return Ok(0);
}
let client = reqwest::Client::builder()
.timeout(std::time::Duration::from_secs(20))
.build()?;
let mut last_err: Option<anyhow::Error> = None;
for url in &urls {
match fetch_one(&client, url).await {
Ok(catalog) => {
let count = catalog.apps.len();
write_cache(data_dir, &catalog)?;
// Invalidate the in-process cache so the next read re-parses.
*CACHE.lock().unwrap() = None;
info!("app-catalog: refreshed from {} ({} apps)", url, count);
return Ok(count);
}
Err(e) => {
debug!("app-catalog: fetch {} failed: {}", url, e);
last_err = Some(e);
}
}
}
Err(last_err.unwrap_or_else(|| anyhow::anyhow!("no catalog mirrors reachable")))
}
async fn fetch_one(client: &reqwest::Client, url: &str) -> anyhow::Result<AppCatalog> {
let resp = client.get(url).send().await?;
if !resp.status().is_success() {
anyhow::bail!("HTTP {}", resp.status());
}
let body = resp.text().await?;
let catalog: AppCatalog = serde_json::from_str(&body)?;
// DHT Phase 0 authenticity: verify the release-root signature when present.
// We verify against the raw JSON (the exact bytes the publisher signed),
// not a re-serialization of the typed struct, so unknown forward-compat
// fields stay part of the signed preimage. Unsigned catalogs are still
// accepted during the migration window — same trust level as today's
// manifest — but a *present* signature that fails is a hard reject so a
// tampering mirror cannot pass off altered bytes.
let raw: serde_json::Value = serde_json::from_str(&body)?;
match crate::trust::verify_detached(&raw)? {
crate::trust::SignatureStatus::Unsigned => {
debug!("app-catalog: unsigned (accepted during migration window)");
}
crate::trust::SignatureStatus::Verified {
signer_did,
anchored,
} => {
if anchored {
info!(
"app-catalog: release-root signature verified ({})",
signer_did
);
} else {
warn!(
"app-catalog: signature self-consistent but release-root anchor \
not pinned ({}); cannot confirm signer identity",
signer_did
);
}
}
}
Ok(catalog)
}
fn write_cache(data_dir: &Path, catalog: &AppCatalog) -> anyhow::Result<()> {
let dest = data_dir.join(APP_CATALOG_FILE);
let tmp = data_dir.join(format!("{}.tmp", APP_CATALOG_FILE));
let json = serde_json::to_string_pretty(catalog)?;
std::fs::write(&tmp, json)?;
std::fs::rename(&tmp, &dest)?;
Ok(())
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn parses_and_ignores_unknown_fields() {
let json = r#"{
"schema": 1,
"updated": "2026-06-16",
"future_field": "ignored",
"signature": "sig123",
"signed_by": "did:key:zABC",
"apps": {
"indeedhub": {
"version": "1.0.1",
"image": "146.59.87.168:3000/lfg2025/indeedhub:1.0.1",
"digest": "blake3:deadbeef",
"size": 12345,
"another_future_field": true
}
}
}"#;
let cat: AppCatalog = serde_json::from_str(json).unwrap();
assert_eq!(cat.schema, 1);
assert_eq!(cat.signature.as_deref(), Some("sig123"));
let e = cat.apps.get("indeedhub").unwrap();
assert_eq!(e.version, "1.0.1");
assert_eq!(
e.image.as_deref(),
Some("146.59.87.168:3000/lfg2025/indeedhub:1.0.1")
);
assert_eq!(e.digest.as_deref(), Some("blake3:deadbeef"));
}
#[test]
fn entry_carries_embedded_manifest() {
let json = r#"{
"schema": 1,
"apps": {
"demo": {
"version": "1.0.0",
"manifest": {
"app": {
"id": "demo",
"name": "Demo",
"version": "1.0.0",
"container": { "image": "registry/demo:1.0.0" }
}
}
}
}
}"#;
let cat: AppCatalog = serde_json::from_str(json).unwrap();
let e = cat.apps.get("demo").unwrap();
let m = e.manifest.as_ref().expect("manifest present");
assert_eq!(m["app"]["id"], "demo");
}
#[test]
fn empty_catalog_when_absent_is_default() {
let cat = AppCatalog::default();
assert!(cat.apps.is_empty());
assert!(cat.signature.is_none());
}
#[test]
fn catalog_url_derived_from_mirror() {
let mirrors = vec![crate::update::UpdateMirror {
url: "http://146.59.87.168:3000/lfg2025/archy/raw/branch/main/releases/manifest.json"
.to_string(),
label: "Server 1".to_string(),
}];
let urls = catalog_urls_from_mirrors(&mirrors);
assert_eq!(
urls,
vec![
"http://146.59.87.168:3000/lfg2025/archy/raw/branch/main/releases/app-catalog.json"
.to_string()
]
);
}
}

View File

@ -96,6 +96,35 @@ impl BootReconciler {
}
}
// Companion self-heal runs on its OWN cadence, decoupled from the
// per-app reconcile pass. On a heavily loaded node `reconcile_existing`
// over dozens of apps can take well over a minute, which would delay a
// companion-unit repair (deleted/lost unit file) past any reasonable
// safety window. Detecting + rewriting a companion unit is cheap, so it
// gets a dedicated `interval` loop. The handle is aborted when the main
// loop exits (shutdown uses `notify_one`, so we must NOT add a second
// waiter on `self.shutdown` — it would steal the single wake permit).
let companion_handle = if self.companion_stage {
let orchestrator = self.orchestrator.clone();
let interval = self.interval;
Some(tokio::spawn(async move {
loop {
let installed = orchestrator.manifest_ids().await;
for (companion, err) in crate::container::companion::reconcile(&installed).await
{
tracing::warn!(
companion = %companion,
error = %err,
"companion reconcile failed"
);
}
time::sleep(interval).await;
}
}))
} else {
None
};
// Initial pass: no delay.
self.tick().await;
@ -111,23 +140,15 @@ impl BootReconciler {
}
}
}
if let Some(handle) = companion_handle {
handle.abort();
}
}
async fn tick(&self) {
let report = self.orchestrator.reconcile_existing().await;
Self::log_report(&report);
if !self.companion_stage {
return;
}
let installed = self.orchestrator.manifest_ids().await;
for (companion, err) in crate::container::companion::reconcile(&installed).await {
tracing::warn!(
companion = %companion,
error = %err,
"companion reconcile failed"
);
}
}
fn log_report(report: &ReconcileReport) {

View File

@ -102,8 +102,15 @@ const LND_UI: &[CompanionSpec] = &[CompanionSpec {
],
pre_start: None,
bind_mounts: &[],
ports: &[(18083, 80)],
host_network: false,
// Host networking so the app's own nginx can proxy the archipelago backend
// same-origin (127.0.0.1:5678), exactly like fips-ui / electrs-ui. The
// previous bridge + 18083→80 mapping forced the browser to fetch the
// backend cross-origin from the app's port, which depended on the host
// nginx route + a CORS Origin/Host match and broke on http-only nodes
// (e.g. .116: blank fields, QR "failed to fetch"). The app's nginx now
// listens on 18083 directly (NOT 80 — that would collide with host nginx).
ports: &[],
host_network: true,
}];
const ELECTRS_UI: &[CompanionSpec] = &[CompanionSpec {
@ -214,13 +221,26 @@ async fn ensure_image_present(spec: &CompanionSpec) -> Result<String> {
for dir in spec.build_dir_candidates {
let dockerfile = PathBuf::from(dir).join("Dockerfile");
if fs::try_exists(&dockerfile).await.unwrap_or(false) {
// `:local` is a deliberate manual override — never auto-rebuild it.
if image_exists(&local_image_compat).await {
return Ok(local_image_compat);
}
// Reuse the auto-built `:latest` only when the build context has NOT
// changed since it was built. Without this staleness check an
// already-present image is reused forever, so edits to the baked-in
// context (Dockerfile, nginx.conf, …) never reach the node — this is
// exactly why the guardian-CSS nginx fix never reached the fleet.
if image_exists(&local_image).await {
return Ok(local_image);
if !context_is_newer_than_image(dir, &local_image).await {
return Ok(local_image);
}
info!(
companion = spec.name,
"build context changed since image built; rebuilding {dir}"
);
} else {
info!(companion = spec.name, "building locally from {dir}");
}
info!(companion = spec.name, "building locally from {dir}");
let out = command_output_with_timeout(
Command::new("podman").args(["build", "-t", &local_image, dir]),
COMPANION_BUILD_TIMEOUT,
@ -265,7 +285,15 @@ async fn ensure_image_present(spec: &CompanionSpec) -> Result<String> {
async fn image_exists(image: &str) -> bool {
let mut cmd = Command::new("podman");
cmd.args(["image", "inspect", image]);
// Only the exit status matters. WITHOUT a `--format`, `podman image inspect`
// prints the image's full multi-KB manifest JSON; `.status()` inherits the
// service's stdout, so on a hit that whole blob lands in the journal — once
// per companion image, every reconcile pass. That flood spikes journald +
// IO and starves the async runtime (UI websocket then drops → "connection
// lost"/reconnect). Discard the child's stdout/stderr; we read neither.
cmd.args(["image", "inspect", image])
.stdout(std::process::Stdio::null())
.stderr(std::process::Stdio::null());
match tokio::time::timeout(COMPANION_IMAGE_CHECK_TIMEOUT, cmd.status()).await {
Ok(Ok(status)) => status.success(),
Ok(Err(err)) => {
@ -279,6 +307,73 @@ async fn image_exists(image: &str) -> bool {
}
}
/// Returns true if any file in the build context `dir` is newer than the
/// already-built `image`, signalling the cached image is stale and must be
/// rebuilt. Conservative: if either timestamp can't be determined we return
/// false (reuse the cache) to avoid rebuild storms on every reconcile pass.
async fn context_is_newer_than_image(dir: &str, image: &str) -> bool {
let image_created = match image_created_unix(image).await {
Some(t) => t,
None => return false,
};
match newest_mtime_unix(PathBuf::from(dir)).await {
Some(ctx) => ctx > image_created,
None => false,
}
}
/// Build timestamp of `image` as Unix seconds, via `podman image inspect`.
async fn image_created_unix(image: &str) -> Option<i64> {
let mut cmd = Command::new("podman");
cmd.args(["image", "inspect", "--format", "{{.Created.Unix}}", image]);
let out = command_output_with_timeout(
&mut cmd,
COMPANION_IMAGE_CHECK_TIMEOUT,
"podman image created time",
)
.await
.ok()?;
if !out.status.success() {
return None;
}
String::from_utf8_lossy(&out.stdout).trim().parse::<i64>().ok()
}
/// Newest modification time (Unix seconds) across all files under `dir`,
/// walked recursively. Runs on a blocking thread since it touches the fs.
async fn newest_mtime_unix(dir: PathBuf) -> Option<i64> {
tokio::task::spawn_blocking(move || newest_mtime_blocking(&dir))
.await
.ok()
.flatten()
}
fn newest_mtime_blocking(dir: &std::path::Path) -> Option<i64> {
let mut newest: Option<i64> = None;
let mut stack = vec![dir.to_path_buf()];
while let Some(p) = stack.pop() {
let entries = match std::fs::read_dir(&p) {
Ok(e) => e,
Err(_) => continue,
};
for entry in entries.flatten() {
let meta = match entry.metadata() {
Ok(m) => m,
Err(_) => continue,
};
if meta.is_dir() {
stack.push(entry.path());
} else if let Ok(modified) = meta.modified() {
if let Ok(dur) = modified.duration_since(std::time::UNIX_EPOCH) {
let secs = dur.as_secs() as i64;
newest = Some(newest.map_or(secs, |n| n.max(secs)));
}
}
}
}
newest
}
async fn command_output_with_timeout(
cmd: &mut Command,
timeout: Duration,
@ -439,12 +534,15 @@ mod tests {
}
#[test]
fn lnd_ui_uses_port_mapping_not_host_port_80() {
fn lnd_ui_uses_host_network_for_same_origin_backend_proxy() {
// lnd-ui is host-networked (its nginx listens on 18083 directly) so the
// app can proxy the archipelago backend same-origin instead of fetching
// it cross-origin from its app port — see the spec comment for why.
let spec = &LND_UI[0];
let u = build_unit(spec, "localhost/lnd-ui:latest");
assert_eq!(u.name, "archy-lnd-ui");
assert!(matches!(u.network, NetworkMode::Bridge(ref n) if n == "bridge"));
assert_eq!(u.ports, vec![(18083, 80, "tcp".into())]);
assert!(matches!(u.network, NetworkMode::Host));
assert!(u.ports.is_empty());
}
#[test]

View File

@ -172,8 +172,10 @@ impl DockerPackageScanner {
// Extract actual version from container image tag
let running_version = 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 =
image_versions::available_update_for_app(&app_id, &container.image);
crate::container::app_catalog::available_update_for_app(&app_id, &container.image);
let package = PackageDataEntry {
state: package_state.clone(),
@ -363,6 +365,13 @@ fn get_app_metadata(app_id: &str) -> AppMetadata {
repo: "https://github.com/fedimint/fedimint".to_string(),
tier: "",
},
"fedimint-clientd" | "fmcd" => AppMetadata {
title: "Fedimint Client".to_string(),
description: "Fedimint ecash client daemon (fmcd) — lets your node hold Fedimint ecash and join federations".to_string(),
icon: "/assets/img/app-icons/fedimint.png".to_string(),
repo: "https://github.com/minmoto/fmcd".to_string(),
tier: "",
},
"morphos" | "morphos-server" => AppMetadata {
title: "Morphos".to_string(),
description: "Self-hosted file converter".to_string(),
@ -682,16 +691,37 @@ fn extract_lan_address(ports: &[String]) -> Option<String> {
None
}
/// netbird's dashboard launch URL: HTTPS on 8087 (the proxy terminates TLS —
/// the dashboard needs a secure context for OIDC PKCE, issue #15) at the node's
/// primary host IP so it's reachable from the LAN. Manifest-driven netbird no
/// longer writes `dashboard.env`, so this is derived from host facts (the same
/// `{{HOST_IP}}` the orchestrator bakes into the cert/config); it falls back to
/// the static localhost mapping when the host IP can't be read. URL shape is
/// identical to the legacy installer's, so the existing https reachability
/// wrapper still applies.
async fn netbird_configured_launch_url() -> Option<String> {
let env = tokio::fs::read_to_string("/var/lib/archipelago/netbird/dashboard.env")
if let Some(ip) = first_host_ip().await {
return Some(format!("https://{ip}:8087"));
}
PodmanClient::lan_address_for("netbird")
}
/// First address from `hostname -I` — the node's primary host IP. Mirrors the
/// orchestrator's `detect_host_ip` so launch URLs match the cert/config the
/// orchestrator renders for `{{HOST_IP}}`.
async fn first_host_ip() -> Option<String> {
let out = tokio::process::Command::new("hostname")
.arg("-I")
.output()
.await
.ok()?;
env.lines()
.find_map(|line| line.strip_prefix("NETBIRD_MGMT_API_ENDPOINT="))
.map(str::trim)
.filter(|s| !s.is_empty())
if !out.status.success() {
return None;
}
String::from_utf8_lossy(&out.stdout)
.split_whitespace()
.next()
.map(ToOwned::to_owned)
.or_else(|| PodmanClient::lan_address_for("netbird"))
}
async fn reachable_lan_address(app_id: &str, candidate: Option<String>) -> Option<String> {
@ -699,7 +729,7 @@ async fn reachable_lan_address(app_id: &str, candidate: Option<String>) -> Optio
if !requires_reachable_launch(app_id) {
return Some(url);
}
let Some(port) = url.rsplit(':').next().and_then(|p| p.parse::<u16>().ok()) else {
let Some(port) = launch_url_port(&url) else {
return None;
};
if launch_port_reachable(port).await {
@ -710,6 +740,23 @@ async fn reachable_lan_address(app_id: &str, candidate: Option<String>) -> Optio
}
}
/// Extract the TCP port from a launch URL's authority.
///
/// The candidate URL can carry a path when it comes from a manifest
/// `interfaces.main` declaration (e.g. `http://localhost:8096/`). A naive
/// `rsplit(':')` then yields `"8096/"`, which fails to parse and silently
/// drops a reachable launch URL. Reading digits after the final colon mirrors
/// `port_from_url` in the RPC layer and tolerates a trailing path.
fn launch_url_port(url: &str) -> Option<u16> {
let after_colon = url.rsplit_once(':')?.1;
after_colon
.chars()
.take_while(|c| c.is_ascii_digit())
.collect::<String>()
.parse::<u16>()
.ok()
}
async fn launch_port_reachable(port: u16) -> bool {
matches!(
tokio::time::timeout(
@ -788,3 +835,26 @@ fn package_state_str(state: &PackageState) -> &str {
PackageState::Updating => "updating",
}
}
#[cfg(test)]
mod launch_url_port_tests {
use super::launch_url_port;
#[test]
fn parses_port_with_trailing_path() {
// Regression: manifest interfaces.main yields a path-suffixed URL.
// The old rsplit(':') parse produced "8096/" and dropped the URL.
assert_eq!(launch_url_port("http://localhost:8096/"), Some(8096));
assert_eq!(launch_url_port("http://localhost:8175/admin"), Some(8175));
}
#[test]
fn parses_bare_authority_port() {
assert_eq!(launch_url_port("http://localhost:8083"), Some(8083));
}
#[test]
fn rejects_url_without_port() {
assert_eq!(launch_url_port("http://localhost/"), None);
}
}

View File

@ -0,0 +1,203 @@
//! Manifest-driven lifecycle hook executor (Task #20).
//!
//! Runs an app's declarative `post_install` hooks against its **own** running
//! container. Hooks are an allowlisted, reviewed escape hatch — NOT arbitrary
//! host scripts:
//!
//! - `exec` runs *inside the container* (`podman exec`), never on the host, and
//! inherits the container's (already dropped) capabilities.
//! - `copy_from_host.src` is resolved against an allowlist root, canonicalised,
//! and rejected on any escape; only then is it `podman cp`'d into the container.
//! - Execution is **best-effort + idempotent**: each step is logged, a failure is
//! warned and the remaining steps still run, so a transient hook error never
//! bricks an install. Authors must make steps safe to re-run (e.g. `grep -q … ||`).
//!
//! See `docs/manifest-hooks-design.md`.
use std::path::{Path, PathBuf};
use std::time::Duration;
use anyhow::{bail, Result};
use archipelago_container::{AppManifest, HookStep};
/// Upper bound on a single hook command. Generous — config rewrites + nginx
/// reloads are fast, but an image with a hung entrypoint shouldn't wedge install.
const HOOK_TIMEOUT: Duration = Duration::from_secs(60);
/// Roots a `copy_from_host.src` may resolve within. A src is joined onto each
/// root, canonicalised, and accepted only if it stays inside that root:
/// - the app's own data dir (`<data_dir>/<app_id>`), and
/// - `/opt/archipelago` (covers the orchestrator's bundled `web-ui/` assets,
/// e.g. indeedhub's `web-ui/nostr-provider.js`).
fn allowlist_roots(app_id: &str, data_dir: &Path) -> Vec<PathBuf> {
vec![data_dir.join(app_id), PathBuf::from("/opt/archipelago")]
}
/// Resolve a hook copy source against the allowlist. Returns the canonical
/// absolute path iff it exists and lies within an allowlist root. Defence in
/// depth: `AppManifest::validate` already rejects absolute / `..` srcs, but we
/// re-check here and canonicalise so a symlink inside a root can't escape it.
fn resolve_copy_src(src: &str, app_id: &str, data_dir: &Path) -> Result<PathBuf> {
if src.is_empty() || src.starts_with('/') || src.contains("..") {
bail!("hook copy src '{src}' is not an allowlisted relative path");
}
for root in allowlist_roots(app_id, data_dir) {
let Ok(root_canon) = root.canonicalize() else {
continue;
};
let Ok(canon) = root.join(src).canonicalize() else {
continue;
};
if canon.starts_with(&root_canon) {
return Ok(canon);
}
}
bail!("hook copy src '{src}' did not resolve inside an allowlist root")
}
/// Run an app's declarative `post_install` hooks against its running container.
/// Best-effort: never returns an error — a failed step is warned and skipped.
/// Called from the install path after the container is created + running, and
/// only when a fresh container was created (see `install_fresh`).
pub async fn run_post_install(manifest: &AppManifest, container_name: &str, data_dir: &Path) {
let steps = &manifest.app.hooks.post_install;
if steps.is_empty() {
return;
}
let app_id = &manifest.app.id;
tracing::info!(
app_id = %app_id,
container = %container_name,
steps = steps.len(),
"running manifest post_install hooks"
);
for (i, step) in steps.iter().enumerate() {
match run_step(step, container_name, app_id, data_dir).await {
Ok(()) => tracing::debug!(app_id = %app_id, step = i, "post_install hook step ok"),
Err(err) => tracing::warn!(
app_id = %app_id,
container = %container_name,
step = i,
error = %err,
"post_install hook step failed (continuing best-effort)"
),
}
}
}
async fn run_step(
step: &HookStep,
container: &str,
app_id: &str,
data_dir: &Path,
) -> Result<()> {
match step {
HookStep::Exec { exec } => {
let mut args: Vec<&str> = Vec::with_capacity(exec.len() + 2);
args.push("exec");
args.push(container);
args.extend(exec.iter().map(String::as_str));
// `exec` spawns a process INSIDE the container's cgroup. When the
// container was started by archipelago.service, that cgroup is under
// the service's slice and a bare `podman exec` from the service can't
// write its `cgroup.procs` ("crun: ... Permission denied / OCI
// permission denied"). Run it in a transient user scope (its own
// delegated cgroup) — mirrors `podman_user_scope` for pasta starts.
run_podman(&args, /* scoped */ true).await
}
HookStep::CopyFromHost { copy_from_host } => {
let abs = resolve_copy_src(&copy_from_host.src, app_id, data_dir)?;
let abs = abs.to_string_lossy().into_owned();
let dest = format!("{container}:{}", copy_from_host.dest);
// `cp` is a host-side copy (no in-container process), so no scope needed.
run_podman(&["cp", &abs, &dest], /* scoped */ false).await
}
}
}
/// Run a podman command, optionally inside a transient systemd user scope. The
/// scope gives the invocation its own delegated cgroup so `podman exec` can
/// place its child process — without it, an exec launched from the service's
/// own cgroup is denied write to the container's `cgroup.procs`.
async fn run_podman(args: &[&str], scoped: bool) -> Result<()> {
let rendered = args.join(" ");
let mut cmd = if scoped {
let mut c = tokio::process::Command::new("systemd-run");
c.args(["--user", "--scope", "--quiet", "--collect", "podman"]);
c.args(args);
c
} else {
let mut c = tokio::process::Command::new("podman");
c.args(args);
c
};
let out = tokio::time::timeout(HOOK_TIMEOUT, cmd.output())
.await
.map_err(|_| anyhow::anyhow!("podman {rendered} timed out after {:?}", HOOK_TIMEOUT))?
.map_err(|e| anyhow::anyhow!("podman {rendered}: {e}"))?;
if !out.status.success() {
bail!(
"podman {rendered} exited {}: {}",
out.status,
String::from_utf8_lossy(&out.stderr).trim()
);
}
Ok(())
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn resolve_copy_src_accepts_file_in_app_data_dir() {
let tmp = tempfile::tempdir().unwrap();
let data_dir = tmp.path();
let app_dir = data_dir.join("myapp/web-ui");
std::fs::create_dir_all(&app_dir).unwrap();
std::fs::write(app_dir.join("provider.js"), b"x").unwrap();
let got = resolve_copy_src("web-ui/provider.js", "myapp", data_dir).unwrap();
assert!(got.ends_with("myapp/web-ui/provider.js"));
assert!(got.is_absolute());
}
#[test]
fn resolve_copy_src_rejects_absolute() {
let tmp = tempfile::tempdir().unwrap();
assert!(resolve_copy_src("/etc/passwd", "myapp", tmp.path()).is_err());
}
#[test]
fn resolve_copy_src_rejects_traversal() {
let tmp = tempfile::tempdir().unwrap();
assert!(resolve_copy_src("web-ui/../../etc/shadow", "myapp", tmp.path()).is_err());
}
#[test]
fn resolve_copy_src_rejects_missing_file() {
// Inside the allowlist shape but the file doesn't exist → canonicalize fails.
let tmp = tempfile::tempdir().unwrap();
std::fs::create_dir_all(tmp.path().join("myapp")).unwrap();
assert!(resolve_copy_src("nope.js", "myapp", tmp.path()).is_err());
}
#[test]
fn resolve_copy_src_rejects_symlink_escape() {
// A symlink inside the app dir pointing outside it must be rejected by
// the post-canonicalisation prefix check.
let tmp = tempfile::tempdir().unwrap();
let app_dir = tmp.path().join("myapp");
std::fs::create_dir_all(&app_dir).unwrap();
let secret = tmp.path().join("secret.txt");
std::fs::write(&secret, b"s").unwrap();
let link = app_dir.join("link.js");
if std::os::unix::fs::symlink(&secret, &link).is_ok() {
// `secret.txt` lives in the tmp root, NOT under <data_dir>/myapp, so
// the canonical target escapes the app-data root. It also isn't under
// /opt/archipelago. Must be rejected.
assert!(resolve_copy_src("link.js", "myapp", tmp.path()).is_err());
}
}
}

View File

@ -213,7 +213,7 @@ pub fn available_update_for_app(app_id: &str, running_image: &str) -> Option<Str
available_update_for_images(&pinned, running_image)
}
fn available_update_for_images(pinned: &str, running_image: &str) -> Option<String> {
pub fn available_update_for_images(pinned: &str, running_image: &str) -> Option<String> {
let pinned_version = extract_version_from_image(&pinned);
if is_floating_tag(&pinned_version) {
return None;
@ -255,7 +255,7 @@ fn is_floating_tag(tag: &str) -> bool {
matches!(tag, "latest" | "stable" | "release" | "main")
}
fn image_without_registry_or_tag(image: &str) -> &str {
pub fn image_without_registry_or_tag(image: &str) -> &str {
let without_tag = strip_tag(image);
match without_tag.split_once('/') {
Some((first, rest))

View File

@ -11,7 +11,16 @@ use crate::update::host_sudo;
pub const DEFAULT_DATA_DIR: &str = "/var/lib/archipelago/lnd";
pub const DEFAULT_CONF_PATH: &str = "/var/lib/archipelago/lnd/lnd.conf";
const LND_REST_BASE_URL: &str = "https://127.0.0.1:18080";
pub const WALLET_PASSWORD: &str = "hellohello";
/// Per-node LND wallet password file (random, 0600). Replaces the old
/// fleet-wide hardcoded constant: each node's wallet password is now unique,
/// high-entropy, and recorded here so the unattended boot path can auto-unlock.
const WALLET_PASSWORD_SECRET: &str = "/var/lib/archipelago/secrets/lnd-wallet-password";
/// Legacy fleet-wide wallet password (builds that hardcoded it). Kept ONLY as an
/// unlock fallback so wallets created by those builds still open; new wallets
/// never use it, and the login-path migration rotates away from it.
const LEGACY_WALLET_PASSWORD: &str = "hellohello";
#[derive(Debug, Clone)]
pub struct EnsurePaths {
@ -79,15 +88,125 @@ pub async fn ensure_wallet_initialized() -> Result<()> {
if file_exists_as_root(admin_macaroon).await && lnd_getinfo_ready(admin_macaroon).await {
return Ok(());
}
unlock_existing_wallet().await?;
wait_for_admin_macaroon(admin_macaroon).await?;
return Ok(());
match unlock_existing_wallet().await? {
true => {
wait_for_admin_macaroon(admin_macaroon).await?;
return Ok(());
}
false => {
// Every candidate password was actively rejected: this wallet was
// created with a password this node no longer has, so it can never
// auto-unlock unattended. Alpha nodes hold no real funds and a wallet
// locked with an unknown password is already inaccessible, so wipe +
// recreate it on the per-node secret to self-heal at boot.
recreate_wallet_destructively().await?;
wait_for_admin_macaroon(admin_macaroon).await?;
return Ok(());
}
}
}
init_wallet_via_rest().await?;
wait_for_admin_macaroon(admin_macaroon).await
}
/// LND data subdirectories holding wallet + channel + graph state. Removing them
/// returns LND to a NON_EXISTING wallet state. Funds-bearing data lives here too,
/// so deletion is destructive — only done once the wallet is already unrecoverable.
const LND_STATE_DIRS: &[&str] = &[
"/var/lib/archipelago/lnd/data/chain",
"/var/lib/archipelago/lnd/data/graph",
];
/// Podman container name for the core LND app (see `compute_container_name`:
/// non-UI core apps keep their bare id). LND runs as a plain bridge-network
/// container, not a Quadlet unit, so it is restarted via `podman`, not systemctl.
const LND_CONTAINER: &str = "lnd";
/// Archipelago data dir (default; not overridden in prod). Holds the
/// `user-stopped.json` that gates health-monitor auto-restart.
const ARCHY_DATA_DIR: &str = "/var/lib/archipelago";
/// Destroy an unrecoverable LND wallet and recreate a fresh one keyed to the
/// per-node secret. Suppresses health-monitor auto-restart for the wipe window,
/// stops LND, deletes its wallet/chain/graph state as root, restarts it, waits
/// for NON_EXISTING, then inits a fresh wallet. Destructive — only called when no
/// candidate password can open the existing wallet.
async fn recreate_wallet_destructively() -> Result<()> {
tracing::warn!(
"[lnd] wallet is locked with an unknown password and cannot auto-unlock; \
wiping and recreating it on the per-node secret (DESTRUCTIVE)"
);
// The health monitor restarts any container it sees stopped; mark LND
// user-stopped so it doesn't re-launch (and re-open the wallet) mid-wipe.
// Always cleared below so LND auto-recovers normally afterwards.
let data_dir = std::path::Path::new(ARCHY_DATA_DIR);
crate::crash_recovery::mark_user_stopped(data_dir, LND_CONTAINER).await;
let result = wipe_and_reinit_wallet().await;
crate::crash_recovery::clear_user_stopped(data_dir, LND_CONTAINER).await;
result
}
async fn wipe_and_reinit_wallet() -> Result<()> {
podman_user_scoped(&["stop", LND_CONTAINER])
.await
.context("stopping lnd before wallet wipe")?;
for dir in LND_STATE_DIRS {
let status = host_sudo(&["rm", "-rf", dir])
.await
.with_context(|| format!("removing {dir}"))?;
if !status.success() {
anyhow::bail!("removing {dir} exited with {status}");
}
}
podman_user_scoped(&["start", LND_CONTAINER])
.await
.context("restarting lnd after wallet wipe")?;
wait_for_wallet_state("NON_EXISTING").await?;
init_wallet_via_rest().await
}
/// Run `podman <args>` inside a transient `systemd-run --user --scope`, matching
/// how the orchestrator/health-monitor manage rootless containers (keeps the
/// container out of the archipelago service's cgroup).
async fn podman_user_scoped(args: &[&str]) -> Result<()> {
let out = tokio::process::Command::new("systemd-run")
.args(["--user", "--scope", "--quiet", "--collect", "podman"])
.args(args)
.output()
.await
.with_context(|| format!("systemd-run --user --scope podman {}", args.join(" ")))?;
if !out.status.success() {
anyhow::bail!(
"podman {} failed: {}",
args.join(" "),
String::from_utf8_lossy(&out.stderr).trim()
);
}
Ok(())
}
/// Poll `/v1/state` until LND reports `target`, or time out after ~120s.
async fn wait_for_wallet_state(target: &str) -> Result<()> {
let client = reqwest::Client::builder()
.no_proxy()
.timeout(std::time::Duration::from_secs(5))
.danger_accept_invalid_certs(true)
.build()
.context("building LND REST client")?;
for _ in 0..120 {
if wallet_state(&client).await.as_deref() == Some(target) {
return Ok(());
}
tokio::time::sleep(std::time::Duration::from_secs(1)).await;
}
anyhow::bail!("LND did not reach state {target} after wallet wipe")
}
async fn file_exists_as_root(path: &str) -> bool {
if std::path::Path::new(path).exists() {
return true;
@ -121,11 +240,96 @@ async fn read_file_as_root(path: &str) -> Result<Vec<u8>> {
}
}
async fn unlock_existing_wallet() -> Result<()> {
/// Read the per-node wallet password from the secrets file, if present.
/// Never generates one — absence means "fall back to legacy / not set yet".
async fn read_wallet_password() -> Option<String> {
let bytes = fs::read(WALLET_PASSWORD_SECRET).await.ok()?;
let pw = String::from_utf8_lossy(&bytes).trim().to_string();
(!pw.is_empty()).then_some(pw)
}
/// Return the per-node wallet password, generating and persisting a fresh
/// 256-bit one (base64, 0600) if none exists. Use ONLY when creating a NEW
/// wallet — calling it merely to unlock an existing wallet would record a
/// password that doesn't match it.
pub(crate) async fn ensure_wallet_password() -> Result<String> {
if let Some(pw) = read_wallet_password().await {
return Ok(pw);
}
use rand::RngCore;
let mut raw = [0u8; 32];
rand::rngs::OsRng.fill_bytes(&mut raw);
let pw = base64::engine::general_purpose::URL_SAFE_NO_PAD.encode(raw);
let path = std::path::Path::new(WALLET_PASSWORD_SECRET);
if let Some(dir) = path.parent() {
fs::create_dir_all(dir)
.await
.with_context(|| format!("creating {}", dir.display()))?;
}
fs::write(path, &pw)
.await
.with_context(|| format!("writing {WALLET_PASSWORD_SECRET}"))?;
use std::os::unix::fs::PermissionsExt;
let _ = fs::set_permissions(path, std::fs::Permissions::from_mode(0o600)).await;
Ok(pw)
}
/// Candidate passwords to try when unlocking an EXISTING wallet, in order: the
/// per-node secret (current scheme) first, then the legacy constant so wallets
/// created by older builds still open.
async fn unlock_password_candidates() -> Vec<String> {
let mut v = Vec::new();
if let Some(pw) = read_wallet_password().await {
v.push(pw);
}
v.push(LEGACY_WALLET_PASSWORD.to_string());
v
}
/// Outcome of a single unlock attempt — lets the caller fail fast on a wrong
/// password (no point retrying) vs keep waiting for LND to come up.
enum UnlockAttempt {
Unlocked,
WrongPassword,
NotReady,
}
/// One unlock POST, no internal retry. Distinguishes "invalid passphrase"
/// (WrongPassword — try the next candidate, don't retry) from transient
/// not-ready / connection errors (NotReady — worth retrying).
async fn try_unlock_once(client: &reqwest::Client, password: &str) -> UnlockAttempt {
let body = serde_json::json!({
"wallet_password": base64::engine::general_purpose::STANDARD.encode(password)
});
match client
.post(format!("{LND_REST_BASE_URL}/v1/unlockwallet"))
.json(&body)
.send()
.await
{
Ok(resp) => {
let status = resp.status();
let text = resp.text().await.unwrap_or_default();
if status.is_success() || text.contains("already unlocked") {
UnlockAttempt::Unlocked
} else if text.contains("invalid passphrase") {
UnlockAttempt::WrongPassword
} else {
UnlockAttempt::NotReady
}
}
Err(_) => UnlockAttempt::NotReady,
}
}
/// Unlock an existing wallet. Ok(true) = unlocked; Ok(false) = every candidate
/// password was actively rejected (unrecoverable — caller should recreate);
/// Err = transient (LND not ready / timeout — caller should retry, NOT wipe).
async fn unlock_existing_wallet() -> Result<bool> {
unlock_existing_wallet_via_rest().await
}
async fn unlock_existing_wallet_via_rest() -> Result<()> {
async fn unlock_existing_wallet_via_rest() -> Result<bool> {
let client = reqwest::Client::builder()
.no_proxy()
.timeout(std::time::Duration::from_secs(20))
@ -133,57 +337,130 @@ async fn unlock_existing_wallet_via_rest() -> Result<()> {
.build()
.context("building LND REST client")?;
let wallet_password = base64::engine::general_purpose::STANDARD.encode(WALLET_PASSWORD);
match post_lnd_unlocker_json::<serde_json::Value>(
&client,
"/v1/unlockwallet",
serde_json::json!({ "wallet_password": wallet_password }),
)
.await
.context("unlocking existing LND wallet")?
{
UnlockerResponse::Value(_) | UnlockerResponse::WalletAlreadyExists => Ok(()),
let candidates = unlock_password_candidates().await;
// Retry only while LND's unlocker isn't ready yet. If every candidate is
// *actively rejected* (invalid passphrase), retrying can't help — fail fast
// with a clear message instead of hanging the boot path for 60s+ (the wallet
// was created with a password this node doesn't have → migration/recovery).
for _ in 0..60 {
let mut all_rejected = true;
for pw in &candidates {
match try_unlock_once(&client, pw).await {
UnlockAttempt::Unlocked => return Ok(true),
UnlockAttempt::WrongPassword => {}
UnlockAttempt::NotReady => all_rejected = false,
}
}
if all_rejected {
tracing::warn!(
"[lnd] none of the {} candidate password(s) unlock the wallet — it was created \
with a password this node does not have",
candidates.len()
);
return Ok(false);
}
tokio::time::sleep(std::time::Duration::from_secs(1)).await;
}
anyhow::bail!("LND wallet unlock timed out waiting for the unlocker to become ready")
}
/// Current LND wallet state via the unauthenticated `/v1/state` endpoint
/// (NON_EXISTING / LOCKED / UNLOCKED / RPC_ACTIVE / …). None if unreachable.
async fn wallet_state(client: &reqwest::Client) -> Option<String> {
let resp = client
.get(format!("{LND_REST_BASE_URL}/v1/state"))
.send()
.await
.ok()?;
let v: serde_json::Value = resp.json().await.ok()?;
v.get("state")
.and_then(|s| s.as_str())
.map(|s| s.to_string())
}
/// ChangePassword via WalletUnlocker (wallet must be LOCKED). Both passwords are
/// base64-encoded. Ok(true) = current accepted and rotated; Ok(false) = current
/// rejected (wrong password — try the next candidate); Err = transport/other.
async fn change_wallet_password(
client: &reqwest::Client,
current: &str,
new: &str,
) -> Result<bool> {
let body = serde_json::json!({
"current_password": base64::engine::general_purpose::STANDARD.encode(current),
"new_password": base64::engine::general_purpose::STANDARD.encode(new),
});
let resp = client
.post(format!("{LND_REST_BASE_URL}/v1/changepassword"))
.json(&body)
.send()
.await
.context("calling LND changepassword")?;
let status = resp.status();
let text = resp.text().await.unwrap_or_default();
if status.is_success() {
Ok(true)
} else if text.contains("invalid passphrase") {
Ok(false)
} else {
anyhow::bail!("LND changepassword returned {status}: {text}")
}
}
#[allow(dead_code)]
async fn unlock_existing_wallet_via_lncli() -> Result<()> {
let mut last_err = None;
for _ in 0..60 {
let mut cmd = tokio::process::Command::new("podman");
cmd.args(["exec", "-i", "lnd", "lncli", "unlock", "--stdin"]);
cmd.stdin(std::process::Stdio::piped());
cmd.stdout(std::process::Stdio::piped());
cmd.stderr(std::process::Stdio::piped());
/// Best-effort migration of a LOCKED wallet onto the per-node secret. Called at
/// login, when the onboarding password is available as a candidate. If the
/// per-node secret already opens the wallet, just unlock. Otherwise try each
/// candidate as the CURRENT password and ChangePassword it to a fresh per-node
/// secret so all future boots auto-unlock. Ok(true) = healed/unlocked;
/// Ok(false) = not locked, or no candidate worked (seed-recovery required).
pub(crate) async fn migrate_locked_wallet(candidates: &[String]) -> Result<bool> {
let client = reqwest::Client::builder()
.no_proxy()
.timeout(std::time::Duration::from_secs(20))
.danger_accept_invalid_certs(true)
.build()
.context("building LND REST client")?;
let mut child = cmd.spawn().context("spawning lncli wallet unlock")?;
if let Some(mut stdin) = child.stdin.take() {
use tokio::io::AsyncWriteExt;
stdin
.write_all(format!("{}\n", WALLET_PASSWORD).as_bytes())
.await
.context("writing lncli password")?;
}
let out = child
.wait_with_output()
.await
.context("waiting for lncli")?;
if out.status.success() {
return Ok(());
}
let stderr = String::from_utf8_lossy(&out.stderr);
let stdout = String::from_utf8_lossy(&out.stdout);
let msg = format!("{stderr}{stdout}");
if msg.contains("wallet already unlocked") || msg.contains("already unlocked") {
return Ok(());
}
last_err = Some(msg);
tokio::time::sleep(std::time::Duration::from_secs(1)).await;
// Only act on a wallet that is actually LOCKED.
if wallet_state(&client).await.as_deref() != Some("LOCKED") {
return Ok(false);
}
anyhow::bail!(
"lncli wallet unlock failed: {}",
last_err.unwrap_or_else(|| "unknown error".to_string())
)
// If the per-node secret already opens it, nothing to rotate — just unlock.
if let Some(secret) = read_wallet_password().await {
if matches!(
try_unlock_once(&client, &secret).await,
UnlockAttempt::Unlocked
) {
return Ok(true);
}
}
// The wallet's new password becomes the per-node secret (generate if absent).
let new_secret = ensure_wallet_password().await?;
// ChangePassword requires LOCKED; bail out if a prior step already unlocked.
if wallet_state(&client).await.as_deref() != Some("LOCKED") {
return Ok(true);
}
for cand in candidates {
if cand.is_empty() || *cand == new_secret {
continue;
}
match change_wallet_password(&client, cand, &new_secret).await {
Ok(true) => {
tracing::info!("[lnd-migrate] rotated locked wallet onto the per-node secret");
return Ok(true);
}
Ok(false) => continue, // wrong current password — try next candidate
Err(e) => tracing::debug!("[lnd-migrate] changepassword error: {e}"),
}
}
tracing::warn!(
"[lnd-migrate] no candidate password opened the wallet — seed-recovery required"
);
Ok(false)
}
#[derive(Debug, Deserialize)]
@ -225,7 +502,8 @@ async fn init_wallet_via_rest() -> Result<()> {
anyhow::bail!("LND genseed returned no seed words");
}
let wallet_password = base64::engine::general_purpose::STANDARD.encode(WALLET_PASSWORD);
let wallet_password =
base64::engine::general_purpose::STANDARD.encode(ensure_wallet_password().await?);
let req = InitWalletRequest {
wallet_password,
cipher_seed_mnemonic: seed.cipher_seed_mnemonic,
@ -239,7 +517,9 @@ async fn init_wallet_via_rest() -> Result<()> {
.context("initializing LND wallet")?
{
UnlockerResponse::Value(_) => {}
UnlockerResponse::WalletAlreadyExists => unlock_existing_wallet().await?,
UnlockerResponse::WalletAlreadyExists => {
unlock_existing_wallet().await?;
}
}
Ok(())
@ -450,7 +730,16 @@ mod tests {
}
#[test]
fn wallet_password_is_valid_for_lncli() {
assert!(WALLET_PASSWORD.len() > 8);
fn legacy_wallet_password_is_valid_for_lncli() {
// Legacy fallback must still be a valid lncli passphrase (>8 chars).
assert!(LEGACY_WALLET_PASSWORD.len() > 8);
}
#[tokio::test]
async fn unlock_candidates_always_include_legacy_fallback() {
// With no per-node secret on disk in the test env, candidates fall back
// to the legacy constant so old wallets still open.
let cands = unlock_password_candidates().await;
assert!(cands.iter().any(|p| p == LEGACY_WALLET_PASSWORD));
}
}

View File

@ -1,3 +1,4 @@
pub mod app_catalog;
pub mod bitcoin_ui;
pub mod boot_reconciler;
pub mod companion;
@ -5,11 +6,13 @@ pub mod data_manager;
pub mod dev_orchestrator;
pub mod docker_packages;
pub mod filebrowser;
pub mod hooks;
pub mod image_versions;
pub mod lnd;
pub mod prod_orchestrator;
pub mod quadlet;
pub mod registry;
pub mod secrets;
pub mod traits;
pub use boot_reconciler::{BootReconciler, DEFAULT_INTERVAL as RECONCILER_DEFAULT_INTERVAL};

Some files were not shown because too many files have changed in this diff Show More