archy/tests/lifecycle/bats/bitcoin-receive.bats
archipelago 7b77462ddf fix(tests): lnd.newaddress settle window for the post-cascade unlock race
Gate test 24 probed lnd.newaddress moments after the bitcoin bounce
cascade-restarted lnd; the auto-unlocker was still retrying against a
starting gRPC, so the probe saw LND_WALLET_LOCKED on a node that unlocks
itself seconds later (verified on .228 — same request succeeds post-run).
Treat WALLET_LOCKED as settling with a bounded 120s retry, mirroring the
e21f3baf settle window for tests 123/124; every other error still fails
fast, and a genuinely stuck-locked wallet still fails after the window.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-09 17:05:42 -04:00

114 lines
4.5 KiB
Bash

#!/usr/bin/env bats
# tests/lifecycle/bats/bitcoin-receive.bats
#
# Regression coverage for the Bitcoin "Receive" flow. Receive addresses come
# from LND's hot wallet via the `lnd.newaddress` RPC, so this exercises the
# exact path that broke on the fleet:
# - .116: LND REST published on the wrong host port (8080 vs the manifest's
# 18080) -> connection refused -> receive failed with the generic
# "Operation failed. Check server logs." message.
# - .228: the same family surfaced to the UI as a *false* "wallet is locked".
#
# These tests run on the archy host (they shell into podman / curl localhost).
#
# Tiers: read-only only — generating a receive address is non-destructive.
load '../lib/rpc.bash'
setup_file() {
: "${ARCHY_PASSWORD:?Set ARCHY_PASSWORD env var to the UI password}"
export ARCHY_FORCE_LOGIN=1
rpc_login
unset ARCHY_FORCE_LOGIN
}
teardown_file() {
rpc_logout_local
}
# Resolve the LND REST host port from the manifest (single source of truth) so
# this test follows the manifest rather than hard-coding 18080.
_lnd_rest_host_port() {
local mf
for mf in \
"${ARCHIPELAGO_APPS_DIR:-/opt/archipelago/apps}/lnd/manifest.yml" \
"${ARCHIPELAGO_APPS_DIR:-/opt/archipelago/apps}/lnd/manifest.yaml" \
"$BATS_TEST_DIRNAME/../../../apps/lnd/manifest.yml"; do
[[ -r "$mf" ]] || continue
# The REST mapping is the `- host: <N>` whose following `container:` is 8080.
awk '
/- host:/ { host=$3 }
/container:/ { if ($2 == 8080 && host != "") { print host; exit } }
' "$mf"
return 0
done
}
_lnd_running() {
rpc_result container-list 2>/dev/null \
| jq -e '.[] | select(.name == "lnd" and .state == "running")' >/dev/null 2>&1
}
# ────────────────────────────────────────────────────────────────────
# Read-only tier
# ────────────────────────────────────────────────────────────────────
@test "LND REST is reachable on the manifest host port (catches port drift)" {
_lnd_running || skip "lnd not running"
local port
port=$(_lnd_rest_host_port)
[[ -n "$port" ]] || skip "could not resolve LND REST host port from manifest"
# A TCP connect is enough: drift (container published on a different host
# port) shows up as connection-refused here, exactly as on .116.
run curl -sk -o /dev/null --max-time 8 "https://127.0.0.1:${port}/v1/getinfo"
if [ "$status" -ne 0 ]; then
echo "LND REST not reachable on host port ${port} (curl exit $status) — likely published-port drift" >&2
return 1
fi
}
@test "lnd.newaddress returns a bech32 address when lnd is running" {
_lnd_running || skip "lnd not running"
# The bitcoin bounce in bitcoin-knots.bats cascade-restarts lnd (24fd97ed).
# After a restart lnd's gRPC comes up seconds before the auto-unlocker gets
# through (its UnlockWallet calls log "waiting to start" until then), so
# LND_WALLET_LOCKED inside that window is the node settling, not broken —
# retry up to 120s. Any other error, or a wallet still locked after the
# window, fails immediately below.
local deadline=$((SECONDS + 120)) err addr
while :; do
run rpc_call lnd.newaddress
[ "$status" -eq 0 ]
err=$(echo "$output" | jq -r '.error.message // .error // empty')
addr=$(echo "$output" | jq -r '.result.address // empty')
[[ "$err" == *LND_WALLET_LOCKED* && $SECONDS -lt $deadline ]] || break
sleep 10
done
# The whole point of the fix: a running lnd must hand back a real address.
if [[ -n "$err" ]]; then
echo "lnd.newaddress errored on a running node: $err" >&2
return 1
fi
if [[ "$addr" != bc1* ]]; then
echo "expected a bech32 (bc1…) address, got: '$addr'" >&2
return 1
fi
}
@test "receive errors are specific, never the generic catch-all" {
# Even when receive legitimately can't produce an address, the message must be
# actionable (start with 'Bitcoin address' and/or carry a [CODE] token) — the
# generic 'Operation failed' is what hid the real cause on .116.
run rpc_call lnd.newaddress
[ "$status" -eq 0 ]
local err
err=$(echo "$output" | jq -r '.error.message // .error // empty')
if [[ "$err" == "Operation failed. Check server logs for details." ]]; then
echo "receive returned the generic catch-all instead of a specific reason" >&2
return 1
fi
}