fix(tests): bound the lnd getinfo probe + track the backend-recreate cascade gap

lnd.bats retry loop had no per-exec timeout — a wedged lnd RPC (chain-blind
after bitcoin-knots was recreated under it) hung one podman exec, and the
whole gate, indefinitely (.228, 30+ min at test 75). timeout 10 per attempt
keeps the intended ~4min bound. Tracker: new §C item for the root cause —
apps cache their backend container's IP; a backend recreate must cascade a
dependent restart/alert or lnd goes chain-blind silently.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

docs/1.8.0-RELEASE-HARDENING-PLAN.md

@@ -202,6 +202,13 @@ modules; production request/boot paths are essentially panic-free. The real risk
       `no such object` phrasing added to all 3 `is_missing_container_error` classifiers.
       Follow-up (open): reconciler-side cleanup of an orphan umbrella `mempool` container
       when the split stack owns the frontend, so the stale-tile state can't arise at all.
+- [ ] 🟠 **Backend recreate must cascade to dependent apps** (found on .228 2026-07-08):
+      when bitcoin-knots was recreated mid-gate (one-time secret-env recreate) it got a new
+      archy-net IP; **lnd caches the resolved backend IP** and kept dialing the dead one
+      ("no route to host") for 30+ min — chain-blind with open channels, silently (container
+      "running", health green). Repair was a manual lnd restart. Fix = reconciler/health
+      monitor restarts (or at least alerts on) apps whose declared backend container was
+      recreated; same class applies to electrumx/btcpay/nbxplorer → bitcoin links.
 
 ---
 

tests/lifecycle/bats/lnd.bats

@@ -53,8 +53,11 @@ teardown_file() {
   # lnd's RPC readiness LAGS the container "running" state: after a (re)start the
   # wallet must auto-unlock before lncli answers, so a single-shot getinfo races
   # that window and false-fails. Retry until ready (~90s), like a health probe.
+  # `timeout 10` per attempt: a wedged lnd RPC (e.g. chain-blind after its
+  # bitcoin backend was recreated under it, .228 2026-07-08) otherwise hangs
+  # a single exec — and with it the whole suite — indefinitely.
   run sh -lc 'for i in $(seq 1 80); do
-    podman exec lnd lncli \
+    timeout 10 podman exec lnd lncli \
       --tlscertpath /root/.lnd/tls.cert \
       --macaroonpath /root/.lnd/data/chain/bitcoin/mainnet/readonly.macaroon \
       --rpcserver localhost:10009 getinfo >/dev/null 2>&1 && exit 0