From b565c31ea914e6dac901380fea0e1a04d3843319 Mon Sep 17 00:00:00 2001
From: archipelago <archipelago@localhost>
Date: Sat, 8 Aug 2026 20:58:32 -0400
Subject: [PATCH] test(lifecycle): don't let one RPC hiccup hide which app
 failed

The stop/start/restart loop carefully accumulates per-app failures into
$fails and prints them, but the three rpc_result calls were bare. Under
bats' errexit a bare call ends the test immediately, so the summary that
names the app never ran.

On 2026-08-08 that turned a single transient error into an unattributable
failure: the test died at package.stop with no indication which of the
ten targets was involved. It was mempool, and the identical call returned
{"status":"stopping"} by hand a few minutes later.

Each call now records <id>:<phase>-rpc and moves to the next app, so the
run reports what actually broke.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
---
 tests/lifecycle/bats/all-apps-lifecycle.bats | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/tests/lifecycle/bats/all-apps-lifecycle.bats b/tests/lifecycle/bats/all-apps-lifecycle.bats
index fce49404..d35c4c6b 100644
--- a/tests/lifecycle/bats/all-apps-lifecycle.bats
+++ b/tests/lifecycle/bats/all-apps-lifecycle.bats
@@ -129,11 +129,21 @@ catalog_install_payload() {
   local fails="" id
   for id in $(target_apps); do
     [[ "$(app_state "$id")" == "running" ]] || continue   # only cycle running apps
-    rpc_result package.stop "{\"id\":\"$id\"}" >/dev/null 2>&1
+    # Each rpc_result must be allowed to fail without aborting the loop.
+    # rpc_result returns non-zero whenever the response carries .error, and
+    # under bats' errexit a bare call ends the test right there — so a single
+    # transient RPC hiccup killed the run BEFORE the $fails summary below could
+    # name the app. That is exactly what happened on 2026-08-08: the whole test
+    # died at package.stop with no indication of which of the ten targets it was
+    # (it was mempool, and the same call succeeded by hand moments later).
+    rpc_result package.stop "{\"id\":\"$id\"}" >/dev/null 2>&1 \
+      || { fails+="$id:stop-rpc "; continue; }
     wait_state "$id" stopped 120 || { fails+="$id:stop "; }
-    rpc_result package.start "{\"id\":\"$id\"}" >/dev/null 2>&1
+    rpc_result package.start "{\"id\":\"$id\"}" >/dev/null 2>&1 \
+      || { fails+="$id:start-rpc "; continue; }
     wait_state "$id" running 240 || { fails+="$id:start "; continue; }
-    rpc_result package.restart "{\"id\":\"$id\"}" >/dev/null 2>&1
+    rpc_result package.restart "{\"id\":\"$id\"}" >/dev/null 2>&1 \
+      || { fails+="$id:restart-rpc "; continue; }
     wait_state "$id" running 240 || { fails+="$id:restart "; }
   done
   [[ -z "$fails" ]] || { echo "# lifecycle failures: $fails" >&3; false; }