Classify recovered AMQP redeploy errors

scripts/redeploy-fleetd.sh

@@ -116,6 +116,41 @@ check_log_path_matches_plist() {
   ok "log path check: script and plist agree ($resolved_out)"
 }
 
+# Classify ERROR lines in one fresh log region. RabbitMQ's client reports a lost TCP connection
+# through ForgivingExceptionHandler. We only quiet its exact "Connection reset" error after one of
+# fleetd's own recovery listeners later reports a completed AMQP recovery. Every other ERROR, and
+# every unmatched reset, stays unexplained so a failed broker link remains loud.
+classify_amqp_connection_errors() {
+  local log_file="$1" line pending_resets=0
+  REDEPLOY_ERROR_COUNT=0
+  REDEPLOY_RECOVERED_AMQP_ERRORS=0
+  REDEPLOY_UNEXPLAINED_ERRORS=0
+
+  while IFS= read -r line || [ -n "$line" ]; do
+    case "$line" in
+      *' ERROR '*|*' SEVERE '*)
+        REDEPLOY_ERROR_COUNT=$((REDEPLOY_ERROR_COUNT + 1))
+        case "$line" in
+          *'com.rabbitmq.client.impl.ForgivingExceptionHandler'*'Connection reset'*)
+            pending_resets=$((pending_resets + 1))
+            ;;
+          *)
+            REDEPLOY_UNEXPLAINED_ERRORS=$((REDEPLOY_UNEXPLAINED_ERRORS + 1))
+            ;;
+        esac
+        ;;
+      *'AMQP connection recovered; cleared held replies for fresh redelivery'*|*'AMQP lead mailbox connection recovered; cleared held messages for fresh redelivery'*)
+        if [ "$pending_resets" -gt 0 ]; then
+          pending_resets=$((pending_resets - 1))
+          REDEPLOY_RECOVERED_AMQP_ERRORS=$((REDEPLOY_RECOVERED_AMQP_ERRORS + 1))
+        fi
+        ;;
+    esac
+  done < "$log_file"
+
+  REDEPLOY_UNEXPLAINED_ERRORS=$((REDEPLOY_UNEXPLAINED_ERRORS + pending_resets))
+}
+
 # CB-600: sourceable for testing. When this file is SOURCED (not executed) it stops here — nothing
 # below runs — so a test harness can `source` it to call check_log_path_matches_plist (or the
 # other pure helpers above) against a throwaway plist fixture without ever reaching the mutating
@@ -361,15 +396,21 @@ tail -n "+$((RESTART_MARK + 1))" "$OUT" 2>/dev/null \
   | grep -iE 'deferred|classification:|fleet health:|coverage' | tail -8 | sed 's/^/   /' \
   || echo "   (nothing reported)"
 
-# Errors since the restart, anchored to the marker so old noise cannot leak in.
-ERRS="$(tail -n "+$((RESTART_MARK + 1))" "$OUT" 2>/dev/null | grep -cE ' (ERROR|SEVERE) ' || true)"
+# Errors since the restart, anchored to the marker so old noise cannot leak in. Keep the fresh
+# region in a file because the classifier must preserve the order of errors and recoveries.
+FRESH_LOG="$(mktemp -t fleetd-fresh-log)"
+trap 'rm -f "$FRESH_LOG"' EXIT
+tail -n "+$((RESTART_MARK + 1))" "$OUT" > "$FRESH_LOG" 2>/dev/null || true
+classify_amqp_connection_errors "$FRESH_LOG"
 say "result"
 ok "pid $NEW_PID, jar $(jar_id)"
-if [ "${ERRS:-0}" -gt 0 ]; then
-  warn "$ERRS ERROR lines since restart:"
-  tail -n "+$((RESTART_MARK + 1))" "$OUT" | grep -E ' (ERROR|SEVERE) ' | tail -5 | sed 's/^/   /'
-else
+if [ "$REDEPLOY_ERROR_COUNT" -eq 0 ]; then
   ok "no ERROR lines since restart"
+elif [ "$REDEPLOY_UNEXPLAINED_ERRORS" -eq 0 ]; then
+  ok "$REDEPLOY_RECOVERED_AMQP_ERRORS AMQP connection reset ERROR lines recovered since restart"
+else
+  warn "$REDEPLOY_ERROR_COUNT ERROR lines since restart:"
+  grep -E ' (ERROR|SEVERE) ' "$FRESH_LOG" | tail -5 | sed 's/^/   /'
 fi
 echo
 echo "   Next: call fleet_whoami and confirm it still answers 'primary'. A lead whose tab label"