fix: correct state file ownership and function naming across watchdogs

stability_watchdog: remove SYS_WATCHDOG_FAILED_FILE from state file
touch list — skip list is owned by docker_watchdog, not stability.

docker_watchdog: rename check_system_watchdog_state →
check_resource_watchdog_state (reads RW_STATE_FILE from resource_watchdog,
not SYS_WATCHDOG_STATE_FILE from stability_watchdog). Update all comments
and state file docs to reflect correct ownership.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Watchdogs/docker_watchdog.sh

@@ -53,8 +53,8 @@
 #   Timeout protection    — all docker commands wrapped in timeout
 #   Docker daemon check   — each cycle begins with daemon health check; hung daemon →
 #                           restart via rc.docker → stability_watchdog.sh escalates if needed
-#   RAM emergency defer   — reads SYS_WATCHDOG_STATE_FILE; stands down while
-#                           stability_watchdog.sh is managing a RAM emergency
+#   RAM emergency defer   — reads RW_STATE_FILE; stands down while
+#                           resource_watchdog.sh is managing a RAM emergency
 #
 # ==============================================================================================
 # DESIGN PRINCIPLES
@@ -116,10 +116,10 @@
 #   critical, skip cycle. stability_watchdog.sh handles further escalation.
 #
 # RAM Emergency Deferral
-#   Reads SYS_WATCHDOG_STATE_FILE each cycle. If stability_watchdog.sh has set
+#   Reads RW_STATE_FILE each cycle. If resource_watchdog.sh has set
 #   mem_shutdown_active=true, all restart logic defers until the flag clears.
 #   Stale state guard: if file is >2 hours old with flag still set,
-#   stability_watchdog.sh has likely stopped — watchdog resumes normal operation.
+#   resource_watchdog.sh has likely stopped — watchdog resumes normal operation.
 #
 # Timeout Protection
 #   All docker commands wrapped in timeout. Daemon hangs cannot stall the
@@ -133,13 +133,10 @@
 # STATE FILES
 # ==============================================================================================
 #
-#   WATCHDOG_STATE_FILE            — strike counts (default: /tmp — resets on reboot)
-#   SYS_WATCHDOG_FAILED_FILE       — skip list (default: /boot/config — survives reboots)
-#   WATCHDOG_CONTAINER_RESTART_LOG — restart history for loop detection
-#   SYS_WATCHDOG_STATE_FILE        — shared state with system_watchdog.sh (RAM emergency flag)
-#
-# /tmp files reset on reboot — correct, pre-reboot strike counts are meaningless after it.
-# /boot/config files survive reboots — correct, a skip-listed container is still broken after one.
+#   WATCHDOG_STATE_FILE            — strike counts, daemon flags (STATE_DIR — survives reboots)
+#   SYS_WATCHDOG_FAILED_FILE       — container skip list (STATE_DIR — survives reboots)
+#   WATCHDOG_CONTAINER_RESTART_LOG — restart history for loop detection (DATA_DIR)
+#   RW_STATE_FILE                  — read-only: resource_watchdog RAM emergency flag
 #
 # ==============================================================================================
 # CONFIGURATION
@@ -489,7 +486,7 @@ _dr_raw=$(get_strikes "daemon_restarted_flag" "$WATCHDOG_STATE_FILE")
 #   0 = normal — run all checks
 #   1 = RAM emergency active — defer container management this cycle
 
-check_system_watchdog_state() {
+check_resource_watchdog_state() {
     # Returns 0 = normal operation | 1 = defer, resource_watchdog RAM emergency active
     local state_file="$RW_STATE_FILE"
 
@@ -635,7 +632,7 @@ CYCLE_START=$(date +%s)
     # ── RAM emergency check — resource_watchdog.sh managing containers ────────────────────────
     # If resource_watchdog.sh has triggered a hard RAM shutdown, defer all container
     # management this run to prevent undoing the emergency stop and re-pressuring RAM.
-    if ! check_system_watchdog_state; then
+    if ! check_resource_watchdog_state; then
         MEM_KB=$(awk '/MemAvailable/ {print $2}' /proc/meminfo)
         MEM_GB=$(( MEM_KB / 1024 / 1024 ))
         warn "RAM emergency active (${MEM_GB}GB free) — resource_watchdog.sh managing containers"

Watchdogs/stability_watchdog.sh

@@ -134,7 +134,7 @@ SYS_WATCHDOG_REBOOT_WINDOW=$(( SYS_WATCHDOG_REBOOT_WINDOW_HRS * 3600 ))
 
 # Ensure state files exist
 for state_file in "$SYS_WATCHDOG_STATE_FILE" "$SYS_WATCHDOG_REBOOT_LOG" \
-                  "$SYS_WATCHDOG_FAILED_FILE" "$SYS_WATCHDOG_OOM_FILE"; do
+                  "$SYS_WATCHDOG_OOM_FILE"; do
     touch "$state_file" 2>/dev/null || {
         error "Cannot create state file: $state_file"
         exit 1