Add strike system to arr_corruption_scan.sh — require repeat corrupt detections before remediating

Arrs_Stack/arr_corruption_scan.sh

@@ -64,7 +64,13 @@
 #                             container almost certainly mounts shares differently)
 #
 # master.conf
-#   CORRUPTION_SCAN_STATE_FILE — path to the clean-file skip-cache (default in DATA_DIR)
+#   CORRUPTION_SCAN_STATE_FILE   — path to the clean-file skip-cache (default in DATA_DIR)
+#   CORRUPTION_SCAN_STRIKES_FILE — path to the consecutive-corrupt-detection counter (default
+#                                  in DATA_DIR), keyed by host path
+#   CORRUPTION_SCAN_STRIKE_LIMIT — consecutive corrupt detections required before --remediate
+#                                  acts on a file (default 2) — guards against a one-off
+#                                  ffprobe hiccup (mid-write file, NFS blip) triggering an
+#                                  unnecessary delete+re-search. Resets on a clean re-probe.
 #   SONARR_VERSION_MAJOR       — reused from sonarr_cleanup.sh for the API version check
 #
 # ==============================================================================================
@@ -165,6 +171,36 @@ CORRUPTION_SCAN_STATE_FILE="${CORRUPTION_SCAN_STATE_FILE:-$DATA_DIR/corruption_s
 mkdir -p "$(dirname "$CORRUPTION_SCAN_STATE_FILE")"
 touch "$CORRUPTION_SCAN_STATE_FILE"
 
+CORRUPTION_SCAN_STRIKES_FILE="${CORRUPTION_SCAN_STRIKES_FILE:-$DATA_DIR/corruption_scan_strikes.tsv}"
+CORRUPTION_SCAN_STRIKE_LIMIT="${CORRUPTION_SCAN_STRIKE_LIMIT:-2}"
+mkdir -p "$(dirname "$CORRUPTION_SCAN_STRIKES_FILE")"
+touch "$CORRUPTION_SCAN_STRIKES_FILE"
+
+# Thin wrappers around common.sh's wd_state_get/wd_state_set — same shape as
+# stability_watchdog.sh's get_strikes/set_strikes/increment_strikes/reset_strikes, keyed here
+# by host path instead of a watchdog check name. Requires repeat corrupt detections across
+# separate scan runs before --remediate acts, so a one-off ffprobe hiccup (mid-write file,
+# NFS blip) can't trigger an unnecessary delete+re-search on its own.
+get_scan_strikes() {
+    wd_state_get "$1" "$CORRUPTION_SCAN_STRIKES_FILE"
+}
+set_scan_strikes() {
+    wd_state_set "$1" "$2" "$CORRUPTION_SCAN_STRIKES_FILE"
+}
+increment_scan_strikes() {
+    local current
+    current=$(get_scan_strikes "$1")
+    [[ -z "$current" ]] && current=0
+    (( current++ ))
+    set_scan_strikes "$1" "$current"
+    echo "$current"
+}
+reset_scan_strikes() {
+    local current
+    current=$(get_scan_strikes "$1")
+    [[ -n "$current" && "$current" != "0" ]] && set_scan_strikes "$1" 0
+}
+
 if [[ "$SHOW_STATUS" == true ]]; then
     echo ""
     echo "━━━━━ $ICON_SUMMARY STATUS ━━━━━"
@@ -174,6 +210,7 @@ if [[ "$SHOW_STATUS" == true ]]; then
     echo "$ICON_GEAR    FFprobe binary:    $FFPROBE_BIN"
     echo "$ICON_GEAR    FFprobe path map:  ${#FFPROBE_PATH_MAP[@]} entries"
     echo "$ICON_GEAR    State file:        $CORRUPTION_SCAN_STATE_FILE"
+    echo "$ICON_GEAR    Strike limit:      $CORRUPTION_SCAN_STRIKE_LIMIT"
     echo "$ICON_GEAR    Remediate:         $REMEDIATE"
     echo "$ICON_GEAR    Scan limit:        ${SCAN_LIMIT:-unlimited}"
     echo "$ICON_GEAR    Path filter:       ${PATH_FILTER:-none}"
@@ -278,6 +315,7 @@ SCANNED=0
 SKIPPED_CACHED=0
 SKIPPED_UNMAPPED=0
 CORRUPT_COUNT=0
+STRIKE_HELD=0
 REMEDIATED=0
 REMEDIATE_FAILED=0
 
@@ -318,6 +356,7 @@ while IFS= read -r item; do
     fi
 
     if [[ "$result" == "clean" ]]; then
+        reset_scan_strikes "$host_path"
         echo -e "${host_path}\t${stamp}" >> "$FRESH_CLEAN_TMP"
         [[ "$ENABLE_LOGGING" == true ]] && echo "  $ICON_SUCCESS $host_path"
         continue
@@ -326,13 +365,21 @@ while IFS= read -r item; do
     # corrupt:<reason>
     reason="${result#corrupt:}"
     (( CORRUPT_COUNT++ ))
-    echo "  $ICON_ERROR CORRUPT: $host_path"
+    strikes=$(increment_scan_strikes "$host_path")
+    echo "  $ICON_ERROR CORRUPT: $host_path (strike $strikes/$CORRUPTION_SCAN_STRIKE_LIMIT)"
     [[ "$ENABLE_LOGGING" == true ]] && echo "      $reason"
 
     if [[ "$REMEDIATE" != true ]]; then
         continue
     fi
 
+    if (( strikes < CORRUPTION_SCAN_STRIKE_LIMIT )); then
+        warn "  $host_path — strike $strikes/$CORRUPTION_SCAN_STRIKE_LIMIT, not yet remediating (needs repeat confirmation)"
+        (( STRIKE_HELD++ ))
+        continue
+    fi
+    reset_scan_strikes "$host_path"
+
     episode_id=$(echo "$item" | jq -r '.episodeId // empty')
     title=$(echo "$item" | jq -r '.sceneName // .relativePath // .path')
 
@@ -389,6 +436,7 @@ echo "$ICON_SUCCESS Skipped (cached):    $SKIPPED_CACHED"
 echo "$ICON_WARN    Skipped (unmapped):  $SKIPPED_UNMAPPED"
 echo "$ICON_ERROR   Corrupt found:       $CORRUPT_COUNT"
 if [[ "$REMEDIATE" == true ]]; then
+    echo "$ICON_WARN    Held (strikes):      $STRIKE_HELD"
     echo "$ICON_SUCCESS Remediated:          $REMEDIATED"
     echo "$ICON_ERROR   Remediation failed:  $REMEDIATE_FAILED"
 fi

Deployment/master.conf.template

@@ -1185,6 +1185,12 @@
                                     # queued behind other moves already in progress, not just its
                                     # own copy time
     CORRUPTION_SCAN_STATE_FILE="${DATA_DIR}/corruption_scan_state.tsv"  # clean-file skip-cache
+    CORRUPTION_SCAN_STRIKES_FILE="${DATA_DIR}/corruption_scan_strikes.tsv"  # consecutive corrupt-detection counts, keyed by host path
+    CORRUPTION_SCAN_STRIKE_LIMIT=2  # consecutive corrupt detections (across separate scan runs)
+                                    # required before --remediate deletes+re-searches — guards
+                                    # against a one-off ffprobe hiccup (mid-write file, NFS blip)
+                                    # triggering an unnecessary delete. Resets to 0 the moment a
+                                    # file probes clean again.
     SONARR_EXTENSIONS=("mkv" "mp4" "avi" "m4v" "ts" "wmv" "mov")
     SONARR_PROTECTED_PATTERNS=(
         # Subtitles