rm old comments

Refactors a large set of CT update scripts to use the shared `create_backup`/`restore_backup` helpers instead of per-script manual copy/move logic. This removes duplicated backup code, temp-file cleanup paths, and inconsistent restore behavior while keeping data/config restoration in the correct order for build/deploy steps. Several update paths were also aligned to use `CLEAN_INSTALL=1` during release deploys, with minor message/comment tweaks where restore timing is important.

CHANGELOG.md

@@ -505,26 +505,14 @@ Exercise vigilance regarding copycat or coat-tailing sites that seek to exploit
 
 </details>
 
-## 2026-07-21
-
-### 🚀 Updated Scripts
-
-  - #### ✨ New Features
-
-    - Pangolin: Bump Version to 1.21.0 [@MickLesk](https://github.com/MickLesk) ([#15938](https://github.com/community-scripts/ProxmoxVE/pull/15938))
-
-  - #### 🔧 Refactor
-
-    - Standardize CT update backup handling [@MickLesk](https://github.com/MickLesk) ([#15937](https://github.com/community-scripts/ProxmoxVE/pull/15937))
-
 ## 2026-07-20
 
 ### 🚀 Updated Scripts
 
   - #### 🐞 Bug Fixes
 
-    - RomM: use backup helpers in update / clear folder [@MickLesk](https://github.com/MickLesk) ([#15915](https://github.com/community-scripts/ProxmoxVE/pull/15915))
     - fix: vikunja: asset selection [@CrazyWolf13](https://github.com/CrazyWolf13) ([#15929](https://github.com/community-scripts/ProxmoxVE/pull/15929))
+    - RomM: use backup helpers in update / clear folder [@MickLesk](https://github.com/MickLesk) ([#15915](https://github.com/community-scripts/ProxmoxVE/pull/15915))
     - Zammad : bind Elasticsearch to 127.0.0.1 [@MickLesk](https://github.com/MickLesk) ([#15909](https://github.com/community-scripts/ProxmoxVE/pull/15909))
     - Omada: fix package version extraction [@MickLesk](https://github.com/MickLesk) ([#15908](https://github.com/community-scripts/ProxmoxVE/pull/15908))
     - fix(wanderer): use PocketBase-relative plugin symlink in unprivileged LXC [@michelroegl-brunner](https://github.com/michelroegl-brunner) ([#15911](https://github.com/community-scripts/ProxmoxVE/pull/15911))
@@ -541,7 +529,6 @@ Exercise vigilance regarding copycat or coat-tailing sites that seek to exploit
 
   - #### ✨ New Features
 
-    - core: refactor to single-reporter telemetry and better error_handling [@MickLesk](https://github.com/MickLesk) ([#15933](https://github.com/community-scripts/ProxmoxVE/pull/15933))
     - tools.func: add support for extracting 7z archives [@MickLesk](https://github.com/MickLesk) ([#15919](https://github.com/community-scripts/ProxmoxVE/pull/15919))
     - Meilisearch : use dumpless Meilisearch upgrades [@MickLesk](https://github.com/MickLesk) ([#15921](https://github.com/community-scripts/ProxmoxVE/pull/15921))
 

ct/pangolin.sh

@@ -6,7 +6,7 @@ source <(curl -fsSL https://raw.githubusercontent.com/community-scripts/ProxmoxV
 # Source: https://pangolin.net/ | Github: https://github.com/fosrl/pangolin
 
 APP="Pangolin"
-PANGOLIN_VERSION="${PANGOLIN_VERSION:-1.21.0}"
+PANGOLIN_VERSION="${PANGOLIN_VERSION:-1.20.0}"
 var_tags="${var_tags:-proxy}"
 var_cpu="${var_cpu:-2}"
 var_ram="${var_ram:-4096}"

install/pangolin-install.sh

@@ -22,7 +22,7 @@ msg_ok "Installed Dependencies"
 NODE_VERSION="24" setup_nodejs
 PG_VERSION="17" setup_postgresql
 PG_DB_NAME="pangolin" PG_DB_USER="pangolin" setup_postgresql_db
-PANGOLIN_VERSION="${PANGOLIN_VERSION:-1.21.0}"
+PANGOLIN_VERSION="${PANGOLIN_VERSION:-1.20.0}"
 fetch_and_deploy_gh_release "pangolin" "fosrl/pangolin" "tarball" "$PANGOLIN_VERSION"
 fetch_and_deploy_gh_release "gerbil" "fosrl/gerbil" "singlefile" "latest" "/usr/bin" "gerbil_linux_$(arch_resolve)"
 fetch_and_deploy_gh_release "traefik" "traefik/traefik" "prebuild" "latest" "/usr/bin" "traefik_v*_linux_$(arch_resolve).tar.gz"

misc/alpine-install.func

@@ -6,10 +6,6 @@
 if ! command -v curl >/dev/null 2>&1; then
   apk update && apk add curl >/dev/null 2>&1
 fi
-# Mark container context BEFORE error handling starts: error_handler/on_exit
-# must write local failure artifacts instead of talking to the telemetry API
-# (the host is the single telemetry reporter).
-export TELEMETRY_CONTEXT="container"
 source <(curl -fsSL https://raw.githubusercontent.com/community-scripts/ProxmoxVE/main/misc/core.func)
 source <(curl -fsSL https://raw.githubusercontent.com/community-scripts/ProxmoxVE/main/misc/error_handler.func)
 load_functions
@@ -45,7 +41,7 @@ post_progress_to_api() {
 
   curl -fsS -m 5 -X POST "https://telemetry.community-scripts.org/telemetry" \
     -H "Content-Type: application/json" \
-    -d "{\"random_id\":\"${RANDOM_UUID}\",\"execution_id\":\"${EXECUTION_ID:-${RANDOM_UUID}}\",\"type\":\"lxc\",\"nsapp\":\"${app:-unknown}\",\"status\":\"${progress_status}\",\"platform\":\"${TELEMETRY_PLATFORM:-}\",\"repo_source\":\"${REPO_SOURCE:-}\",\"repo_slug\":\"${REPO_SLUG:-}\"}" &>/dev/null || true
+    -d "{\"random_id\":\"${RANDOM_UUID}\",\"execution_id\":\"${EXECUTION_ID:-${RANDOM_UUID}}\",\"type\":\"lxc\",\"nsapp\":\"${app:-unknown}\",\"status\":\"${progress_status}\"}" &>/dev/null || true
 }
 
 # This function enables IPv6 if it's not disabled and sets verbose mode

misc/build.func

@@ -4072,11 +4072,6 @@ build_container() {
   export RANDOM_UUID="$RANDOM_UUID"
   export EXECUTION_ID="$EXECUTION_ID"
   export SESSION_ID="$SESSION_ID"
-  # Repo attribution + platform for container-side progress pings (the
-  # container inherits the host's detection instead of re-detecting)
-  export REPO_SOURCE="${REPO_SOURCE:-}"
-  export REPO_SLUG="${REPO_SLUG:-}"
-  export TELEMETRY_PLATFORM="pve"
   export CACHER="$APT_CACHER"
   export CACHER_IP="$APT_CACHER_IP"
   if [[ -n "${HTTP_PROXY:-}" ]]; then
@@ -4900,16 +4895,6 @@ EOF
         # Point INSTALL_LOG to combined log so get_full_log() finds it
         INSTALL_LOG="$combined_log"
       fi
-
-      # Pull the structured error capture (.errinfo) from the container.
-      # It contains EXACTLY the output of the command that failed (written by
-      # silent()/error_handler inside the container) and is the primary source
-      # for the telemetry error trace - instead of a generic log tail.
-      local host_errinfo="/tmp/.errinfo-${SESSION_ID}"
-      if timeout 8 pct pull "$CTID" "/root/.install-${SESSION_ID}.log.errinfo" "$host_errinfo" 2>/dev/null && [[ -s "$host_errinfo" ]]; then
-        TELEMETRY_ERRINFO="$host_errinfo"
-        export TELEMETRY_ERRINFO
-      fi
     fi
 
     # Defense-in-depth: Ensure error handling stays disabled during recovery.
@@ -5185,8 +5170,6 @@ EOF
         echo -e "  Verbose: ${GN}enabled${CL}"
         echo ""
         msg_info "Restarting installation..."
-        # New telemetry execution for the retry (previous one keeps its "failed")
-        declare -f telemetry_new_attempt &>/dev/null && telemetry_new_attempt
         # Re-run build_container
         build_container
         return $?
@@ -5226,10 +5209,6 @@ EOF
           echo ""
           msg_info "Re-running installation script..."
 
-          # New telemetry execution for the in-place retry
-          declare -f telemetry_new_attempt &>/dev/null && telemetry_new_attempt
-          declare -f post_to_api &>/dev/null && post_to_api 2>/dev/null || true
-
           # Re-run install script in existing container (don't destroy/recreate)
           set +Eeuo pipefail
           trap - ERR
@@ -5293,7 +5272,6 @@ EOF
           echo -e "  Verbose: ${GN}enabled${CL}"
           echo ""
           msg_info "Restarting installation..."
-          declare -f telemetry_new_attempt &>/dev/null && telemetry_new_attempt
           build_container
           return $?
         fi
@@ -5323,7 +5301,6 @@ EOF
           echo -e "  Verbose: ${GN}enabled${CL}"
           echo ""
           msg_info "Restarting installation..."
-          declare -f telemetry_new_attempt &>/dev/null && telemetry_new_attempt
           build_container
           return $?
         fi
@@ -5348,7 +5325,6 @@ EOF
           echo -e "  Verbose: ${GN}enabled${CL}"
           echo ""
           msg_info "Restarting installation..."
-          declare -f telemetry_new_attempt &>/dev/null && telemetry_new_attempt
           build_container
           return $?
         fi
@@ -7023,16 +6999,6 @@ ensure_log_on_host() {
         rm -f "$temp_log"
       fi
     fi
-    # Also pull the structured error capture (.errinfo) so the telemetry error
-    # trace shows the failing command's exact output (signal-exit paths reach
-    # this via on_exit before/instead of the recovery flow)
-    if [[ -z "${TELEMETRY_ERRINFO:-}" || ! -s "${TELEMETRY_ERRINFO:-}" ]]; then
-      local host_errinfo="/tmp/.errinfo-${SESSION_ID}"
-      if timeout 8 pct pull "$CTID" "/root/.install-${SESSION_ID}.log.errinfo" "$host_errinfo" 2>/dev/null && [[ -s "$host_errinfo" ]]; then
-        TELEMETRY_ERRINFO="$host_errinfo"
-        export TELEMETRY_ERRINFO
-      fi
-    fi
     if [[ -s "$combined_log" ]]; then
       INSTALL_LOG="$combined_log"
     fi

misc/core.func

@@ -546,12 +546,6 @@ silent() {
   set +Eeuo pipefail
   trap - ERR
 
-  # Byte offset BEFORE the command runs - everything the log grows by is
-  # exactly this command's output (used for the .errinfo telemetry capture)
-  local start_bytes=0
-  [[ -f "$logfile" ]] && start_bytes=$(stat -c%s "$logfile" 2>/dev/null || echo 0)
-  [[ ! "$start_bytes" =~ ^[0-9]+$ ]] && start_bytes=0
-
   "$@" >>"$logfile" 2>&1
   local rc=$?
 
@@ -573,43 +567,12 @@ silent() {
     export _SILENT_FAILED_LINE="$caller_line"
     export _SILENT_FAILED_LOG="$logfile"
 
-    # ── Structured error capture (.errinfo) for telemetry ──
-    # Extract exactly THIS command's output (from the recorded byte offset),
-    # strip ANSI/progress noise, keep the last 60 lines. The host builds the
-    # telemetry error trace from this file (pulled from the container on
-    # failure). Self-contained - containers don't source api.func.
-    {
-      local flat_cmd
-      flat_cmd=$(printf '%s' "$cmd" | tr '\n' ' ' | head -c 300)
-      echo "EXIT_CODE=${rc}"
-      echo "LINE=${caller_line}"
-      echo "COMMAND=${flat_cmd}"
-      echo "--- OUTPUT ---"
-      if [[ -s "$logfile" ]]; then
-        local segment
-        segment=$(tail -c +"$((start_bytes + 1))" "$logfile" 2>/dev/null |
-          sed 's/\r$//' |
-          sed 's/\x1b\[[0-9;]*[a-zA-Z]//g' |
-          grep -avE '^(Get:|Hit:|Ign:|Fetched |Reading package lists|Reading state information|Building dependency tree|Selecting previously|Preparing to unpack|Unpacking |Processing triggers for|\(Reading database|[0-9]+%[[:space:]]*\[)' |
-          grep -avE '^[[:space:]]*$' |
-          tail -n 60)
-        # If the noise filter swallowed everything, fall back to the raw tail
-        if [[ -z "$segment" ]]; then
-          segment=$(tail -c +"$((start_bytes + 1))" "$logfile" 2>/dev/null |
-            sed 's/\r$//' | sed 's/\x1b\[[0-9;]*[a-zA-Z]//g' | tail -n 60)
-        fi
-        printf '%s' "$segment" | head -c 10240
-      fi
-    } >"${logfile}.errinfo" 2>/dev/null || true
-
     return "$rc"
   fi
 
   # Clear stale flags on success (prevents false positives if a previous
   # $STD cmd || true failed and a later non-silent command triggers error_handler)
   unset _SILENT_FAILED_RC _SILENT_FAILED_CMD _SILENT_FAILED_LINE _SILENT_FAILED_LOG 2>/dev/null || true
-  # Also drop a stale .errinfo from a previously tolerated failure ($STD cmd || true)
-  rm -f "${logfile}.errinfo" 2>/dev/null || true
 }
 
 # ------------------------------------------------------------------------------

misc/error_handler.func

@@ -7,17 +7,12 @@
 # License: MIT | https://github.com/community-scripts/ProxmoxVE/raw/main/LICENSE
 # ------------------------------------------------------------------------------
 #
-# Provides error handling and signal management for all scripts.
+# Provides comprehensive error handling and signal management for all scripts.
-#
+# Includes:
-# TELEMETRY CONTRACT:
+#   - Exit code explanations (shell, package managers, databases, custom codes)
-#   - HOST context: this file reports terminal statuses via post_update_to_api
+#   - Error handler with detailed logging
-#     (full metadata + focused error trace).
+#   - Signal handlers (EXIT, INT, TERM)
-#   - CONTAINER context: this file NEVER talks to the telemetry API. It writes
+#   - Initialization function for trap setup
-#     two local artifacts that the host picks up after lxc-attach returns:
-#       /root/.install-<SESSION_ID>.failed        → exit code (flag file)
-#       /root/.install-<SESSION_ID>.log.errinfo   → structured error capture
-#     This guarantees the server only ever sees ONE terminal event per
-#     execution - the host's complete one.
 #
 # Usage:
 #   source <(curl -fsSL .../error_handler.func)
@@ -26,14 +21,15 @@
 # ------------------------------------------------------------------------------
 
 # ==============================================================================
-# SECTION 1: EXIT CODE EXPLANATIONS (fallback)
+# SECTION 1: EXIT CODE EXPLANATIONS
 # ==============================================================================
 
 # ------------------------------------------------------------------------------
 # explain_exit_code()
 #
-# - Canonical version lives in api.func (sourced before this file on the host)
+# - Canonical version is defined in api.func (sourced before this file)
-# - This fallback covers the container context where api.func is not sourced
+# - This section only provides a fallback if api.func was not loaded
+# - See api.func SECTION 1 for the authoritative exit code mappings
 # ------------------------------------------------------------------------------
 if ! declare -f explain_exit_code &>/dev/null; then
   explain_exit_code() {
@@ -98,6 +94,8 @@ if ! declare -f explain_exit_code &>/dev/null; then
     100) echo "APT: Package manager error (broken packages / dependency problems)" ;;
     101) echo "APT: Configuration error (bad sources.list, malformed config)" ;;
     102) echo "APT: Lock held by another process (dpkg/apt still running)" ;;
+
+    # --- Script Validation & Setup (103-123) ---
     103) echo "Validation: Shell is not Bash" ;;
     104) echo "Validation: Not running as root (or invoked via sudo)" ;;
     105) echo "Validation: Proxmox VE version not supported" ;;
@@ -179,8 +177,9 @@ if ! declare -f explain_exit_code &>/dev/null; then
     223) echo "Proxmox: Template not available after download" ;;
     224) echo "Proxmox: PBS storage is for backups only" ;;
     225) echo "Proxmox: No template available for OS/Version" ;;
-    226) echo "Proxmox: VM disk import or post-creation setup failed" ;;
     231) echo "Proxmox: LXC stack upgrade failed" ;;
+
+    # --- Tools & Addon Scripts (232-238) ---
     232) echo "Tools: Wrong execution environment (run on PVE host, not inside LXC)" ;;
     233) echo "Tools: Application not installed (update prerequisite missing)" ;;
     234) echo "Tools: No LXC containers found or available" ;;
@@ -188,6 +187,7 @@ if ! declare -f explain_exit_code &>/dev/null; then
     236) echo "Tools: Required hardware not detected" ;;
     237) echo "Tools: Dependency package installation failed" ;;
     238) echo "Tools: OS or distribution not supported for this addon" ;;
+
     239) echo "npm/Node.js: Unexpected runtime error or dependency failure" ;;
     243) echo "Node.js: Out of memory (JavaScript heap out of memory)" ;;
     245) echo "Node.js: Invalid command-line option" ;;
@@ -195,11 +195,14 @@ if ! declare -f explain_exit_code &>/dev/null; then
     247) echo "Node.js: Fatal internal error" ;;
     248) echo "Node.js: Invalid C++ addon / N-API failure" ;;
     249) echo "npm/pnpm/yarn: Unknown fatal error" ;;
+
+    # --- Application Install/Update Errors (250-254) ---
     250) echo "App: Download failed or version not determined" ;;
     251) echo "App: File extraction failed (corrupt or incomplete archive)" ;;
     252) echo "App: Required file or resource not found" ;;
     253) echo "App: Data migration required — update aborted" ;;
     254) echo "App: User declined prompt or input timed out" ;;
+
     255) echo "DPKG: Fatal internal error" ;;
     *) echo "Unknown error" ;;
     esac
@@ -207,98 +210,24 @@ if ! declare -f explain_exit_code &>/dev/null; then
 fi
 
 # ==============================================================================
-# SECTION 2: CONTEXT DETECTION & CONTAINER ARTIFACTS
+# SECTION 2: ERROR HANDLERS
-# ==============================================================================
-
-# ------------------------------------------------------------------------------
-# _is_container_context()
-#
-# - Returns 0 (true) when running INSIDE the LXC container being installed
-# - TELEMETRY_CONTEXT can override the heuristic ("host" / "container");
-#   install.func sets TELEMETRY_CONTEXT=container during bootstrap
-# ------------------------------------------------------------------------------
-_is_container_context() {
-  case "${TELEMETRY_CONTEXT:-}" in
-  container) return 0 ;;
-  host) return 1 ;;
-  esac
-  # Proxmox/Incus tooling exists only on the host
-  command -v pveversion &>/dev/null && return 1
-  command -v pct &>/dev/null && return 1
-  command -v incus &>/dev/null && return 1
-  # systemd-detect-virt reports lxc inside containers
-  if command -v systemd-detect-virt &>/dev/null; then
-    case "$(systemd-detect-virt -c 2>/dev/null)" in
-    lxc | lxc-libvirt | openvz) return 0 ;;
-    esac
-  fi
-  # PCT_OSTYPE is exported into the install environment by the host
-  [[ -n "${PCT_OSTYPE:-}" ]] && return 0
-  return 1
-}
-
-# ------------------------------------------------------------------------------
-# _container_write_failure()
-#
-# - Writes the failure artifacts inside the container for the host to pick up:
-#   * flag file with the exit code
-#   * .errinfo capture (if silent() has not already written a better one)
-#   * copy of the install log
-# - This REPLACES any direct telemetry send from the container
-# - Arguments: $1 = exit_code, $2 = command (optional), $3 = line (optional)
-# ------------------------------------------------------------------------------
-_container_write_failure() {
-  local exit_code="${1:-1}"
-  local command="${2:-}"
-  local line="${3:-}"
-  local sid="${SESSION_ID:-error}"
-
-  # Flag file with exit code (host reads this after lxc-attach returns)
-  echo "$exit_code" >"/root/.install-${sid}.failed" 2>/dev/null || true
-
-  # Keep the install log where the host expects it
-  if [[ -n "${INSTALL_LOG:-}" && -f "${INSTALL_LOG}" && "${INSTALL_LOG}" != "/root/.install-${sid}.log" ]]; then
-    cp "${INSTALL_LOG}" "/root/.install-${sid}.log" 2>/dev/null || true
-  fi
-
-  # Structured error capture (skip if silent() already wrote the exact
-  # output segment of the failing command - that one is always better).
-  # Self-contained: api.func is NOT sourced inside containers.
-  local errinfo="${INSTALL_LOG:-/root/.install-${sid}.log}.errinfo"
-  if [[ ! -s "$errinfo" ]]; then
-    local flat_cmd
-    flat_cmd=$(printf '%s' "${command:-unknown}" | tr '\n' ' ' | head -c 300)
-    {
-      echo "EXIT_CODE=${exit_code}"
-      echo "LINE=${line:-0}"
-      echo "COMMAND=${flat_cmd}"
-      echo "--- OUTPUT ---"
-      if [[ -n "${INSTALL_LOG:-}" && -s "${INSTALL_LOG}" ]]; then
-        tail -n 80 "${INSTALL_LOG}" 2>/dev/null |
-          sed 's/\r$//' |
-          sed 's/\x1b\[[0-9;]*[a-zA-Z]//g' |
-          grep -avE '^(Get:|Hit:|Ign:|Fetched |Reading package lists|Reading state information|Building dependency tree|Selecting previously|Preparing to unpack|Unpacking |Processing triggers for|\(Reading database|[0-9]+%[[:space:]]*\[)' |
-          grep -avE '^[[:space:]]*$' |
-          tail -n 60 | head -c 10240
-      fi
-    } >"$errinfo" 2>/dev/null || true
-  fi
-}
-
-# ==============================================================================
-# SECTION 3: ERROR HANDLER
 # ==============================================================================
 
 # ------------------------------------------------------------------------------
 # error_handler()
 #
 # - Main error handler triggered by ERR trap
-# - Displays error message with line number, exit code, explanation, command
+# - Arguments: exit_code, command, line_number
-# - Shows last 20 lines of the active log
+# - Behavior:
-# - Emits actionable hints for common failure patterns (OOM, APT, network...)
+#   * Returns silently if exit_code is 0 (success)
-# - HOST: reports "failed" to telemetry (full payload via api.func)
+#   * Sources explain_exit_code() for detailed error description
-# - CONTAINER: writes failure artifacts, sends nothing
+#   * Displays error message with:
-# - Exits with original exit code
+#     - Line number where error occurred
+#     - Exit code with explanation
+#     - Command that failed
+#   * Shows last 20 lines of SILENT_LOGFILE if available
+#   * Copies log to container /root for later inspection
+#   * Exits with original exit code
 # ------------------------------------------------------------------------------
 error_handler() {
   local exit_code=${1:-$?}
@@ -308,10 +237,12 @@ error_handler() {
   command="${command//\$STD/}"
 
   # If error originated from silent(), use its captured metadata
+  # This provides the actual command and line number instead of "silent ..."
   if [[ -n "${_SILENT_FAILED_RC:-}" ]]; then
     exit_code="$_SILENT_FAILED_RC"
     command="$_SILENT_FAILED_CMD"
     line_number="$_SILENT_FAILED_LINE"
+    # Clear flags to prevent stale data on subsequent errors
     unset _SILENT_FAILED_RC _SILENT_FAILED_CMD _SILENT_FAILED_LINE
   fi
 
@@ -319,12 +250,8 @@ error_handler() {
     return 0
   fi
 
-  # Export the failure location so telemetry can include the "where"
+  # Stop spinner and restore cursor FIRST — before any output
-  FAILED_COMMAND="$command"
+  # This prevents spinner text overlapping with error messages
-  FAILED_LINE="$line_number"
-  export FAILED_COMMAND FAILED_LINE
-
-  # Stop spinner and restore cursor FIRST - before any output
   if declare -f stop_spinner >/dev/null 2>&1; then
     stop_spinner 2>/dev/null || true
   fi
@@ -332,18 +259,18 @@ error_handler() {
 
   local explanation
   explanation="$(explain_exit_code "$exit_code")"
-  if [[ "$explanation" == curl:* && ! "$command" =~ (^|[[:space:]])([^[:space:]]*/)?curl([[:space:]]|$) ]]; then
-    explanation="Command failed with exit status ${exit_code}"
-  fi
 
-  # ── Telemetry / failure artifacts ──
+  # ALWAYS report failure to API immediately - don't wait for container checks
-  if _is_container_context; then
+  # This ensures we capture failures that occur before/after container exists
-    _container_write_failure "$exit_code" "$command" "$line_number"
+  if declare -f post_update_to_api &>/dev/null; then
-  elif declare -f post_update_to_api &>/dev/null; then
     post_update_to_api "failed" "$exit_code" 2>/dev/null || true
+  else
+    # Container context: post_update_to_api not available (api.func not sourced)
+    # Send status directly via curl so container failures are never lost
+    _send_abort_telemetry "$exit_code" 2>/dev/null || true
   fi
 
-  # ── Display ──
+  # Use msg_error if available, fallback to echo
   if declare -f msg_error >/dev/null 2>&1; then
     msg_error "in line ${line_number}: exit code ${exit_code} (${explanation}): while executing command ${command}"
   else
@@ -361,7 +288,8 @@ error_handler() {
     } >>"$DEBUG_LOGFILE"
   fi
 
-  # Get active log file (prefer silent()'s logfile when available)
+  # Get active log file (BUILD_LOG or INSTALL_LOG)
+  # Prefer silent()'s logfile when available (contains the actual command output)
   local active_log=""
   if [[ -n "${_SILENT_FAILED_LOG:-}" && -s "${_SILENT_FAILED_LOG}" ]]; then
     active_log="$_SILENT_FAILED_LOG"
@@ -372,17 +300,21 @@ error_handler() {
     active_log="$SILENT_LOGFILE"
   fi
 
+  # If active_log points to a container-internal path that doesn't exist on host,
+  # fall back to BUILD_LOG (host-side log)
   if [[ -n "$active_log" && ! -s "$active_log" && -n "${BUILD_LOG:-}" && -s "${BUILD_LOG}" ]]; then
     active_log="$BUILD_LOG"
   fi
 
+  # Show last log lines if available
   if [[ -n "$active_log" && -s "$active_log" ]]; then
     echo -e "\n${TAB}--- Last 20 lines of log ---"
     tail -n 20 "$active_log"
     echo -e "${TAB}-----------------------------------\n"
   fi
 
-  # ── Node.js heap OOM detection with actionable guidance ──
+  # Detect probable Node.js heap OOM and print actionable guidance.
+  # This avoids generic SIGABRT/SIGKILL confusion for frontend build failures.
   local node_oom_detected="false"
   local node_build_context="false"
   if [[ "$command" =~ (npm|pnpm|yarn|node|vite|turbo) ]]; then
@@ -399,6 +331,7 @@ error_handler() {
   if [[ "$node_oom_detected" == "true" ]] || { [[ "$node_build_context" == "true" ]] && [[ "$exit_code" =~ ^(134|137)$ ]]; }; then
     local heap_hint_mb=""
 
+    # If explicitly configured, prefer the current value for troubleshooting output.
     if [[ -n "${NODE_OPTIONS:-}" ]] && [[ "${NODE_OPTIONS}" =~ max-old-space-size=([0-9]+) ]]; then
       heap_hint_mb="${BASH_REMATCH[1]}"
     elif [[ -n "${var_ram:-}" ]] && [[ "${var_ram}" =~ ^[0-9]+$ ]]; then
@@ -425,13 +358,14 @@ error_handler() {
     fi
   fi
 
-  # ── Log-pattern analysis: actionable hints for common failure causes ──
+  # ── Log-pattern analysis: detect common failure causes and emit actionable hints ──
   if [[ -n "$active_log" && -s "$active_log" ]]; then
     local _log_tail
     _log_tail=$(tail -n 60 "$active_log" 2>/dev/null || true)
 
     # 1. APT/dpkg dependency conflict
     if echo "$_log_tail" | grep -qE "Depends:|depends on.*but.*not installed|broken packages|unmet dep|dependency problems"; then
+      # Check for PostgreSQL-specific version mismatch (most actionable)
       local _pg_conflict
       _pg_conflict=$(echo "$_log_tail" | grep -oE 'postgresql-[0-9]+ but.*installed' | head -1 || true)
       if [[ -n "$_pg_conflict" ]]; then
@@ -452,7 +386,7 @@ error_handler() {
         msg_warn "Hint: A repository GPG key may be missing, expired, or the keyring file is not yet present (/usr/share/postgresql-common/pgdg/apt.postgresql.org.asc etc.)."
         msg_warn "Hint: Install the 'postgresql-common' package first, or re-add the repository with its correct signing key."
       fi
-    # 3. Network / DNS failure
+    # 3. Network / DNS failure during apt-get or curl
     elif echo "$_log_tail" | grep -qE "Could not resolve|Failed to fetch|Unable to connect|Name or service not known|Network is unreachable|curl.*resolve"; then
       if declare -f msg_warn >/dev/null 2>&1; then
         msg_warn "Network or DNS failure detected."
@@ -473,12 +407,17 @@ error_handler() {
     fi
   fi
 
-  # ── Context-specific cleanup ──
+  # Detect context: Container (INSTALL_LOG set + inside container /root) vs Host
-  if _is_container_context; then
+  if [[ -n "${INSTALL_LOG:-}" && -f "${INSTALL_LOG:-}" && -d /root ]]; then
-    # Container: artifacts already written above; nothing more to do
+    # CONTAINER CONTEXT: Copy log and create flag file for host
-    :
+    local container_log="/root/.install-${SESSION_ID:-error}.log"
+    cp "${INSTALL_LOG}" "$container_log" 2>/dev/null || true
+
+    # Create error flag file with exit code for host detection
+    echo "$exit_code" >"/root/.install-${SESSION_ID:-error}.failed" 2>/dev/null || true
+    # Log path is shown by host as combined log - no need to show container path
   else
-    # HOST: show log path and offer container cleanup
+    # HOST CONTEXT: Show local log path and offer container cleanup
     if [[ -n "$active_log" && -s "$active_log" ]]; then
       if declare -f msg_custom >/dev/null 2>&1; then
         msg_custom "📋" "${YW}" "Full log: ${active_log}"
@@ -496,6 +435,7 @@ error_handler() {
         echo -en "${YW}Remove broken container ${CTID}? (Y/n) [auto-remove in 60s]: ${CL}"
       fi
 
+      # Read user response
       local response=""
       if read -t 60 -r response; then
         if [[ -z "$response" || "$response" =~ ^[Yy]$ ]]; then
@@ -536,6 +476,12 @@ error_handler() {
           echo -e "${GN}✔${CL} Container ${CTID} removed"
         fi
       fi
+
+      # Force one final status update attempt after cleanup
+      # This ensures status is updated even if the first attempt failed (e.g., HTTP 400)
+      if declare -f post_update_to_api &>/dev/null; then
+        post_update_to_api "failed" "$exit_code" "force"
+      fi
     fi
   fi
 
@@ -543,33 +489,106 @@ error_handler() {
 }
 
 # ==============================================================================
-# SECTION 4: TELEMETRY & CLEANUP HELPERS FOR SIGNAL HANDLERS
+# SECTION 3: TELEMETRY & CLEANUP HELPERS FOR SIGNAL HANDLERS
 # ==============================================================================
 
 # ------------------------------------------------------------------------------
-# _send_abort_telemetry()  (compatibility name)
+# _send_abort_telemetry()
 #
-# - HOST: reports via post_update_to_api (signals map to "aborted" there)
+# - Sends failure/abort status to telemetry API
-# - CONTAINER: writes failure artifacts instead of sending anything
+# - Works in BOTH host context (post_update_to_api available) and
+#   container context (only curl available, api.func not sourced)
+# - Container context is critical: without this, container-side failures
+#   and signal exits are never reported, leaving records stuck in
+#   "installing" or "configuring" forever
 # - Arguments: $1 = exit_code
 # ------------------------------------------------------------------------------
 _send_abort_telemetry() {
   local exit_code="${1:-1}"
-  if _is_container_context; then
+  # Try full API function first (host context - api.func sourced)
-    _container_write_failure "$exit_code"
-    return 0
-  fi
   if declare -f post_update_to_api &>/dev/null; then
     post_update_to_api "failed" "$exit_code" 2>/dev/null || true
+    return
   fi
+  # Fallback: direct curl (container context - api.func NOT sourced)
+  # This is the ONLY way containers can report failures to telemetry
+  command -v curl &>/dev/null || return 0
+  [[ "${DIAGNOSTICS:-no}" == "no" ]] && return 0
+  [[ -z "${RANDOM_UUID:-}" ]] && return 0
+
+  # Collect last 200 log lines for error diagnosis (best-effort)
+  # Container context has no get_full_log(), so we gather as much as possible
+  local error_text=""
+  local logfile=""
+  if [[ -n "${INSTALL_LOG:-}" && -s "${INSTALL_LOG}" ]]; then
+    logfile="${INSTALL_LOG}"
+  elif [[ -n "${SILENT_LOGFILE:-}" && -s "${SILENT_LOGFILE}" ]]; then
+    logfile="${SILENT_LOGFILE}"
+  fi
+
+  if [[ -n "$logfile" ]]; then
+    error_text=$(tail -n 200 "$logfile" 2>/dev/null | sed 's/\x1b\[[0-9;]*[a-zA-Z]//g; s/\\/\\\\/g; s/"/\\"/g; s/\r//g' | tr '\n' '|' | sed 's/|$//' | head -c 16384 | tr -d '\000-\010\013\014\016-\037\177') || true
+  fi
+
+  # Prepend exit code explanation header (like build_error_string does on host)
+  local explanation=""
+  if declare -f explain_exit_code &>/dev/null; then
+    explanation=$(explain_exit_code "$exit_code" 2>/dev/null) || true
+  fi
+  if [[ -n "$explanation" && -n "$error_text" ]]; then
+    error_text="exit_code=${exit_code} | ${explanation}|---|${error_text}"
+  elif [[ -n "$explanation" && -z "$error_text" ]]; then
+    error_text="exit_code=${exit_code} | ${explanation}"
+  fi
+
+  # Calculate duration if start time is available
+  local duration=""
+  if [[ -n "${DIAGNOSTICS_START_TIME:-}" ]]; then
+    duration=$(($(date +%s) - DIAGNOSTICS_START_TIME))
+  fi
+
+  # Categorize error if function is available (may not be in minimal container context)
+  local error_category=""
+  if declare -f categorize_error &>/dev/null; then
+    error_category=$(categorize_error "$exit_code" 2>/dev/null) || true
+  fi
+
+  # Build JSON payload with error context
+  local payload
+  payload="{\"random_id\":\"${RANDOM_UUID}\",\"execution_id\":\"${EXECUTION_ID:-${RANDOM_UUID}}\",\"type\":\"${TELEMETRY_TYPE:-lxc}\",\"nsapp\":\"${NSAPP:-${app:-unknown}}\",\"status\":\"failed\",\"exit_code\":${exit_code}"
+  [[ -n "$error_text" ]] && payload="${payload},\"error\":\"${error_text}\""
+  [[ -n "$error_category" ]] && payload="${payload},\"error_category\":\"${error_category}\""
+  [[ -n "$duration" ]] && payload="${payload},\"duration\":${duration}"
+  payload="${payload}}"
+
+  local api_url="${TELEMETRY_URL:-https://telemetry.community-scripts.org/telemetry}"
+
+  # 2 attempts (retry once on failure) — original had no retry
+  local attempt
+  for attempt in 1 2; do
+    if curl -fsS -m 5 -X POST "$api_url" \
+      -H "Content-Type: application/json" \
+      -d "$payload" &>/dev/null; then
+      return 0
+    fi
+    [[ $attempt -eq 1 ]] && sleep 1
+  done
   return 0
 }
 
 # ------------------------------------------------------------------------------
 # _stop_container_if_installing()
 #
-# - Stops the LXC container if we're in the install phase (host only)
+# - Stops the LXC container if we're in the install phase
 # - Prevents orphaned container processes when the host exits due to a signal
+#   (SSH disconnect, Ctrl+C, SIGTERM) — without this, the container keeps
+#   running and may send "configuring" status AFTER the host already sent
+#   "failed", leaving records permanently stuck in "configuring"
+# - Only acts when:
+#   * CONTAINER_INSTALLING flag is set (during lxc-attach in build_container)
+#   * CTID is set (container was created)
+#   * pct command is available (we're on the Proxmox host, not inside a container)
+# - Does NOT destroy the container — just stops it for potential debugging
 # ------------------------------------------------------------------------------
 _stop_container_if_installing() {
   [[ "${CONTAINER_INSTALLING:-}" == "true" ]] || return 0
@@ -579,47 +598,51 @@ _stop_container_if_installing() {
 }
 
 # ==============================================================================
-# SECTION 5: SIGNAL HANDLERS
+# SECTION 4: SIGNAL HANDLERS
 # ==============================================================================
 
 # ------------------------------------------------------------------------------
 # on_exit()
 #
 # - EXIT trap handler — runs on EVERY script termination
-# - CONTAINER: ensures failure artifacts exist on non-zero exit (this also
+# - Catches orphaned "installing"/"configuring" records:
-#   covers silent()'s direct `exit $rc`, which bypasses the ERR trap)
+#   * If post_to_api sent "installing" but post_update_to_api never ran
-# - HOST: catches executions that never sent a final status:
+#   * Reports final status to prevent records stuck forever
-#   * non-zero exit → "failed" (signal codes map to "aborted")
+# - Best-effort log collection for failed installs
-#   * zero exit with an "installing" record but no final → "aborted"
+# - Stops orphaned container processes on failure
-#     (e.g. user cancelled a whiptail dialog, script exited cleanly)
+# - Cleans up lock files
 # ------------------------------------------------------------------------------
 on_exit() {
   local exit_code=$?
 
-  if _is_container_context; then
+  # Report orphaned telemetry records
-    if [[ $exit_code -ne 0 ]]; then
+  # Two scenarios handled:
-      _container_write_failure "$exit_code" "${FAILED_COMMAND:-}" "${FAILED_LINE:-}"
+  # 1. POST_TO_API_DONE=true but POST_UPDATE_DONE=false: Record was created but
-    fi
+  #    never got a final status update → send abort/done now.
-  else
+  # 2. POST_TO_API_DONE=false but DIAGNOSTICS=yes: Initial post failed (server
-    if [[ "${POST_UPDATE_DONE:-}" != "true" ]] && declare -f post_update_to_api >/dev/null 2>&1; then
+  #    unreachable/timeout), but the server has fallback create-on-update logic,
+  #    so a status update can still create the record. Worth one last try.
+  if [[ "${POST_UPDATE_DONE:-}" != "true" ]]; then
+    if [[ "${POST_TO_API_DONE:-}" == "true" || "${DIAGNOSTICS:-no}" == "yes" ]]; then
       if [[ $exit_code -ne 0 ]]; then
-        post_update_to_api "failed" "$exit_code" 2>/dev/null || true
+        _send_abort_telemetry "$exit_code"
-      elif [[ "${POST_TO_API_DONE:-}" == "true" ]]; then
+      elif [[ "${INSTALL_COMPLETE:-}" == "true" ]] && declare -f post_update_to_api >/dev/null 2>&1; then
-        # Clean exit but no success was ever reported: the user backed out
+        # Only report success if the install was explicitly marked complete.
-        # somewhere. Report as aborted so the record doesn't stay "installing".
+        # Without this guard, early bailouts (e.g. user cancelled) with exit 0
-        post_update_to_api "aborted" "0" 2>/dev/null || true
+        # would be falsely reported as successful installations.
+        post_update_to_api "done" "0" 2>/dev/null || true
       fi
     fi
+  fi
 
-    # Best-effort log collection on failure
+  # Best-effort log collection on failure (non-critical, telemetry already sent)
-    if [[ $exit_code -ne 0 ]] && declare -f ensure_log_on_host >/dev/null 2>&1; then
+  if [[ $exit_code -ne 0 ]] && declare -f ensure_log_on_host >/dev/null 2>&1; then
-      ensure_log_on_host 2>/dev/null || true
+    ensure_log_on_host 2>/dev/null || true
-    fi
+  fi
 
-    # Stop orphaned container if we're in the install phase
+  # Stop orphaned container if we're in the install phase and exiting with error
-    if [[ $exit_code -ne 0 ]]; then
+  if [[ $exit_code -ne 0 ]]; then
-      _stop_container_if_installing
+    _stop_container_if_installing
-    fi
   fi
 
   [[ -n "${lockfile:-}" && -e "$lockfile" ]] && rm -f "$lockfile"
@@ -627,19 +650,21 @@ on_exit() {
 }
 
 # ------------------------------------------------------------------------------
-# on_interrupt() - SIGINT (Ctrl+C)
+# on_interrupt()
+#
+# - SIGINT (Ctrl+C) trap handler
+# - Reports status FIRST (time-critical: container may be dying)
+# - Stops orphaned container to prevent "configuring" ghost records
+# - Exits with code 130 (128 + SIGINT=2)
 # ------------------------------------------------------------------------------
 on_interrupt() {
+  # Stop spinner and restore cursor before any output
   if declare -f stop_spinner >/dev/null 2>&1; then
     stop_spinner 2>/dev/null || true
   fi
   printf "\e[?25h" 2>/dev/null || true
 
-  if _is_container_context; then
+  _send_abort_telemetry "130"
-    _container_write_failure "130"
-  elif declare -f post_update_to_api &>/dev/null; then
-    post_update_to_api "aborted" "130" 2>/dev/null || true
-  fi
   _stop_container_if_installing
   if declare -f msg_error >/dev/null 2>&1; then
     msg_error "Interrupted by user (SIGINT)" 2>/dev/null || true
@@ -650,19 +675,21 @@ on_interrupt() {
 }
 
 # ------------------------------------------------------------------------------
-# on_terminate() - SIGTERM
+# on_terminate()
+#
+# - SIGTERM trap handler
+# - Reports status FIRST (time-critical: process being killed)
+# - Stops orphaned container to prevent "configuring" ghost records
+# - Exits with code 143 (128 + SIGTERM=15)
 # ------------------------------------------------------------------------------
 on_terminate() {
+  # Stop spinner and restore cursor before any output
   if declare -f stop_spinner >/dev/null 2>&1; then
     stop_spinner 2>/dev/null || true
   fi
   printf "\e[?25h" 2>/dev/null || true
 
-  if _is_container_context; then
+  _send_abort_telemetry "143"
-    _container_write_failure "143"
-  elif declare -f post_update_to_api &>/dev/null; then
-    post_update_to_api "aborted" "143" 2>/dev/null || true
-  fi
   _stop_container_if_installing
   if declare -f msg_error >/dev/null 2>&1; then
     msg_error "Terminated by signal (SIGTERM)" 2>/dev/null || true
@@ -673,32 +700,45 @@ on_terminate() {
 }
 
 # ------------------------------------------------------------------------------
-# on_hangup() - SIGHUP (SSH disconnect, terminal closed)
+# on_hangup()
+#
+# - SIGHUP trap handler (SSH disconnect, terminal closed)
+# - CRITICAL: This was previously MISSING from catch_errors(), causing
+#   container processes to become orphans on SSH disconnect — the #1 cause
+#   of records stuck in "installing" and "configuring" states
+# - Reports status via direct curl (terminal is already closed, no output)
+# - Stops orphaned container to prevent ghost records
+# - Exits with code 129 (128 + SIGHUP=1)
 # ------------------------------------------------------------------------------
 on_hangup() {
+  # Stop spinner (no cursor restore needed — terminal is already gone)
   if declare -f stop_spinner >/dev/null 2>&1; then
     stop_spinner 2>/dev/null || true
   fi
 
-  if _is_container_context; then
+  _send_abort_telemetry "129"
-    _container_write_failure "129"
-  elif declare -f post_update_to_api &>/dev/null; then
-    post_update_to_api "aborted" "129" 2>/dev/null || true
-  fi
   _stop_container_if_installing
   exit 129
 }
 
 # ==============================================================================
-# SECTION 6: INITIALIZATION
+# SECTION 5: INITIALIZATION
 # ==============================================================================
 
 # ------------------------------------------------------------------------------
 # catch_errors()
 #
 # - Initializes error handling and signal traps
-# - set -Ee -o pipefail (+ set -u when STRICT_UNSET=1)
+# - Enables strict error handling:
-# - Traps: ERR → error_handler, EXIT → on_exit, INT/TERM/HUP → signal handlers
+#   * set -Ee: Exit on error, inherit ERR trap in functions
+#   * set -o pipefail: Pipeline fails if any command fails
+#   * set -u: (optional) Exit on undefined variable (if STRICT_UNSET=1)
+# - Sets up traps:
+#   * ERR  → error_handler (script errors)
+#   * EXIT → on_exit      (any termination — cleanup + orphan detection)
+#   * INT  → on_interrupt  (Ctrl+C)
+#   * TERM → on_terminate  (kill / systemd stop)
+#   * HUP  → on_hangup     (SSH disconnect / terminal closed)
 # - Call this function early in every script
 # ------------------------------------------------------------------------------
 catch_errors() {

misc/install.func

@@ -32,11 +32,6 @@ if ! command -v curl >/dev/null 2>&1; then
   apt update >/dev/null 2>&1
   apt install -y curl >/dev/null 2>&1
 fi
-# Mark container context BEFORE error handling starts: error_handler/on_exit
-# must write local failure artifacts instead of talking to the telemetry API
-# (the host is the single telemetry reporter).
-export TELEMETRY_CONTEXT="container"
-
 source <(curl -fsSL https://raw.githubusercontent.com/community-scripts/ProxmoxVE/main/misc/core.func)
 source <(curl -fsSL https://raw.githubusercontent.com/community-scripts/ProxmoxVE/main/misc/error_handler.func)
 load_functions
@@ -70,12 +65,9 @@ post_progress_to_api() {
 
   local progress_status="${1:-configuring}"
 
-  # Progress pings are the ONLY telemetry a container sends (terminal statuses
-  # are reported by the host). Include execution_id + platform + repo
-  # attribution (exported by the host) so the server can correlate and filter.
   curl -fsS -m 5 -X POST "https://telemetry.community-scripts.org/telemetry" \
     -H "Content-Type: application/json" \
-    -d "{\"random_id\":\"${RANDOM_UUID}\",\"execution_id\":\"${EXECUTION_ID:-${RANDOM_UUID}}\",\"type\":\"lxc\",\"nsapp\":\"${app:-unknown}\",\"status\":\"${progress_status}\",\"platform\":\"${TELEMETRY_PLATFORM:-}\",\"repo_source\":\"${REPO_SOURCE:-}\",\"repo_slug\":\"${REPO_SLUG:-}\"}" &>/dev/null || true
+    -d "{\"random_id\":\"${RANDOM_UUID}\",\"execution_id\":\"${EXECUTION_ID:-${RANDOM_UUID}}\",\"type\":\"lxc\",\"nsapp\":\"${app:-unknown}\",\"status\":\"${progress_status}\"}" &>/dev/null || true
 }
 
 # ==============================================================================

misc/vm-core.func

@@ -573,10 +573,8 @@ cleanup() {
       if [[ $exit_code -ne 0 ]]; then
         post_update_to_api "failed" "$exit_code"
       else
-        # Exited cleanly but description()/success was never called: the user
+        # Exited cleanly but description()/success was never called — shouldn't happen
-        # backed out of a dialog. Report as aborted - NOT "failed 1" (which
+        post_update_to_api "failed" "1"
-        # produced meaningless 'General error' records with no error text).
-        post_update_to_api "aborted" "0"
       fi
     fi
   fi