Compare commits

...

2 Commits

Author SHA1 Message Date
CanbiZ (MickLesk)
ee74c8f158 fix: improve error trace propagation for telemetry
- post_update_to_api: Attempts 2/3 now send medium_error (16KB truncated
  log) instead of short_error (generic description only). This is the
  primary fix — when attempt 1 fails (120KB payload too large/timeout),
  attempts 2/3 no longer discard all log data.

- _send_abort_telemetry: Increased container fallback from 20 to 200
  log lines (capped at 16KB). Added SILENT_LOGFILE as fallback source.
  Added exit code explanation header and error_category to payload.

- get_error_text/get_full_log: Added SILENT_LOGFILE as last-resort
  fallback when INSTALL_LOG, combined log, and BUILD_LOG are all
  empty/missing.
2026-03-02 14:24:18 +01:00
CanbiZ (MickLesk)
7dbb0a75ef fix: replace generic exit 1 with specific exit codes in ct/ and install/ scripts
Part of #12467 — scripts only (no framework changes).

New exit codes 250-254 registered in api.func and error_handler.func:
- 250: App download failed or version not determined
- 251: App file extraction failed (corrupt/incomplete archive)
- 252: App required file or resource not found
- 253: App data migration required — update aborted
- 254: App user declined prompt or input timed out

Existing codes reused where applicable:
- 10: privileged/Docker required (unifi-os-server)
- 64: invalid user input (postgresql, tomcat)
- 71: system error (pulse useradd)
- 150: service failed to start (docker, npmplus)
- 153: build failed (booklore)
- 233: app not installed (evcc, endurain, grafana, loki, itsm-ng)
- 236: hardware not detected (unifi-os-server /dev/net/tun)
- 238: OS not supported (frigate)
2026-03-02 13:27:28 +01:00
28 changed files with 110 additions and 44 deletions

View File

@@ -39,7 +39,7 @@ function update_script() {
COMPOSE_FILE=$(find /opt/komodo -maxdepth 1 -type f -name '*.compose.yaml' ! -name 'compose.env' | head -n1)
if [[ -z "$COMPOSE_FILE" ]]; then
msg_error "No valid compose file found in /opt/komodo!"
exit 1
exit 252
fi
$STD docker compose -p komodo -f "$COMPOSE_FILE" --env-file /opt/komodo/compose.env pull
$STD docker compose -p komodo -f "$COMPOSE_FILE" --env-file /opt/komodo/compose.env up -d

View File

@@ -26,7 +26,7 @@ function update_script() {
if [[ ! -d /opt/endurain ]]; then
msg_error "No ${APP} installation found!"
exit 1
exit 233
fi
if check_for_gh_release "endurain" "endurain-project/endurain"; then
msg_info "Stopping Service"

View File

@@ -25,7 +25,7 @@ function update_script() {
check_container_resources
if ! command -v evcc >/dev/null 2>&1; then
msg_error "No ${APP} Installation Found!"
exit 1
exit 233
fi
if [[ -f /etc/apt/sources.list.d/evcc-stable.list ]]; then

View File

@@ -26,7 +26,7 @@ function update_script() {
if ! dpkg -s grafana >/dev/null 2>&1; then
msg_error "No ${APP} Installation Found!"
exit 1
exit 233
fi
if [[ -f /etc/apt/sources.list.d/grafana.list ]] || [[ ! -f /etc/apt/sources.list.d/grafana.sources ]]; then

View File

@@ -26,7 +26,7 @@ function update_script() {
if [[ ! -f /etc/itsm-ng/config_db.php ]]; then
msg_error "No ${APP} Installation Found!"
exit 1
exit 233
fi
setup_mariadb

View File

@@ -45,7 +45,7 @@ function update_script() {
if [[ -z "$KASM_URL" ]] || [[ -z "$KASM_VERSION" ]]; then
msg_error "Unable to detect latest Kasm release URL."
exit 1
exit 250
fi
msg_info "Checked for new version"

View File

@@ -43,7 +43,7 @@ function update_script() {
COMPOSE_FILE=$(find /opt/komodo -maxdepth 1 -type f -name '*.compose.yaml' ! -name 'compose.env' | head -n1)
if [[ -z "$COMPOSE_FILE" ]]; then
msg_error "No valid compose file found in /opt/komodo!"
exit 1
exit 252
fi
$STD docker compose -p komodo -f "$COMPOSE_FILE" --env-file /opt/komodo/compose.env pull
$STD docker compose -p komodo -f "$COMPOSE_FILE" --env-file /opt/komodo/compose.env up -d

View File

@@ -26,7 +26,7 @@ function update_script() {
if ! dpkg -s loki >/dev/null 2>&1; then
msg_error "No ${APP} Installation Found!"
exit 1
exit 233
fi
CHOICE=$(msg_menu "Loki Update Options" \

View File

@@ -44,7 +44,7 @@ function update_script() {
echo -e "${TAB}${GATEWAY}${BGN}https://github.com/community-scripts/ProxmoxVE/discussions/9223${CL}"
echo -e ""
msg_custom "⚠️" "Update aborted. Please migrate your data first."
exit 1
exit 253
fi
fi

View File

@@ -34,14 +34,14 @@ function update_script() {
msg_warn "This requires MANUAL config changes in /etc/vikunja/config.yml."
msg_warn "See: https://vikunja.io/changelog/whats-new-in-vikunja-1.0.0/#config-changes"
read -rp "Continue with update? (y to proceed): " -t 30 CONFIRM1 || exit 1
read -rp "Continue with update? (y to proceed): " -t 30 CONFIRM1 || exit 254
[[ "$CONFIRM1" =~ ^[yY]$ ]] || exit 0
echo
msg_warn "Vikunja may not start after the update until you manually adjust the config."
msg_warn "Details: https://vikunja.io/changelog/whats-new-in-vikunja-1.0.0/#config-changes"
read -rp "Acknowledge and continue? (y): " -t 30 CONFIRM2 || exit 1
read -rp "Acknowledge and continue? (y): " -t 30 CONFIRM2 || exit 254
[[ "$CONFIRM2" =~ ^[yY]$ ]] || exit 0
fi

View File

@@ -14,7 +14,7 @@ network_check
update_os
read -r -p "${TAB3}Enter PostgreSQL version (15/16/17): " ver
[[ $ver =~ ^(15|16|17)$ ]] || { echo "Invalid version"; exit 1; }
[[ $ver =~ ^(15|16|17)$ ]] || { echo "Invalid version"; exit 64; }
msg_info "Installing PostgreSQL ${ver}"
$STD apk add --no-cache postgresql${ver} postgresql${ver}-contrib postgresql${ver}-openrc sudo

View File

@@ -25,7 +25,7 @@ case $version in
;;
*)
msg_error "Invalid JDK version selected. Please enter 8, 11, 17 or 21."
exit 1
exit 64
;;
esac
;;
@@ -39,7 +39,7 @@ case $version in
;;
*)
msg_error "Invalid JDK version selected. Please enter 11, 17 or 21."
exit 1
exit 64
;;
esac
;;
@@ -53,13 +53,13 @@ case $version in
;;
*)
msg_error "Invalid JDK version selected. Please enter 17 or 21."
exit 1
exit 64
;;
esac
;;
*)
msg_error "Invalid Tomcat version selected. Please enter 9, 10.1 or 11."
exit 1
exit 64
;;
esac

View File

@@ -59,7 +59,7 @@ mkdir -p /opt/booklore/dist
JAR_PATH=$(find /opt/booklore/booklore-api/build/libs -maxdepth 1 -type f -name "booklore-api-*.jar" ! -name "*plain*" | head -n1)
if [[ -z "$JAR_PATH" ]]; then
msg_error "Backend JAR not found"
exit 1
exit 153
fi
cp "$JAR_PATH" /opt/booklore/dist/app.jar
msg_ok "Built Backend"

View File

@@ -86,7 +86,7 @@ EOF
msg_ok "Docker TCP socket available on $socket"
else
msg_error "Docker failed to restart. Check journalctl -xeu docker.service"
exit 1
exit 150
fi
fi

View File

@@ -21,7 +21,7 @@ msg_info "Fetching latest EMQX Enterprise version"
LATEST_VERSION=$(curl -fsSL https://www.emqx.com/en/downloads/enterprise | grep -oP '/en/downloads/enterprise/v\K[0-9]+\.[0-9]+\.[0-9]+' | sort -V | tail -n1)
if [[ -z "$LATEST_VERSION" ]]; then
msg_error "Failed to determine latest EMQX version"
exit 1
exit 250
fi
msg_ok "Latest version: v$LATEST_VERSION"

View File

@@ -17,7 +17,7 @@ update_os
source /etc/os-release
if [[ "$VERSION_ID" != "12" ]]; then
msg_error "Frigate requires Debian 12 (Bookworm) due to Python 3.11 dependencies"
exit 1
exit 238
fi
msg_info "Converting APT sources to DEB822 format"

View File

@@ -31,7 +31,7 @@ fi
if [[ -z "$KASM_URL" ]] || [[ -z "$KASM_VERSION" ]]; then
msg_error "Unable to detect latest Kasm release URL."
exit 1
exit 250
fi
msg_ok "Detected Kasm Workspaces version $KASM_VERSION"

View File

@@ -51,7 +51,7 @@ while true; do
attempts=$((attempts + 1))
if [[ "$attempts" -ge 3 ]]; then
msg_error "Maximum attempts reached. Exiting."
exit 1
exit 254
fi
done
@@ -76,11 +76,11 @@ for i in {1..60}; do
elif [[ "$STATUS" == "unhealthy" ]]; then
msg_error "NPMplus container is unhealthy! Check logs."
docker logs "$CONTAINER_ID"
exit 1
exit 150
fi
fi
sleep 2
[[ $i -eq 60 ]] && msg_error "NPMplus container did not become healthy within 120s." && docker logs "$CONTAINER_ID" && exit 1
[[ $i -eq 60 ]] && msg_error "NPMplus container did not become healthy within 120s." && docker logs "$CONTAINER_ID" && exit 150
done
msg_ok "Builded and started NPMplus"

View File

@@ -78,11 +78,11 @@ if curl -fL# -C - -o "$TMP_TAR" "$OLLAMA_URL"; then
msg_ok "Installed Ollama ${RELEASE}"
else
msg_error "Extraction failed archive corrupt or incomplete"
exit 1
exit 251
fi
else
msg_error "Download failed $OLLAMA_URL not reachable"
exit 1
exit 250
fi
msg_info "Creating ollama User and Group"

View File

@@ -59,7 +59,7 @@ EOF
else
msg_error "Failed to download or verify GPG key from $KEY_URL"
[[ -f "$TMP_KEY_CONTENT" ]] && rm -f "$TMP_KEY_CONTENT"
exit 1
exit 250
fi
rm -f "$TMP_KEY_CONTENT"

View File

@@ -34,7 +34,7 @@ for server in "${servers[@]}"; do
done
if ((attempt >= MAX_ATTEMPTS)); then
msg_error "No more attempts - aborting script!"
exit 1
exit 254
fi
done

View File

@@ -16,7 +16,7 @@ update_os
read -r -p "${TAB3}Enter PostgreSQL version (15/16/17/18): " ver
[[ $ver =~ ^(15|16|17|18)$ ]] || {
echo "Invalid version"
exit 1
exit 64
}
PG_VERSION=$ver setup_postgresql

View File

@@ -25,7 +25,7 @@ if useradd -r -m -d /opt/pulse-home -s /usr/sbin/nologin pulse; then
msg_ok "Created User"
else
msg_error "User creation failed"
exit 1
exit 71
fi
mkdir -p /etc/pulse

View File

@@ -34,7 +34,7 @@ while true; do
[Nn]|[Nn][Oo]|"")
msg_error "Terms not accepted. Installation cannot proceed."
msg_error "Please review the terms and run the script again if you wish to proceed."
exit 1
exit 254
;;
*)
msg_error "Invalid response. Please enter 'y' for yes or 'n' for no."
@@ -47,7 +47,7 @@ DOWNLOAD_URL=$(curl -s "https://www.splunk.com/en_us/download/splunk-enterprise.
RELEASE=$(echo "$DOWNLOAD_URL" | sed 's|.*/releases/\([^/]*\)/.*|\1|')
$STD curl -fsSL -o "splunk-enterprise.tgz" "$DOWNLOAD_URL" || {
msg_error "Failed to download Splunk Enterprise from the provided link."
exit 1
exit 250
}
$STD tar -xzf "splunk-enterprise.tgz" -C /opt
rm -f "splunk-enterprise.tgz"

View File

@@ -16,13 +16,13 @@ update_os
if [[ "${CTTYPE:-1}" != "0" ]]; then
msg_error "UniFi OS Server requires a privileged LXC container."
msg_error "Recreate the container with unprivileged=0."
exit 1
exit 10
fi
if [[ ! -e /dev/net/tun ]]; then
msg_error "Missing /dev/net/tun in container."
msg_error "Enable TUN/TAP (var_tun=yes) or add /dev/net/tun passthrough."
exit 1
exit 236
fi
msg_info "Installing dependencies"
@@ -48,7 +48,7 @@ TEMP_JSON="$(mktemp)"
if ! curl -fsSL "$API_URL" -o "$TEMP_JSON"; then
rm -f "$TEMP_JSON"
msg_error "Failed to fetch data from Ubiquiti API"
exit 1
exit 250
fi
LATEST=$(jq -r '
._embedded.firmware
@@ -62,7 +62,7 @@ UOS_URL=$(echo "$LATEST" | jq -r '._links.data.href')
rm -f "$TEMP_JSON"
if [[ -z "$UOS_URL" || -z "$UOS_VERSION" || "$UOS_URL" == "null" ]]; then
msg_error "Failed to parse UniFi OS Server version or download URL"
exit 1
exit 250
fi
msg_ok "Found UniFi OS Server ${UOS_VERSION}"

View File

@@ -31,7 +31,7 @@ if gpg --verify /tmp/zerotier-install.sh >/dev/null 2>&1; then
$STD bash /tmp/zerotier-install.sh
else
msg_warn "Could not verify signature of Zerotier-One install script. Exiting..."
exit 1
exit 250
fi
msg_ok "Setup Zerotier-One"

View File

@@ -134,6 +134,7 @@ detect_repo_source
# * Proxmox custom codes (200-231)
# * Tools & Addon Scripts (232-238)
# * Node.js/npm errors (239, 243, 245-249)
# * Application Install/Update errors (250-254)
# - Returns description string for given exit code
# ------------------------------------------------------------------------------
explain_exit_code() {
@@ -322,6 +323,13 @@ explain_exit_code() {
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" ;;
# --- DPKG ---
255) echo "DPKG: Fatal internal error" ;;
@@ -385,6 +393,11 @@ get_error_text() {
logfile="$BUILD_LOG"
fi
# Try SILENT_LOGFILE as last resort (captures $STD command output)
if [[ -z "$logfile" || ! -s "$logfile" ]] && [[ -n "${SILENT_LOGFILE:-}" && -s "${SILENT_LOGFILE}" ]]; then
logfile="$SILENT_LOGFILE"
fi
if [[ -n "$logfile" && -s "$logfile" ]]; then
tail -n 20 "$logfile" 2>/dev/null | sed 's/\r$//' | sed 's/\x1b\[[0-9;]*[a-zA-Z]//g'
fi
@@ -430,6 +443,13 @@ get_full_log() {
fi
fi
# Fall back to SILENT_LOGFILE (captures $STD command output)
if [[ -z "$logfile" || ! -s "$logfile" ]]; then
if [[ -n "${SILENT_LOGFILE:-}" && -s "${SILENT_LOGFILE}" ]]; then
logfile="$SILENT_LOGFILE"
fi
fi
if [[ -n "$logfile" && -s "$logfile" ]]; then
# Strip ANSI codes, carriage returns, and anonymize IP addresses (GDPR)
sed 's/\r$//' "$logfile" 2>/dev/null |
@@ -868,7 +888,7 @@ post_update_to_api() {
esac
# For failed/unknown status, resolve exit code and error description
local short_error=""
local short_error="" medium_error=""
if [[ "$pb_status" == "failed" ]] || [[ "$pb_status" == "unknown" ]]; then
if [[ "$raw_exit_code" =~ ^[0-9]+$ ]]; then
exit_code="$raw_exit_code"
@@ -888,6 +908,18 @@ post_update_to_api() {
short_error=$(json_escape "$(explain_exit_code "$exit_code")")
error_category=$(categorize_error "$exit_code")
[[ -z "$error" ]] && error="Unknown error"
# Build medium error for attempt 2: explanation + last 100 log lines (≤16KB)
# This is the critical middle ground between full 120KB log and generic-only description
local medium_log=""
medium_log=$(get_full_log 16384) || true # 16KB max
if [[ -z "$medium_log" ]]; then
medium_log=$(get_error_text) || true
fi
local medium_full
medium_full=$(build_error_string "$exit_code" "$medium_log")
medium_error=$(json_escape "$medium_full")
[[ -z "$medium_error" ]] && medium_error="$short_error"
fi
# Calculate duration if timer was started
@@ -946,7 +978,7 @@ EOF
return 0
fi
# ── Attempt 2: Short error text (no full log) ──
# ── Attempt 2: Medium error text (truncated log ≤16KB instead of full 120KB) ──
sleep 1
local RETRY_PAYLOAD
RETRY_PAYLOAD=$(
@@ -966,7 +998,7 @@ EOF
"pve_version": "${pve_version}",
"method": "${METHOD:-default}",
"exit_code": ${exit_code},
"error": "${short_error}",
"error": "${medium_error}",
"error_category": "${error_category}",
"install_duration": ${duration},
"cpu_vendor": "${cpu_vendor}",
@@ -989,7 +1021,7 @@ EOF
return 0
fi
# ── Attempt 3: Minimal payload (bare minimum to set status) ──
# ── Attempt 3: Minimal payload with medium error (bare minimum to set status) ──
sleep 2
local MINIMAL_PAYLOAD
MINIMAL_PAYLOAD=$(
@@ -1001,7 +1033,7 @@ EOF
"nsapp": "${NSAPP:-unknown}",
"status": "${pb_status}",
"exit_code": ${exit_code},
"error": "${short_error}",
"error": "${medium_error}",
"error_category": "${error_category}",
"install_duration": ${duration}
}

View File

@@ -195,6 +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
@@ -400,10 +408,29 @@ _send_abort_telemetry() {
[[ "${DIAGNOSTICS:-no}" == "no" ]] && return 0
[[ -z "${RANDOM_UUID:-}" ]] && return 0
# Collect last 20 log lines for error diagnosis (best-effort)
# 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
error_text=$(tail -n 20 "$INSTALL_LOG" 2>/dev/null | sed 's/\x1b\[[0-9;]*[a-zA-Z]//g; s/\\/\\\\/g; s/"/\\"/g; s/\r//g' | tr '\n' '|' | sed 's/|$//' | tr -d '\000-\010\013\014\016-\037\177') || true
logfile="${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} | ${explanation}"
fi
# Calculate duration if start time is available
@@ -412,10 +439,17 @@ _send_abort_telemetry() {
duration=$(($(date +%s) - DIAGNOSTICS_START_TIME))
fi
# Categorize error if function is available (may not be in minimal container context)
local error_category=""
if declare -f categorize_error &>/dev/null; then
error_category=$(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}}"