Proxmox/ProxmoxVE
1
0
Fork 1
mirror of https://github.com/community-scripts/ProxmoxVE.git synced 2026-03-03 09:25:55 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix: improve error trace propagation for telemetry

Browse Source 
- 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.
This commit is contained in:
CanbiZ (MickLesk)
2026-03-02 14:23:59 +01:00
parent 7dbb0a75ef
commit ee74c8f158
2 changed files with 57 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
misc/error_handler.func
View File

@@ -408,10 +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} | ${explanation}"
fi
# Calculate duration if start time is available
@@ -420,10 +439,17 @@ _send_abort_telemetry() {
duration=$(($(date +%s) - DIAGNOSTICS_START_TIME))
fi
# Categorize error if function is available (may not be in minimal container context)
local error_category=""
if declare -f categorize_error &>/dev/null; then
error_category=$(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}}"