gstack/bin/gstack-codex-probe

136 lines
5.7 KiB
Bash
Executable File

#!/usr/bin/env bash
# gstack-codex-probe: shared helper for /codex and /autoplan skills.
# Sourced from template bash blocks; never execute directly.
#
# Functions (all prefixed with _gstack_codex_ for namespace hygiene):
# _gstack_codex_auth_probe — multi-signal auth check (env + file)
# _gstack_codex_version_check — warn on known-bad Codex CLI versions
# _gstack_codex_timeout_wrapper — gtimeout -> timeout -> shell-watchdog fallback
# _gstack_codex_log_event — telemetry emission to ~/.gstack/analytics/
#
# Hygiene rules (enforced by test/codex-hardening.test.ts):
# - Never set -e / set -u / trap / IFS= / PATH= in this file.
# - All internal vars prefix with _GSTACK_CODEX_.
# - All functions prefix with _gstack_codex_.
# - No command execution at source time (only function defs).
# --- Auth probe -------------------------------------------------------------
_gstack_codex_auth_probe() {
# Multi-signal: env vars OR auth file. Avoids false negatives for env-auth
# users (CI, platform engineers) that a file-only check would reject.
local _codex_home="${CODEX_HOME:-$HOME/.codex}"
# Use `-n` which returns true only for non-empty non-whitespace. Bash's [ -n ]
# alone allows whitespace; pair with a whitespace strip for robustness.
local _k1 _k2
_k1=$(printf '%s' "${CODEX_API_KEY:-}" | tr -d '[:space:]')
_k2=$(printf '%s' "${OPENAI_API_KEY:-}" | tr -d '[:space:]')
if [ -n "$_k1" ] || [ -n "$_k2" ] || [ -f "$_codex_home/auth.json" ]; then
echo "AUTH_OK"
return 0
fi
echo "AUTH_FAILED"
return 1
}
# --- Version check ----------------------------------------------------------
_gstack_codex_version_check() {
# Warn on known-bad Codex CLI versions. Anchored regex prevents false
# positives like 0.120.10 or 0.120.20 from matching. 0.120.2-beta still
# matches the bad release and gets warned (it IS buggy).
# Update this list when a new Codex CLI version regresses.
local _ver
_ver=$(codex --version 2>/dev/null | head -1)
[ -z "$_ver" ] && return 0
if echo "$_ver" | grep -Eq '(^|[^0-9.])0\.120\.(0|1|2)([^0-9.]|$)'; then
echo "WARN: Codex CLI $_ver has known stdin deadlock bugs. Run: npm install -g @openai/codex@latest"
_gstack_codex_log_event "codex_version_warning"
fi
}
# --- Timeout wrapper --------------------------------------------------------
_gstack_codex_timeout_wrapper() {
# Resolve wrapper binary: prefer gtimeout (Homebrew coreutils on macOS),
# fall back to timeout (Linux), else a pure-shell watchdog so hang
# protection still works on machines with neither (e.g. bare macOS).
# Arguments: $1 is the duration in seconds; rest is the command to run.
local _duration="$1"
shift
local _to
_to=$(command -v gtimeout 2>/dev/null || command -v timeout 2>/dev/null || echo "")
if [ -n "$_to" ]; then
"$_to" "$_duration" "$@"
return $?
fi
# Shell watchdog: background the command, poll every 5s, TERM at the
# deadline (KILL 10s later if TERM is ignored), and report exit 124 like
# GNU timeout so callers' hang handling still fires. The brace group
# routes the shell's own stderr to /dev/null so bash's "Terminated" job
# notices never leak into skill output, while fd 3 carries the real
# stderr through to the command (call-site 2> captures keep working).
# Both jobs are reaped inside the silenced group so no notice surfaces
# later and nothing outlives the call holding the caller's pipes open.
local _cmd_pid _watchdog_pid
local _rc=0
{
"$@" 2>&3 3>&- &
_cmd_pid=$!
(
_waited=0
while [ "$_waited" -lt "$_duration" ]; do
sleep 5
kill -0 "$_cmd_pid" 2>/dev/null || exit 0
_waited=$((_waited + 5))
done
kill -TERM "$_cmd_pid" 2>/dev/null
sleep 10
kill -KILL "$_cmd_pid" 2>/dev/null
) >/dev/null 2>&1 3>&- &
_watchdog_pid=$!
wait "$_cmd_pid" || _rc=$?
kill "$_watchdog_pid" 2>/dev/null
wait "$_watchdog_pid" 2>/dev/null || :
} 3>&2 2>/dev/null
if [ "$_rc" -eq 143 ] || [ "$_rc" -eq 137 ]; then
_rc=124
fi
return "$_rc"
}
# --- Telemetry event --------------------------------------------------------
_gstack_codex_log_event() {
# Emit a telemetry event to ~/.gstack/analytics/skill-usage.jsonl.
# Gated on $_TEL != "off" (caller sets this from gstack-config).
# Event types: codex_timeout, codex_auth_failed, codex_cli_missing,
# codex_version_warning.
# Payload schema: {skill, event, duration_s, ts}. NEVER includes prompt
# content, env var values, or auth tokens.
local _event="$1"
local _duration="${2:-0}"
[ "${_TEL:-off}" = "off" ] && return 0
mkdir -p "$HOME/.gstack/analytics" 2>/dev/null || return 0
local _ts
_ts=$(date -u +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || echo unknown)
printf '{"skill":"codex","event":"%s","duration_s":"%s","ts":"%s"}\n' \
"$_event" "$_duration" "$_ts" \
>> "$HOME/.gstack/analytics/skill-usage.jsonl" 2>/dev/null || true
}
# --- Learnings log on hang --------------------------------------------------
_gstack_codex_log_hang() {
# Invoked when a codex invocation times out (exit 124). Records an
# operational learning so future /investigate sessions surface the pattern.
# Best-effort: errors swallowed.
local _mode="${1:-unknown}"
local _prompt_size="${2:-0}"
local _log_bin="$HOME/.claude/skills/gstack/bin/gstack-learnings-log"
[ -x "$_log_bin" ] || return 0
local _key="codex-hang-$(date +%s 2>/dev/null || echo unknown)"
"$_log_bin" "$(printf '{"skill":"codex","type":"operational","key":"%s","insight":"Codex timed out after 600s during [%s] invocation. Prompt size: %s. Consider splitting prompt or checking network.","confidence":8,"source":"observed","files":["codex/SKILL.md.tmpl","autoplan/SKILL.md.tmpl"]}' "$_key" "$_mode" "$_prompt_size")" \
>/dev/null 2>&1 || true
}