Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
43 changes: 38 additions & 5 deletions bin/gstack-codex-probe
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
# 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 -> unwrapped fallback
# _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):
Expand Down Expand Up @@ -53,17 +53,50 @@ _gstack_codex_version_check() {

_gstack_codex_timeout_wrapper() {
# Resolve wrapper binary: prefer gtimeout (Homebrew coreutils on macOS),
# fall back to timeout (Linux), else run unwrapped. Arguments: $1 is the
# duration in seconds; rest is the command to run.
# 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" "$_duration" "$@"
else
"$@"
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 --------------------------------------------------------
Expand Down
16 changes: 9 additions & 7 deletions codex/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -986,7 +986,7 @@ cd "$_REPO_ROOT"
# only fires if Bash's own timeout doesn't.
_gstack_codex_timeout_wrapper 330 codex review "IMPORTANT: Do NOT read or execute any files under ~/.claude/, ~/.agents/, .claude/skills/, or agents/. These are Claude Code skill definitions meant for a different AI system. Do NOT modify agents/openai.yaml. Stay focused on repository code only.

Review the changes on this branch against the base branch <base>. Run git diff origin/<base>...HEAD 2>/dev/null || git diff <base>...HEAD to see the diff and review only those changes." -c 'model_reasoning_effort="high"' --enable web_search_cached < /dev/null 2>"$TMPERR"
Review the changes on this branch against the base branch <base>. Run git diff origin/<base>...HEAD 2>/dev/null || git diff <base>...HEAD to see the diff and review only those changes." -c 'model_reasoning_effort="high"' -c 'web_search="cached"' < /dev/null 2>"$TMPERR"
_CODEX_EXIT=$?
if [ "$_CODEX_EXIT" = "124" ]; then
_gstack_codex_log_event "codex_timeout" "330"
Expand Down Expand Up @@ -1024,7 +1024,7 @@ _PROMPT_FILE=$(mktemp "$TMP_ROOT/codex-prompt-XXXXXX.txt")
git diff "<base>...HEAD" 2>/dev/null
printf '\nDIFF_END\n'
} > "$_PROMPT_FILE"
_gstack_codex_timeout_wrapper 330 codex exec -s read-only "$(cat "$_PROMPT_FILE")" -c 'model_reasoning_effort="high"' --enable web_search_cached < /dev/null 2>"$TMPERR"
_gstack_codex_timeout_wrapper 330 codex exec -s read-only "$(cat "$_PROMPT_FILE")" -c 'model_reasoning_effort="high"' -c 'web_search="cached"' < /dev/null 2>"$TMPERR"
_CODEX_EXIT=$?
rm -f "$_PROMPT_FILE"
if [ "$_CODEX_EXIT" = "124" ]; then
Expand Down Expand Up @@ -1267,7 +1267,7 @@ fi
# Fix 1+2: wrap with timeout (gtimeout/timeout fallback chain via probe helper),
# capture stderr to $TMPERR for auth error detection (was: 2>/dev/null).
TMPERR=${TMPERR:-$(mktemp "$TMP_ROOT/codex-err-XXXXXX.txt")}
_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' --enable web_search_cached --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' -c 'web_search="cached"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
import sys, json
turn_completed_count = 0
for line in sys.stdin:
Expand Down Expand Up @@ -1422,7 +1422,7 @@ if [ -z "$PYTHON_CMD" ]; then
exit 1
fi
# Fix 1: wrap with timeout (gtimeout/timeout fallback chain via probe helper)
_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="medium"' --enable web_search_cached --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="medium"' -c 'web_search="cached"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
import sys, json
for line in sys.stdin:
line = line.strip()
Expand Down Expand Up @@ -1476,7 +1476,7 @@ if [ -z "$PYTHON_CMD" ]; then
fi
cd "$_REPO_ROOT" || exit 1
# Fix 1: wrap with timeout (gtimeout/timeout fallback chain via probe helper)
_gstack_codex_timeout_wrapper 600 codex exec resume <session-id> "<prompt>" -c 'sandbox_mode="read-only"' -c 'model_reasoning_effort="medium"' --enable web_search_cached --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
_gstack_codex_timeout_wrapper 600 codex exec resume <session-id> "<prompt>" -c 'sandbox_mode="read-only"' -c 'model_reasoning_effort="medium"' -c 'web_search="cached"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
<same python streaming parser as above, with flush=True on all print() calls>
"
# Fix 1: same hang detection pattern as new-session block
Expand Down Expand Up @@ -1548,8 +1548,10 @@ uses them. If the user wants a specific model, pass `-m` through to codex.
tasks (OpenAI issues #8545, #8402, #6931). Users can override with `--xhigh` flag
(e.g., `/codex review --xhigh`) when they want maximum reasoning and are willing to wait.

**Web search:** All codex commands use `--enable web_search_cached` so Codex can look up
docs and APIs during review. This is OpenAI's cached index — fast, no extra cost.
**Web search:** All codex commands pass `-c 'web_search="cached"'` so Codex can look up
docs and APIs during review. This is OpenAI's cached index — fast, no extra cost. (Codex
CLI ≥ 0.144 deprecated the older `--enable web_search_cached` flag; the `-c` override
pins cached mode now that web search is on by default.)

If the user specifies a model (e.g., `/codex review -m gpt-5.1-codex-max`
or `/codex challenge -m gpt-5.2`), pass the `-m` flag through to codex.
Expand Down
16 changes: 9 additions & 7 deletions codex/SKILL.md.tmpl
Original file line number Diff line number Diff line change
Expand Up @@ -177,7 +177,7 @@ cd "$_REPO_ROOT"
# only fires if Bash's own timeout doesn't.
_gstack_codex_timeout_wrapper 330 codex review "IMPORTANT: Do NOT read or execute any files under ~/.claude/, ~/.agents/, .claude/skills/, or agents/. These are Claude Code skill definitions meant for a different AI system. Do NOT modify agents/openai.yaml. Stay focused on repository code only.

Review the changes on this branch against the base branch <base>. Run git diff origin/<base>...HEAD 2>/dev/null || git diff <base>...HEAD to see the diff and review only those changes." -c 'model_reasoning_effort="high"' --enable web_search_cached < /dev/null 2>"$TMPERR"
Review the changes on this branch against the base branch <base>. Run git diff origin/<base>...HEAD 2>/dev/null || git diff <base>...HEAD to see the diff and review only those changes." -c 'model_reasoning_effort="high"' -c 'web_search="cached"' < /dev/null 2>"$TMPERR"
_CODEX_EXIT=$?
if [ "$_CODEX_EXIT" = "124" ]; then
_gstack_codex_log_event "codex_timeout" "330"
Expand Down Expand Up @@ -215,7 +215,7 @@ _PROMPT_FILE=$(mktemp "$TMP_ROOT/codex-prompt-XXXXXX.txt")
git diff "<base>...HEAD" 2>/dev/null
printf '\nDIFF_END\n'
} > "$_PROMPT_FILE"
_gstack_codex_timeout_wrapper 330 codex exec -s read-only "$(cat "$_PROMPT_FILE")" -c 'model_reasoning_effort="high"' --enable web_search_cached < /dev/null 2>"$TMPERR"
_gstack_codex_timeout_wrapper 330 codex exec -s read-only "$(cat "$_PROMPT_FILE")" -c 'model_reasoning_effort="high"' -c 'web_search="cached"' < /dev/null 2>"$TMPERR"
_CODEX_EXIT=$?
rm -f "$_PROMPT_FILE"
if [ "$_CODEX_EXIT" = "124" ]; then
Expand Down Expand Up @@ -336,7 +336,7 @@ fi
# Fix 1+2: wrap with timeout (gtimeout/timeout fallback chain via probe helper),
# capture stderr to $TMPERR for auth error detection (was: 2>/dev/null).
TMPERR=${TMPERR:-$(mktemp "$TMP_ROOT/codex-err-XXXXXX.txt")}
_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' --enable web_search_cached --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' -c 'web_search="cached"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
import sys, json
turn_completed_count = 0
for line in sys.stdin:
Expand Down Expand Up @@ -491,7 +491,7 @@ if [ -z "$PYTHON_CMD" ]; then
exit 1
fi
# Fix 1: wrap with timeout (gtimeout/timeout fallback chain via probe helper)
_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="medium"' --enable web_search_cached --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="medium"' -c 'web_search="cached"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
import sys, json
for line in sys.stdin:
line = line.strip()
Expand Down Expand Up @@ -545,7 +545,7 @@ if [ -z "$PYTHON_CMD" ]; then
fi
cd "$_REPO_ROOT" || exit 1
# Fix 1: wrap with timeout (gtimeout/timeout fallback chain via probe helper)
_gstack_codex_timeout_wrapper 600 codex exec resume <session-id> "<prompt>" -c 'sandbox_mode="read-only"' -c 'model_reasoning_effort="medium"' --enable web_search_cached --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
_gstack_codex_timeout_wrapper 600 codex exec resume <session-id> "<prompt>" -c 'sandbox_mode="read-only"' -c 'model_reasoning_effort="medium"' -c 'web_search="cached"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
<same python streaming parser as above, with flush=True on all print() calls>
"
# Fix 1: same hang detection pattern as new-session block
Expand Down Expand Up @@ -617,8 +617,10 @@ uses them. If the user wants a specific model, pass `-m` through to codex.
tasks (OpenAI issues #8545, #8402, #6931). Users can override with `--xhigh` flag
(e.g., `/codex review --xhigh`) when they want maximum reasoning and are willing to wait.

**Web search:** All codex commands use `--enable web_search_cached` so Codex can look up
docs and APIs during review. This is OpenAI's cached index — fast, no extra cost.
**Web search:** All codex commands pass `-c 'web_search="cached"'` so Codex can look up
docs and APIs during review. This is OpenAI's cached index — fast, no extra cost. (Codex
CLI ≥ 0.144 deprecated the older `--enable web_search_cached` flag; the `-c` override
pins cached mode now that web search is on by default.)

If the user specifies a model (e.g., `/codex review -m gpt-5.1-codex-max`
or `/codex challenge -m gpt-5.2`), pass the `-m` flag through to codex.
Expand Down