CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-09 22:48:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(review): skip nested codex spawns when already running under a Codex host (#2519)

Browse Source 
/review executed inside a Codex host spawned the codex specialist passes
anyway — the same model reviewing itself, at multiplied cost (observed:
15M tokens for a single /review).

Detection per maintainer decision 7: a presence probe of the Codex session
env. A live Codex session exports CODEX_THREAD_ID and CODEX_SANDBOX into
every shell it spawns — verified during implementation against a live
`codex exec 'env | grep -i codex'` capture on codex 0.147.0
(CODEX_THREAD_ID, CODEX_SANDBOX=seatbelt, CODEX_SANDBOX_NETWORK_DISABLED=1,
CODEX_CI=1). The shared codexPreflight in scripts/resolvers/constants.ts
(consumed by all three review.ts army blocks: adversarial, codex plan
review, codex doc review) now yields CODEX_MODE=under_codex and instructs
exactly one printed notice — '[running under Codex — nested codex passes
skipped; set GSTACK_FORCE_CODEX_REVIEW=1 to force]'. The override env var
forces the nested passes for users who really want them. codex/SKILL.md.tmpl
Step 0.5 gains the same probe: /codex under a Codex host stops with a
one-line notice, since its whole value is a SECOND model's opinion.

test/codex-under-codex-detection.test.ts runs the rendered preflight bash
under all four env combinations (thread-id only, sandbox only, forced,
clean) and asserts the probe + notice render in the three preflight
consumers and the codex skill.

Fixes #2519

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-08-16 10:59:35 -07:00
co-authored by Claude Fable 5
parent 73c96f9c12
commit ae47c29b82
11 changed files with 200 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codex/SKILL.md
+12 -1
View File
@@ -895,7 +895,11 @@ known-bad list. Sourcing `gstack-codex-probe` loads the shared helpers that both
_TEL=$(~/.claude/skills/gstack/bin/gstack-config get telemetry 2>/dev/null || echo off)
source ~/.claude/skills/gstack/bin/gstack-codex-probe
if ! _gstack_codex_auth_probe >/dev/null; then
# Running-under-Codex presence probe (#2519): a live Codex session exports
# CODEX_THREAD_ID / CODEX_SANDBOX into every shell it spawns.
if [ "${GSTACK_FORCE_CODEX_REVIEW:-0}" != "1" ] && { [ -n "${CODEX_THREAD_ID:-}" ] || [ -n "${CODEX_SANDBOX:-}" ]; }; then
echo "UNDER_CODEX"
elif ! _gstack_codex_auth_probe >/dev/null; then
_gstack_codex_log_event "codex_auth_failed"
echo "AUTH_FAILED"
else
@@ -904,6 +908,13 @@ fi
_gstack_codex_version_check # warns if known-bad, non-blocking
```
If the output contains `UNDER_CODEX`, stop with exactly one line:
"[running under Codex — /codex would nest the same model at multiplied token
cost; skipped. Set `GSTACK_FORCE_CODEX_REVIEW=1` to force.]" The whole value
of this skill is a SECOND model's opinion; inside a Codex host it is the same
model reviewing itself, and nested spawns have burned 15M tokens in one
/review (#2519).
If the output contains `AUTH_FAILED`, stop and tell the user:
"No Codex authentication found. Run `codex login` or set `$CODEX_API_KEY` / `$OPENAI_API_KEY`, then re-run this skill."
codex/SKILL.md.tmpl
+12 -1
View File
@@ -68,7 +68,11 @@ known-bad list. Sourcing `gstack-codex-probe` loads the shared helpers that both
_TEL=$(~/.claude/skills/gstack/bin/gstack-config get telemetry 2>/dev/null || echo off)
source ~/.claude/skills/gstack/bin/gstack-codex-probe
if ! _gstack_codex_auth_probe >/dev/null; then
# Running-under-Codex presence probe (#2519): a live Codex session exports
# CODEX_THREAD_ID / CODEX_SANDBOX into every shell it spawns.
if [ "${GSTACK_FORCE_CODEX_REVIEW:-0}" != "1" ] && { [ -n "${CODEX_THREAD_ID:-}" ] || [ -n "${CODEX_SANDBOX:-}" ]; }; then
echo "UNDER_CODEX"
elif ! _gstack_codex_auth_probe >/dev/null; then
_gstack_codex_log_event "codex_auth_failed"
echo "AUTH_FAILED"
else
@@ -77,6 +81,13 @@ fi
_gstack_codex_version_check # warns if known-bad, non-blocking
```
If the output contains `UNDER_CODEX`, stop with exactly one line:
"[running under Codex — /codex would nest the same model at multiplied token
cost; skipped. Set `GSTACK_FORCE_CODEX_REVIEW=1` to force.]" The whole value
of this skill is a SECOND model's opinion; inside a Codex host it is the same
model reviewing itself, and nested spawns have burned 15M tokens in one
/review (#2519).
If the output contains `AUTH_FAILED`, stop and tell the user:
"No Codex authentication found. Run `codex login` or set `$CODEX_API_KEY` / `$OPENAI_API_KEY`, then re-run this skill."
document-release/sections/release-body.md
+9
View File
@@ -377,6 +377,14 @@ _CODEX_CFG=$(~/.claude/skills/gstack/bin/gstack-config get codex_reviews 2>/dev/
source ~/.claude/skills/gstack/bin/gstack-codex-probe 2>/dev/null || true
if [ "$_CODEX_CFG" = "disabled" ]; then
_CODEX_MODE="disabled"
# Running-under-Codex presence probe (#2519): a live Codex session exports
# CODEX_THREAD_ID / CODEX_SANDBOX into every shell it spawns (verified
# against a live `codex exec 'env | grep -i codex'` capture, codex 0.147.0).
# Nested codex spawns from inside a Codex host multiply token burn
# (observed: one /review = 15M tokens). GSTACK_FORCE_CODEX_REVIEW=1 forces
# the nested passes anyway.
elif [ "${GSTACK_FORCE_CODEX_REVIEW:-0}" != "1" ] && { [ -n "${CODEX_THREAD_ID:-}" ] || [ -n "${CODEX_SANDBOX:-}" ]; }; then
_CODEX_MODE="under_codex"
elif ! command -v codex >/dev/null 2>&1; then
_CODEX_MODE="not_installed"; _gstack_codex_log_event "codex_cli_missing" 2>/dev/null || true
elif ! _gstack_codex_auth_probe >/dev/null 2>&1; then
@@ -392,6 +400,7 @@ echo "CODEX_MODE: $_CODEX_MODE"
Branch on the echoed `CODEX_MODE`:
- **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip this section entirely; do NOT fall back to a Claude subagent — disabled means no extra review step. Print: "Codex review skipped (codex_reviews disabled). Re-enable: `gstack-config set codex_reviews enabled`."
- **`not_installed`** — Codex CLI absent. Print: "Codex not installed — using Claude subagent. Install for cross-model coverage: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
- **`under_codex`** — this session is already running INSIDE a Codex host, so spawning codex again is the same model reviewing itself at multiplied token cost (#2519). Print exactly one line: "[running under Codex — nested codex passes skipped; set GSTACK_FORCE_CODEX_REVIEW=1 to force]" and skip the codex invocations below; run the section's free in-host pass instead if it defines one.
- **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — using Claude subagent. Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
- **`model_unusable`** — authed but the account cannot use its configured model (#2477: HTTP 400 on every call, usually a stale `model =` pin in `~/.codex/config.toml`). Relay the probe's HINT lines, tell the user the one-line fix (update the pin; `[notice.model_migrations]` names the replacement), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
- **`ready`** — run the Codex pass below.
plan-ceo-review/sections/review-sections.md
+9
View File
@@ -270,6 +270,14 @@ _CODEX_CFG=$(~/.claude/skills/gstack/bin/gstack-config get codex_reviews 2>/dev/
source ~/.claude/skills/gstack/bin/gstack-codex-probe 2>/dev/null || true
if [ "$_CODEX_CFG" = "disabled" ]; then
_CODEX_MODE="disabled"
# Running-under-Codex presence probe (#2519): a live Codex session exports
# CODEX_THREAD_ID / CODEX_SANDBOX into every shell it spawns (verified
# against a live `codex exec 'env | grep -i codex'` capture, codex 0.147.0).
# Nested codex spawns from inside a Codex host multiply token burn
# (observed: one /review = 15M tokens). GSTACK_FORCE_CODEX_REVIEW=1 forces
# the nested passes anyway.
elif [ "${GSTACK_FORCE_CODEX_REVIEW:-0}" != "1" ] && { [ -n "${CODEX_THREAD_ID:-}" ] || [ -n "${CODEX_SANDBOX:-}" ]; }; then
_CODEX_MODE="under_codex"
elif ! command -v codex >/dev/null 2>&1; then
_CODEX_MODE="not_installed"; _gstack_codex_log_event "codex_cli_missing" 2>/dev/null || true
elif ! _gstack_codex_auth_probe >/dev/null 2>&1; then
@@ -285,6 +293,7 @@ echo "CODEX_MODE: $_CODEX_MODE"
Branch on the echoed `CODEX_MODE`:
- **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip this section entirely; do NOT fall back to a Claude subagent — disabled means no extra review step. Print: "Codex review skipped (codex_reviews disabled). Re-enable: `gstack-config set codex_reviews enabled`."
- **`not_installed`** — Codex CLI absent. Print: "Codex not installed — using Claude subagent. Install for cross-model coverage: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
- **`under_codex`** — this session is already running INSIDE a Codex host, so spawning codex again is the same model reviewing itself at multiplied token cost (#2519). Print exactly one line: "[running under Codex — nested codex passes skipped; set GSTACK_FORCE_CODEX_REVIEW=1 to force]" and skip the codex invocations below; run the section's free in-host pass instead if it defines one.
- **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — using Claude subagent. Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
- **`model_unusable`** — authed but the account cannot use its configured model (#2477: HTTP 400 on every call, usually a stale `model =` pin in `~/.codex/config.toml`). Relay the probe's HINT lines, tell the user the one-line fix (update the pin; `[notice.model_migrations]` names the replacement), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
- **`ready`** — run the Codex pass below.
plan-devex-review/sections/review-sections.md
+9
View File
@@ -256,6 +256,14 @@ _CODEX_CFG=$(~/.claude/skills/gstack/bin/gstack-config get codex_reviews 2>/dev/
source ~/.claude/skills/gstack/bin/gstack-codex-probe 2>/dev/null || true
if [ "$_CODEX_CFG" = "disabled" ]; then
_CODEX_MODE="disabled"
# Running-under-Codex presence probe (#2519): a live Codex session exports
# CODEX_THREAD_ID / CODEX_SANDBOX into every shell it spawns (verified
# against a live `codex exec 'env | grep -i codex'` capture, codex 0.147.0).
# Nested codex spawns from inside a Codex host multiply token burn
# (observed: one /review = 15M tokens). GSTACK_FORCE_CODEX_REVIEW=1 forces
# the nested passes anyway.
elif [ "${GSTACK_FORCE_CODEX_REVIEW:-0}" != "1" ] && { [ -n "${CODEX_THREAD_ID:-}" ] || [ -n "${CODEX_SANDBOX:-}" ]; }; then
_CODEX_MODE="under_codex"
elif ! command -v codex >/dev/null 2>&1; then
_CODEX_MODE="not_installed"; _gstack_codex_log_event "codex_cli_missing" 2>/dev/null || true
elif ! _gstack_codex_auth_probe >/dev/null 2>&1; then
@@ -271,6 +279,7 @@ echo "CODEX_MODE: $_CODEX_MODE"
Branch on the echoed `CODEX_MODE`:
- **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip this section entirely; do NOT fall back to a Claude subagent — disabled means no extra review step. Print: "Codex review skipped (codex_reviews disabled). Re-enable: `gstack-config set codex_reviews enabled`."
- **`not_installed`** — Codex CLI absent. Print: "Codex not installed — using Claude subagent. Install for cross-model coverage: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
- **`under_codex`** — this session is already running INSIDE a Codex host, so spawning codex again is the same model reviewing itself at multiplied token cost (#2519). Print exactly one line: "[running under Codex — nested codex passes skipped; set GSTACK_FORCE_CODEX_REVIEW=1 to force]" and skip the codex invocations below; run the section's free in-host pass instead if it defines one.
- **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — using Claude subagent. Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
- **`model_unusable`** — authed but the account cannot use its configured model (#2477: HTTP 400 on every call, usually a stale `model =` pin in `~/.codex/config.toml`). Relay the probe's HINT lines, tell the user the one-line fix (update the pin; `[notice.model_migrations]` names the replacement), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
- **`ready`** — run the Codex pass below.
plan-eng-review/sections/review-sections.md
+9
View File
@@ -351,6 +351,14 @@ _CODEX_CFG=$(~/.claude/skills/gstack/bin/gstack-config get codex_reviews 2>/dev/
source ~/.claude/skills/gstack/bin/gstack-codex-probe 2>/dev/null || true
if [ "$_CODEX_CFG" = "disabled" ]; then
_CODEX_MODE="disabled"
# Running-under-Codex presence probe (#2519): a live Codex session exports
# CODEX_THREAD_ID / CODEX_SANDBOX into every shell it spawns (verified
# against a live `codex exec 'env | grep -i codex'` capture, codex 0.147.0).
# Nested codex spawns from inside a Codex host multiply token burn
# (observed: one /review = 15M tokens). GSTACK_FORCE_CODEX_REVIEW=1 forces
# the nested passes anyway.
elif [ "${GSTACK_FORCE_CODEX_REVIEW:-0}" != "1" ] && { [ -n "${CODEX_THREAD_ID:-}" ] || [ -n "${CODEX_SANDBOX:-}" ]; }; then
_CODEX_MODE="under_codex"
elif ! command -v codex >/dev/null 2>&1; then
_CODEX_MODE="not_installed"; _gstack_codex_log_event "codex_cli_missing" 2>/dev/null || true
elif ! _gstack_codex_auth_probe >/dev/null 2>&1; then
@@ -366,6 +374,7 @@ echo "CODEX_MODE: $_CODEX_MODE"
Branch on the echoed `CODEX_MODE`:
- **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip this section entirely; do NOT fall back to a Claude subagent — disabled means no extra review step. Print: "Codex review skipped (codex_reviews disabled). Re-enable: `gstack-config set codex_reviews enabled`."
- **`not_installed`** — Codex CLI absent. Print: "Codex not installed — using Claude subagent. Install for cross-model coverage: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
- **`under_codex`** — this session is already running INSIDE a Codex host, so spawning codex again is the same model reviewing itself at multiplied token cost (#2519). Print exactly one line: "[running under Codex — nested codex passes skipped; set GSTACK_FORCE_CODEX_REVIEW=1 to force]" and skip the codex invocations below; run the section's free in-host pass instead if it defines one.
- **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — using Claude subagent. Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
- **`model_unusable`** — authed but the account cannot use its configured model (#2477: HTTP 400 on every call, usually a stale `model =` pin in `~/.codex/config.toml`). Relay the probe's HINT lines, tell the user the one-line fix (update the pin; `[notice.model_migrations]` names the replacement), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
- **`ready`** — run the Codex pass below.
review/SKILL.md
+9
View File
@@ -1681,6 +1681,14 @@ _CODEX_CFG=$(~/.claude/skills/gstack/bin/gstack-config get codex_reviews 2>/dev/
source ~/.claude/skills/gstack/bin/gstack-codex-probe 2>/dev/null || true
if [ "$_CODEX_CFG" = "disabled" ]; then
_CODEX_MODE="disabled"
# Running-under-Codex presence probe (#2519): a live Codex session exports
# CODEX_THREAD_ID / CODEX_SANDBOX into every shell it spawns (verified
# against a live `codex exec 'env | grep -i codex'` capture, codex 0.147.0).
# Nested codex spawns from inside a Codex host multiply token burn
# (observed: one /review = 15M tokens). GSTACK_FORCE_CODEX_REVIEW=1 forces
# the nested passes anyway.
elif [ "${GSTACK_FORCE_CODEX_REVIEW:-0}" != "1" ] && { [ -n "${CODEX_THREAD_ID:-}" ] || [ -n "${CODEX_SANDBOX:-}" ]; }; then
_CODEX_MODE="under_codex"
elif ! command -v codex >/dev/null 2>&1; then
_CODEX_MODE="not_installed"; _gstack_codex_log_event "codex_cli_missing" 2>/dev/null || true
elif ! _gstack_codex_auth_probe >/dev/null 2>&1; then
@@ -1696,6 +1704,7 @@ echo "CODEX_MODE: $_CODEX_MODE"
Branch on the echoed `CODEX_MODE`:
- **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip the Codex passes only; the Claude adversarial subagent below STILL runs (it is free and fast). Print: "Codex passes skipped (codex_reviews disabled) — running Claude adversarial only."
- **`not_installed`** — Codex CLI absent. Print: "Codex not installed — using Claude subagent. Install for cross-model coverage: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
- **`under_codex`** — this session is already running INSIDE a Codex host, so spawning codex again is the same model reviewing itself at multiplied token cost (#2519). Print exactly one line: "[running under Codex — nested codex passes skipped; set GSTACK_FORCE_CODEX_REVIEW=1 to force]" and skip the codex invocations below; run the section's free in-host pass instead if it defines one.
- **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — using Claude subagent. Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
- **`model_unusable`** — authed but the account cannot use its configured model (#2477: HTTP 400 on every call, usually a stale `model =` pin in `~/.codex/config.toml`). Relay the probe's HINT lines, tell the user the one-line fix (update the pin; `[notice.model_migrations]` names the replacement), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
- **`ready`** — run the Codex pass below.
scripts/resolvers/constants.ts
+9
View File
@@ -118,6 +118,14 @@ _CODEX_CFG=$(~/.claude/skills/gstack/bin/gstack-config get codex_reviews 2>/dev/
source ~/.claude/skills/gstack/bin/gstack-codex-probe 2>/dev/null || true
if [ "$_CODEX_CFG" = "disabled" ]; then
${m}="disabled"
# Running-under-Codex presence probe (#2519): a live Codex session exports
# CODEX_THREAD_ID / CODEX_SANDBOX into every shell it spawns (verified
# against a live \`codex exec 'env | grep -i codex'\` capture, codex 0.147.0).
# Nested codex spawns from inside a Codex host multiply token burn
# (observed: one /review = 15M tokens). GSTACK_FORCE_CODEX_REVIEW=1 forces
# the nested passes anyway.
elif [ "\${GSTACK_FORCE_CODEX_REVIEW:-0}" != "1" ] && { [ -n "\${CODEX_THREAD_ID:-}" ] || [ -n "\${CODEX_SANDBOX:-}" ]; }; then
${m}="under_codex"
elif ! command -v codex >/dev/null 2>&1; then
${m}="not_installed"; _gstack_codex_log_event "codex_cli_missing" 2>/dev/null || true
elif ! _gstack_codex_auth_probe >/dev/null 2>&1; then
@@ -133,6 +141,7 @@ echo "CODEX_MODE: $${m}"
Branch on the echoed \`CODEX_MODE\`:
- **\`disabled\`** — the user turned Codex reviews off (\`codex_reviews=disabled\`). ${disabledLine}
- **\`not_installed\`** — Codex CLI absent. Print: "Codex not installed — using Claude subagent. Install for cross-model coverage: \`npm install -g @openai/codex\`." Fall back to the Claude subagent path.
- **\`under_codex\`** — this session is already running INSIDE a Codex host, so spawning codex again is the same model reviewing itself at multiplied token cost (#2519). Print exactly one line: "[running under Codex — nested codex passes skipped; set GSTACK_FORCE_CODEX_REVIEW=1 to force]" and skip the codex invocations below; run the section's free in-host pass instead if it defines one.
- **\`not_authed\`** — installed but no credentials. Print: "Codex installed but not authenticated — using Claude subagent. Run \`codex login\` or set \`$CODEX_API_KEY\`." Fall back to the Claude subagent path.
- **\`model_unusable\`** — authed but the account cannot use its configured model (#2477: HTTP 400 on every call, usually a stale \`model =\` pin in \`~/.codex/config.toml\`). Relay the probe's HINT lines, tell the user the one-line fix (update the pin; \`[notice.model_migrations]\` names the replacement), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to \`ready\`.
- **\`ready\`** — run the Codex pass below.`;
ship/sections/adversarial.md
+9
View File
@@ -23,6 +23,14 @@ _CODEX_CFG=$(~/.claude/skills/gstack/bin/gstack-config get codex_reviews 2>/dev/
source ~/.claude/skills/gstack/bin/gstack-codex-probe 2>/dev/null || true
if [ "$_CODEX_CFG" = "disabled" ]; then
_CODEX_MODE="disabled"
# Running-under-Codex presence probe (#2519): a live Codex session exports
# CODEX_THREAD_ID / CODEX_SANDBOX into every shell it spawns (verified
# against a live `codex exec 'env | grep -i codex'` capture, codex 0.147.0).
# Nested codex spawns from inside a Codex host multiply token burn
# (observed: one /review = 15M tokens). GSTACK_FORCE_CODEX_REVIEW=1 forces
# the nested passes anyway.
elif [ "${GSTACK_FORCE_CODEX_REVIEW:-0}" != "1" ] && { [ -n "${CODEX_THREAD_ID:-}" ] || [ -n "${CODEX_SANDBOX:-}" ]; }; then
_CODEX_MODE="under_codex"
elif ! command -v codex >/dev/null 2>&1; then
_CODEX_MODE="not_installed"; _gstack_codex_log_event "codex_cli_missing" 2>/dev/null || true
elif ! _gstack_codex_auth_probe >/dev/null 2>&1; then
@@ -38,6 +46,7 @@ echo "CODEX_MODE: $_CODEX_MODE"
Branch on the echoed `CODEX_MODE`:
- **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip the Codex passes only; the Claude adversarial subagent below STILL runs (it is free and fast). Print: "Codex passes skipped (codex_reviews disabled) — running Claude adversarial only."
- **`not_installed`** — Codex CLI absent. Print: "Codex not installed — using Claude subagent. Install for cross-model coverage: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
- **`under_codex`** — this session is already running INSIDE a Codex host, so spawning codex again is the same model reviewing itself at multiplied token cost (#2519). Print exactly one line: "[running under Codex — nested codex passes skipped; set GSTACK_FORCE_CODEX_REVIEW=1 to force]" and skip the codex invocations below; run the section's free in-host pass instead if it defines one.
- **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — using Claude subagent. Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
- **`model_unusable`** — authed but the account cannot use its configured model (#2477: HTTP 400 on every call, usually a stale `model =` pin in `~/.codex/config.toml`). Relay the probe's HINT lines, tell the user the one-line fix (update the pin; `[notice.model_migrations]` names the replacement), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
- **`ready`** — run the Codex pass below.
test/codex-under-codex-detection.test.ts
+104
View File
@@ -0,0 +1,104 @@
/**
* Running-under-Codex detection (#2519, maintainer decision 7).
*
* /review executed inside a Codex host used to spawn nested codex
* specialists — the same model reviewing itself at multiplied token cost
* (observed: 15M tokens for one /review). A live Codex session exports
* CODEX_THREAD_ID / CODEX_SANDBOX into every shell it spawns (verified
* against a live `codex exec 'env | grep -i codex'` capture on codex
* 0.147.0: CODEX_THREAD_ID, CODEX_SANDBOX=seatbelt,
* CODEX_SANDBOX_NETWORK_DISABLED=1, CODEX_CI=1). The shared codexPreflight
* presence-probes those vars and yields CODEX_MODE=under_codex, skipping
* nested spawns with a one-line notice; GSTACK_FORCE_CODEX_REVIEW=1
* overrides.
*/
import { describe, test, expect } from 'bun:test';
import { spawnSync } from 'child_process';
import * as fs from 'fs';
import * as path from 'path';
import { codexPreflight } from '../scripts/resolvers/constants';
const ROOT = path.resolve(import.meta.dir, '..');
/** Extract the runnable bash from the rendered preflight (strip fences/prose). */
function preflightBash(): string {
const rendered = codexPreflight({ disabledBehavior: 'codex-only' });
const start = rendered.indexOf('```bash') + '```bash'.length;
const end = rendered.indexOf('```', start);
return rendered.slice(start, end);
}
function runPreflight(env: Record<string, string>): string {
const result = spawnSync('bash', ['-c', `set +e\n${preflightBash()}`], {
env: {
// Minimal PATH without codex so the not_installed branch is reachable
// and no real gstack-config/codex runs. The block's fallbacks
// (`|| echo enabled`) keep it self-contained.
PATH: '/usr/bin:/bin',
HOME: '/nonexistent-home',
...env,
},
timeout: 10000,
});
return (result.stdout ?? '').toString();
}
describe('under-codex detection bash (#2519)', () => {
test('CODEX_THREAD_ID present -> under_codex', () => {
const out = runPreflight({ CODEX_THREAD_ID: '01a00ba9-ff91-7143-b424-c2d9b0cc89ff' });
expect(out).toContain('CODEX_MODE: under_codex');
});
test('CODEX_SANDBOX present (no thread id) -> under_codex', () => {
const out = runPreflight({ CODEX_SANDBOX: 'seatbelt' });
expect(out).toContain('CODEX_MODE: under_codex');
});
test('GSTACK_FORCE_CODEX_REVIEW=1 overrides the presence probe', () => {
const out = runPreflight({
CODEX_THREAD_ID: '01a00ba9-ff91-7143-b424-c2d9b0cc89ff',
CODEX_SANDBOX: 'seatbelt',
GSTACK_FORCE_CODEX_REVIEW: '1',
});
expect(out).not.toContain('CODEX_MODE: under_codex');
// With codex absent from the restricted PATH, the forced probe falls
// through to the ordinary availability chain.
expect(out).toContain('CODEX_MODE: not_installed');
});
test('no CODEX_* env -> ordinary availability chain', () => {
const out = runPreflight({});
expect(out).not.toContain('CODEX_MODE: under_codex');
expect(out).toContain('CODEX_MODE: not_installed');
});
});
describe('under-codex wiring renders (#2519)', () => {
test('rendered adversarial section carries the probe + override + notice', () => {
const rendered = fs.readFileSync(
path.join(ROOT, 'ship', 'sections', 'adversarial.md'),
'utf-8',
);
expect(rendered).toContain('CODEX_THREAD_ID');
expect(rendered).toContain('GSTACK_FORCE_CODEX_REVIEW');
expect(rendered).toContain('under_codex');
expect(rendered).toContain('nested codex passes skipped');
});
test('rendered codex skill stops with the one-line notice when under codex', () => {
const rendered = fs.readFileSync(path.join(ROOT, 'codex', 'SKILL.md'), 'utf-8');
expect(rendered).toContain('UNDER_CODEX');
expect(rendered).toContain('GSTACK_FORCE_CODEX_REVIEW=1');
});
test('all three codexPreflight consumers render the probe', () => {
for (const file of [
path.join(ROOT, 'ship', 'sections', 'adversarial.md'),
path.join(ROOT, 'plan-ceo-review', 'sections', 'review-sections.md'),
path.join(ROOT, 'document-release', 'sections', 'release-body.md'),
]) {
const rendered = fs.readFileSync(file, 'utf-8');
expect(rendered).toContain('under_codex');
}
});
});
test/fixtures/golden/factory-ship-SKILL.md
Vendored
+9
View File
@@ -2497,6 +2497,14 @@ _CODEX_CFG=$($GSTACK_ROOT/bin/gstack-config get codex_reviews 2>/dev/null || ech
source $GSTACK_ROOT/bin/gstack-codex-probe 2>/dev/null || true
if [ "$_CODEX_CFG" = "disabled" ]; then
_CODEX_MODE="disabled"
# Running-under-Codex presence probe (#2519): a live Codex session exports
# CODEX_THREAD_ID / CODEX_SANDBOX into every shell it spawns (verified
# against a live `codex exec 'env | grep -i codex'` capture, codex 0.147.0).
# Nested codex spawns from inside a Codex host multiply token burn
# (observed: one /review = 15M tokens). GSTACK_FORCE_CODEX_REVIEW=1 forces
# the nested passes anyway.
elif [ "${GSTACK_FORCE_CODEX_REVIEW:-0}" != "1" ] && { [ -n "${CODEX_THREAD_ID:-}" ] || [ -n "${CODEX_SANDBOX:-}" ]; }; then
_CODEX_MODE="under_codex"
elif ! command -v codex >/dev/null 2>&1; then
_CODEX_MODE="not_installed"; _gstack_codex_log_event "codex_cli_missing" 2>/dev/null || true
elif ! _gstack_codex_auth_probe >/dev/null 2>&1; then
@@ -2512,6 +2520,7 @@ echo "CODEX_MODE: $_CODEX_MODE"
Branch on the echoed `CODEX_MODE`:
- **`disabled`** — the user turned Codex reviews off (`codex_reviews=disabled`). Skip the Codex passes only; the Claude adversarial subagent below STILL runs (it is free and fast). Print: "Codex passes skipped (codex_reviews disabled) — running Claude adversarial only."
- **`not_installed`** — Codex CLI absent. Print: "Codex not installed — using Claude subagent. Install for cross-model coverage: `npm install -g @openai/codex`." Fall back to the Claude subagent path.
- **`under_codex`** — this session is already running INSIDE a Codex host, so spawning codex again is the same model reviewing itself at multiplied token cost (#2519). Print exactly one line: "[running under Codex — nested codex passes skipped; set GSTACK_FORCE_CODEX_REVIEW=1 to force]" and skip the codex invocations below; run the section's free in-host pass instead if it defines one.
- **`not_authed`** — installed but no credentials. Print: "Codex installed but not authenticated — using Claude subagent. Run `codex login` or set `$CODEX_API_KEY`." Fall back to the Claude subagent path.
- **`model_unusable`** — authed but the account cannot use its configured model (#2477: HTTP 400 on every call, usually a stale `model =` pin in `~/.codex/config.toml`). Relay the probe's HINT lines, tell the user the one-line fix (update the pin; `[notice.model_migrations]` names the replacement), and fall back to the Claude subagent path. The ~10s round trip is cached for 1h; timeouts fail open to `ready`.
- **`ready`** — run the Codex pass below.