mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-12 07:59:02 +02:00
v1.84.1.0 fix: default Codex and Claude to frontier models (#2835)
* fix: default cross-model workflows to frontier models * chore: bump version and changelog (v1.82.1.0) Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: repair frontier eval budgets and workflow instructions Preserve frontier models and quality thresholds while fixing truncated judge output, ordered section expansion, consent checks, QA scoring, and ship audit gates. Add regression coverage and refresh generated docs. Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: resolve workflow gaps exposed by frontier evals Clarify plan-review ordering and fallback modes, preserve deploy readiness gates, honor configured merge methods, correct benchmark and canary contracts, and restore vendored installs on setup failure. Cover recovery with real-shell regressions. Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: use agent capture budgets for deploy evals Multi-turn deploy and benchmark sessions were incorrectly limited to the single-call judge timeout. Use the existing capture tier and leave outer-test cleanup headroom, with a free policy regression test. Keep all behavioral assertions and frontier models unchanged. Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: clarify retro workflow and evaluate compare instructions Include compare mode in the frontier judge excerpt, define metric sources and snapshot ordering, and preserve the existing prompt-size budget. Co-authored-by: OpenAI Codex <noreply@openai.com> * fix: make documentation release review and publication consistent Review before commit, clarify changelog safeguards and unavailable reviewer modes, and preserve raw PR bodies across separate shell calls. Keep title sync in one shell and add regression coverage. Co-authored-by: OpenAI Codex <noreply@openai.com> --------- Co-authored-by: OpenAI Codex <noreply@openai.com>
This commit is contained in:
Garry Tan
co-authored by
OpenAI Codex
OpenAI Codex
parent
c8f0c4e368
commit
71f6048e8a
+19
-17
@@ -4,7 +4,7 @@
|
||||
#
|
||||
# Functions (all prefixed with _gstack_codex_ for namespace hygiene):
|
||||
# _gstack_codex_auth_probe — multi-signal auth check (env + file)
|
||||
# _gstack_codex_model_probe — round-trip probe of the configured model (#2477)
|
||||
# _gstack_codex_model_probe — round-trip probe of gstack's selected model (#2477)
|
||||
# _gstack_codex_version_check — warn on known-bad Codex CLI versions
|
||||
# _gstack_codex_timeout_wrapper — gtimeout -> timeout -> unwrapped fallback
|
||||
# _gstack_codex_log_event — telemetry emission to ~/.gstack/analytics/
|
||||
@@ -38,17 +38,16 @@ _gstack_codex_auth_probe() {
|
||||
|
||||
_gstack_codex_model_probe() {
|
||||
# Auth-exists is a weaker signal than the auth probe implies: a ChatGPT
|
||||
# account with a stale `model = "..."` pin in ~/.codex/config.toml passes
|
||||
# the auth probe, then EVERY invocation dies with an HTTP 400 ("The
|
||||
# '<model>' model is not supported when using Codex with a ChatGPT
|
||||
# account") and no guidance. A short real round trip with the configured
|
||||
# model catches model rejection, entitlement changes, and stale pins in
|
||||
# one shot (#2477).
|
||||
# account can be valid while the model gstack will request is unavailable.
|
||||
# A short real round trip with gstack's selected model catches model
|
||||
# rejection and entitlement changes in one shot (#2477). gstack pins a
|
||||
# frontier default rather than inheriting Codex CLI's built-in default,
|
||||
# because that default can lag the most capable available model.
|
||||
#
|
||||
# Contract:
|
||||
# MODEL_OK (exit 0) — round trip succeeded; cached 1h.
|
||||
# MODEL_UNUSABLE (exit 1) — deterministic model 400; hints printed.
|
||||
# Cached 15 min: the 400 is config-driven, so re-probing every preflight
|
||||
# Cached 15 min: the 400 is model/entitlement-driven, so re-probing every preflight
|
||||
# charged the affected user a 30s round trip + real tokens per review
|
||||
# section, forever. Editing config.toml (the fix) changes the cache
|
||||
# signature and re-probes immediately; the short TTL covers server-side
|
||||
@@ -66,19 +65,22 @@ _gstack_codex_model_probe() {
|
||||
local _codex_home="${CODEX_HOME:-$HOME/.codex}"
|
||||
local _gstack_home="${GSTACK_HOME:-$HOME/.gstack}"
|
||||
local _cache="$_gstack_home/.codex-model-probe"
|
||||
# Cache signature: config.toml + auth.json mtimes. Editing the model pin
|
||||
# or re-logging-in invalidates the cached MODEL_OK immediately.
|
||||
local _model="${GSTACK_CODEX_MODEL:-gpt-6-astra}"
|
||||
# Cache signature: config.toml + auth.json mtimes + gstack model selection.
|
||||
# Editing the model env/config or re-logging-in invalidates the cached result
|
||||
# immediately.
|
||||
# GNU-first stat order + numeric validation (the #2195 pattern): on GNU
|
||||
# stat, `-f` means FILESYSTEM mode, so the BSD-first form emitted a
|
||||
# multi-line filesystem block on Linux — the signature then never matched
|
||||
# its own cache line and the cache missed on every read. BSD stat rejects
|
||||
# `-c` cleanly, so GNU-first degrades correctly on macOS.
|
||||
local _cfg_m _auth_m _sig
|
||||
local _cfg_m _auth_m _model_sig _sig
|
||||
_cfg_m=$(stat -c %Y "$_codex_home/config.toml" 2>/dev/null || stat -f %m "$_codex_home/config.toml" 2>/dev/null || echo 0)
|
||||
_auth_m=$(stat -c %Y "$_codex_home/auth.json" 2>/dev/null || stat -f %m "$_codex_home/auth.json" 2>/dev/null || echo 0)
|
||||
case "$_cfg_m" in ''|*[!0-9]*) _cfg_m=0 ;; esac
|
||||
case "$_auth_m" in ''|*[!0-9]*) _auth_m=0 ;; esac
|
||||
_sig="${_cfg_m}-${_auth_m}"
|
||||
_model_sig=$(printf '%s' "$_model" | sed 's/[^A-Za-z0-9._:-]/_/g')
|
||||
_sig="${_cfg_m}-${_auth_m}-${_model_sig}"
|
||||
local _now
|
||||
_now=$(date +%s 2>/dev/null || echo 0)
|
||||
if [ -f "$_cache" ]; then
|
||||
@@ -94,13 +96,13 @@ _gstack_codex_model_probe() {
|
||||
fi
|
||||
if [ "$_c_status" = "MODEL_UNUSABLE" ] && [ "$_c_sig" = "$_sig" ] && [ $((_now - _c_ts)) -lt 900 ]; then
|
||||
echo "MODEL_UNUSABLE (cached)"
|
||||
echo "HINT: the rejected model comes from the 'model = ' line in $_codex_home/config.toml."
|
||||
echo "HINT: check its [notice.model_migrations] table — Codex records the intended replacement there."
|
||||
echo "HINT: gstack requested model '$_model'."
|
||||
echo "HINT: set GSTACK_CODEX_MODEL=<supported-model> or pass an explicit -c model=... override."
|
||||
return 1
|
||||
fi
|
||||
fi
|
||||
local _out _code
|
||||
_out=$(_gstack_codex_timeout_wrapper 30 codex exec --skip-git-repo-check -s read-only "reply OK" </dev/null 2>&1)
|
||||
_out=$(_gstack_codex_timeout_wrapper 30 codex exec --skip-git-repo-check -s read-only -c "model=\"$_model\"" "reply OK" </dev/null 2>&1)
|
||||
_code=$?
|
||||
if [ "$_code" -eq 0 ]; then
|
||||
mkdir -p "$_gstack_home" 2>/dev/null || true
|
||||
@@ -113,8 +115,8 @@ _gstack_codex_model_probe() {
|
||||
printf 'MODEL_UNUSABLE %s %s\n' "$_now" "$_sig" > "$_cache" 2>/dev/null || true
|
||||
echo "MODEL_UNUSABLE"
|
||||
printf '%s\n' "$_out" | grep -i "model" | head -3
|
||||
echo "HINT: the rejected model comes from the 'model = ' line in $_codex_home/config.toml."
|
||||
echo "HINT: check its [notice.model_migrations] table — Codex records the intended replacement there."
|
||||
echo "HINT: gstack requested model '$_model'."
|
||||
echo "HINT: set GSTACK_CODEX_MODEL=<supported-model> or pass an explicit -c model=... override."
|
||||
_gstack_codex_log_event "codex_model_unusable" 2>/dev/null || true
|
||||
return 1
|
||||
fi
|
||||
|
||||
Reference in New Issue
Block a user