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:
co-authored by
OpenAI Codex
parent
c8f0c4e368
commit
71f6048e8a
@@ -35,7 +35,7 @@ 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")}
|
||||
_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 "$PYTHON_CMD" -u -c "
|
||||
_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c "model=\"${GSTACK_CODEX_MODEL:-gpt-6-astra}\"" -c 'model_reasoning_effort="high"' -c 'web_search="cached"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
|
||||
import sys, json
|
||||
turn_completed_count = 0
|
||||
turn_failed = False
|
||||
|
||||
@@ -33,7 +33,7 @@ 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")}
|
||||
_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="high"' {{CODEX_WEB_SEARCH_FLAG}} --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
|
||||
_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only {{CODEX_MODEL_CONFIG_FLAG}} -c 'model_reasoning_effort="high"' {{CODEX_WEB_SEARCH_FLAG}} --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
|
||||
import sys, json
|
||||
turn_completed_count = 0
|
||||
turn_failed = False
|
||||
|
||||
@@ -78,7 +78,7 @@ 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"' -c 'web_search="cached"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
|
||||
_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only -c "model=\"${GSTACK_CODEX_MODEL:-gpt-6-astra}\"" -c 'model_reasoning_effort="medium"' -c 'web_search="cached"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
|
||||
import sys, json
|
||||
turn_completed_count = 0
|
||||
turn_failed = False
|
||||
@@ -153,7 +153,7 @@ 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"' -c '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=\"${GSTACK_CODEX_MODEL:-gpt-6-astra}\"" -c 'model_reasoning_effort="medium"' -c 'web_search="cached"' --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
|
||||
<same python streaming parser as above, with flush=True on all print() calls>
|
||||
"
|
||||
# Fix 1: same hang detection pattern as new-session block
|
||||
|
||||
@@ -76,7 +76,7 @@ if [ -z "$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 "$_REPO_ROOT" -s read-only -c 'model_reasoning_effort="medium"' {{CODEX_WEB_SEARCH_FLAG}} --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
|
||||
_gstack_codex_timeout_wrapper 600 codex exec "<prompt>" -C "$_REPO_ROOT" -s read-only {{CODEX_MODEL_CONFIG_FLAG}} -c 'model_reasoning_effort="medium"' {{CODEX_WEB_SEARCH_FLAG}} --json < /dev/null 2>"$TMPERR" | PYTHONUNBUFFERED=1 "$PYTHON_CMD" -u -c "
|
||||
import sys, json
|
||||
turn_completed_count = 0
|
||||
turn_failed = False
|
||||
@@ -151,7 +151,7 @@ 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"' {{CODEX_WEB_SEARCH_FLAG}} --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"' {{CODEX_MODEL_CONFIG_FLAG}} -c 'model_reasoning_effort="medium"' {{CODEX_WEB_SEARCH_FLAG}} --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
|
||||
|
||||
@@ -45,7 +45,7 @@ cd "$_REPO_ROOT"
|
||||
# The 330s wrapper sits BELOW the 360s Bash gate so the wrapper fires FIRST
|
||||
# and a stall surfaces as a diagnosable exit 124 with an explicit message,
|
||||
# never as a silent harness kill that downstream reads as "no findings".
|
||||
_gstack_codex_timeout_wrapper 330 codex review --base <base> -c 'sandbox_mode="read-only"' -c 'model_reasoning_effort="high"' -c 'web_search="cached"' < /dev/null 2>"$TMPERR"
|
||||
_gstack_codex_timeout_wrapper 330 codex review --base <base> -c 'sandbox_mode="read-only"' -c "model=\"${GSTACK_CODEX_MODEL:-gpt-6-astra}\"" -c "review_model=\"${GSTACK_CODEX_MODEL:-gpt-6-astra}\"" -c 'model_reasoning_effort="high"' -c 'web_search="cached"' < /dev/null 2>"$TMPERR"
|
||||
_CODEX_EXIT=$?
|
||||
if [ "$_CODEX_EXIT" = "124" ]; then
|
||||
_gstack_codex_log_event "codex_timeout" "330"
|
||||
@@ -86,7 +86,7 @@ _PROMPT_FILE=$(mktemp "$TMP_ROOT/codex-prompt-XXXXXX")
|
||||
git diff "<base>...HEAD" 2>/dev/null
|
||||
printf '\nDIFF_END\n'
|
||||
} > "$_PROMPT_FILE"
|
||||
_gstack_codex_timeout_wrapper 330 codex exec -s read-only "$(cat "$_PROMPT_FILE")" -c 'model_reasoning_effort="high"' -c 'web_search="cached"' < /dev/null 2>"$TMPERR"
|
||||
_gstack_codex_timeout_wrapper 330 codex exec -s read-only "$(cat "$_PROMPT_FILE")" -c "model=\"${GSTACK_CODEX_MODEL:-gpt-6-astra}\"" -c 'model_reasoning_effort="high"' -c 'web_search="cached"' < /dev/null 2>"$TMPERR"
|
||||
_CODEX_EXIT=$?
|
||||
rm -f "$_PROMPT_FILE"
|
||||
if [ "$_CODEX_EXIT" = "124" ]; then
|
||||
|
||||
@@ -43,7 +43,7 @@ cd "$_REPO_ROOT"
|
||||
# The 330s wrapper sits BELOW the 360s Bash gate so the wrapper fires FIRST
|
||||
# and a stall surfaces as a diagnosable exit 124 with an explicit message,
|
||||
# never as a silent harness kill that downstream reads as "no findings".
|
||||
_gstack_codex_timeout_wrapper 330 codex review --base <base> -c 'sandbox_mode="read-only"' -c 'model_reasoning_effort="high"' {{CODEX_WEB_SEARCH_FLAG}} < /dev/null 2>"$TMPERR"
|
||||
_gstack_codex_timeout_wrapper 330 codex review --base <base> -c 'sandbox_mode="read-only"' {{CODEX_REVIEW_MODEL_CONFIG_FLAG}} -c 'model_reasoning_effort="high"' {{CODEX_WEB_SEARCH_FLAG}} < /dev/null 2>"$TMPERR"
|
||||
_CODEX_EXIT=$?
|
||||
if [ "$_CODEX_EXIT" = "124" ]; then
|
||||
_gstack_codex_log_event "codex_timeout" "330"
|
||||
@@ -84,7 +84,7 @@ _PROMPT_FILE=$(mktemp "$TMP_ROOT/codex-prompt-XXXXXX")
|
||||
git diff "<base>...HEAD" 2>/dev/null
|
||||
printf '\nDIFF_END\n'
|
||||
} > "$_PROMPT_FILE"
|
||||
_gstack_codex_timeout_wrapper 330 codex exec -s read-only "$(cat "$_PROMPT_FILE")" -c 'model_reasoning_effort="high"' {{CODEX_WEB_SEARCH_FLAG}} < /dev/null 2>"$TMPERR"
|
||||
_gstack_codex_timeout_wrapper 330 codex exec -s read-only "$(cat "$_PROMPT_FILE")" {{CODEX_MODEL_CONFIG_FLAG}} -c 'model_reasoning_effort="high"' {{CODEX_WEB_SEARCH_FLAG}} < /dev/null 2>"$TMPERR"
|
||||
_CODEX_EXIT=$?
|
||||
rm -f "$_PROMPT_FILE"
|
||||
if [ "$_CODEX_EXIT" = "124" ]; then
|
||||
|
||||
Reference in New Issue
Block a user