CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-08-22 22:17:16 +02:00
Code Issues Packages Projects Releases Wiki Activity

v1.67.2.0 feat: gpt-5.6-sol bounded-scope profile for Codex installs (#2633)

Browse Source 
* feat: model taxonomy gains gpt-5.6-sol + per-host generation defaults

Adds 'gpt-5.6-sol' to the model taxonomy with exact-match-only resolution
(Terra/Luna/suffixed IDs deliberately fall back to generic gpt) and replaces
the hardcoded 'claude' generation default with a validated
HostConfig.defaultModel: codex renders the gpt profile when --model is
absent, every other host keeps claude. Codex ship golden regenerated
accordingly; ADDING_A_HOST documents the new field.

* feat: gpt-5.6-sol bounded-scope overlay + scope-aware resolvers

The Sol profile pins the explicit task as the lake: adjacent work is
report-only, investigation is bounded, runs terminate on one clean
verification pass, and the AskUserQuestion decision-brief format is never
trimmed. The overlay wrapper grants scope-interpretation precedence while
concrete workflow steps, gates, and skill-mandated re-verification loops
still win. Sol-specific Completeness Principle and first-run intro copy.
New SETUP_COMMAND resolver renders './setup --host <host>' for every
non-claude host so generated upgrade skills reinstall their own host.

* feat: setup reads the Codex model from config.toml

New resolve-codex-generation-model.ts reads the top-level model from
${CODEX_HOME:-~/.codex}/config.toml, validates against the model allowlist,
strips control characters from every config-derived string it surfaces,
guards against non-absolute config locations, and warns on Sol near-misses.
setup runs it on EVERY invocation (read-only TOML lookup) so a plain
./setup can never clobber a Sol user's rendered profile with the hardcoded
fallback; --model <id> overrides for one run and prints the persistence
hint. Kiro installs render the claude profile before copying (Kiro fronts
Claude-family models), rewrite the baked setup command to --host kiro, and
restore the resolved Codex profile after; the codex skills path honors
CODEX_HOME. Static pins cover the resolver wiring, fail-closed exit,
quoted argv, and the Kiro sandwich.

* feat: hermetic Codex runner hardening + Sol scope-termination E2E

The Codex E2E runner copies auth.json only (operator plugins, MCP servers,
rules, and skills no longer leak into hermetic evals), pins CODEX_HOME to
the temp dir, and supports per-run model, TOML overrides, and
--ignore-user-config. New periodic E2E installs the FULL generated
investigate skill on gpt-5.6-sol against a planted one-line bug with decoy
TODOs: the fix must land inside the boundary (untracked files counted via
git status --porcelain), decoys stay byte-identical, the regression oracle
survives unweakened, nothing gets committed, all within 30 tool calls.
The shared .agents tree is snapshotted and restored exactly in beforeAll;
fixture commits disable gpg signing. Wired into the periodic CI matrix,
paid-shard globs, eval scripts, touchfiles/E2E_TIERS
(codex-sol-scope-termination), and diff-based selection. Real-file
periodic-tier classification pins both codex E2Es out of the gate tier.
Free-tier test proves an explicit --model overrides the host default
through the real generation CLI.

* chore: bump version and changelog (v1.67.2.0)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: post-ship documentation sync for v1.67.2.0

- README: Codex skills path is CODEX_HOME-aware; state that
  --model overrides detection for one run only (persist via
  the Codex config.toml model key)
- CONTRIBUTING: add the model-overlay axis to the per-host
  config table (per-host defaultModel, override precedence)
- CLAUDE.md: eval results dir is ~/.gstack/projects/<slug>/evals/
  (legacy fallback ~/.gstack-dev/evals/), matching eval-store.ts
  and the eval:* CLI headers

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: post-ship documentation sync (v1.67.2.0)

Sol exact-match and near-miss warning documented in README; CODEX_HOME-aware
uninstall and troubleshooting paths; hermetic auth.json-only detail and the
build-clobber gotcha in CLAUDE.md; eval-store location corrected in
ARCHITECTURE.md; defaultModel row in the ADDING_A_HOST field reference;
resolver test count corrected in the CHANGELOG entry.

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-08-18 17:00:04 -07:00
committed by GitHub
co-authored by Claude Fable 5
parent c86e6472eb
commit 60e51342b5
38 changed files with 1194 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files
setup
+76 -9
View File
@@ -12,6 +12,7 @@ Usage: ./setup [options]
Options:
--host <name> Install for a specific host (claude, codex, kiro, factory,
opencode, openclaw, hermes, gbrain, auto). Default: claude.
--model <id> Codex model profile override. Otherwise reads Codex config.
--prefix Install skills with the gstack- prefix (e.g. /gstack-review).
--no-prefix Install skills with short names (e.g. /review). Default.
--team Switch to team mode (per-repo gstack with auto-update).
@@ -22,6 +23,7 @@ Options:
Examples:
./setup # solo install for Claude Code
./setup --host codex # install for OpenAI Codex CLI
./setup --host codex --model gpt-5.6-sol
./setup --team # team mode for a shared repo
./setup --no-prefix # use short slash-command names
@@ -52,7 +54,7 @@ INSTALL_GSTACK_DIR="$(cd "$(dirname "$0")" && pwd)"
SOURCE_GSTACK_DIR="$(cd "$(dirname "$0")" && pwd -P)"
INSTALL_SKILLS_DIR="$(dirname "$INSTALL_GSTACK_DIR")"
BROWSE_BIN="$SOURCE_GSTACK_DIR/browse/dist/browse"
CODEX_SKILLS="$HOME/.codex/skills"
CODEX_SKILLS="${CODEX_HOME:-$HOME/.codex}/skills"
CODEX_GSTACK="$CODEX_SKILLS/gstack"
FACTORY_SKILLS="$HOME/.factory/skills"
FACTORY_GSTACK="$FACTORY_SKILLS/gstack"
@@ -171,10 +173,14 @@ SKILL_PREFIX_FLAG=0
TEAM_MODE=0
NO_TEAM_MODE=0
PLAN_TUNE_HOOKS_MODE="" # "" = resolve from env/config/prompt; "yes"/"no" = explicit
MODEL_OVERRIDE=""
MODEL_OVERRIDE_SET=0
while [ $# -gt 0 ]; do
case "$1" in
--host) [ -z "$2" ] && echo "Missing value for --host (expected claude, codex, kiro, factory, opencode, cursor, slate, openclaw, hermes, gbrain, or auto)" >&2 && exit 1; HOST="$2"; shift 2 ;;
--host=*) HOST="${1#--host=}"; shift ;;
--model) [ -z "$2" ] && echo "Missing value for --model" >&2 && exit 1; MODEL_OVERRIDE="$2"; MODEL_OVERRIDE_SET=1; shift 2 ;;
--model=*) MODEL_OVERRIDE="${1#--model=}"; MODEL_OVERRIDE_SET=1; shift ;;
--local) LOCAL_INSTALL=1; shift ;;
--prefix) SKILL_PREFIX=1; SKILL_PREFIX_FLAG=1; shift ;;
--no-prefix) SKILL_PREFIX=0; SKILL_PREFIX_FLAG=1; shift ;;
@@ -317,6 +323,11 @@ elif [ "$HOST" = "cursor" ]; then
INSTALL_CURSOR=1
fi
if [ "$MODEL_OVERRIDE_SET" -eq 1 ] && [ "$INSTALL_CODEX" -eq 0 ]; then
echo "Error: --model is supported only when Codex is selected (--host codex or --host auto with Codex installed)." >&2
exit 1
fi
migrate_direct_codex_install() {
local gstack_dir="$1"
local codex_gstack="$2"
@@ -534,6 +545,31 @@ cleanup_copied_bun() {
prepare_bun_for_windows_compile
trap cleanup_copied_bun EXIT
# Resolve the model overlay used for generated Codex skills. Setup auto-detects
# only Codex because it has one canonical TOML config surface; direct generator
# calls remain deterministic and use the host default unless --model is explicit.
# The resolver runs on EVERY setup, not just codex installs: step 1b regenerates
# .agents/ unconditionally, and existing ~/.codex/skills symlinks point into it —
# a plain `./setup` on a Sol user's machine must not clobber their profile with
# the hardcoded fallback. The resolver is a read-only TOML lookup that falls
# back to gpt when no Codex config exists.
CODEX_GENERATION_MODEL="gpt"
CODEX_GENERATION_MODEL_SOURCE="default (gpt)"
_CODEX_MODEL_ARGS=(run scripts/resolve-codex-generation-model.ts)
if [ "$MODEL_OVERRIDE_SET" -eq 1 ]; then
_CODEX_MODEL_ARGS+=(--explicit "$MODEL_OVERRIDE")
fi
_CODEX_MODEL_OUTPUT="$(cd "$SOURCE_GSTACK_DIR" && bun_cmd "${_CODEX_MODEL_ARGS[@]}")"
IFS=$'\t' read -r CODEX_GENERATION_MODEL CODEX_GENERATION_MODEL_SOURCE <<< "$_CODEX_MODEL_OUTPUT"
if [ -z "$CODEX_GENERATION_MODEL" ]; then
echo "gstack setup failed: Codex model resolver returned no model" >&2
exit 1
fi
if [ "$INSTALL_CODEX" -eq 1 ] || [ "$CODEX_GENERATION_MODEL" != "gpt" ]; then
log "Codex skill profile: $CODEX_GENERATION_MODEL"
log "Source: $CODEX_GENERATION_MODEL_SOURCE"
fi
# 1. Build browse binary if needed (smart rebuild: stale sources, package.json, lock)
NEEDS_BUILD=0
if [ ! -x "$BROWSE_BIN" ]; then
@@ -632,18 +668,19 @@ fi
# 1b. Generate .agents/ Codex skill docs — always regenerate to prevent stale descriptions.
# .agents/ is no longer committed — generated at setup time from .tmpl templates.
# bun run build already does this, but we need it when NEEDS_BUILD=0 (binary is fresh).
# bun run build generates the host-default artifact. Always render Codex again
# with the resolved user profile so a build cannot overwrite a Sol-specific render.
# Always regenerate: generation is fast (<2s) and mtime-based staleness checks are fragile
# (miss stale files when timestamps match after clone/checkout/upgrade).
AGENTS_DIR="$SOURCE_GSTACK_DIR/.agents/skills"
NEEDS_AGENTS_GEN=1
if [ "$NEEDS_AGENTS_GEN" -eq 1 ] && [ "$NEEDS_BUILD" -eq 0 ]; then
if [ "$NEEDS_AGENTS_GEN" -eq 1 ]; then
log "Generating .agents/ skill docs..."
(
cd "$SOURCE_GSTACK_DIR"
bun_cmd install --frozen-lockfile 2>/dev/null || bun_cmd install
bun_cmd run gen:skill-docs --host codex
bun_cmd run gen:skill-docs --host codex --model "$CODEX_GENERATION_MODEL"
)
fi
@@ -1038,11 +1075,11 @@ link_codex_skill_dirs() {
if [ ! -d "$agents_dir" ]; then
echo " Generating .agents/ skill docs..."
( cd "$gstack_dir" && bun_cmd run gen:skill-docs --host codex )
( cd "$gstack_dir" && bun_cmd run gen:skill-docs --host codex --model "$CODEX_GENERATION_MODEL" )
fi
if [ ! -d "$agents_dir" ]; then
echo " warning: .agents/skills/ generation failed — run 'bun run gen:skill-docs --host codex' manually" >&2
echo " warning: .agents/skills/ generation failed — run 'bun run gen:skill-docs --host codex --model $CODEX_GENERATION_MODEL' manually" >&2
return 1
fi
@@ -1686,6 +1723,12 @@ if [ "$INSTALL_CODEX" -eq 1 ]; then
log "gstack ready (codex)."
log " browse: $BROWSE_BIN"
log " codex skills: $CODEX_SKILLS"
log " model profile: $CODEX_GENERATION_MODEL ($CODEX_GENERATION_MODEL_SOURCE)"
log " model changes: rerun ./setup --host codex"
if [ "$MODEL_OVERRIDE_SET" -eq 1 ]; then
log " note: --model applies to this run only. To persist across upgrades,"
log " set model = \"$MODEL_OVERRIDE\" in \${CODEX_HOME:-~/.codex}/config.toml."
fi
fi
# 6. Install for Kiro CLI (copy from .agents/skills, rewrite paths)
@@ -1694,6 +1737,15 @@ if [ "$INSTALL_KIRO" -eq 1 ]; then
AGENTS_DIR="$SOURCE_GSTACK_DIR/.agents/skills"
mkdir -p "$KIRO_SKILLS"
# Kiro builds from the codex-shaped render but fronts Claude-family models
# (hosts/kiro.ts defaultModel: 'claude'). Re-render with the claude overlay
# before copying so Kiro skills never ship the GPT/Sol behavioral patch;
# the resolved Codex profile is restored right after the copy loop.
if [ "$CODEX_GENERATION_MODEL" != "claude" ]; then
log "Rendering claude-profile skills for Kiro..."
( cd "$SOURCE_GSTACK_DIR" && bun_cmd run gen:skill-docs --host codex --model claude )
fi
# Create gstack dir with symlinks for runtime assets, copy+sed for SKILL.md
KIRO_GSTACK="$KIRO_SKILLS/gstack"
# Remove old whole-dir symlink from previous installs
@@ -1712,9 +1764,15 @@ if [ "$INSTALL_KIRO" -eq 1 ]; then
mkdir -p "$KIRO_GSTACK/supabase"
_link_or_copy "$SOURCE_GSTACK_DIR/supabase/config.sh" "$KIRO_GSTACK/supabase/config.sh"
fi
# gstack-upgrade skill
# gstack-upgrade skill — sed COPY, never a symlink: a symlink would track
# .agents after the Codex-profile restore below (wrong overlay AND a baked
# './setup --host codex' that reinstalls the wrong host on /gstack-upgrade).
if [ -f "$AGENTS_DIR/gstack-upgrade/SKILL.md" ]; then
_link_or_copy "$AGENTS_DIR/gstack-upgrade/SKILL.md" "$KIRO_GSTACK/gstack-upgrade/SKILL.md"
sed -e 's|\$HOME/.codex/skills/gstack|$HOME/.kiro/skills/gstack|g' \
-e "s|~/.codex/skills/gstack|~/.kiro/skills/gstack|g" \
-e "s|~/.claude/skills/gstack|~/.kiro/skills/gstack|g" \
-e 's|\./setup --host codex|./setup --host kiro|g' \
"$AGENTS_DIR/gstack-upgrade/SKILL.md" > "$KIRO_GSTACK/gstack-upgrade/SKILL.md"
fi
# Review runtime assets (individual files, not whole dir)
for f in checklist.md design-checklist.md greptile-triage.md TODOS-format.md; do
@@ -1738,10 +1796,12 @@ if [ "$INSTALL_KIRO" -eq 1 ]; then
target_dir="$KIRO_SKILLS/$skill_name"
mkdir -p "$target_dir"
# Generated Codex skills use $HOME/.codex (not ~/), plus $GSTACK_ROOT variables.
# Rewrite the default GSTACK_ROOT value and any remaining literal paths.
# Rewrite the default GSTACK_ROOT value, any remaining literal paths, and
# the SETUP_COMMAND host (the artifact was rendered for codex).
sed -e 's|\$HOME/.codex/skills/gstack|$HOME/.kiro/skills/gstack|g' \
-e "s|~/.codex/skills/gstack|~/.kiro/skills/gstack|g" \
-e "s|~/.claude/skills/gstack|~/.kiro/skills/gstack|g" \
-e 's|\./setup --host codex|./setup --host kiro|g' \
"$skill_dir/SKILL.md" > "$target_dir/SKILL.md"
# Carved skills (v2 plan T9): rewrite + copy each sections/*.md the same way,
# so a runtime "Read sections/<name>.md" resolves under ~/.kiro and doesn't
@@ -1754,6 +1814,7 @@ if [ "$INSTALL_KIRO" -eq 1 ]; then
sed -e 's|\$HOME/.codex/skills/gstack|$HOME/.kiro/skills/gstack|g' \
-e "s|~/.codex/skills/gstack|~/.kiro/skills/gstack|g" \
-e "s|~/.claude/skills/gstack|~/.kiro/skills/gstack|g" \
-e 's|\./setup --host codex|./setup --host kiro|g' \
"$section_file" > "$target_dir/sections/$(basename "$section_file")"
done
fi
@@ -1762,6 +1823,12 @@ if [ "$INSTALL_KIRO" -eq 1 ]; then
echo " browse: $BROWSE_BIN"
echo " kiro skills: $KIRO_SKILLS"
fi
# Restore the resolved Codex profile — ~/.codex/skills symlinks point into
# .agents/skills, so the tree must not stay on the Kiro claude render.
if [ "$CODEX_GENERATION_MODEL" != "claude" ]; then
( cd "$SOURCE_GSTACK_DIR" && bun_cmd run gen:skill-docs --host codex --model "$CODEX_GENERATION_MODEL" )
fi
fi
# 6b. Install for Factory Droid