feat: multi-agent support — gstack works on Codex, Gemini CLI, and Cursor (v0.9.0) (#226)

* refactor: host-aware gen-skill-docs + --host codex generation

Refactor gen-skill-docs.ts for multi-agent support:
- Add Host type, HostPaths interface, HOST_PATHS config
- Decompose generatePreamble() into 7 composable sub-functions
- Replace all hardcoded .claude/skills/gstack paths with ctx.paths
- Replace static findTemplates() list with dynamic filesystem scan
- Add --host codex|agents flag (aliases, same output)
- Add processTemplate host routing to .agents/skills/gstack-*/
- Add codexSkillName() with double-prefix prevention
- Add transformFrontmatter() — keeps only name + description for Codex
- Add extractHookSafetyProse() — converts hooks to inline advisory
- Add body text path rewriting for remaining hardcoded paths
- Exclude /codex skill from Codex generation (self-referential)

Claude output is unchanged (verified via --dry-run).
SKILL.md is an open standard: .agents/skills/ works on Codex, Gemini CLI, and Cursor.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: generate Codex/Gemini/Cursor skills into .agents/skills/

Generated 21 skill files for the open SKILL.md standard:
- Output: .agents/skills/gstack-*/SKILL.md (one per skill)
- Frontmatter: name + description only (no allowed-tools/version)
- No .claude/skills/ paths in any generated file
- /codex skill excluded (Claude wrapper, self-referential on Codex)
- Hook skills (careful/freeze/guard) get inline safety prose
- Build script generates both hosts: bun run build

Supported agents (all read .agents/skills/):
- Codex CLI
- Gemini CLI
- Cursor

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: dual-host setup + find-browse for Codex/Gemini/Cursor

- setup: add --host codex|claude|auto flag, install to ~/.codex/skills/
  when targeting Codex, auto-detect installed agents
- find-browse: priority chain .codex > .agents > .claude (both
  workspace-local and global)
- dev-setup/teardown: create .agents/skills/gstack symlinks for dev mode

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* test: Codex generation tests + CI + docs for multi-agent support

Tests (28 new):
- Codex output path routing, frontmatter validation (name+description only)
- No .claude/skills/ path leaks in Codex output (regression guard)
- /codex skill exclusion, hook→prose conversion, multiline YAML
- --host agents alias, dynamic template discovery
- Codex skill validation + $B command validation
- find-browse priority chain verification
- Replace static ALL_SKILLS list with dynamic filesystem scan

CI:
- Add Codex freshness check to skill-docs workflow

Docs:
- AGENTS.md: Codex-facing project instructions
- README: multi-agent installation section
- CONTRIBUTING: dual-host development workflow
- CHANGELOG: v0.9.0 multi-agent support entry

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat: Codex E2E test harness — verify skills work on Codex CLI

New test infrastructure:
- CodexSessionRunner: spawns codex exec, parses JSONL stream, returns
  structured results (output, reasoning, toolCalls, tokens)
- JSONL parser ported from Python (codex/SKILL.md.tmpl) to TypeScript
- Temp HOME skill installation for Codex discovery testing

E2E tests (gated behind EVALS=1 + codex + OPENAI_API_KEY):
- codex-discover-skill: installs skill, verifies Codex finds it
- codex-review-findings: runs gstack-review via Codex, validates output

Integrates with existing eval infrastructure:
- Diff-based test selection via touchfiles
- Eval persistence via EvalCollector
- bun run test:codex / test:codex:all convenience scripts

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: bump VERSION to 0.9.0 to match CHANGELOG

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: Codex sidecar paths + setup installs generated skills

Two bugs found by Codex adversarial review:

1. Sidecar path mismatch: generated Codex skills referenced
   .agents/skills/gstack-review/checklist.md but setup creates
   sidecars at .agents/skills/gstack/review/. Fixed path rewriter
   to emit .agents/skills/gstack/review/ (matching setup layout).

2. Setup installed Claude-format source dirs for Codex global
   install instead of the generated Codex-format skills. Split
   link_skill_dirs into link_claude_skill_dirs (source dirs for
   Claude) and link_codex_skill_dirs (generated .agents/skills/
   gstack-* dirs for Codex).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* test: comprehensive Codex path rewriting + setup install tests

17 new tests covering:
- Sidecar path rewriting: .claude/skills/review → .agents/skills/gstack/review/
  (catches the bug where checklist.md was unreachable at gstack-review/)
- All 4 path rewrite rules tested individually across all skills
- Greptile triage sidecar path correctness
- Ship skill sidecar paths for pre-landing review
- Claude output regression guard: zero Codex paths in any Claude skill
- Setup script validation: separate link functions for Claude vs Codex,
  link_codex_skill_dirs reads from .agents/skills/, create_agents_sidecar
  links runtime assets (bin, browse, review, qa)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: regenerate Codex skills after investigate rename merge

Remove stale gstack-debug, add gstack-investigate, regenerate all
Codex skills to pick up changes merged from main (investigate rename,
platform-agnostic templates, review helpers).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: Codex E2E uses ~/.codex/ auth, not OPENAI_API_KEY

- Remove OPENAI_API_KEY gate from test prerequisites
- Copy real ~/.codex/ auth config into temp HOME so codex can authenticate
- Increase review test timeout to 540s (codex does thorough 60+ tool call reviews)
- Document in CLAUDE.md that Codex uses its own auth config

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-03-19 18:20:50 -07:00
committed by GitHub
parent 3b22fc39e6
commit 8ddfab233d
42 changed files with 12244 additions and 146 deletions
+134 -15
View File
@@ -1,5 +1,5 @@
#!/usr/bin/env bash
# gstack setup — build browser binary + register all skills with Claude Code
# gstack setup — build browser binary + register skills with Claude Code / Codex
set -e
if ! command -v bun >/dev/null 2>&1; then
@@ -12,6 +12,37 @@ GSTACK_DIR="$(cd "$(dirname "$0")" && pwd)"
SKILLS_DIR="$(dirname "$GSTACK_DIR")"
BROWSE_BIN="$GSTACK_DIR/browse/dist/browse"
# ─── Parse --host flag ─────────────────────────────────────────
HOST="claude"
while [ $# -gt 0 ]; do
case "$1" in
--host) HOST="$2"; shift 2 ;;
--host=*) HOST="${1#--host=}"; shift ;;
*) shift ;;
esac
done
case "$HOST" in
claude|codex|auto) ;;
*) echo "Unknown --host value: $HOST (expected claude, codex, or auto)" >&2; exit 1 ;;
esac
# For auto: detect which agents are installed
INSTALL_CLAUDE=0
INSTALL_CODEX=0
if [ "$HOST" = "auto" ]; then
command -v claude >/dev/null 2>&1 && INSTALL_CLAUDE=1
command -v codex >/dev/null 2>&1 && INSTALL_CODEX=1
# If neither found, default to claude
if [ "$INSTALL_CLAUDE" -eq 0 ] && [ "$INSTALL_CODEX" -eq 0 ]; then
INSTALL_CLAUDE=1
fi
elif [ "$HOST" = "claude" ]; then
INSTALL_CLAUDE=1
elif [ "$HOST" = "codex" ]; then
INSTALL_CODEX=1
fi
ensure_playwright_browser() {
(
cd "$GSTACK_DIR"
@@ -66,16 +97,17 @@ fi
# 3. Ensure ~/.gstack global state directory exists
mkdir -p "$HOME/.gstack/projects"
# 4. Only create skill symlinks if we're inside a .claude/skills directory
SKILLS_BASENAME="$(basename "$SKILLS_DIR")"
if [ "$SKILLS_BASENAME" = "skills" ]; then
linked=()
for skill_dir in "$GSTACK_DIR"/*/; do
# ─── Helper: link Claude skill subdirectories into a skills parent directory ──
link_claude_skill_dirs() {
local gstack_dir="$1"
local skills_dir="$2"
local linked=()
for skill_dir in "$gstack_dir"/*/; do
if [ -f "$skill_dir/SKILL.md" ]; then
skill_name="$(basename "$skill_dir")"
# Skip node_modules
[ "$skill_name" = "node_modules" ] && continue
target="$SKILLS_DIR/$skill_name"
target="$skills_dir/$skill_name"
# Create or update symlink; skip if a real file/directory exists
if [ -L "$target" ] || [ ! -e "$target" ]; then
ln -snf "gstack/$skill_name" "$target"
@@ -83,19 +115,106 @@ if [ "$SKILLS_BASENAME" = "skills" ]; then
fi
fi
done
echo "gstack ready."
echo " browse: $BROWSE_BIN"
if [ ${#linked[@]} -gt 0 ]; then
echo " linked skills: ${linked[*]}"
fi
else
echo "gstack ready."
echo " browse: $BROWSE_BIN"
echo " (skipped skill symlinks — not inside .claude/skills/)"
}
# ─── Helper: link generated Codex skills into a skills parent directory ──
# Installs from .agents/skills/gstack-* (the generated Codex-format skills)
# instead of source dirs (which have Claude paths).
link_codex_skill_dirs() {
local gstack_dir="$1"
local skills_dir="$2"
local agents_dir="$gstack_dir/.agents/skills"
local linked=()
if [ ! -d "$agents_dir" ]; then
echo " warning: no .agents/skills/ directory found — run 'bun run build' first" >&2
return 1
fi
for skill_dir in "$agents_dir"/gstack*/; do
if [ -f "$skill_dir/SKILL.md" ]; then
skill_name="$(basename "$skill_dir")"
target="$skills_dir/$skill_name"
# Create or update symlink
if [ -L "$target" ] || [ ! -e "$target" ]; then
ln -snf "$skill_dir" "$target"
linked+=("$skill_name")
fi
fi
done
if [ ${#linked[@]} -gt 0 ]; then
echo " linked skills: ${linked[*]}"
fi
}
# ─── Helper: create .agents/skills/gstack/ sidecar symlinks ──────────
# Codex/Gemini/Cursor read skills from .agents/skills/. We link runtime
# assets (bin/, browse/dist/, review/, qa/, etc.) so skill templates can
# resolve paths like $SKILL_ROOT/review/design-checklist.md.
create_agents_sidecar() {
local repo_root="$1"
local agents_gstack="$repo_root/.agents/skills/gstack"
mkdir -p "$agents_gstack"
# Sidecar directories that skills reference at runtime
for asset in bin browse review qa; do
local src="$GSTACK_DIR/$asset"
local dst="$agents_gstack/$asset"
if [ -d "$src" ] || [ -f "$src" ]; then
if [ -L "$dst" ] || [ ! -e "$dst" ]; then
ln -snf "$src" "$dst"
fi
fi
done
}
# 4. Install for Claude (default)
SKILLS_BASENAME="$(basename "$SKILLS_DIR")"
if [ "$INSTALL_CLAUDE" -eq 1 ]; then
if [ "$SKILLS_BASENAME" = "skills" ]; then
link_claude_skill_dirs "$GSTACK_DIR" "$SKILLS_DIR"
echo "gstack ready (claude)."
echo " browse: $BROWSE_BIN"
else
echo "gstack ready (claude)."
echo " browse: $BROWSE_BIN"
echo " (skipped skill symlinks — not inside .claude/skills/)"
fi
fi
# 4. First-time welcome + legacy cleanup
# 5. Install for Codex
if [ "$INSTALL_CODEX" -eq 1 ]; then
CODEX_SKILLS="$HOME/.codex/skills"
CODEX_GSTACK="$CODEX_SKILLS/gstack"
mkdir -p "$CODEX_SKILLS"
# Symlink gstack source for runtime assets (bin/, browse/dist/)
if [ -L "$CODEX_GSTACK" ] || [ ! -e "$CODEX_GSTACK" ]; then
ln -snf "$GSTACK_DIR" "$CODEX_GSTACK"
fi
# Install generated Codex-format skills (not Claude source dirs)
link_codex_skill_dirs "$GSTACK_DIR" "$CODEX_SKILLS"
echo "gstack ready (codex)."
echo " browse: $BROWSE_BIN"
echo " codex skills: $CODEX_SKILLS"
fi
# 6. Create .agents/ sidecar symlinks (useful for Codex/Gemini/Cursor workspace-local)
if [ "$INSTALL_CODEX" -eq 1 ]; then
# Detect repo root: if we're inside a skills directory, go up two levels
if [ "$SKILLS_BASENAME" = "skills" ]; then
REPO_ROOT="$(dirname "$SKILLS_DIR")"
else
REPO_ROOT="$GSTACK_DIR"
fi
create_agents_sidecar "$REPO_ROOT"
fi
# 7. First-time welcome + legacy cleanup
if [ ! -d "$HOME/.gstack" ]; then
mkdir -p "$HOME/.gstack"
echo " Welcome! Run /gstack-upgrade anytime to stay current."