mirror of https://github.com/garrytan/gstack.git
Merge f44448ff9b into 2beb636f7c
This commit is contained in:
Mattias Petersson
GitHub
commit
57df4277b7
|
|
@ -23,6 +23,7 @@ bin/gstack-global-discover*
|
|||
.hermes/
|
||||
.gbrain/
|
||||
.gbrain-source
|
||||
.gemini/
|
||||
.context/
|
||||
extension/.auth.json
|
||||
# xterm assets are vendored from npm at build time; not source-of-truth.
|
||||
|
|
|
|||
22
CHANGELOG.md
22
CHANGELOG.md
|
|
@ -1,5 +1,27 @@
|
|||
# Changelog
|
||||
|
||||
## [1.61.0.0] - 2026-07-12
|
||||
|
||||
## **Permanent Antigravity (Agy) integration and benchmark support are live.**
|
||||
## **gstack now runs on Agy, registers/updates plugins automatically, and supports Agy model benchmarks.**
|
||||
|
||||
Agy integration is now permanent and first-class. Running setup with `--host agy` generates and imports Agy-compatible skills, excludes incompatible skills, and registers the gstack plugin in Agy's plugin configuration. This release also fixes several test-suite and helper issues that were causing CI failures, and adds Agy model benchmarking.
|
||||
|
||||
### Itemized changes
|
||||
|
||||
#### Added
|
||||
|
||||
- `hosts/agy.ts`: Declarative host configuration for Agy.
|
||||
- `test/helpers/providers/agy.ts`: Agy benchmark runner adapter that executes `agy --print` with safely skipped permissions.
|
||||
- `docs/AGY.md`: User documentation for Agy installation and integration.
|
||||
|
||||
#### Fixed
|
||||
|
||||
- `setup`: Support `--host agy` flag, build `plugin.json` and skill directories under `.gemini/config/plugins/gstack`, and trigger `agy plugin install`.
|
||||
- `bin/gstack-codex-session-import`: Added `-r` flag to `xargs` pipeline to prevent listing files in current directory when empty.
|
||||
- `test/gbrain-detect-install.test.ts`: Appended bun's executable directory to test environment `PATH` to resolve shebang resolution failures.
|
||||
- `test/gbrain-refresh-install-render.test.ts`: Resolved regex pattern mismatch in status check.
|
||||
|
||||
## [1.60.1.0] - 2026-07-09
|
||||
|
||||
## **The /autoplan dual-voice eval is back on the board, catching real regressions.**
|
||||
|
|
|
|||
|
|
@ -65,7 +65,7 @@ case "$MODE" in
|
|||
exit 0
|
||||
fi
|
||||
LATEST=$(find "$CODEX_SESSIONS_ROOT" -type f -name "rollout-*.jsonl" -print 2>/dev/null \
|
||||
| xargs ls -t 2>/dev/null | head -1 || true)
|
||||
| xargs -r ls -t 2>/dev/null | head -1 || true)
|
||||
if [ -z "$LATEST" ]; then
|
||||
echo "NO_SESSIONS: no rollout-*.jsonl files under $CODEX_SESSIONS_ROOT"
|
||||
exit 0
|
||||
|
|
|
|||
|
|
@ -31,11 +31,13 @@ import { runBenchmark, formatTable, formatJson, formatMarkdown, type BenchmarkIn
|
|||
import { ClaudeAdapter } from '../test/helpers/providers/claude';
|
||||
import { GptAdapter } from '../test/helpers/providers/gpt';
|
||||
import { GeminiAdapter } from '../test/helpers/providers/gemini';
|
||||
import { AgyAdapter } from '../test/helpers/providers/agy';
|
||||
|
||||
const ADAPTER_FACTORIES = {
|
||||
claude: () => new ClaudeAdapter(),
|
||||
gpt: () => new GptAdapter(),
|
||||
gemini: () => new GeminiAdapter(),
|
||||
agy: () => new AgyAdapter(),
|
||||
};
|
||||
|
||||
type OutputFormat = 'table' | 'json' | 'markdown';
|
||||
|
|
@ -76,13 +78,13 @@ function positionalArgs(args: string[]): string[] {
|
|||
return positional;
|
||||
}
|
||||
|
||||
function parseProviders(s: string | undefined): Array<'claude' | 'gpt' | 'gemini'> {
|
||||
function parseProviders(s: string | undefined): Array<'claude' | 'gpt' | 'gemini' | 'agy'> {
|
||||
if (!s) return ['claude'];
|
||||
const seen = new Set<'claude' | 'gpt' | 'gemini'>();
|
||||
const seen = new Set<'claude' | 'gpt' | 'gemini' | 'agy'>();
|
||||
for (const p of s.split(',').map(x => x.trim()).filter(Boolean)) {
|
||||
if (p === 'claude' || p === 'gpt' || p === 'gemini') seen.add(p);
|
||||
if (p === 'claude' || p === 'gpt' || p === 'gemini' || p === 'agy') seen.add(p);
|
||||
else {
|
||||
console.error(`WARN: unknown provider '${p}' — skipping. Valid: claude, gpt, gemini.`);
|
||||
console.error(`WARN: unknown provider '${p}' — skipping. Valid: claude, gpt, gemini, agy.`);
|
||||
}
|
||||
}
|
||||
return seen.size ? Array.from(seen) : ['claude'];
|
||||
|
|
@ -149,7 +151,7 @@ async function main(): Promise<void> {
|
|||
|
||||
async function dryRunReport(opts: {
|
||||
prompt: string;
|
||||
providers: Array<'claude' | 'gpt' | 'gemini'>;
|
||||
providers: Array<'claude' | 'gpt' | 'gemini' | 'agy'>;
|
||||
workdir: string;
|
||||
timeoutMs: number;
|
||||
output: OutputFormat;
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
# Adding a New Host to gstack
|
||||
|
||||
gstack uses a declarative host config system. Each supported AI coding agent
|
||||
(Claude, Codex, Factory, Kiro, OpenCode, Slate, Cursor, OpenClaw) is defined
|
||||
(Claude, Codex, Factory, Kiro, OpenCode, Slate, Cursor, OpenClaw, Hermes, GBrain, Agy) is defined
|
||||
as a typed TypeScript config object. Adding a new host means creating one file
|
||||
and re-exporting it. Zero code changes to the generator, setup, or tooling.
|
||||
|
||||
|
|
@ -17,6 +17,9 @@ hosts/
|
|||
├── slate.ts # Slate (Random Labs)
|
||||
├── cursor.ts # Cursor
|
||||
├── openclaw.ts # OpenClaw (hybrid: config + adapter)
|
||||
├── hermes.ts # Hermes
|
||||
├── gbrain.ts # GBrain
|
||||
├── agy.ts # Google Antigravity
|
||||
└── index.ts # Registry: imports all, derives Host type
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,71 @@
|
|||
# Google Antigravity (Agy) Integration
|
||||
|
||||
gstack supports Google Antigravity (Agy) as a first-class agent host. This integration allows you to generate and run Agy-compatible skills, load them dynamically via the `agy` plugin system, and benchmark agy models alongside Claude, OpenAI, and Gemini.
|
||||
|
||||
## Features
|
||||
|
||||
- **Automatic Setup**: Installs gstack skills directly into the Antigravity config directory via `./setup --host agy`.
|
||||
- **Agy Plugin Compatibility**: Packages skills as a standard Agy plugin with a `plugin.json` manifest, automatically registered with `agy plugin install`.
|
||||
- **Exclusion of Incompatible Skills**: Automatically filters out Claude-specific wrappers (like `gstack-codex`) from Agy generation.
|
||||
- **Benchmark Integration**: Register Agy as a benchmark provider using `agy --print` to trace latency, quality, and tokens.
|
||||
|
||||
---
|
||||
|
||||
## Setup & Installation
|
||||
|
||||
To generate and install gstack skills into your local Antigravity environment:
|
||||
|
||||
```bash
|
||||
./setup --host agy
|
||||
```
|
||||
|
||||
### What Setup Does
|
||||
|
||||
1. **Precompile & Prepare**: Ensures the browse tool and other runtime dependencies are compiled.
|
||||
2. **Generate Skills**: Runs `bun run gen:skill-docs --host agy` to generate Agy-compatible frontmatter.
|
||||
3. **Initialize Plugin**: Creates the plugin directory structure under `.gemini/config/plugins/gstack`.
|
||||
4. **Symlink/Copy Assets**: Places necessary executables (`bin`, `browse`, `review`, `qa`) into the plugin root.
|
||||
5. **Register Plugin**: Invokes `agy plugin install` to import the gstack plugin into `~/.gemini/config/import_manifest.json`.
|
||||
|
||||
---
|
||||
|
||||
## Plugin Structure
|
||||
|
||||
When installed, the gstack plugin resides at:
|
||||
`~/.gemini/config/plugins/gstack/`
|
||||
|
||||
The directory layout matches the standard Agy plugin structure:
|
||||
|
||||
```
|
||||
~/.gemini/config/plugins/gstack/
|
||||
├── plugin.json # Manifest declaring name, version, and license
|
||||
├── skills/ # Generated Agy-compatible skills
|
||||
│ ├── gstack/ # Root gstack skill (/gstack)
|
||||
│ ├── gstack-qa/ # QA testing skill (/qa)
|
||||
│ └── ...
|
||||
├── bin/ # Shared executables and CLI tools
|
||||
└── browse/ # Browse tool distribution files
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Benchmarking with Agy
|
||||
|
||||
Agy is registered as a model benchmark provider. You can execute prompts against Agy using the gstack benchmark runner.
|
||||
|
||||
### Pre-requisites
|
||||
- The `agy` CLI must be installed and available in your `PATH`.
|
||||
- Credentials must be configured in `~/.gemini/oauth_creds.json`.
|
||||
|
||||
### Run Benchmark
|
||||
To run a dry run and check availability:
|
||||
```bash
|
||||
gstack-model-benchmark --models agy --dry-run
|
||||
```
|
||||
|
||||
To execute a benchmark run:
|
||||
```bash
|
||||
gstack-model-benchmark --models agy --prompt "Explain quantum computing in one sentence."
|
||||
```
|
||||
|
||||
The runner automatically passes `--dangerously-skip-permissions` to the CLI to run headless without hanging on interactive permission prompts.
|
||||
|
|
@ -0,0 +1,59 @@
|
|||
import type { HostConfig } from '../scripts/host-config';
|
||||
|
||||
const agy: HostConfig = {
|
||||
name: 'agy',
|
||||
displayName: 'Antigravity',
|
||||
cliCommand: 'agy',
|
||||
cliAliases: [],
|
||||
|
||||
globalRoot: '.gemini/config/plugins/gstack/skills',
|
||||
localSkillRoot: '.gemini/config/plugins/gstack/skills',
|
||||
hostSubdir: '.gemini/config/plugins/gstack',
|
||||
usesEnvVars: true,
|
||||
|
||||
frontmatter: {
|
||||
mode: 'allowlist',
|
||||
keepFields: [
|
||||
'name',
|
||||
'preamble-tier',
|
||||
'version',
|
||||
'description',
|
||||
'allowed-tools',
|
||||
'triggers',
|
||||
'hooks',
|
||||
'gbrain',
|
||||
],
|
||||
descriptionLimit: null,
|
||||
},
|
||||
|
||||
generation: {
|
||||
generateMetadata: false,
|
||||
skipSkills: ['codex'],
|
||||
},
|
||||
|
||||
pathRewrites: [
|
||||
{ from: '~/.claude/skills/gstack', to: '$GSTACK_ROOT' },
|
||||
{ from: '.claude/skills/gstack', to: '.gemini/config/plugins/gstack/skills' },
|
||||
{ from: '.claude/skills', to: '.gemini/config/plugins/gstack' },
|
||||
],
|
||||
|
||||
toolRewrites: {},
|
||||
|
||||
suppressedResolvers: ['GBRAIN_CONTEXT_LOAD', 'GBRAIN_SAVE_RESULTS'],
|
||||
|
||||
runtimeRoot: {
|
||||
globalSymlinks: ['bin', 'browse/dist', 'browse/bin', 'gstack-upgrade', 'ETHOS.md'],
|
||||
globalFiles: {
|
||||
'review': ['checklist.md', 'TODOS-format.md'],
|
||||
},
|
||||
},
|
||||
|
||||
install: {
|
||||
prefixable: false,
|
||||
linkingStrategy: 'symlink-generated',
|
||||
},
|
||||
|
||||
learningsMode: 'basic',
|
||||
};
|
||||
|
||||
export default agy;
|
||||
|
|
@ -16,9 +16,10 @@ import cursor from './cursor';
|
|||
import openclaw from './openclaw';
|
||||
import hermes from './hermes';
|
||||
import gbrain from './gbrain';
|
||||
import agy from './agy';
|
||||
|
||||
/** All registered host configs. Add new hosts here. */
|
||||
export const ALL_HOST_CONFIGS: HostConfig[] = [claude, codex, factory, kiro, opencode, slate, cursor, openclaw, hermes, gbrain];
|
||||
export const ALL_HOST_CONFIGS: HostConfig[] = [claude, codex, factory, kiro, opencode, slate, cursor, openclaw, hermes, gbrain, agy];
|
||||
|
||||
/** Map from host name to config. */
|
||||
export const HOST_CONFIG_MAP: Record<string, HostConfig> = Object.fromEntries(
|
||||
|
|
@ -65,4 +66,4 @@ export function getExternalHosts(): HostConfig[] {
|
|||
}
|
||||
|
||||
// Re-export individual configs for direct import
|
||||
export { claude, codex, factory, kiro, opencode, slate, cursor, openclaw, hermes, gbrain };
|
||||
export { claude, codex, factory, kiro, opencode, slate, cursor, openclaw, hermes, gbrain, agy };
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
{
|
||||
"name": "gstack",
|
||||
"version": "1.60.1.0",
|
||||
"version": "1.61.0.0",
|
||||
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
|
||||
"license": "MIT",
|
||||
"type": "module",
|
||||
|
|
|
|||
124
setup
124
setup
|
|
@ -24,6 +24,9 @@ FACTORY_SKILLS="$HOME/.factory/skills"
|
|||
FACTORY_GSTACK="$FACTORY_SKILLS/gstack"
|
||||
OPENCODE_SKILLS="$HOME/.config/opencode/skills"
|
||||
OPENCODE_GSTACK="$OPENCODE_SKILLS/gstack"
|
||||
AGY_PLUGINS="$HOME/.gemini/config/plugins"
|
||||
AGY_GSTACK="$AGY_PLUGINS/gstack"
|
||||
AGY_SKILLS="$AGY_GSTACK/skills"
|
||||
|
||||
IS_WINDOWS=0
|
||||
case "$(uname -s)" in
|
||||
|
|
@ -85,7 +88,7 @@ NO_TEAM_MODE=0
|
|||
PLAN_TUNE_HOOKS_MODE="" # "" = resolve from env/config/prompt; "yes"/"no" = explicit
|
||||
while [ $# -gt 0 ]; do
|
||||
case "$1" in
|
||||
--host) [ -z "$2" ] && echo "Missing value for --host (expected claude, codex, kiro, factory, opencode, openclaw, hermes, gbrain, or auto)" >&2 && exit 1; HOST="$2"; shift 2 ;;
|
||||
--host) [ -z "$2" ] && echo "Missing value for --host (expected claude, codex, kiro, factory, opencode, openclaw, hermes, gbrain, agy, or auto)" >&2 && exit 1; HOST="$2"; shift 2 ;;
|
||||
--host=*) HOST="${1#--host=}"; shift ;;
|
||||
--local) LOCAL_INSTALL=1; shift ;;
|
||||
--prefix) SKILL_PREFIX=1; SKILL_PREFIX_FLAG=1; shift ;;
|
||||
|
|
@ -101,7 +104,7 @@ while [ $# -gt 0 ]; do
|
|||
done
|
||||
|
||||
case "$HOST" in
|
||||
claude|codex|kiro|factory|opencode|auto) ;;
|
||||
claude|codex|kiro|factory|opencode|agy|auto) ;;
|
||||
openclaw)
|
||||
echo ""
|
||||
echo "OpenClaw integration uses a different model — OpenClaw spawns Claude Code"
|
||||
|
|
@ -136,7 +139,7 @@ case "$HOST" in
|
|||
echo "GBrain setup and brain skills ship from the GBrain repo."
|
||||
echo ""
|
||||
exit 0 ;;
|
||||
*) echo "Unknown --host value: $HOST (expected claude, codex, kiro, factory, opencode, openclaw, hermes, gbrain, or auto)" >&2; exit 1 ;;
|
||||
*) echo "Unknown --host value: $HOST (expected claude, codex, kiro, factory, opencode, openclaw, hermes, gbrain, agy, or auto)" >&2; exit 1 ;;
|
||||
esac
|
||||
|
||||
# ─── Resolve skill prefix preference ─────────────────────────
|
||||
|
|
@ -200,14 +203,16 @@ INSTALL_CODEX=0
|
|||
INSTALL_KIRO=0
|
||||
INSTALL_FACTORY=0
|
||||
INSTALL_OPENCODE=0
|
||||
INSTALL_AGY=0
|
||||
if [ "$HOST" = "auto" ]; then
|
||||
command -v claude >/dev/null 2>&1 && INSTALL_CLAUDE=1
|
||||
command -v codex >/dev/null 2>&1 && INSTALL_CODEX=1
|
||||
command -v kiro-cli >/dev/null 2>&1 && INSTALL_KIRO=1
|
||||
command -v droid >/dev/null 2>&1 && INSTALL_FACTORY=1
|
||||
command -v opencode >/dev/null 2>&1 && INSTALL_OPENCODE=1
|
||||
command -v agy >/dev/null 2>&1 && INSTALL_AGY=1
|
||||
# If none found, default to claude
|
||||
if [ "$INSTALL_CLAUDE" -eq 0 ] && [ "$INSTALL_CODEX" -eq 0 ] && [ "$INSTALL_KIRO" -eq 0 ] && [ "$INSTALL_FACTORY" -eq 0 ] && [ "$INSTALL_OPENCODE" -eq 0 ]; then
|
||||
if [ "$INSTALL_CLAUDE" -eq 0 ] && [ "$INSTALL_CODEX" -eq 0 ] && [ "$INSTALL_KIRO" -eq 0 ] && [ "$INSTALL_FACTORY" -eq 0 ] && [ "$INSTALL_OPENCODE" -eq 0 ] && [ "$INSTALL_AGY" -eq 0 ]; then
|
||||
INSTALL_CLAUDE=1
|
||||
fi
|
||||
elif [ "$HOST" = "claude" ]; then
|
||||
|
|
@ -220,6 +225,8 @@ elif [ "$HOST" = "factory" ]; then
|
|||
INSTALL_FACTORY=1
|
||||
elif [ "$HOST" = "opencode" ]; then
|
||||
INSTALL_OPENCODE=1
|
||||
elif [ "$HOST" = "agy" ]; then
|
||||
INSTALL_AGY=1
|
||||
fi
|
||||
|
||||
migrate_direct_codex_install() {
|
||||
|
|
@ -475,6 +482,16 @@ if [ "$INSTALL_OPENCODE" -eq 1 ] && [ "$NEEDS_BUILD" -eq 0 ]; then
|
|||
)
|
||||
fi
|
||||
|
||||
# 1e. Generate .gemini/ Agy skill docs
|
||||
if [ "$INSTALL_AGY" -eq 1 ] && [ "$NEEDS_BUILD" -eq 0 ]; then
|
||||
log "Generating .gemini/ skill docs..."
|
||||
(
|
||||
cd "$SOURCE_GSTACK_DIR"
|
||||
bun_cmd install --frozen-lockfile 2>/dev/null || bun_cmd install
|
||||
bun_cmd run gen:skill-docs --host agy
|
||||
)
|
||||
fi
|
||||
|
||||
# 2. Ensure Playwright's Chromium is available
|
||||
if ! ensure_playwright_browser; then
|
||||
echo "Installing Playwright Chromium..."
|
||||
|
|
@ -972,6 +989,88 @@ link_opencode_skill_dirs() {
|
|||
fi
|
||||
}
|
||||
|
||||
create_agy_runtime_root() {
|
||||
local gstack_dir="$1"
|
||||
local agy_gstack="$2"
|
||||
local agy_dir="$gstack_dir/.gemini/config/plugins/gstack/skills"
|
||||
|
||||
if [ -L "$agy_gstack" ]; then
|
||||
rm -f "$agy_gstack"
|
||||
elif [ -d "$agy_gstack" ] && [ "$agy_gstack" != "$gstack_dir" ]; then
|
||||
rm -rf "$agy_gstack"
|
||||
fi
|
||||
|
||||
mkdir -p "$agy_gstack" "$agy_gstack/browse" "$agy_gstack/design" "$agy_gstack/gstack-upgrade" "$agy_gstack/review" "$agy_gstack/qa" "$agy_gstack/plan-devex-review" "$agy_gstack/skills"
|
||||
|
||||
# Create plugin.json for agy plugin structure
|
||||
echo '{"name": "gstack", "version": "1.58.5.0", "description": "gstack skills for Google Antigravity", "author": {"name": "gstack"}, "license": "MIT"}' > "$agy_gstack/plugin.json"
|
||||
|
||||
if [ -d "$gstack_dir/bin" ]; then
|
||||
_link_or_copy "$gstack_dir/bin" "$agy_gstack/bin"
|
||||
fi
|
||||
if [ -d "$gstack_dir/browse/dist" ]; then
|
||||
_link_or_copy "$gstack_dir/browse/dist" "$agy_gstack/browse/dist"
|
||||
fi
|
||||
if [ -d "$gstack_dir/browse/bin" ]; then
|
||||
_link_or_copy "$gstack_dir/browse/bin" "$agy_gstack/browse/bin"
|
||||
fi
|
||||
if [ -d "$gstack_dir/design/dist" ]; then
|
||||
_link_or_copy "$gstack_dir/design/dist" "$agy_gstack/design/dist"
|
||||
fi
|
||||
for f in checklist.md design-checklist.md greptile-triage.md TODOS-format.md; do
|
||||
if [ -f "$gstack_dir/review/$f" ]; then
|
||||
_link_or_copy "$gstack_dir/review/$f" "$agy_gstack/review/$f"
|
||||
fi
|
||||
done
|
||||
if [ -d "$gstack_dir/review/specialists" ]; then
|
||||
_link_or_copy "$gstack_dir/review/specialists" "$agy_gstack/review/specialists"
|
||||
fi
|
||||
if [ -d "$gstack_dir/qa/templates" ]; then
|
||||
_link_or_copy "$gstack_dir/qa/templates" "$agy_gstack/qa/templates"
|
||||
fi
|
||||
if [ -d "$gstack_dir/qa/references" ]; then
|
||||
_link_or_copy "$gstack_dir/qa/references" "$agy_gstack/qa/references"
|
||||
fi
|
||||
if [ -f "$gstack_dir/plan-devex-review/dx-hall-of-fame.md" ]; then
|
||||
_link_or_copy "$gstack_dir/plan-devex-review/dx-hall-of-fame.md" "$agy_gstack/plan-devex-review/dx-hall-of-fame.md"
|
||||
fi
|
||||
if [ -f "$gstack_dir/ETHOS.md" ]; then
|
||||
_link_or_copy "$gstack_dir/ETHOS.md" "$agy_gstack/ETHOS.md"
|
||||
fi
|
||||
}
|
||||
|
||||
link_agy_skill_dirs() {
|
||||
local gstack_dir="$1"
|
||||
local skills_dir="$2"
|
||||
local agy_dir="$gstack_dir/.gemini/config/plugins/gstack/skills"
|
||||
local linked=()
|
||||
|
||||
if [ ! -d "$agy_dir" ]; then
|
||||
echo " Generating .gemini/ skill docs..."
|
||||
( cd "$gstack_dir" && bun run gen:skill-docs --host agy )
|
||||
fi
|
||||
|
||||
if [ ! -d "$agy_dir" ]; then
|
||||
echo " warning: .gemini/config/plugins/gstack/skills/ generation failed — run 'bun run gen:skill-docs --host agy' manually" >&2
|
||||
return 1
|
||||
fi
|
||||
|
||||
for skill_dir in "$agy_dir"/gstack*/; do
|
||||
if [ -f "$skill_dir/SKILL.md" ]; then
|
||||
skill_name="$(basename "$skill_dir")"
|
||||
[ "$skill_name" = "gstack" ] && continue
|
||||
target="$skills_dir/$skill_name"
|
||||
if [ -L "$target" ] || [ ! -e "$target" ]; then
|
||||
_link_or_copy "$skill_dir" "$target"
|
||||
linked+=("$skill_name")
|
||||
fi
|
||||
fi
|
||||
done
|
||||
if [ ${#linked[@]} -gt 0 ]; then
|
||||
echo " linked skills: ${linked[*]}"
|
||||
fi
|
||||
}
|
||||
|
||||
# 4. Install for Claude (default)
|
||||
SKILLS_BASENAME="$(basename "$INSTALL_SKILLS_DIR")"
|
||||
SKILLS_PARENT_BASENAME="$(basename "$(dirname "$INSTALL_SKILLS_DIR")")"
|
||||
|
|
@ -1193,6 +1292,23 @@ if [ "$INSTALL_OPENCODE" -eq 1 ]; then
|
|||
echo " opencode skills: $OPENCODE_SKILLS"
|
||||
fi
|
||||
|
||||
# 6d. Install for Agy
|
||||
if [ "$INSTALL_AGY" -eq 1 ]; then
|
||||
AGY_GSTACK_SOURCE="$SOURCE_GSTACK_DIR/.gemini/config/plugins/gstack"
|
||||
AGY_SKILLS_SOURCE="$AGY_GSTACK_SOURCE/skills"
|
||||
mkdir -p "$AGY_SKILLS_SOURCE"
|
||||
create_agy_runtime_root "$SOURCE_GSTACK_DIR" "$AGY_GSTACK_SOURCE"
|
||||
link_agy_skill_dirs "$SOURCE_GSTACK_DIR" "$AGY_SKILLS_SOURCE"
|
||||
# Register/import the plugin into Agy
|
||||
if command -v agy >/dev/null 2>&1; then
|
||||
echo "Registering gstack plugin with Agy..."
|
||||
agy plugin install "$AGY_GSTACK_SOURCE" >/dev/null 2>&1 || agy plugin import "$AGY_GSTACK_SOURCE" --force >/dev/null 2>&1 || true
|
||||
fi
|
||||
echo "gstack ready (agy)."
|
||||
echo " browse: $BROWSE_BIN"
|
||||
echo " agy skills: $AGY_SKILLS"
|
||||
fi
|
||||
|
||||
# 7. Create .agents/ sidecar symlinks for the real Codex skill target.
|
||||
# The root Codex skill ends up pointing at $SOURCE_GSTACK_DIR/.agents/skills/gstack,
|
||||
# so the runtime assets must live there for both global and repo-local installs.
|
||||
|
|
|
|||
|
|
@ -36,12 +36,13 @@ function run(args: string[], opts: { env?: Record<string, string> } = {}): { sta
|
|||
|
||||
describe('gstack-model-benchmark --dry-run', () => {
|
||||
test('prints provider availability report and exits 0', () => {
|
||||
const r = run(['--prompt', 'hi', '--models', 'claude,gpt,gemini', '--dry-run']);
|
||||
const r = run(['--prompt', 'hi', '--models', 'claude,gpt,gemini,agy', '--dry-run']);
|
||||
expect(r.status).toBe(0);
|
||||
expect(r.stdout).toContain('gstack-model-benchmark --dry-run');
|
||||
expect(r.stdout).toContain('claude');
|
||||
expect(r.stdout).toContain('gpt');
|
||||
expect(r.stdout).toContain('gemini');
|
||||
expect(r.stdout).toContain('agy');
|
||||
expect(r.stdout).toContain('no prompts sent');
|
||||
});
|
||||
|
||||
|
|
@ -86,12 +87,12 @@ describe('gstack-model-benchmark --dry-run', () => {
|
|||
});
|
||||
|
||||
test('each adapter reports either OK or NOT READY, never crashes', () => {
|
||||
const r = run(['--prompt', 'hi', '--models', 'claude,gpt,gemini', '--dry-run']);
|
||||
const r = run(['--prompt', 'hi', '--models', 'claude,gpt,gemini,agy', '--dry-run']);
|
||||
expect(r.status).toBe(0);
|
||||
// Each provider line must end in OK or NOT READY
|
||||
const lines = r.stdout.split('\n');
|
||||
const adapterLines = lines.filter(l => /^\s+(claude|gpt|gemini):/.test(l));
|
||||
expect(adapterLines.length).toBe(3);
|
||||
const adapterLines = lines.filter(l => /^\s+(claude|gpt|gemini|agy):/.test(l));
|
||||
expect(adapterLines.length).toBe(4);
|
||||
for (const line of adapterLines) {
|
||||
expect(line).toMatch(/(OK|NOT READY)/);
|
||||
}
|
||||
|
|
@ -116,7 +117,7 @@ describe('gstack-model-benchmark --dry-run', () => {
|
|||
TERM: process.env.TERM ?? 'xterm',
|
||||
HOME: emptyHome,
|
||||
};
|
||||
const result = spawnSync('bun', ['run', BIN, '--prompt', 'hi', '--models', 'claude,gpt,gemini', '--dry-run'], {
|
||||
const result = spawnSync('bun', ['run', BIN, '--prompt', 'hi', '--models', 'claude,gpt,gemini,agy', '--dry-run'], {
|
||||
cwd: ROOT,
|
||||
env: minimalEnv,
|
||||
encoding: 'utf-8',
|
||||
|
|
@ -124,14 +125,15 @@ describe('gstack-model-benchmark --dry-run', () => {
|
|||
});
|
||||
expect(result.status).toBe(0);
|
||||
const out = result.stdout?.toString() ?? '';
|
||||
// gpt + gemini must report NOT READY in this clean env (their auth check
|
||||
// gpt + gemini + agy must report NOT READY in this clean env (their auth check
|
||||
// reads paths under the overridden HOME).
|
||||
expect(out).toMatch(/gpt:\s+NOT READY/);
|
||||
expect(out).toMatch(/gemini:\s+NOT READY/);
|
||||
expect(out).toMatch(/agy:\s+NOT READY/);
|
||||
// Every NOT READY line must include a concrete remediation hint so users
|
||||
// can resolve the missing auth. This is the regression we care about.
|
||||
const notReadyLines = out.split('\n').filter(l => l.includes('NOT READY'));
|
||||
expect(notReadyLines.length).toBeGreaterThanOrEqual(2);
|
||||
expect(notReadyLines.length).toBeGreaterThanOrEqual(3);
|
||||
for (const line of notReadyLines) {
|
||||
expect(line).toMatch(/(install|Install|login|export|Run|Log in)/);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -24,8 +24,10 @@ const INSTALL = path.join(ROOT, 'bin', 'gstack-gbrain-install');
|
|||
// Minimal PATH with POSIX tools + homebrew (for jq/git/curl) but no user-bin
|
||||
// dirs — this keeps `gbrain` out of PATH deterministically across dev machines
|
||||
// while still finding jq, git, curl, sed, cat, etc. Each test can prepend a
|
||||
// fake-gbrain dir when it wants to simulate presence.
|
||||
const SAFE_PATH = '/usr/bin:/bin:/usr/sbin:/sbin:/opt/homebrew/bin:/usr/local/bin';
|
||||
// fake-gbrain dir when it wants to simulate presence. We append the active Bun
|
||||
// directory so the script shebang can find bun.
|
||||
const BUN_DIR = path.dirname(process.execPath);
|
||||
const SAFE_PATH = `/usr/bin:/bin:/usr/sbin:/sbin:/opt/homebrew/bin:/usr/local/bin:${BUN_DIR}`;
|
||||
|
||||
let tmpHome: string;
|
||||
let tmpHomeReal: string;
|
||||
|
|
|
|||
|
|
@ -13,7 +13,7 @@ const SRC = fs.readFileSync(path.join(ROOT, 'bin', 'gstack-config'), 'utf-8');
|
|||
// satisfied by unrelated text elsewhere in the file.
|
||||
function okBranch(): string {
|
||||
const start = SRC.indexOf('gbrain-refresh)');
|
||||
const ok = SRC.indexOf('ok)', start);
|
||||
const ok = SRC.indexOf('ok|timeout)', start);
|
||||
const end = SRC.indexOf(';;', ok);
|
||||
if (start < 0 || ok < 0 || end < 0) throw new Error('Could not locate gbrain-refresh ok) branch');
|
||||
return SRC.slice(ok, end);
|
||||
|
|
|
|||
|
|
@ -2372,16 +2372,17 @@ describe('setup script validation', () => {
|
|||
expect(claudeSection).toContain('link_claude_root_skill_alias "$SOURCE_GSTACK_DIR" "$INSTALL_SKILLS_DIR"');
|
||||
});
|
||||
|
||||
test('setup supports --host auto|claude|codex|kiro|opencode', () => {
|
||||
test('setup supports --host auto|claude|codex|kiro|opencode|agy', () => {
|
||||
expect(setupContent).toContain('--host');
|
||||
expect(setupContent).toContain('claude|codex|kiro|factory|opencode|auto');
|
||||
expect(setupContent).toContain('claude|codex|kiro|factory|opencode|agy|auto');
|
||||
});
|
||||
|
||||
test('auto mode detects claude, codex, kiro, and opencode binaries', () => {
|
||||
test('auto mode detects claude, codex, kiro, opencode, and agy binaries', () => {
|
||||
expect(setupContent).toContain('command -v claude');
|
||||
expect(setupContent).toContain('command -v codex');
|
||||
expect(setupContent).toContain('command -v kiro-cli');
|
||||
expect(setupContent).toContain('command -v opencode');
|
||||
expect(setupContent).toContain('command -v agy');
|
||||
});
|
||||
|
||||
// T1: Sidecar skip guard — prevents .agents/skills/gstack from being linked as a skill
|
||||
|
|
@ -2423,6 +2424,23 @@ describe('setup script validation', () => {
|
|||
expect(setupContent).toContain('dx-hall-of-fame.md');
|
||||
});
|
||||
|
||||
test('setup supports --host agy with install section and agy plugin path vars', () => {
|
||||
expect(setupContent).toContain('INSTALL_AGY=');
|
||||
expect(setupContent).toContain('AGY_PLUGINS="$HOME/.gemini/config/plugins"');
|
||||
expect(setupContent).toContain('AGY_GSTACK="$AGY_PLUGINS/gstack"');
|
||||
expect(setupContent).toContain('AGY_SKILLS="$AGY_GSTACK/skills"');
|
||||
});
|
||||
|
||||
test('setup installs agy plugin into a nested gstack runtime root and validates registration', () => {
|
||||
expect(setupContent).toContain('create_agy_runtime_root');
|
||||
expect(setupContent).toContain('.gemini/config/plugins/gstack');
|
||||
expect(setupContent).toContain('review/specialists');
|
||||
expect(setupContent).toContain('qa/templates');
|
||||
expect(setupContent).toContain('qa/references');
|
||||
expect(setupContent).toContain('dx-hall-of-fame.md');
|
||||
expect(setupContent).toContain('agy plugin install');
|
||||
});
|
||||
|
||||
test('create_agents_sidecar links runtime assets', () => {
|
||||
// Sidecar must link bin, browse, review, qa
|
||||
const fnStart = setupContent.indexOf('create_agents_sidecar()');
|
||||
|
|
@ -3062,7 +3080,7 @@ describe('plan-mode-info resolver (handshake-replacement)', () => {
|
|||
// Non-Claude hosts render to hostSubdirs (.agents/, .openclaw/, etc). The
|
||||
// plan-mode-info resolver has no host-scoping — all hosts get the new
|
||||
// section, none get the old handshake. Scan all candidate host dirs.
|
||||
const hostDirs = ['.agents', '.openclaw', '.opencode', '.factory', '.hermes', '.kiro', '.cursor', '.slate'];
|
||||
const hostDirs = ['.agents', '.openclaw', '.opencode', '.factory', '.hermes', '.kiro', '.cursor', '.slate', '.gemini/config/plugins/gstack'];
|
||||
let checked = 0;
|
||||
for (const host of hostDirs) {
|
||||
const skillsRoot = path.join(ROOT, host, 'skills');
|
||||
|
|
|
|||
|
|
@ -11,15 +11,16 @@ import type { ProviderAdapter, RunOpts, RunResult } from './providers/types';
|
|||
import { ClaudeAdapter } from './providers/claude';
|
||||
import { GptAdapter } from './providers/gpt';
|
||||
import { GeminiAdapter } from './providers/gemini';
|
||||
import { AgyAdapter } from './providers/agy';
|
||||
|
||||
export interface BenchmarkInput {
|
||||
prompt: string;
|
||||
workdir: string;
|
||||
timeoutMs?: number;
|
||||
/** Adapter names to run (e.g., ['claude', 'gpt', 'gemini']). */
|
||||
providers: Array<'claude' | 'gpt' | 'gemini'>;
|
||||
/** Adapter names to run (e.g., ['claude', 'gpt', 'gemini', 'agy']). */
|
||||
providers: Array<'claude' | 'gpt' | 'gemini' | 'agy'>;
|
||||
/** Optional per-provider model overrides. */
|
||||
models?: Partial<Record<'claude' | 'gpt' | 'gemini', string>>;
|
||||
models?: Partial<Record<'claude' | 'gpt' | 'gemini' | 'agy', string>>;
|
||||
/** If true, skip providers whose available() returns !ok. If false, include them with error. */
|
||||
skipUnavailable?: boolean;
|
||||
}
|
||||
|
|
@ -44,10 +45,11 @@ export interface BenchmarkReport {
|
|||
entries: BenchmarkEntry[];
|
||||
}
|
||||
|
||||
const ADAPTERS: Record<'claude' | 'gpt' | 'gemini', () => ProviderAdapter> = {
|
||||
const ADAPTERS: Record<'claude' | 'gpt' | 'gemini' | 'agy', () => ProviderAdapter> = {
|
||||
claude: () => new ClaudeAdapter(),
|
||||
gpt: () => new GptAdapter(),
|
||||
gemini: () => new GeminiAdapter(),
|
||||
agy: () => new AgyAdapter(),
|
||||
};
|
||||
|
||||
export async function runBenchmark(input: BenchmarkInput): Promise<BenchmarkReport> {
|
||||
|
|
|
|||
|
|
@ -0,0 +1,87 @@
|
|||
import type { ProviderAdapter, RunOpts, RunResult, AvailabilityCheck } from './types';
|
||||
import { estimateCostUsd } from '../pricing';
|
||||
import { execFileSync, spawnSync } from 'child_process';
|
||||
import * as fs from 'fs';
|
||||
import * as path from 'path';
|
||||
import * as os from 'os';
|
||||
|
||||
/**
|
||||
* Agy adapter — wraps the `agy` CLI using `agy --print`.
|
||||
*
|
||||
* Auth comes from ~/.gemini/oauth_creds.json.
|
||||
*/
|
||||
export class AgyAdapter implements ProviderAdapter {
|
||||
readonly name = 'agy';
|
||||
readonly family = 'gemini' as const;
|
||||
|
||||
async available(): Promise<AvailabilityCheck> {
|
||||
const res = spawnSync('sh', ['-c', 'command -v agy'], { timeout: 2000 });
|
||||
if (res.status !== 0) {
|
||||
return { ok: false, reason: 'agy CLI not found on PATH. Install per Google Antigravity instructions.' };
|
||||
}
|
||||
const newCfgDir = path.join(os.homedir(), '.gemini');
|
||||
const newOauth = path.join(newCfgDir, 'oauth_creds.json');
|
||||
const hasCfg = fs.existsSync(newOauth);
|
||||
if (!hasCfg) {
|
||||
return { ok: false, reason: 'No Agy auth found. Log in via `agy` or authenticate.' };
|
||||
}
|
||||
return { ok: true };
|
||||
}
|
||||
|
||||
async run(opts: RunOpts): Promise<RunResult> {
|
||||
const start = Date.now();
|
||||
const args = ['--print', opts.prompt, '--dangerously-skip-permissions'];
|
||||
if (opts.model) args.push('--model', opts.model);
|
||||
if (opts.extraArgs) args.push(...opts.extraArgs);
|
||||
|
||||
try {
|
||||
const out = execFileSync('agy', args, {
|
||||
cwd: opts.workdir,
|
||||
timeout: opts.timeoutMs,
|
||||
encoding: 'utf-8',
|
||||
maxBuffer: 32 * 1024 * 1024,
|
||||
});
|
||||
|
||||
// Estimate tokens as agy does not output NDJSON/JSON tokens yet in print mode
|
||||
const inputTokens = Math.ceil(opts.prompt.length / 4);
|
||||
const outputTokens = Math.ceil(out.length / 4);
|
||||
|
||||
return {
|
||||
output: out.trim(),
|
||||
tokens: { input: inputTokens, output: outputTokens },
|
||||
durationMs: Date.now() - start,
|
||||
toolCalls: 0,
|
||||
modelUsed: opts.model || 'gemini-2.5-flash',
|
||||
};
|
||||
} catch (err: unknown) {
|
||||
const durationMs = Date.now() - start;
|
||||
const e = err as { code?: string; stderr?: Buffer; signal?: string; message?: string };
|
||||
const stderr = e.stderr?.toString() ?? '';
|
||||
if (e.signal === 'SIGTERM' || e.code === 'ETIMEDOUT') {
|
||||
return this.emptyResult(durationMs, { code: 'timeout', reason: `exceeded ${opts.timeoutMs}ms` }, opts.model);
|
||||
}
|
||||
if (/unauthorized|auth|login|api key/i.test(stderr)) {
|
||||
return this.emptyResult(durationMs, { code: 'auth', reason: stderr.slice(0, 400) }, opts.model);
|
||||
}
|
||||
if (/rate[- ]?limit|429|quota/i.test(stderr)) {
|
||||
return this.emptyResult(durationMs, { code: 'rate_limit', reason: stderr.slice(0, 400) }, opts.model);
|
||||
}
|
||||
return this.emptyResult(durationMs, { code: 'unknown', reason: (e.message ?? stderr ?? 'unknown').slice(0, 400) }, opts.model);
|
||||
}
|
||||
}
|
||||
|
||||
estimateCost(tokens: { input: number; output: number; cached?: number }, model?: string): number {
|
||||
return estimateCostUsd(tokens, model ?? 'gemini-2.5-flash');
|
||||
}
|
||||
|
||||
private emptyResult(durationMs: number, error: RunResult['error'], model?: string): RunResult {
|
||||
return {
|
||||
output: '',
|
||||
tokens: { input: 0, output: 0 },
|
||||
durationMs,
|
||||
toolCalls: 0,
|
||||
modelUsed: model ?? 'gemini-2.5-flash',
|
||||
error,
|
||||
};
|
||||
}
|
||||
}
|
||||
|
|
@ -22,6 +22,7 @@ import {
|
|||
slate,
|
||||
cursor,
|
||||
openclaw,
|
||||
agy,
|
||||
} from '../hosts/index';
|
||||
import { HOST_PATHS } from '../scripts/resolvers/types';
|
||||
|
||||
|
|
@ -30,8 +31,8 @@ const ROOT = path.resolve(import.meta.dir, '..');
|
|||
// ─── hosts/index.ts ─────────────────────────────────────────
|
||||
|
||||
describe('hosts/index.ts', () => {
|
||||
test('ALL_HOST_CONFIGS has 10 hosts', () => {
|
||||
expect(ALL_HOST_CONFIGS.length).toBe(10);
|
||||
test('ALL_HOST_CONFIGS has 11 hosts', () => {
|
||||
expect(ALL_HOST_CONFIGS.length).toBe(11);
|
||||
});
|
||||
|
||||
test('ALL_HOST_NAMES matches config names', () => {
|
||||
|
|
@ -53,6 +54,7 @@ describe('hosts/index.ts', () => {
|
|||
expect(slate.name).toBe('slate');
|
||||
expect(cursor.name).toBe('cursor');
|
||||
expect(openclaw.name).toBe('openclaw');
|
||||
expect(agy.name).toBe('agy');
|
||||
});
|
||||
|
||||
test('getHostConfig returns correct config', () => {
|
||||
|
|
|
|||
|
|
@ -22,6 +22,7 @@ import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
|||
import { ClaudeAdapter } from './helpers/providers/claude';
|
||||
import { GptAdapter } from './helpers/providers/gpt';
|
||||
import { GeminiAdapter } from './helpers/providers/gemini';
|
||||
import { AgyAdapter } from './helpers/providers/agy';
|
||||
import { runBenchmark } from './helpers/benchmark-runner';
|
||||
import * as fs from 'fs';
|
||||
import * as path from 'path';
|
||||
|
|
@ -39,6 +40,7 @@ const PROMPT = 'Reply with exactly this text and nothing else: ok';
|
|||
const claude = new ClaudeAdapter();
|
||||
const gpt = new GptAdapter();
|
||||
const gemini = new GeminiAdapter();
|
||||
const agy = new AgyAdapter();
|
||||
|
||||
// Use a temp working directory so provider CLIs can't accidentally touch the repo.
|
||||
// Created in beforeAll / cleaned in afterAll so concurrent CI runs don't leak.
|
||||
|
|
@ -80,6 +82,14 @@ describeIfEvals('multi-provider benchmark adapters (live)', () => {
|
|||
}
|
||||
});
|
||||
|
||||
test('agy: available() returns structured ok/reason', async () => {
|
||||
const check = await agy.available();
|
||||
expect(check).toHaveProperty('ok');
|
||||
if (!check.ok) {
|
||||
expect(typeof check.reason).toBe('string');
|
||||
}
|
||||
});
|
||||
|
||||
test('claude: trivial prompt produces parseable output', async () => {
|
||||
const check = await claude.available();
|
||||
if (!check.ok) {
|
||||
|
|
@ -140,11 +150,31 @@ describeIfEvals('multi-provider benchmark adapters (live)', () => {
|
|||
expect(result.modelUsed.length).toBeGreaterThan(0);
|
||||
}, 150_000);
|
||||
|
||||
test('agy: trivial prompt produces parseable output', async () => {
|
||||
const check = await agy.available();
|
||||
if (!check.ok) {
|
||||
process.stderr.write(`\nagy live smoke: SKIPPED — ${check.reason}\n`);
|
||||
return;
|
||||
}
|
||||
const result = await agy.run({ prompt: PROMPT, workdir, timeoutMs: 120_000 });
|
||||
if (result.error) {
|
||||
throw new Error(`agy errored: ${result.error.code} — ${result.error.reason}`);
|
||||
}
|
||||
expect(typeof result.output).toBe('string');
|
||||
expect(result.tokens.input).toBeGreaterThan(0);
|
||||
expect(result.tokens.output).toBeGreaterThan(0);
|
||||
expect(result.durationMs).toBeGreaterThan(0);
|
||||
expect(typeof result.modelUsed).toBe('string');
|
||||
const cost = agy.estimateCost(result.tokens, result.modelUsed);
|
||||
expect(cost).toBeGreaterThan(0);
|
||||
}, 150_000);
|
||||
|
||||
test('timeout error surfaces as error.code=timeout (no exception)', async () => {
|
||||
// Use whatever adapter is available first — all three should share timeout semantics.
|
||||
// Use whatever adapter is available first — all should share timeout semantics.
|
||||
const adapter = (await claude.available()).ok ? claude
|
||||
: (await gpt.available()).ok ? gpt
|
||||
: (await gemini.available()).ok ? gemini
|
||||
: (await agy.available()).ok ? agy
|
||||
: null;
|
||||
if (!adapter) {
|
||||
process.stderr.write('\ntimeout smoke: SKIPPED — no provider available\n');
|
||||
|
|
@ -160,16 +190,16 @@ describeIfEvals('multi-provider benchmark adapters (live)', () => {
|
|||
}, 30_000);
|
||||
|
||||
test('runBenchmark: Promise.allSettled means one unavailable provider does not block others', async () => {
|
||||
// Use the full runner with all three providers — whichever are unauthed should
|
||||
// Use the full runner with all providers — whichever are unauthed should
|
||||
// return entries with available=false and not crash the batch.
|
||||
const report = await runBenchmark({
|
||||
prompt: PROMPT,
|
||||
workdir,
|
||||
providers: ['claude', 'gpt', 'gemini'],
|
||||
providers: ['claude', 'gpt', 'gemini', 'agy'],
|
||||
timeoutMs: 120_000,
|
||||
skipUnavailable: false,
|
||||
});
|
||||
expect(report.entries).toHaveLength(3);
|
||||
expect(report.entries).toHaveLength(4);
|
||||
for (const e of report.entries) {
|
||||
expect(['claude', 'gpt', 'gemini']).toContain(e.family);
|
||||
if (e.available) {
|
||||
|
|
|
|||
Loading…
Reference in New Issue