mirror of
https://github.com/garrytan/gstack.git
synced 2026-08-23 06:27:14 +02:00
Garry TanandClaude Fable 5
60e51342b5
* 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>
89 lines
5.2 KiB
JSON
89 lines
5.2 KiB
JSON
{
|
|
"name": "gstack",
|
|
"version": "1.67.2",
|
|
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
|
|
"license": "MIT",
|
|
"type": "module",
|
|
"bin": {
|
|
"browse": "./browse/dist/browse",
|
|
"make-pdf": "./make-pdf/dist/pdf"
|
|
},
|
|
"scripts": {
|
|
"build": "bash scripts/build.sh",
|
|
"vendor:xterm": "mkdir -p extension/lib && cp node_modules/xterm/lib/xterm.js extension/lib/xterm.js && cp node_modules/xterm/css/xterm.css extension/lib/xterm.css && cp node_modules/xterm-addon-fit/lib/xterm-addon-fit.js extension/lib/xterm-addon-fit.js",
|
|
"dev:make-pdf": "bun run make-pdf/src/cli.ts",
|
|
"dev:design": "bun run design/src/cli.ts",
|
|
"build:diagram-render": "cd lib/diagram-render && bun install && bun run scripts/build.ts",
|
|
"gen:skill-docs": "bun run scripts/gen-skill-docs.ts",
|
|
"gen:skill-docs:user": "bun run scripts/gen-skill-docs.ts --respect-detection",
|
|
"dev": "bun run browse/src/cli.ts",
|
|
"server": "bun run browse/src/server.ts",
|
|
"test": "bun run scripts/test-free-shards.ts && (bun run slop:diff 2>/dev/null || true)",
|
|
"test:free": "bun run scripts/test-free-shards.ts",
|
|
"test:windows": "bun run scripts/test-free-shards.ts --windows-only",
|
|
"test:evals": "EVALS=1 bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/codex-e2e-sol-scope.test.ts test/gemini-e2e.test.ts",
|
|
"test:evals:all": "EVALS=1 EVALS_ALL=1 bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/codex-e2e-sol-scope.test.ts test/gemini-e2e.test.ts",
|
|
"test:e2e": "EVALS=1 bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/codex-e2e-sol-scope.test.ts test/gemini-e2e.test.ts",
|
|
"test:e2e:all": "EVALS=1 EVALS_ALL=1 bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/codex-e2e-sol-scope.test.ts test/gemini-e2e.test.ts",
|
|
"test:gate": "EVALS=1 EVALS_TIER=gate bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/codex-e2e-sol-scope.test.ts test/gemini-e2e.test.ts",
|
|
"test:periodic": "EVALS=1 EVALS_TIER=periodic EVALS_ALL=1 bun test --retry 1 --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e.test.ts test/codex-e2e-sol-scope.test.ts test/gemini-e2e.test.ts",
|
|
"test:gate:sharded": "bun run scripts/test-paid-shards.ts --tier gate",
|
|
"test:periodic:sharded": "EVALS_ALL=1 bun run scripts/test-paid-shards.ts --tier periodic",
|
|
"test:codex": "EVALS=1 bun test test/codex-e2e.test.ts test/codex-e2e-sol-scope.test.ts",
|
|
"test:codex:all": "EVALS=1 EVALS_ALL=1 bun test test/codex-e2e.test.ts test/codex-e2e-sol-scope.test.ts",
|
|
"test:gemini": "EVALS=1 bun test test/gemini-e2e.test.ts",
|
|
"test:gemini:all": "EVALS=1 EVALS_ALL=1 bun test test/gemini-e2e.test.ts",
|
|
"skill:check": "bun run scripts/skill-check.ts",
|
|
"dev:skill": "bun run scripts/dev-skill.ts",
|
|
"start": "bun run browse/src/server.ts",
|
|
"eval:bg": "bin/gstack-detach --label evals --lock gstack-evals --timeout 5400 -- bun run test:evals",
|
|
"eval:bg:all": "bin/gstack-detach --label evals-all --lock gstack-evals --timeout 7200 -- bun run test:evals:all",
|
|
"eval:bg:gate": "bin/gstack-detach --label evals-gate --lock gstack-evals --timeout 25200 -- bun run test:gate:sharded",
|
|
"eval:bg:periodic": "bin/gstack-detach --label evals-periodic --lock gstack-evals --timeout 32400 -- bun run test:periodic:sharded",
|
|
"eval:list": "bun run scripts/eval-list.ts",
|
|
"eval:compare": "bun run scripts/eval-compare.ts",
|
|
"eval:summary": "bun run scripts/eval-summary.ts",
|
|
"eval:watch": "bun run scripts/eval-watch.ts",
|
|
"eval:select": "bun run scripts/eval-select.ts",
|
|
"analytics": "bun run scripts/analytics.ts",
|
|
"test:audit": "bun test test/audit-compliance.test.ts",
|
|
"slop": "npx slop-scan scan . 2>/dev/null || echo 'slop-scan not available (install with: npm i -g slop-scan)'",
|
|
"slop:diff": "bun run scripts/slop-diff.ts"
|
|
},
|
|
"dependencies": {
|
|
"@huggingface/transformers": "^4.2.0",
|
|
"@ngrok/ngrok": "^1.7.0",
|
|
"cross-spawn": "^7.0.6",
|
|
"diff": "^9.0.0",
|
|
"html-to-docx": "1.8.0",
|
|
"marked": "^18.0.9",
|
|
"playwright": "^1.62.1",
|
|
"socks": "^2.8.9"
|
|
},
|
|
"engines": {
|
|
"bun": ">=1.0.0"
|
|
},
|
|
"keywords": [
|
|
"browser",
|
|
"automation",
|
|
"playwright",
|
|
"headless",
|
|
"cli",
|
|
"claude",
|
|
"ai-agent",
|
|
"devtools"
|
|
],
|
|
"devDependencies": {
|
|
"@anthropic-ai/claude-agent-sdk": "0.2.117",
|
|
"@anthropic-ai/sdk": "^0.78.0",
|
|
"xterm": "5",
|
|
"xterm-addon-fit": "^0.8.0"
|
|
},
|
|
"overrides": {
|
|
"adm-zip": "^0.6.0"
|
|
},
|
|
"patchedDependencies": {
|
|
"playwright-core@1.62.1": "patches/playwright-core@1.62.1.patch"
|
|
}
|
|
}
|