mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-31 22:14:25 +01:00
Garry TanandMatt Van Horn
fe6d1ae62a
* fix: mark Remaining Work provenance so restore verifies guessed steps first (#3004) /context-save now starts every Remaining Work item with `Open.` and ends it with how this session knows it: `(path run)` with the observed outcome, `(path read)` or `(path assumed)` for concrete paths, and `(target state checked)`, `(code read)` or `(path assumed)` for writing steps. /context-restore keeps saved order and original text but splits the list into Next steps and Verify first (assumed, code-read, failed runs and unmarked concrete or writing items), prints a banner for pre-marker checkpoints, and option A walks saved order so an unverified first item is verified before any later step runs. Adds a prompt-byte contract test for the marker wire format and a periodic behavior E2E (context-restore-provenance-order) that seeds an assumed item ahead of a run item plus a code-read write. Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com> * fix(design): never overwrite a paid design image (#1529) Every image the API returns now goes through one persistence path (design/src/persist.ts): mkdir, exclusive `wx` claim that bumps x.png -> x-2.png ... x-999.png, write, fsync, close. A failure after the bytes arrived removes the claimed file and keeps a 0600 recovery copy in the temp dir; empty image data is a failure, never a 0-byte PNG. The API call is the only thing inside each retry loop, so a local save failure never buys a second image (variants, iterate fallback, generate --retry). generate, iterate, evolve and variants (both branches) print the same run fields (requested, saved, selected, failures, recovered) on every exit, with exit 0 / 2 (nothing saved) / 3 (stopped after saving). Each generate --retry attempt is its own saved image listed in `attempts`. compare accepts --images-file and JSON-array --images. The gallery lists bumped names, orders history by mtime then board-images.json, and marks approvals by approved_path. New bin/gstack-design-claim publishes staged images without clobbering; bin/gstack-design-approved resolves an approval record (legacy letter-only records still resolve; a missing approved_path is an error, never a substitute). Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com> * fix(design skills): read the paths $D printed, never fixed variant names (#1529) Every design flow now captures each generating $D command's JSON and exit code without set -e, does round accounting before the first board, check or inline view (stopping when nothing was saved), and carries the printed paths forward. Boards are built from board-images.json via compare --images-file after archiving any earlier feedback.json, and approvals map the confirmed letter through that file and record approved_path. design-shotgun subagents generate into a per-run mktemp staging directory and publish with bin/gstack-design-claim instead of a shared /tmp/variant-X.png plus cp. design-html and taste memory resolve approvals with gstack-design-approved; design-review verifies against the printed target path. test/design-printed-paths.test.ts bans fixed variant names, variant globs, variant-{letter} reads, cp/mv of $D output and literal check paths in the generated skills and resolvers (one content-anchored allowlist entry: the design-html discovery probe), and pins the accounting/board marker order. test/design-approval-flow.test.ts runs the generated board and approval blocks through a stubbed two-round flow. * chore: release v1.91.17.0 (mvanhorn fix wave: checkpoint provenance, never-overwrite design images) * fix(design): keep iterate sessions in the OS temp dir and normalize tripwire paths on Windows * fix(setup-deploy): report failing status commands, specify merge-method, health and workflow checks --------- Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>
109 lines
6.8 KiB
JSON
109 lines
6.8 KiB
JSON
{
|
|
"name": "gstack",
|
|
"version": "1.91.19",
|
|
"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",
|
|
"build:cso": "bash scripts/build-cso.sh",
|
|
"format:cso": "prettier --write 'lib/cso/*.ts'",
|
|
"format:cso:check": "prettier --check 'lib/cso/*.ts'",
|
|
"typecheck": "tsc -p tsconfig.json",
|
|
"typecheck:test": "bun run scripts/typecheck-test.ts",
|
|
"test:cso:docker": "bun test --max-concurrency 1 test/cso-docker-integration.test.ts test/cso-node-lifecycle-integration.test.ts test/cso-stack-cold-integration.test.ts",
|
|
"test:cso:macos": "bun test test/cso-macos-launcher.test.ts test/cso-registry-socket.test.ts",
|
|
"test:cso:windows": "bun test test/cso-windows-launcher.test.ts",
|
|
"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",
|
|
"build:gates": "bun build --compile make-pdf/src/cli.ts --outfile make-pdf/dist/pdf && bun build --compile browse/src/cli.ts --outfile browse/dist/browse && bun run build:diagram-render",
|
|
"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",
|
|
"test:free": "bun run scripts/test-free-shards.ts",
|
|
"test:windows": "bun run scripts/test-free-shards.ts --windows-only",
|
|
"test:ubicloud": "bash scripts/ubicloud/test-free.sh",
|
|
"test:evals": "EVALS=1 bun test --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/llm-judge-recommendation.test.ts test/carve-section-loading*.test.ts",
|
|
"test:evals:all": "EVALS=1 EVALS_ALL=1 bun test --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/llm-judge-recommendation.test.ts test/carve-section-loading*.test.ts",
|
|
"test:e2e": "EVALS=1 bun test --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e*.test.ts test/carve-section-loading*.test.ts",
|
|
"test:e2e:all": "EVALS=1 EVALS_ALL=1 bun test --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e*.test.ts test/carve-section-loading*.test.ts",
|
|
"test:gate": "EVALS=1 EVALS_TIER=gate bun test --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/llm-judge-recommendation.test.ts test/carve-section-loading*.test.ts",
|
|
"test:periodic": "EVALS=1 EVALS_TIER=periodic EVALS_ALL=1 bun test --concurrent --max-concurrency ${EVALS_CONCURRENCY:-15} test/skill-llm-eval*.test.ts test/skill-e2e-*.test.ts test/skill-routing-e2e.test.ts test/codex-e2e*.test.ts test/llm-judge-recommendation.test.ts test/carve-section-loading*.test.ts",
|
|
"test:gate:sharded": "bun run scripts/test-paid-shards.ts --tier gate",
|
|
"test:periodic:sharded": "EVALS_ALL=1 bun run scripts/test-paid-shards.ts --tier periodic",
|
|
"test:codex": "EVALS=1 bun test test/codex-e2e.test.ts test/codex-e2e-sol-scope.test.ts",
|
|
"test:codex:all": "EVALS=1 EVALS_ALL=1 bun test test/codex-e2e.test.ts test/codex-e2e-sol-scope.test.ts",
|
|
"skill:check": "bun run scripts/skill-check.ts",
|
|
"dev:skill": "bun run scripts/dev-skill.ts",
|
|
"start": "bun run browse/src/server.ts",
|
|
"eval:bg": "bin/gstack-detach --label evals --lock gstack-evals --timeout 5400 -- bun run test:evals",
|
|
"eval:bg:all": "bin/gstack-detach --label evals-all --lock gstack-evals --timeout 7200 -- bun run test:evals:all",
|
|
"eval:bg:gate": "bin/gstack-detach --label evals-gate --lock gstack-evals --timeout 49320 -- bun run test:gate:sharded",
|
|
"eval:bg:periodic": "bin/gstack-detach --label evals-periodic --lock gstack-evals --timeout 67380 -- bun run test:periodic:sharded",
|
|
"eval:list": "bun run scripts/eval-list.ts",
|
|
"eval:compare": "bun run scripts/eval-compare.ts",
|
|
"eval:summary": "bun run scripts/eval-summary.ts",
|
|
"eval:flake-rank": "bun run scripts/eval-flake-rank.ts",
|
|
"eval:pass-rates": "bun run scripts/eval-flake-rank.ts",
|
|
"eval:watch": "bun run scripts/eval-watch.ts",
|
|
"eval:select": "bun run scripts/eval-select.ts",
|
|
"analytics": "bun run scripts/analytics.ts",
|
|
"test:audit": "bun test test/audit-compliance.test.ts",
|
|
"slop": "npx slop-scan scan . 2>/dev/null || echo 'slop-scan not available (install with: npm i -g slop-scan)'",
|
|
"slop:diff": "bun run scripts/slop-diff.ts",
|
|
"test:quick": "bun run scripts/test-free-shards.ts --quick",
|
|
"test:pr": "EVALS_JOBS=${EVALS_JOBS:-2} bun run scripts/test-paid-shards.ts --tier gate --profile pr",
|
|
"test:release": "EVALS_ALL=1 EVALS_FRESH=1 EVALS_CACHE_PURPOSE=release bun run scripts/test-paid-shards.ts --tier gate --profile full && EVALS_ALL=1 EVALS_FRESH=1 EVALS_CACHE_PURPOSE=release bun run scripts/test-paid-shards.ts --tier periodic --profile full",
|
|
"eval:bg:pr": "bin/gstack-detach --label evals-pr --lock gstack-evals --timeout 92820 -- bun run test:pr",
|
|
"eval:bg:release": "bin/gstack-detach --label evals-release --lock gstack-evals --timeout 116700 -- bun run test:release"
|
|
},
|
|
"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": "^18.0.11",
|
|
"playwright": "^1.62.1",
|
|
"socks": "^2.8.9"
|
|
},
|
|
"engines": {
|
|
"bun": ">=1.4.0"
|
|
},
|
|
"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",
|
|
"@types/bun": "1.4.0",
|
|
"prettier": "3.9.9",
|
|
"typescript": "7.0.2",
|
|
"xterm": "^5.3.0",
|
|
"xterm-addon-fit": "^0.8.0"
|
|
},
|
|
"overrides": {
|
|
"adm-zip": "^0.6.1",
|
|
"ip-address": "10.3.1",
|
|
"sharp": "0.35.4"
|
|
},
|
|
"patchedDependencies": {
|
|
"playwright-core@1.62.1": "patches/playwright-core@1.62.1.patch"
|
|
}
|
|
}
|