mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-01 14:34:42 +01:00
Garry Tanandcapy-ai[bot]
b004c06dbc
* fix(ship-queue): fill trains at 3 READY PRs or one hour, and price every case shard's trial
The 5-PR / 3-hour fill left READY PRs waiting most of a day; .gstack/ship-policy.json
now fills at max_size 3 or fill_hours 1, whichever comes first (fillDue already
dispatches at either bound). train verdict printed cost=$24.41 for a train whose slice
report said cost $32.92 known + 54 of 136 trial(s) cost unknown: E2E records named by a
display label ("/benchmark workflow") were never attributed to their case id, so the
per-case sum was short. A case shard's records now belong to its one case; a multi-case
shard with display-labelled records keeps those trials unknown. The ATTEMPT: line names
how many cases have no cost instead of printing a partial sum as the total.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ci): record the paid-report.ts harness decision and keep ship-queue-train-cost.test.ts off the Windows subset
scripts/lib/paid-report.ts is a pinned shared-harness file, so test/harness-version.test.ts wants a HARNESS_VERSION decision for its edit: non-behavioral, because a case shard's records are attributed to its one case for the trial's cost, class and error fields while no case's outcome, panel verdict or selection changes.
test/ship-queue-train-cost.test.ts drives bin/gstack-ship-queue against the #!/bin/sh gh shim, which windows-latest cannot run (windows-free-shard 2 on #3478 at d5e6a7d), so it joins test/ship-queue-train.test.ts in the Windows exclusion list.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: pin a failed display-labelled trial's fields and the $0.00 cost line; say so in the CHANGELOG
The widened record filter also feeds failedRecord, so a failed display-labelled trial in a case shard now takes failure_class, exit_reason and error from its record (train-gate classes a red infra record INFRA instead of VERDICT). The CHANGELOG entry said only the cost fields changed; it now says both. A train priced at zero prints cost=$0.00.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore(harness): say which panel class the paid-report decision moves
The non-behavioral note now names the one verdict-side effect of attributing a case shard's records to its case: a red whose own record says infra or timeout is classed INFRA instead of VERDICT, which changes rerun and bisect eligibility and not a pass rate.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: document one-case-shard cost attribution and the train verdict cost line; put the undercounted train costs on record
/document-release (ship-owned audit) added the attribution rule and the ATTEMPT: cost-line form to docs/TESTING_INTERNALS.md, docs/troubleshooting.md#cost-unknown and docs/evals/census-red.md. The CHANGELOG headline now says every train cost the coordinator reported until this fix was the undercounted verdict figure (about $24 per train against about $33 real).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: the train verdict prints the known+unknown cost form only when some but not every case is priced
The second /document-release audit tightened docs/TESTING_INTERNALS.md and docs/troubleshooting.md#cost-unknown: a train record with no priced case prints no cost at all (classifyGate's cost is null). The CHANGELOG bullet says the same.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.255.0 stamp
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
119 lines
5.7 KiB
JSON
119 lines
5.7 KiB
JSON
{
|
|
"name": "gstack",
|
|
"version": "1.91.255",
|
|
"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 --no-compile-autoload-dotenv --no-compile-autoload-bunfig && bun build --compile browse/src/cli.ts --outfile browse/dist/browse --no-compile-autoload-dotenv --no-compile-autoload-bunfig && 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",
|
|
"audit:manifest": "bun run scripts/prompt-audit-manifest.ts",
|
|
"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": "bun run scripts/retired-command.ts test:evals",
|
|
"test:evals:all": "bun run scripts/retired-command.ts test:evals:all",
|
|
"test:e2e": "bun run scripts/retired-command.ts test:e2e",
|
|
"test:e2e:all": "bun run scripts/retired-command.ts test:e2e:all",
|
|
"test:gate": "bun run scripts/retired-command.ts test:gate",
|
|
"test:periodic": "bun run scripts/retired-command.ts test:periodic",
|
|
"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": "bun run scripts/retired-command.ts test:codex",
|
|
"test:codex:all": "bun run scripts/retired-command.ts test:codex:all",
|
|
"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": "bun run scripts/retired-command.ts eval:bg",
|
|
"eval:bg:all": "bun run scripts/retired-command.ts eval:bg:all",
|
|
"eval:bg:gate": "bun run scripts/eval-bg.ts gate",
|
|
"eval:bg:periodic": "bun run scripts/eval-bg.ts periodic",
|
|
"test:health": "bun run scripts/test-health-report.ts",
|
|
"test:exercised-map": "bun run scripts/exercised-map.ts",
|
|
"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/retired-command.ts eval:flake-rank",
|
|
"eval:pass-rates": "bun run scripts/eval-flake-rank.ts",
|
|
"eval:watch": "bun run scripts/retired-command.ts eval:watch",
|
|
"eval:select": "bun run scripts/eval-select.ts",
|
|
"analytics": "bun run scripts/analytics.ts",
|
|
"test:audit": "bun run scripts/retired-command.ts test:audit",
|
|
"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": "bun run scripts/eval-bg.ts pr",
|
|
"eval:bg:release": "bun run scripts/eval-bg.ts release"
|
|
},
|
|
"dependencies": {
|
|
"@anthropic-ai/sdk": "^0.78.0",
|
|
"@huggingface/transformers": "^4.3.1",
|
|
"@ngrok/ngrok": "^1.7.0",
|
|
"cross-spawn": "^7.0.6",
|
|
"diff": "^9.0.0",
|
|
"html-to-docx": "1.8.0",
|
|
"html-to-vdom": "0.7.0",
|
|
"marked": "^18.1.1",
|
|
"playwright": "^1.62.1",
|
|
"sharp": "^0.35.4",
|
|
"socks": "^2.8.10",
|
|
"xterm": "^5.3.0",
|
|
"xterm-addon-fit": "^0.8.0"
|
|
},
|
|
"engines": {
|
|
"bun": ">=1.4.2"
|
|
},
|
|
"keywords": [
|
|
"browser",
|
|
"automation",
|
|
"playwright",
|
|
"headless",
|
|
"cli",
|
|
"claude",
|
|
"ai-agent",
|
|
"devtools"
|
|
],
|
|
"devDependencies": {
|
|
"@anthropic-ai/claude-agent-sdk": "0.2.141",
|
|
"@types/bun": "1.4.3",
|
|
"prettier": "3.9.10",
|
|
"typescript": "7.0.2"
|
|
},
|
|
"overrides": {
|
|
"@modelcontextprotocol/sdk": "1.32.0",
|
|
"adm-zip": "^0.6.1",
|
|
"fast-uri": "3.1.9",
|
|
"hono": "4.13.13",
|
|
"image-size": "2.0.4",
|
|
"ip-address": "10.7.4",
|
|
"proxy-addr": "2.0.8",
|
|
"sharp": "0.35.5"
|
|
},
|
|
"patchedDependencies": {
|
|
"playwright-core@1.62.1": "patches/playwright-core@1.62.1.patch"
|
|
}
|
|
}
|