Julius Brussee
99a9aa2f5a
Two guarantees, layered: 1. --test-force-exit on EVERY node --test invocation in the repo (16 package.json scripts, both engine-ci root-test steps, profiles.yml, and the test:windows compat runner) — a test file that leaks a server, socket, or child after a failed assertion now exits when its tests finish instead of pinning the runner until the workflow limit. 2. timeout-minutes on all six engine-ci jobs (25, or 45 for typescript/windows) — engine-ci was the only workflow with none, which is how a single leaked handle occupied a runner for 6 hours, twice. Anything that still finds a way to wedge now dies as a visible failure inside the hour. Verified locally with the flag: root installer 169, subagent-tax 48, mem/js, mcp, browse, shrink, explorer, caveman-learn — all green. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ez7w7BBtKrMZCiZz9ea4cb
@caveman-ai/create-agent
Atomic initializer for @caveman-ai/agent.
npm create @caveman-ai/agent@latest my-agent
cd my-agent
npm run doctor
npm run dev
Initializer creates one required source file, starter eval, strict build config, provider choice, and installs dependencies. Exactly one detected provider credential selects silently. Zero or multiple credentials prompt once. Secrets are never printed or written.
Noninteractive use:
npm create @caveman-ai/agent@latest my-agent -- --provider anthropic
Supported providers: anthropic, openai, google.
Skip dependency installation when another tool owns it:
npm create @caveman-ai/agent@latest my-agent -- --provider openai --no-install
Generated eval starts unapproved. Review expected behavior, set
approved: true, then run npm run build. Local evidence remains inferred;
verified savings remain $0 until active production traffic earns them.
After a locked build, run npm run check before deployment. Doctor makes no
provider call; if signed runtime artifacts are absent, follow its single
caveman setup --install action.