sanity-check

name	sanity-check
description	Run the deferred AgentOS E2E smoke test from public npm packages. Use when the user asks to sanity check, smoke test, or verify a release works.

Sanity Check

This is a P6/full-validation check. It installs from npm in a fresh project, boots an AgentOS VM, spawns a Pi agent session, writes a file, reads it back, and verifies the contents.

Usage

• /sanity-check — run in a temp directory on the host
• /sanity-check docker — run inside a node:22 Docker container
• /sanity-check <custom instructions> — extra instructions, such as "use rc.3", "use pnpm", or "test on node 20"

What it tests

1. npm install of @rivet-dev/agentos-core, @rivet-dev/agentos-pi, @agentos-software/common from the public npm registry
2. Boot a VM with WASM coreutils (bash, cat, sh, etc.) and the Pi SDK ACP adapter
3. Create a Pi agent session with a real Anthropic API key
4. Send a prompt that uses the write tool to create /tmp/test.txt with "Hello from Agent OS!" and the bash tool to run cat /tmp/test.txt
5. Verify the file contents from the host side via vm.readFile()

Requirements

• ANTHROPIC_API_KEY must be set in the environment. If not set, load it from ~/misc/env.txt.
• Node.js 22+ (or Docker with node:22 image)

Steps

1. Set up the test project

Create a temp directory (e.g. /tmp/agentos-sanity-XXXX) with two files:

package.json:

{
  "name": "agentos-sanity-check",
  "private": true,
  "type": "module",
  "dependencies": {
    "@rivet-dev/agentos-core": "*",
    "@rivet-dev/agentos-pi": "*",
    "@agentos-software/common": "*",
    "@mariozechner/pi-coding-agent": "^0.60.0",
    "@agentclientprotocol/sdk": "^0.16.1"
  }
}

If the user specifies a version (e.g. "use rc.3"), pin @rivet-dev/agentos-core and @rivet-dev/agentos-pi to that version.

test.mjs:

import { AgentOs } from "@rivet-dev/agentos-core";
import common from "@agentos-software/common";
import pi from "@rivet-dev/agentos-pi";

const ANTHROPIC_API_KEY = process.env.ANTHROPIC_API_KEY;
if (!ANTHROPIC_API_KEY) {
  console.error("ANTHROPIC_API_KEY is required");
  process.exit(1);
}

console.log("Creating VM with common + pi...");
const vm = await AgentOs.create({ software: [common, pi] });

console.log("Creating PI agent session...");
const { sessionId } = await vm.createSession("pi", {
  env: { ANTHROPIC_API_KEY },
});
console.log(`Session created: ${sessionId}`);

vm.onSessionEvent(sessionId, (event) => {
  const params = event.params;
  if (params?.update?.sessionUpdate === "agent_message_chunk") {
    process.stdout.write(params.update.content?.text ?? "");
  }
});

console.log("\nSending prompt...");
const response = await vm.prompt(
  sessionId,
  'Write the text "Hello from Agent OS!" to /tmp/test.txt using the write tool. Then use the bash tool to run `cat /tmp/test.txt` and tell me what it says.',
);
console.log(`\n\nPrompt completed: ${response.stopReason}`);

console.log("\nVerifying file...");
try {
  const data = await vm.readFile("/tmp/test.txt");
  const text = new TextDecoder().decode(data);
  console.log(`File contents: "${text.trim()}"`);
  if (text.includes("Hello from Agent OS!")) {
    console.log("\n✅ E2E TEST PASSED");
  } else {
    console.log("\n❌ E2E TEST FAILED: wrong content");
    process.exit(1);
  }
} catch (err) {
  console.log(`\n❌ E2E TEST FAILED: ${err.message}`);
  process.exit(1);
}

vm.closeSession(sessionId);
await vm.dispose();

2. Run the test

Default (temp dir on host):

cd /tmp/agentos-sanity-XXXX
npm install
node test.mjs

Docker mode:

docker run --rm \
  -e ANTHROPIC_API_KEY="$ANTHROPIC_API_KEY" \
  -v /tmp/agentos-sanity-XXXX:/app \
  -w /app \
  node:22 \
  bash -c "npm install && timeout 120 node test.mjs"

3. Verify results

• LLM response should stream to stdout showing the agent using write and bash tools
• Final output must include ✅ E2E TEST PASSED
• If it fails, report the error and the stderr output

4. Clean up

Remove the temp directory after the test completes.

Rules

• Always use a fresh temp directory — never run in the repo itself.
• Always install from the public npm registry — never use local links.
• If Docker mode, clean up the container's node_modules via docker run --rm before removing the host temp dir.
• Report the installed versions of @rivet-dev/agentos-core and @agentos-software/common in the output.