Add bounded harness evaluation and rollback loop (#2686)

* feat(ecc2): add bounded harness evaluation loop

* fix(ecc2): preserve harness evidence and legacy IDs
This commit is contained in:
Affaan Mustafa
2026-08-05 18:17:10 -04:00
committed by GitHub
parent f1fec0e539
commit 623f2c020f
15 changed files with 2327 additions and 169 deletions
+135 -14
View File
@@ -9,7 +9,7 @@ const assert = require("assert");
const fs = require("fs");
const os = require("os");
const path = require("path");
const { spawnSync } = require("child_process");
const { spawn, spawnSync } = require("child_process");
const REPO_ROOT = path.join(__dirname, "..", "..");
const ECC_SCRIPT = path.join(REPO_ROOT, "scripts", "ecc.js");
@@ -21,6 +21,7 @@ const {
const {
createSafeItoInvocationEnvironment,
getInvocationCommand,
ITO_RUNTIME_ENVIRONMENT_KEYS,
} = require("../../scripts/lib/ito-environment");
function runCli(args, environment = {}) {
@@ -35,6 +36,34 @@ function runCli(args, environment = {}) {
});
}
function runCliAndObserveFirstOutput(args, environment = {}) {
return new Promise((resolve, reject) => {
const child = spawn(process.execPath, [ECC_SCRIPT, ...args], {
cwd: REPO_ROOT,
env: { ...process.env, NODE_ENV: "test", ...environment },
stdio: ["ignore", "pipe", "pipe"],
});
let stdout = "";
let stderr = "";
let firstOutputAt;
const startedAt = Date.now();
child.stdout.on("data", (chunk) => {
if (firstOutputAt === undefined) firstOutputAt = Date.now();
stdout += chunk;
});
child.stderr.on("data", (chunk) => { stderr += chunk; });
child.once("error", reject);
child.once("close", (status) => resolve({
status,
stdout,
stderr,
startedAt,
firstOutputAt,
closedAt: Date.now(),
}));
});
}
function makeItoProbe(exitCode = 0) {
const directory = fs.mkdtempSync(path.join(os.tmpdir(), "ecc-ito-cli-"));
const log = path.join(directory, "invocation.json");
@@ -72,9 +101,9 @@ function readInvocation(probe) {
return JSON.parse(fs.readFileSync(probe.log, "utf8"));
}
function runTest(name, fn) {
async function runTest(name, fn) {
try {
fn();
await fn();
console.log(`${name}`);
return true;
} catch (error) {
@@ -84,12 +113,12 @@ function runTest(name, fn) {
}
}
function main() {
async function main() {
console.log("\n=== Testing ECC × Itô real CLI bridge ===\n");
const tests = [
["forwards only the reviewed RFQ CLI surface to an explicit local executable", () => {
for (const command of ["auth", "find", "status"]) {
for (const command of ["login", "auth", "find", "status"]) {
const probe = makeItoProbe();
try {
const result = runCli(["ito", command], {
@@ -103,6 +132,31 @@ function main() {
}
}
}],
["forwards the canonical login browser opt-out without performing browser automation", () => {
const probe = makeItoProbe();
try {
const result = runCli(["ito", "login", "--no-browser"], {
ECC_ITO_CLI_EXECUTABLE: probe.executable,
});
assert.strictEqual(result.status, 0, result.stderr);
assert.deepStrictEqual(readInvocation(probe).argv, ["login", "--no-browser"]);
} finally {
fs.rmSync(probe.directory, { recursive: true, force: true });
}
}],
["rejects --no-browser on validation-only auth before spawning", () => {
const probe = makeItoProbe();
try {
const result = runCli(["ito", "auth", "--no-browser"], {
ECC_ITO_CLI_EXECUTABLE: probe.executable,
});
assert.notStrictEqual(result.status, 0);
assert.match(result.stderr, /--no-browser.*only.*login/i);
assert.ok(!fs.existsSync(probe.log));
} finally {
fs.rmSync(probe.directory, { recursive: true, force: true });
}
}],
["normalizes JSON and forwards every RFQ constraint without interpretation", () => {
const probe = makeItoProbe();
try {
@@ -135,12 +189,15 @@ function main() {
fs.rmSync(probe.directory, { recursive: true, force: true });
}
}],
["passes only the required Itô runtime settings across the process boundary", () => {
["login never inherits ITO_API_KEY but preserves secure token settings", () => {
const probe = makeItoProbe();
try {
const result = runCli(["ito", "auth"], {
const result = runCli(["ito", "login"], {
ECC_ITO_CLI_EXECUTABLE: probe.executable,
ITO_API_KEY: "ito_test_key",
ITO_API_KEY: "must-not-cross-without-legacy-mode",
ITO_AUTH_MODE: "device",
ITO_ALLOW_FILE_TOKEN: "1",
ITO_TOKEN_FILE: "/tmp/ito-device-token",
ITO_API_URL: "https://compute.example.test",
ITO_INVENTORY_URL: "https://edge.example.test",
AWS_SECRET_ACCESS_KEY: "must-not-cross",
@@ -149,7 +206,10 @@ function main() {
});
assert.strictEqual(result.status, 0, result.stderr);
const childEnvironment = readInvocation(probe).env;
assert.strictEqual(childEnvironment.ITO_API_KEY, "ito_test_key");
assert.strictEqual(childEnvironment.ITO_API_KEY, undefined);
assert.strictEqual(childEnvironment.ITO_AUTH_MODE, "device");
assert.strictEqual(childEnvironment.ITO_ALLOW_FILE_TOKEN, "1");
assert.strictEqual(childEnvironment.ITO_TOKEN_FILE, "/tmp/ito-device-token");
assert.strictEqual(childEnvironment.ITO_API_URL, "https://compute.example.test");
assert.strictEqual(childEnvironment.ITO_INVENTORY_URL, "https://edge.example.test");
assert.strictEqual(childEnvironment.AWS_SECRET_ACCESS_KEY, undefined);
@@ -160,6 +220,46 @@ function main() {
fs.rmSync(probe.directory, { recursive: true, force: true });
}
}],
["forwards ITO_API_KEY directly to auth, find, and status without legacy mode", () => {
for (const command of ["auth", "find", "status"]) {
const probe = makeItoProbe();
try {
const result = runCli(["ito", command], {
ECC_ITO_CLI_EXECUTABLE: probe.executable,
ITO_API_KEY: "ito_test_key",
});
assert.strictEqual(result.status, 0, result.stderr);
assert.strictEqual(readInvocation(probe).env.ITO_API_KEY, "ito_test_key");
} finally {
fs.rmSync(probe.directory, { recursive: true, force: true });
}
}
}],
["streams device login output before completion and propagates its exit status", async () => {
const probe = makeItoProbe(7);
try {
fs.writeFileSync(
probe.executable,
[
'"use strict";',
'process.stdout.write("device-code-now\\n");',
'setTimeout(() => process.exit(7), 500);',
"",
].join("\n")
);
const result = await runCliAndObserveFirstOutput(["ito", "login"], {
ECC_ITO_CLI_EXECUTABLE: probe.executable,
});
assert.strictEqual(result.status, 7, result.stderr);
assert.match(result.stdout, /device-code-now/);
assert.ok(
result.closedAt - result.firstOutputAt >= 350,
"login output was buffered until process completion",
);
} finally {
fs.rmSync(probe.directory, { recursive: true, force: true });
}
}],
["isolates live node qualification from Itô and unrelated credentials", () => {
const probe = makeItoProbe();
try {
@@ -176,6 +276,9 @@ function main() {
], {
ECC_ITO_CLI_EXECUTABLE: probe.executable,
ITO_API_KEY: "must-not-cross-into-node-qualification",
ITO_AUTH_MODE: "legacy",
ITO_ALLOW_FILE_TOKEN: "1",
ITO_TOKEN_FILE: "/tmp/must-not-cross-token-file",
ITO_API_URL: "https://compute.example.test",
ITO_INVENTORY_URL: "https://edge.example.test",
ITO_ENABLE_SIXTYTWO_LIVE: "1",
@@ -201,6 +304,9 @@ function main() {
assert.strictEqual(invocation.env.SIXTYTWO_TOKEN, "sixtytwo-legacy-test-token");
assert.strictEqual(invocation.env.SSH_AUTH_SOCK, "/tmp/ecc-test-agent.sock");
assert.strictEqual(invocation.env.ITO_API_KEY, undefined);
assert.strictEqual(invocation.env.ITO_AUTH_MODE, undefined);
assert.strictEqual(invocation.env.ITO_ALLOW_FILE_TOKEN, undefined);
assert.strictEqual(invocation.env.ITO_TOKEN_FILE, undefined);
assert.strictEqual(invocation.env.ITO_API_URL, undefined);
assert.strictEqual(invocation.env.ITO_INVENTORY_URL, undefined);
assert.strictEqual(invocation.env.ITO_CLI_DEMO, undefined);
@@ -310,6 +416,14 @@ function main() {
}
}],
["classifies Itō child environments once and fails closed on unknown prefixes", () => {
assert.deepStrictEqual(ITO_RUNTIME_ENVIRONMENT_KEYS, [
"ITO_API_KEY",
"ITO_API_URL",
"ITO_INVENTORY_URL",
"ITO_AUTH_MODE",
"ITO_ALLOW_FILE_TOKEN",
"ITO_TOKEN_FILE",
]);
const safe = createSafeItoInvocationEnvironment(
{
PATH: process.env.PATH,
@@ -338,14 +452,14 @@ function main() {
);
}],
["rejects unsupported browser, paper, and execution operations before spawning", () => {
for (const command of ["rent", "lock", "run", "inference", "mcp"]) {
for (const command of ["rent", "lock", "purchase", "run", "inference", "mcp"]) {
const probe = makeItoProbe();
try {
const result = runCli(["ito", command], {
ECC_ITO_CLI_EXECUTABLE: probe.executable,
});
assert.notStrictEqual(result.status, 0, command);
assert.match(result.stderr, /only auth, find, status, and evals/i);
assert.match(result.stderr, /only login, auth, find, status, and evals/i);
assert.ok(!fs.existsSync(probe.log), `${command} must not spawn the Itô CLI`);
} finally {
fs.rmSync(probe.directory, { recursive: true, force: true });
@@ -510,13 +624,14 @@ function main() {
fs.rmSync(probe.directory, { recursive: true, force: true });
}
}],
["help exposes the truthful CLI and MCP surface without a browser path", () => {
["help separates device login from auth validation", () => {
const probe = makeItoProbe();
try {
const result = runCli(["ito", "--help"], {
ECC_ITO_CLI_EXECUTABLE: probe.executable,
});
assert.strictEqual(result.status, 0, result.stderr);
assert.match(result.stdout, /ecc ito login \[--no-browser\]/);
assert.match(result.stdout, /ecc ito auth/);
assert.match(result.stdout, /ecc ito find/);
assert.match(result.stdout, /ecc ito status/);
@@ -528,9 +643,15 @@ function main() {
assert.match(result.stdout, new RegExp(CANONICAL_PACKAGE.replaceAll("/", "\\/")));
assert.match(result.stdout, /unpublished/i);
assert.match(result.stdout, /never discovers[^\n]*through PATH/i);
assert.match(result.stdout, /device authorization/i);
assert.match(result.stdout, /opens the Itô verification page by default/i);
assert.match(result.stdout, /macOS Keychain/i);
assert.match(result.stdout, /ECC itself performs no browser automation/i);
assert.match(result.stdout, /auth.*validat/i);
assert.match(result.stdout, /ITO_AUTH_MODE=legacy is not\s+required/i);
assert.doesNotMatch(
result.stdout,
/manual copy|open(?:s)? (?:a )?browser|ito_lock|ito_run|npm link|paper|simulat/i
/manual copy|ito_lock|ito_run|npm link|paper|simulat/i
);
assert.ok(!fs.existsSync(probe.log));
} finally {
@@ -542,7 +663,7 @@ function main() {
let passed = 0;
let failed = 0;
for (const [name, fn] of tests) {
if (runTest(name, fn)) passed += 1;
if (await runTest(name, fn)) passed += 1;
else failed += 1;
}