test: comprehensive tests for auth ordering, tunnel, ngrok, headed mode

16 new tests covering:
- /command sits above blanket auth gate (Wintermute bug)
- /command uses getTokenInfo not validateAuth
- /tunnel/start requires root, checks native ngrok config, returns already_active
- /pair creates setup keys not session tokens
- Tab ownership checked before command dispatch
- Activity events include clientId
- Instruction block teaches snapshot→@ref pattern
- pair-agent auto-headed mode, process.execPath, --headless skip
- isNgrokAvailable checks all 3 sources (gstack env, env var, native config)
- handlePairAgent calls /tunnel/start not server restart

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-04-05 00:12:05 -07:00
parent e06f0a6696
commit a5b40045b8
2 changed files with 160 additions and 0 deletions
+67
View File
@@ -77,4 +77,71 @@ describe('Server auth security', () => {
// Should not have wildcard CORS for the SSE stream
expect(streamBlock).not.toContain("Access-Control-Allow-Origin': '*'");
});
// Test 7: /command accepts scoped tokens (not just root)
// This was the Wintermute bug — /command was BELOW the blanket validateAuth gate
// which only accepts root tokens. Scoped tokens got 401'd before reaching getTokenInfo.
test('/command endpoint sits ABOVE the blanket root-only auth gate', () => {
const commandIdx = SERVER_SRC.indexOf("url.pathname === '/command'");
const blanketGateIdx = SERVER_SRC.indexOf("Auth-required endpoints (root token only)");
// /command must appear BEFORE the blanket gate in source order
expect(commandIdx).toBeGreaterThan(0);
expect(blanketGateIdx).toBeGreaterThan(0);
expect(commandIdx).toBeLessThan(blanketGateIdx);
});
// Test 7b: /command uses getTokenInfo (accepts scoped tokens), not validateAuth (root-only)
test('/command uses getTokenInfo for auth, not validateAuth', () => {
const commandBlock = sliceBetween(SERVER_SRC, "url.pathname === '/command'", "Auth-required endpoints");
expect(commandBlock).toContain('getTokenInfo');
expect(commandBlock).not.toContain('validateAuth');
});
// Test 8: /tunnel/start requires root token
test('/tunnel/start requires root token', () => {
const tunnelBlock = sliceBetween(SERVER_SRC, "/tunnel/start", "Refs endpoint");
expect(tunnelBlock).toContain('isRootRequest');
expect(tunnelBlock).toContain('Root token required');
});
// Test 8b: /tunnel/start checks ngrok native config paths
test('/tunnel/start reads ngrok native config files', () => {
const tunnelBlock = sliceBetween(SERVER_SRC, "/tunnel/start", "Refs endpoint");
expect(tunnelBlock).toContain("'ngrok.yml'");
expect(tunnelBlock).toContain('authtoken');
});
// Test 8c: /tunnel/start returns already_active if tunnel is running
test('/tunnel/start returns already_active when tunnel exists', () => {
const tunnelBlock = sliceBetween(SERVER_SRC, "/tunnel/start", "Refs endpoint");
expect(tunnelBlock).toContain('already_active');
expect(tunnelBlock).toContain('tunnelActive');
});
// Test 9: /pair requires root token
test('/pair requires root token', () => {
const pairBlock = sliceBetween(SERVER_SRC, "url.pathname === '/pair'", "/tunnel/start");
expect(pairBlock).toContain('isRootRequest');
expect(pairBlock).toContain('Root token required');
});
// Test 9b: /pair calls createSetupKey (not createToken)
test('/pair creates setup keys, not session tokens', () => {
const pairBlock = sliceBetween(SERVER_SRC, "url.pathname === '/pair'", "/tunnel/start");
expect(pairBlock).toContain('createSetupKey');
expect(pairBlock).not.toContain('createToken');
});
// Test 10: tab ownership check happens before command dispatch
test('tab ownership check runs before command dispatch for scoped tokens', () => {
const handleBlock = sliceBetween(SERVER_SRC, "async function handleCommand", "Block mutation commands while watching");
expect(handleBlock).toContain('checkTabAccess');
expect(handleBlock).toContain('Tab not owned by your agent');
});
// Test 10b: activity attribution includes clientId
test('activity events include clientId from token', () => {
const commandStartBlock = sliceBetween(SERVER_SRC, "Activity: emit command_start", "try {");
expect(commandStartBlock).toContain('clientId: tokenInfo?.clientId');
});
});
+93
View File
@@ -148,4 +148,97 @@ describe('generateInstructionBlock', () => {
expect(block).toContain('403');
expect(block).toContain('429');
});
it('teaches the snapshot→@ref pattern', () => {
const block = generateInstructionBlock({
setupKey: 'gsk_setup_snap',
serverUrl: 'https://test.ngrok.dev',
scopes: ['read', 'write'],
expiresAt: '2026-04-06T00:00:00Z',
});
// Must explain the snapshot→@ref workflow
expect(block).toContain('snapshot');
expect(block).toContain('@e1');
expect(block).toContain('@e2');
expect(block).toContain("Always snapshot first");
expect(block).toContain("Don't guess selectors");
});
it('shows SERVER URL prominently', () => {
const block = generateInstructionBlock({
setupKey: 'gsk_setup_url',
serverUrl: 'https://my-tunnel.ngrok.dev',
scopes: ['read', 'write'],
expiresAt: '2026-04-06T00:00:00Z',
});
expect(block).toContain('SERVER: https://my-tunnel.ngrok.dev');
});
it('includes newtab in COMMAND REFERENCE', () => {
const block = generateInstructionBlock({
setupKey: 'gsk_setup_ref',
serverUrl: 'https://test.ngrok.dev',
scopes: ['read', 'write'],
expiresAt: '2026-04-06T00:00:00Z',
});
expect(block).toContain('"command": "newtab"');
expect(block).toContain('"command": "goto"');
expect(block).toContain('"command": "snapshot"');
expect(block).toContain('"command": "click"');
expect(block).toContain('"command": "fill"');
});
});
// Test CLI source-level behavior (pair-agent headed mode, ngrok detection)
import * as fs from 'fs';
import * as path from 'path';
const CLI_SRC = fs.readFileSync(path.join(import.meta.dir, '../src/cli.ts'), 'utf-8');
describe('pair-agent CLI behavior', () => {
// Extract the pair-agent block: from "pair-agent" dispatch to "process.exit(0)"
const pairStart = CLI_SRC.indexOf("command === 'pair-agent'");
const pairEnd = CLI_SRC.indexOf('process.exit(0)', pairStart);
const pairBlock = CLI_SRC.slice(pairStart, pairEnd);
it('auto-switches to headed mode unless --headless', () => {
expect(pairBlock).toContain("state.mode !== 'headed'");
expect(pairBlock).toContain("--headless");
expect(pairBlock).toContain("connect");
});
it('uses process.execPath for binary path (not argv[1] which is virtual in compiled)', () => {
expect(pairBlock).toContain('process.execPath');
// browseBin should be set to execPath, not argv[1]
expect(pairBlock).toContain('const browseBin = process.execPath');
});
it('isNgrokAvailable checks gstack env, NGROK_AUTHTOKEN, and native config', () => {
const ngrokBlock = CLI_SRC.slice(
CLI_SRC.indexOf('function isNgrokAvailable'),
CLI_SRC.indexOf('// ─── Pair-Agent DX')
);
// Three sources checked (paths are in path.join() calls, check the string literals)
expect(ngrokBlock).toContain("'ngrok.env'");
expect(ngrokBlock).toContain('NGROK_AUTHTOKEN');
expect(ngrokBlock).toContain("'ngrok.yml'");
// Checks macOS, Linux XDG, and legacy paths
expect(ngrokBlock).toContain("'Application Support'");
expect(ngrokBlock).toContain("'.config'");
expect(ngrokBlock).toContain("'.ngrok2'");
});
it('calls POST /tunnel/start when ngrok is available (not restart)', () => {
const handleBlock = CLI_SRC.slice(
CLI_SRC.indexOf('async function handlePairAgent'),
CLI_SRC.indexOf('function main()')
);
expect(handleBlock).toContain('/tunnel/start');
// Must NOT contain server restart logic
expect(handleBlock).not.toContain('Bun.spawn([\'bun\', \'run\'');
expect(handleBlock).not.toContain('BROWSE_TUNNEL');
});
});