mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-02 17:40:02 +02:00
* feat: add surface-aware exploratory QA and ship documentation gates * test: preserve delegated QA setup authority after main integration * fix(qa): clarify exploration order and preserve report artifacts * test(qa): follow the shared setup reference directly * refactor(ship): make verification and recovery routes explicit * test(ship): align evidence and review guards with explicit routes * fix(workflows): clarify ship recovery and functional QA evidence * fix(workflows): clarify approval recovery and full QA coverage * refactor(workflows): order review transactions and clarify ship state * fix(ship): clarify final verification and fail closed at publication * fix(evals): attribute native atomic documentation writes * fix(ship): clarify recovery and documentation lifecycle guidance * fix(test): preserve observed native placeholder styling in CI * fix(codex): report watchdog timeouts without a process-exit race * Checkpoint functional QA implementation and workflow validation repairs * Fix documentation and shared-review fixture contracts * docs: clarify judge reuse and evaluation supervision * test: align review evidence and selected case contracts * test: verify append-only documentation checkpoints and recovery * fix: qualify QA workflows and CI validation repairs * fix: launch shared-libs fixture scripts on Windows * fix: qualify QA deadlines, fixture isolation, and shard cleanup * fix: preserve qualified QA and cancellation repairs * fix: enforce functional fixture authority and share strict event decoding * fix: retain free-test evidence and explain recovery * fix: reject malformed native evidence after decoder consolidation * test: use reliable capture for telemetry privacy filters * test: refresh measured quick coverage and document validation costs * Fix native fixture receipts and preserve VM validation evidence * Align negative judge controls with upstream clarity policy * Fix report-only QA preparation and public evidence handling * Clarify QA-only preparation and current-report preservation * Stream Ship quality judgments with an explicit 64k response contract * Validate compact judge reasoning locally with supported wire schema * Align functional QA fixture instructions with evidence acceptance * Bind native browser diagnostics to execution evidence and align review verdicts * Preserve native diagnostic line boundaries * Serialize functional QA evidence from native captures * Keep large QA evidence fixture payload out of Windows argv
189 lines
6.8 KiB
TypeScript
189 lines
6.8 KiB
TypeScript
/**
|
|
* Live behavioral tests for the v1.62 token-bootstrap contract:
|
|
*
|
|
* - GET /health NEVER carries a token — not in headed mode, not for a
|
|
* chrome-extension:// Origin (the two pre-v1.62 carve-outs). IRON-RULE
|
|
* regression tests.
|
|
* - POST /extension-token releases the token ONLY to the pinned extension
|
|
* Origin (chrome-extension://GSTACK_EXTENSION_ID) with a loopback Host.
|
|
* - Host arrives with a port ('127.0.0.1:34567') and must be parsed to a
|
|
* hostname, not compared literally (amendment C9). 'localhost:34567'
|
|
* is accepted too.
|
|
* - The tunnel surface 404s /extension-token (not in TUNNEL_PATHS).
|
|
*
|
|
* Uses the buildFetchHandler factory (same pattern as server-factory.test.ts)
|
|
* so no listener/browser is needed. Real-HTTP coverage (Host header set by
|
|
* the network stack) lives in pair-agent-e2e.test.ts.
|
|
*/
|
|
|
|
import { describe, test, expect, beforeEach, afterAll } from 'bun:test';
|
|
import * as crypto from 'crypto';
|
|
import * as fs from 'node:fs';
|
|
import * as os from 'node:os';
|
|
import * as path from 'node:path';
|
|
import {
|
|
buildFetchHandler,
|
|
GSTACK_EXTENSION_ID,
|
|
type ServerConfig,
|
|
} from '../src/server';
|
|
import { __resetRegistry } from '../src/token-registry';
|
|
import { BrowserManager } from '../src/browser-manager';
|
|
import { resolveConfig } from '../src/config';
|
|
|
|
const PINNED_ORIGIN = `chrome-extension://${GSTACK_EXTENSION_ID}`;
|
|
const fixtureDir = fs.realpathSync(fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-extension-token-')));
|
|
const fixtureConfig = resolveConfig({ BROWSE_STATE_FILE: path.join(fixtureDir, 'state/browse.json') });
|
|
|
|
afterAll(() => {
|
|
fs.rmSync(fixtureDir, { recursive: true, force: true });
|
|
});
|
|
|
|
function makeConfig(overrides: Partial<ServerConfig> = {}): ServerConfig {
|
|
const token = 'ext-token-test-' + crypto.randomBytes(16).toString('hex');
|
|
return {
|
|
authToken: token,
|
|
browsePort: 34567,
|
|
idleTimeoutMs: 1_800_000,
|
|
config: fixtureConfig,
|
|
browserManager: new BrowserManager(),
|
|
ownsTerminalAgent: false,
|
|
startTime: Date.now(),
|
|
...overrides,
|
|
};
|
|
}
|
|
|
|
function headedBrowserManager(): BrowserManager {
|
|
const bm = new BrowserManager();
|
|
// connectionMode is private; force the headed value the old /health
|
|
// carve-out keyed on.
|
|
(bm as any).connectionMode = 'headed';
|
|
return bm;
|
|
}
|
|
|
|
function tokenRequest(headers: Record<string, string>): Request {
|
|
// Direct handler invocation — no network stack to synthesize Host, so
|
|
// every test sets it explicitly (Bun.serve always delivers one).
|
|
return new Request('http://127.0.0.1:34567/extension-token', {
|
|
method: 'POST',
|
|
headers,
|
|
});
|
|
}
|
|
|
|
describe('GET /health never carries a token (IRON RULE)', () => {
|
|
beforeEach(() => __resetRegistry());
|
|
|
|
test('headed mode: no token field in the body', async () => {
|
|
const handle = buildFetchHandler(makeConfig({ browserManager: headedBrowserManager() }));
|
|
const resp = await handle.fetchLocal(new Request('http://127.0.0.1:34567/health'), null);
|
|
expect(resp.status).toBe(200);
|
|
const body = await resp.json() as any;
|
|
expect(body.token).toBeUndefined();
|
|
expect(body.mode).toBe('headed');
|
|
});
|
|
|
|
test('chrome-extension Origin (even the pinned one): no token field', async () => {
|
|
const handle = buildFetchHandler(makeConfig());
|
|
const resp = await handle.fetchLocal(new Request('http://127.0.0.1:34567/health', {
|
|
headers: { Origin: PINNED_ORIGIN },
|
|
}), null);
|
|
expect(resp.status).toBe(200);
|
|
const body = await resp.json() as any;
|
|
expect(body.token).toBeUndefined();
|
|
});
|
|
|
|
test('headed mode AND pinned chrome-extension Origin together: still no token', async () => {
|
|
const handle = buildFetchHandler(makeConfig({ browserManager: headedBrowserManager() }));
|
|
const resp = await handle.fetchLocal(new Request('http://127.0.0.1:34567/health', {
|
|
headers: { Origin: PINNED_ORIGIN },
|
|
}), null);
|
|
const body = await resp.json() as any;
|
|
expect(body.token).toBeUndefined();
|
|
});
|
|
});
|
|
|
|
describe('POST /extension-token pinned-origin bootstrap', () => {
|
|
beforeEach(() => __resetRegistry());
|
|
|
|
test('pinned Origin + Host with port → 200 with the token', async () => {
|
|
const cfg = makeConfig();
|
|
const handle = buildFetchHandler(cfg);
|
|
const resp = await handle.fetchLocal(tokenRequest({
|
|
Origin: PINNED_ORIGIN,
|
|
Host: '127.0.0.1:34567',
|
|
}), null);
|
|
expect(resp.status).toBe(200);
|
|
const body = await resp.json() as any;
|
|
expect(body.token).toBe(cfg.authToken);
|
|
});
|
|
|
|
test("Host 'localhost:34567' is accepted too (C9 hostname parse)", async () => {
|
|
const cfg = makeConfig();
|
|
const handle = buildFetchHandler(cfg);
|
|
const resp = await handle.fetchLocal(tokenRequest({
|
|
Origin: PINNED_ORIGIN,
|
|
Host: 'localhost:34567',
|
|
}), null);
|
|
expect(resp.status).toBe(200);
|
|
const body = await resp.json() as any;
|
|
expect(body.token).toBe(cfg.authToken);
|
|
});
|
|
|
|
test('wrong extension Origin → 403, no token, no detail', async () => {
|
|
const handle = buildFetchHandler(makeConfig());
|
|
const resp = await handle.fetchLocal(tokenRequest({
|
|
Origin: 'chrome-extension://aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa',
|
|
Host: '127.0.0.1:34567',
|
|
}), null);
|
|
expect(resp.status).toBe(403);
|
|
const body = await resp.json() as any;
|
|
expect(body.token).toBeUndefined();
|
|
// No detail about WHICH check failed
|
|
expect(JSON.stringify(body)).not.toContain('origin');
|
|
expect(JSON.stringify(body)).not.toContain('host');
|
|
});
|
|
|
|
test('missing Origin → 403', async () => {
|
|
const handle = buildFetchHandler(makeConfig());
|
|
const resp = await handle.fetchLocal(tokenRequest({
|
|
Host: '127.0.0.1:34567',
|
|
}), null);
|
|
expect(resp.status).toBe(403);
|
|
});
|
|
|
|
test('web-page Origin → 403 (DNS-rebinding page cannot mint a token)', async () => {
|
|
const handle = buildFetchHandler(makeConfig());
|
|
const resp = await handle.fetchLocal(tokenRequest({
|
|
Origin: 'http://evil.example.com',
|
|
Host: '127.0.0.1:34567',
|
|
}), null);
|
|
expect(resp.status).toBe(403);
|
|
});
|
|
|
|
test('non-loopback Host → 403 even with the pinned Origin', async () => {
|
|
const handle = buildFetchHandler(makeConfig());
|
|
const resp = await handle.fetchLocal(tokenRequest({
|
|
Origin: PINNED_ORIGIN,
|
|
Host: 'evil.example.com:34567',
|
|
}), null);
|
|
expect(resp.status).toBe(403);
|
|
});
|
|
|
|
test('malformed Host → 403, not a crash', async () => {
|
|
const handle = buildFetchHandler(makeConfig());
|
|
const resp = await handle.fetchLocal(tokenRequest({
|
|
Origin: PINNED_ORIGIN,
|
|
Host: ':::not a host:::',
|
|
}), null);
|
|
expect(resp.status).toBe(403);
|
|
});
|
|
|
|
test('tunnel surface 404s /extension-token (not in TUNNEL_PATHS)', async () => {
|
|
const handle = buildFetchHandler(makeConfig());
|
|
const resp = await handle.fetchTunnel(tokenRequest({
|
|
Origin: PINNED_ORIGIN,
|
|
Host: '127.0.0.1:34567',
|
|
}), null);
|
|
expect(resp.status).toBe(404);
|
|
});
|
|
});
|