@runchr/gstack-antigravity 0.1.0 → 0.1.2

package/.agents/skills/gstack/test/codex-e2e.test.ts

@@ -0,0 +1,197 @@
+/**
+ * Codex CLI E2E tests — verify skills work when invoked by Codex.
+ *
+ * Spawns `codex exec` with skills installed in a temp HOME, parses JSONL
+ * output, and validates structured results. Follows the same pattern as
+ * skill-e2e.test.ts but adapted for Codex CLI.
+ *
+ * Prerequisites:
+ * - `codex` binary installed (npm install -g @openai/codex)
+ * - Codex authenticated via ~/.codex/ config (no OPENAI_API_KEY env var needed)
+ * - EVALS=1 env var set (same gate as Claude E2E tests)
+ *
+ * Skips gracefully when prerequisites are not met.
+ */
+
+import { describe, test, expect, afterAll } from 'bun:test';
+import { runCodexSkill, parseCodexJSONL, installSkillToTempHome } from './helpers/codex-session-runner';
+import type { CodexResult } from './helpers/codex-session-runner';
+import { EvalCollector } from './helpers/eval-store';
+import type { EvalTestEntry } from './helpers/eval-store';
+import { selectTests, detectBaseBranch, getChangedFiles, E2E_TOUCHFILES, GLOBAL_TOUCHFILES } from './helpers/touchfiles';
+import * as fs from 'fs';
+import * as path from 'path';
+import * as os from 'os';
+
+const ROOT = path.resolve(import.meta.dir, '..');
+
+// --- Prerequisites check ---
+
+const CODEX_AVAILABLE = (() => {
+  try {
+    const result = Bun.spawnSync(['which', 'codex']);
+    return result.exitCode === 0;
+  } catch { return false; }
+})();
+
+const evalsEnabled = !!process.env.EVALS;
+
+// Skip all tests if codex is not available or EVALS is not set.
+// Note: Codex uses its own auth from ~/.codex/ config — no OPENAI_API_KEY env var needed.
+const SKIP = !CODEX_AVAILABLE || !evalsEnabled;
+
+const describeCodex = SKIP ? describe.skip : describe;
+
+// Log why we're skipping (helpful for debugging CI)
+if (!evalsEnabled) {
+  // Silent — same as Claude E2E tests, EVALS=1 required
+} else if (!CODEX_AVAILABLE) {
+  process.stderr.write('\nCodex E2E: SKIPPED — codex binary not found (install: npm i -g @openai/codex)\n');
+}
+
+// --- Diff-based test selection ---
+
+// Codex E2E touchfiles — keyed by test name, same pattern as E2E_TOUCHFILES
+const CODEX_E2E_TOUCHFILES: Record<string, string[]> = {
+  'codex-discover-skill':    ['codex/**', '.agents/skills/**', 'test/helpers/codex-session-runner.ts'],
+  'codex-review-findings':   ['review/**', '.agents/skills/gstack-review/**', 'codex/**', 'test/helpers/codex-session-runner.ts'],
+};
+
+let selectedTests: string[] | null = null; // null = run all
+
+if (evalsEnabled && !process.env.EVALS_ALL) {
+  const baseBranch = process.env.EVALS_BASE
+    || detectBaseBranch(ROOT)
+    || 'main';
+  const changedFiles = getChangedFiles(baseBranch, ROOT);
+
+  if (changedFiles.length > 0) {
+    const selection = selectTests(changedFiles, CODEX_E2E_TOUCHFILES, GLOBAL_TOUCHFILES);
+    selectedTests = selection.selected;
+    process.stderr.write(`\nCodex E2E selection (${selection.reason}): ${selection.selected.length}/${Object.keys(CODEX_E2E_TOUCHFILES).length} tests\n`);
+    if (selection.skipped.length > 0) {
+      process.stderr.write(`  Skipped: ${selection.skipped.join(', ')}\n`);
+    }
+    process.stderr.write('\n');
+  }
+  // If changedFiles is empty (e.g., on main branch), selectedTests stays null -> run all
+}
+
+/** Skip an individual test if not selected by diff-based selection. */
+function testIfSelected(testName: string, fn: () => Promise<void>, timeout: number) {
+  const shouldRun = selectedTests === null || selectedTests.includes(testName);
+  (shouldRun ? test.concurrent : test.skip)(testName, fn, timeout);
+}
+
+// --- Eval result collector ---
+
+const evalCollector = evalsEnabled && !SKIP ? new EvalCollector('e2e-codex') : null;
+
+/** DRY helper to record a Codex E2E test result into the eval collector. */
+function recordCodexE2E(name: string, result: CodexResult, passed: boolean) {
+  evalCollector?.addTest({
+    name,
+    suite: 'codex-e2e',
+    tier: 'e2e',
+    passed,
+    duration_ms: result.durationMs,
+    cost_usd: 0, // Codex doesn't report cost in the same way; tokens are tracked
+    output: result.output?.slice(0, 2000),
+    turns_used: result.toolCalls.length, // approximate: tool calls as turns
+    exit_reason: result.exitCode === 0 ? 'success' : `exit_code_${result.exitCode}`,
+  });
+}
+
+/** Print cost summary after a Codex E2E test. */
+function logCodexCost(label: string, result: CodexResult) {
+  const durationSec = Math.round(result.durationMs / 1000);
+  console.log(`${label}: ${result.tokens} tokens, ${result.toolCalls.length} tool calls, ${durationSec}s`);
+}
+
+// Finalize eval results on exit
+afterAll(async () => {
+  if (evalCollector) {
+    await evalCollector.finalize();
+  }
+});
+
+// --- Tests ---
+
+describeCodex('Codex E2E', () => {
+
+  testIfSelected('codex-discover-skill', async () => {
+    // Install gstack-review skill to a temp HOME and ask Codex to list skills
+    const skillDir = path.join(ROOT, '.agents', 'skills', 'gstack-review');
+
+    const result = await runCodexSkill({
+      skillDir,
+      prompt: 'List any skills or instructions you have available. Just list the names.',
+      timeoutMs: 60_000,
+      cwd: ROOT,
+      skillName: 'gstack-review',
+    });
+
+    logCodexCost('codex-discover-skill', result);
+
+    // Codex should have produced some output
+    const passed = result.exitCode === 0 && result.output.length > 0;
+    recordCodexE2E('codex-discover-skill', result, passed);
+
+    expect(result.exitCode).toBe(0);
+    expect(result.output.length).toBeGreaterThan(0);
+    // The output should reference the skill name in some form
+    const outputLower = result.output.toLowerCase();
+    expect(
+      outputLower.includes('review') || outputLower.includes('gstack') || outputLower.includes('skill'),
+    ).toBe(true);
+  }, 120_000);
+
+  // Validates that Codex can invoke the gstack-review skill, run a diff-based
+  // code review, and produce structured review output with findings/issues.
+  // Accepts Codex timeout (exit 124/137) as non-failure since that's a CLI perf issue.
+  testIfSelected('codex-review-findings', async () => {
+    // Install gstack-review skill and ask Codex to review the current repo
+    const skillDir = path.join(ROOT, '.agents', 'skills', 'gstack-review');
+
+    const result = await runCodexSkill({
+      skillDir,
+      prompt: 'Run the gstack-review skill on this repository. Review the current branch diff and report your findings.',
+      timeoutMs: 540_000,
+      cwd: ROOT,
+      skillName: 'gstack-review',
+    });
+
+    logCodexCost('codex-review-findings', result);
+
+    // Should produce structured review-like output
+    const output = result.output;
+
+    // Codex may time out on large diffs — accept timeout as "not our fault"
+    // exitCode 124 = killed by timeout, which is a Codex CLI performance issue
+    if (result.exitCode === 124 || result.exitCode === 137) {
+      console.warn(`codex-review-findings: Codex timed out (exit ${result.exitCode}) — skipping assertions`);
+      recordCodexE2E('codex-review-findings', result, true); // don't fail the suite
+      return;
+    }
+
+    const passed = result.exitCode === 0 && output.length > 50;
+    recordCodexE2E('codex-review-findings', result, passed);
+
+    expect(result.exitCode).toBe(0);
+    expect(output.length).toBeGreaterThan(50);
+
+    // Review output should contain some review-like content
+    const outputLower = output.toLowerCase();
+    const hasReviewContent =
+      outputLower.includes('finding') ||
+      outputLower.includes('issue') ||
+      outputLower.includes('review') ||
+      outputLower.includes('change') ||
+      outputLower.includes('diff') ||
+      outputLower.includes('clean') ||
+      outputLower.includes('no issues') ||
+      outputLower.includes('p1') ||
+      outputLower.includes('p2');
+    expect(hasReviewContent).toBe(true);
+  }, 600_000);
+});

package/.agents/skills/gstack/test/fixtures/coverage-audit-fixture.ts

@@ -0,0 +1,76 @@
+/**
+ * Shared fixture for test coverage audit E2E tests.
+ *
+ * Creates a Node.js project with billing source code that has intentional
+ * test coverage gaps: processPayment has happy-path-only tests,
+ * refundPayment has no tests at all.
+ *
+ * Used by: ship-coverage-audit E2E, review-coverage-audit E2E
+ */
+
+import * as fs from 'fs';
+import * as path from 'path';
+import { spawnSync } from 'child_process';
+
+export function createCoverageAuditFixture(dir: string): void {
+  // Create a Node.js project WITH test framework but coverage gaps
+  fs.writeFileSync(path.join(dir, 'package.json'), JSON.stringify({
+    name: 'test-coverage-app',
+    version: '1.0.0',
+    type: 'module',
+    scripts: { test: 'echo "no tests yet"' },
+    devDependencies: { vitest: '^1.0.0' },
+  }, null, 2));
+
+  // Create vitest config
+  fs.writeFileSync(path.join(dir, 'vitest.config.ts'),
+    `import { defineConfig } from 'vitest/config';\nexport default defineConfig({ test: {} });\n`);
+
+  fs.writeFileSync(path.join(dir, 'VERSION'), '0.1.0.0\n');
+  fs.writeFileSync(path.join(dir, 'CHANGELOG.md'), '# Changelog\n');
+
+  // Create source file with multiple code paths
+  fs.mkdirSync(path.join(dir, 'src'), { recursive: true });
+  fs.writeFileSync(path.join(dir, 'src', 'billing.ts'), `
+export function processPayment(amount: number, currency: string) {
+  if (amount <= 0) throw new Error('Invalid amount');
+  if (currency !== 'USD' && currency !== 'EUR') throw new Error('Unsupported currency');
+  return { status: 'success', amount, currency };
+}
+
+export function refundPayment(paymentId: string, reason: string) {
+  if (!paymentId) throw new Error('Payment ID required');
+  if (!reason) throw new Error('Reason required');
+  return { status: 'refunded', paymentId, reason };
+}
+`);
+
+  // Create a test directory with ONE test (partial coverage)
+  fs.mkdirSync(path.join(dir, 'test'), { recursive: true });
+  fs.writeFileSync(path.join(dir, 'test', 'billing.test.ts'), `
+import { describe, test, expect } from 'vitest';
+import { processPayment } from '../src/billing';
+
+describe('processPayment', () => {
+  test('processes valid payment', () => {
+    const result = processPayment(100, 'USD');
+    expect(result.status).toBe('success');
+  });
+  // GAP: no test for invalid amount
+  // GAP: no test for unsupported currency
+  // GAP: refundPayment not tested at all
+});
+`);
+
+  // Init git repo with main branch
+  const run = (cmd: string, args: string[]) =>
+    spawnSync(cmd, args, { cwd: dir, stdio: 'pipe', timeout: 5000 });
+  run('git', ['init', '-b', 'main']);
+  run('git', ['config', 'user.email', 'test@test.com']);
+  run('git', ['config', 'user.name', 'Test']);
+  run('git', ['add', '.']);
+  run('git', ['commit', '-m', 'initial commit']);
+
+  // Create feature branch
+  run('git', ['checkout', '-b', 'feature/billing']);
+}

package/.agents/skills/gstack/test/fixtures/eval-baselines.json

@@ -0,0 +1,7 @@
+{
+  "command_reference": { "clarity": 4, "completeness": 3, "actionability": 4 },
+  "snapshot_flags": { "clarity": 4, "completeness": 4, "actionability": 4 },
+  "browse_skill": { "clarity": 4, "completeness": 4, "actionability": 4 },
+  "qa_workflow": { "clarity": 4, "completeness": 4, "actionability": 4 },
+  "qa_health_rubric": { "clarity": 4, "completeness": 3, "actionability": 4 }
+}

package/.agents/skills/gstack/test/fixtures/qa-eval-checkout-ground-truth.json

@@ -0,0 +1,43 @@
+{
+  "fixture": "qa-eval-checkout.html",
+  "bugs": [
+    {
+      "id": "broken-email-regex",
+      "category": "functional",
+      "severity": "high",
+      "description": "Email validation accepts 'user@' as valid — regex pattern [^@]+@[^@] is missing domain requirement",
+      "detection_hint": "email|regex|validation|accepts|invalid|user@|pattern"
+    },
+    {
+      "id": "nan-total",
+      "category": "functional",
+      "severity": "high",
+      "description": "Clearing the quantity field shows 'Total: $NaN' — parseInt on empty string returns NaN with no fallback",
+      "detection_hint": "NaN|total|quantity|empty|price|calculation|clear"
+    },
+    {
+      "id": "cc-field-overflow",
+      "category": "visual",
+      "severity": "medium",
+      "description": "Credit card input has no maxlength attribute — entering >20 characters causes text to overflow the container",
+      "detection_hint": "credit card|maxlength|overflow|cc|input|long|container"
+    },
+    {
+      "id": "missing-required-zip",
+      "category": "functional",
+      "severity": "medium",
+      "description": "Zip code field has no 'required' attribute — form can be submitted without a zip code",
+      "detection_hint": "zip|required|missing|form|submit|shipping|postal"
+    },
+    {
+      "id": "stripe-not-defined",
+      "category": "console",
+      "severity": "high",
+      "description": "Form submit triggers 'Uncaught ReferenceError: stripe is not defined' — payment SDK not loaded",
+      "detection_hint": "stripe|ReferenceError|not defined|console|error|submit|payment"
+    }
+  ],
+  "total_bugs": 5,
+  "minimum_detection": 2,
+  "max_false_positives": 5
+}

package/.agents/skills/gstack/test/fixtures/qa-eval-ground-truth.json

@@ -0,0 +1,43 @@
+{
+  "fixture": "qa-eval.html",
+  "bugs": [
+    {
+      "id": "broken-link",
+      "category": "functional",
+      "severity": "medium",
+      "description": "Navigation link 'Resources' points to /nonexistent-404-page which returns 404",
+      "detection_hint": "link|404|broken|dead|nonexistent|Resources"
+    },
+    {
+      "id": "disabled-submit",
+      "category": "functional",
+      "severity": "high",
+      "description": "Contact form submit button has 'disabled' attribute permanently — form can never be submitted",
+      "detection_hint": "disabled|submit|button|form|cannot submit|contact"
+    },
+    {
+      "id": "content-overflow",
+      "category": "visual",
+      "severity": "medium",
+      "description": "Statistics text is clipped by overflow:hidden container — content wider than 400px container",
+      "detection_hint": "overflow|clipped|truncated|hidden|text cut|statistics"
+    },
+    {
+      "id": "missing-alt",
+      "category": "accessibility",
+      "severity": "medium",
+      "description": "Logo image (<img src='/logo.png'>) has no alt attribute",
+      "detection_hint": "alt|accessibility|image|a11y|missing alt|logo"
+    },
+    {
+      "id": "console-error",
+      "category": "console",
+      "severity": "high",
+      "description": "TypeError on page load: Cannot read properties of undefined (reading 'map')",
+      "detection_hint": "console|error|TypeError|undefined|map"
+    }
+  ],
+  "total_bugs": 5,
+  "minimum_detection": 2,
+  "max_false_positives": 5
+}

package/.agents/skills/gstack/test/fixtures/qa-eval-spa-ground-truth.json

@@ -0,0 +1,43 @@
+{
+  "fixture": "qa-eval-spa.html",
+  "bugs": [
+    {
+      "id": "broken-route",
+      "category": "functional",
+      "severity": "high",
+      "description": "Products nav link points to #/prodcts (typo) instead of #/products — shows 'Page not found'",
+      "detection_hint": "route|prodcts|typo|products|not found|broken link|navigation"
+    },
+    {
+      "id": "stale-cart-state",
+      "category": "functional",
+      "severity": "medium",
+      "description": "Cart count persists across route changes — never resets when navigating away from products",
+      "detection_hint": "cart|count|state|persist|reset|stale|navigation"
+    },
+    {
+      "id": "async-fetch-error",
+      "category": "functional",
+      "severity": "high",
+      "description": "Product list briefly loads then shows 'Error: Failed to fetch products from API' after 1 second",
+      "detection_hint": "error|fetch|products|API|loading|failed|async"
+    },
+    {
+      "id": "missing-aria-current",
+      "category": "accessibility",
+      "severity": "medium",
+      "description": "Navigation links have no aria-current attribute to indicate the active route",
+      "detection_hint": "aria|current|active|navigation|accessibility|a11y"
+    },
+    {
+      "id": "console-warn-leak",
+      "category": "console",
+      "severity": "medium",
+      "description": "console.warn fires on every route change: 'Possible memory leak detected: 11 event listeners'",
+      "detection_hint": "console|warn|memory leak|listener|event|warning"
+    }
+  ],
+  "total_bugs": 5,
+  "minimum_detection": 2,
+  "max_false_positives": 5
+}

package/.agents/skills/gstack/test/fixtures/review-eval-design-slop.css

@@ -0,0 +1,86 @@
+/* Planted design anti-patterns for E2E eval — 7 issues */
+
+/* Issue 1: [HIGH] Blacklisted font (Papyrus) */
+/* Issue 2: [HIGH] Body text < 16px (14px) */
+body {
+  font-family: 'Papyrus', sans-serif;
+  font-size: 14px;
+  margin: 0;
+  padding: 0;
+}
+
+/* Issue 5: [MEDIUM] Purple/violet gradient background */
+.hero {
+  background: linear-gradient(135deg, #6366f1, #8b5cf6);
+  text-align: center;
+  padding: 80px 20px;
+  color: white;
+}
+
+.hero h1 {
+  text-align: center;
+  font-size: 48px;
+}
+
+.hero p {
+  text-align: center;
+  font-size: 20px;
+}
+
+/* Issue 7: [LOW] 3-column feature grid with icon circles */
+.features {
+  display: grid;
+  grid-template-columns: repeat(3, 1fr);
+  gap: 24px;
+  padding: 60px 40px;
+  text-align: center;
+}
+
+.feature-card {
+  border-radius: 24px;
+  padding: 32px;
+  text-align: center;
+  background: #f9fafb;
+}
+
+/* Icon in colored circle — AI slop pattern */
+.icon-circle {
+  width: 60px;
+  height: 60px;
+  border-radius: 50%;
+  background: #ede9fe;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  margin: 0 auto 16px;
+  font-size: 24px;
+}
+
+/* Issue 3: [HIGH] outline: none without replacement */
+button {
+  outline: none;
+  background: #6366f1;
+  color: white;
+  border: none;
+  padding: 12px 24px;
+  border-radius: 24px;
+  cursor: pointer;
+}
+
+.small-link {
+  font-size: 11px;
+  padding: 4px 8px;
+}
+
+/* Issue 4: [HIGH] !important usage */
+.override {
+  color: red !important;
+  margin-left: 10px !important;
+}
+
+.footer {
+  text-align: center;
+  padding: 40px;
+  background: #1e1b4b;
+  color: white;
+}

package/.agents/skills/gstack/test/fixtures/review-eval-design-slop.html

@@ -0,0 +1,41 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <link rel="stylesheet" href="styles.css">
+  <title>Our Platform</title>
+</head>
+<body>
+  <!-- Issue 6: [MEDIUM] Generic hero copy ("Welcome to...", "all-in-one solution") -->
+  <div class="hero">
+    <h1>Welcome to Our Platform</h1>
+    <p>Your all-in-one solution for everything you need</p>
+    <button>Get Started</button>
+  </div>
+
+  <!-- Issue 7: [LOW] 3-column feature grid with icon-in-circle + title + description -->
+  <div class="features">
+    <div class="feature-card">
+      <div class="icon-circle">&#9733;</div>
+      <h3>Feature One</h3>
+      <p>A short description of this amazing feature that will change your life.</p>
+    </div>
+    <div class="feature-card">
+      <div class="icon-circle">&#9889;</div>
+      <h3>Feature Two</h3>
+      <p>Another incredible capability that sets us apart from the competition.</p>
+    </div>
+    <div class="feature-card">
+      <div class="icon-circle">&#9881;</div>
+      <h3>Feature Three</h3>
+      <p>Yet another powerful tool to streamline your workflow effortlessly.</p>
+    </div>
+  </div>
+
+  <div class="footer">
+    <p class="override">Unlock the power of our platform today</p>
+    <a href="#" class="small-link">Terms of Service</a>
+  </div>
+</body>
+</html>

package/.agents/skills/gstack/test/fixtures/review-eval-enum-diff.rb

@@ -0,0 +1,30 @@
+# Feature branch version: adds "returned" status but misses consumers
+class Order < ApplicationRecord
+  STATUSES = %w[pending processing shipped delivered returned].freeze
+
+  validates :status, inclusion: { in: STATUSES }
+
+  def display_status
+    case status
+    when 'pending'    then 'Awaiting processing'
+    when 'processing' then 'Being prepared'
+    when 'shipped'    then 'On the way'
+    when 'delivered'  then 'Delivered'
+    # BUG: 'returned' not handled — falls through to nil
+    end
+  end
+
+  def can_cancel?
+    # BUG: should 'returned' be cancellable? Not considered.
+    %w[pending processing].include?(status)
+  end
+
+  def notify_customer
+    case status
+    when 'pending'    then OrderMailer.confirmation(self).deliver_later
+    when 'shipped'    then OrderMailer.shipped(self).deliver_later
+    when 'delivered'  then OrderMailer.delivered(self).deliver_later
+    # BUG: 'returned' has no notification — customer won't know return was received
+    end
+  end
+end

package/.agents/skills/gstack/test/fixtures/review-eval-enum.rb

@@ -0,0 +1,27 @@
+# Existing file on main: order model with status handling
+class Order < ApplicationRecord
+  STATUSES = %w[pending processing shipped delivered].freeze
+
+  validates :status, inclusion: { in: STATUSES }
+
+  def display_status
+    case status
+    when 'pending'    then 'Awaiting processing'
+    when 'processing' then 'Being prepared'
+    when 'shipped'    then 'On the way'
+    when 'delivered'  then 'Delivered'
+    end
+  end
+
+  def can_cancel?
+    %w[pending processing].include?(status)
+  end
+
+  def notify_customer
+    case status
+    when 'pending'    then OrderMailer.confirmation(self).deliver_later
+    when 'shipped'    then OrderMailer.shipped(self).deliver_later
+    when 'delivered'  then OrderMailer.delivered(self).deliver_later
+    end
+  end
+end

package/.agents/skills/gstack/test/fixtures/review-eval-vuln.rb

@@ -0,0 +1,14 @@
+class UserController < ApplicationController
+  def show
+    # SQL injection — interpolating user input directly into query
+    @user = User.where("id = #{params[:id]}").first
+    render json: @user
+  end
+
+  def promote
+    # Bypasses ActiveRecord validations — update_column skips callbacks + validation
+    @user = User.find(params[:id])
+    @user.update_column(:role, 'admin')
+    head :ok
+  end
+end