@runchr/gstack-antigravity 0.1.0 → 0.1.2

package/.agents/skills/gstack/test/helpers/touchfiles.ts

@@ -0,0 +1,260 @@
+/**
+ * Diff-based test selection for E2E and LLM-judge evals.
+ *
+ * Each test declares which source files it depends on ("touchfiles").
+ * The test runner checks `git diff` and only runs tests whose
+ * dependencies were modified. Override with EVALS_ALL=1 to run everything.
+ */
+
+import { spawnSync } from 'child_process';
+
+// --- Glob matching ---
+
+/**
+ * Match a file path against a glob pattern.
+ * Supports:
+ *   ** — match any number of path segments
+ *   *  — match within a single segment (no /)
+ */
+export function matchGlob(file: string, pattern: string): boolean {
+  const regexStr = pattern
+    .replace(/\./g, '\\.')
+    .replace(/\*\*/g, '{{GLOBSTAR}}')
+    .replace(/\*/g, '[^/]*')
+    .replace(/\{\{GLOBSTAR\}\}/g, '.*');
+  return new RegExp(`^${regexStr}$`).test(file);
+}
+
+// --- Touchfile maps ---
+
+/**
+ * E2E test touchfiles — keyed by testName (the string passed to runSkillTest).
+ * Each test lists the file patterns that, if changed, require the test to run.
+ */
+export const E2E_TOUCHFILES: Record<string, string[]> = {
+  // Browse core
+  'browse-basic':    ['browse/src/**'],
+  'browse-snapshot': ['browse/src/**'],
+
+  // SKILL.md setup + preamble (depend on ROOT SKILL.md only)
+  'skillmd-setup-discovery':  ['SKILL.md', 'SKILL.md.tmpl'],
+  'skillmd-no-local-binary':  ['SKILL.md', 'SKILL.md.tmpl'],
+  'skillmd-outside-git':      ['SKILL.md', 'SKILL.md.tmpl'],
+
+  'contributor-mode':           ['SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'session-awareness':        ['SKILL.md', 'SKILL.md.tmpl'],
+
+  // QA
+  'qa-quick':       ['qa/**', 'browse/src/**'],
+  'qa-b6-static':   ['qa/**', 'browse/src/**', 'browse/test/fixtures/qa-eval.html', 'test/fixtures/qa-eval-ground-truth.json'],
+  'qa-b7-spa':      ['qa/**', 'browse/src/**', 'browse/test/fixtures/qa-eval-spa.html', 'test/fixtures/qa-eval-spa-ground-truth.json'],
+  'qa-b8-checkout': ['qa/**', 'browse/src/**', 'browse/test/fixtures/qa-eval-checkout.html', 'test/fixtures/qa-eval-checkout-ground-truth.json'],
+  'qa-only-no-fix': ['qa-only/**', 'qa/templates/**'],
+  'qa-fix-loop':    ['qa/**', 'browse/src/**'],
+  'qa-bootstrap':   ['qa/**', 'ship/**'],
+
+  // Review
+  'review-sql-injection':     ['review/**', 'test/fixtures/review-eval-vuln.rb'],
+  'review-enum-completeness': ['review/**', 'test/fixtures/review-eval-enum*.rb'],
+  'review-base-branch':       ['review/**'],
+  'review-design-lite':       ['review/**', 'test/fixtures/review-eval-design-slop.*'],
+
+  // Office Hours
+  'office-hours-spec-review':  ['office-hours/**', 'scripts/gen-skill-docs.ts'],
+
+  // Plan reviews
+  'plan-ceo-review':           ['plan-ceo-review/**'],
+  'plan-ceo-review-selective': ['plan-ceo-review/**'],
+  'plan-ceo-review-benefits':  ['plan-ceo-review/**', 'scripts/gen-skill-docs.ts'],
+  'plan-eng-review':           ['plan-eng-review/**'],
+  'plan-eng-review-artifact':  ['plan-eng-review/**'],
+
+  // Ship
+  'ship-base-branch': ['ship/**', 'bin/gstack-repo-mode'],
+  'ship-local-workflow': ['ship/**', 'scripts/gen-skill-docs.ts'],
+
+  // Setup browser cookies
+  'setup-cookies-detect': ['setup-browser-cookies/**'],
+
+  // Retro
+  'retro':             ['retro/**'],
+  'retro-base-branch': ['retro/**'],
+
+  // Global discover
+  'global-discover':   ['bin/gstack-global-discover.ts', 'test/global-discover.test.ts'],
+
+  // Document-release
+  'document-release': ['document-release/**'],
+
+  // Codex (Claude E2E — tests /codex skill via Claude)
+  'codex-review': ['codex/**'],
+
+  // Codex E2E (tests skills via Codex CLI)
+  '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'],
+
+  // Gemini E2E (tests skills via Gemini CLI)
+  'gemini-discover-skill':  ['.agents/skills/**', 'test/helpers/gemini-session-runner.ts'],
+  'gemini-review-findings': ['review/**', '.agents/skills/gstack-review/**', 'test/helpers/gemini-session-runner.ts'],
+
+
+  // Coverage audit (shared fixture) + triage
+  'ship-coverage-audit': ['ship/**', 'test/fixtures/coverage-audit-fixture.ts', 'bin/gstack-repo-mode'],
+  'review-coverage-audit': ['review/**', 'test/fixtures/coverage-audit-fixture.ts'],
+  'plan-eng-coverage-audit': ['plan-eng-review/**', 'test/fixtures/coverage-audit-fixture.ts'],
+  'ship-triage': ['ship/**', 'bin/gstack-repo-mode'],
+
+  // Design
+  'design-consultation-core':       ['design-consultation/**'],
+  'design-consultation-existing':   ['design-consultation/**'],
+  'design-consultation-research':   ['design-consultation/**'],
+  'design-consultation-preview':    ['design-consultation/**'],
+  'plan-design-review-plan-mode':   ['plan-design-review/**'],
+  'plan-design-review-no-ui-scope': ['plan-design-review/**'],
+  'design-review-fix':              ['design-review/**', 'browse/src/**'],
+
+  // gstack-upgrade
+  'gstack-upgrade-happy-path': ['gstack-upgrade/**'],
+
+  // Deploy skills
+  'land-and-deploy-workflow':   ['land-and-deploy/**', 'scripts/gen-skill-docs.ts'],
+  'canary-workflow':            ['canary/**', 'browse/src/**'],
+  'benchmark-workflow':         ['benchmark/**', 'browse/src/**'],
+  'setup-deploy-workflow':      ['setup-deploy/**', 'scripts/gen-skill-docs.ts'],
+
+  // Autoplan
+  'autoplan-core':  ['autoplan/**', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**'],
+
+  // Skill routing — journey-stage tests (depend on ALL skill descriptions)
+  'journey-ideation':       ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'journey-plan-eng':       ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'journey-think-bigger':   ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'journey-debug':          ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'journey-qa':             ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'journey-code-review':    ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'journey-ship':           ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'journey-docs':           ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'journey-retro':          ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'journey-design-system':  ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'journey-visual-qa':      ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+};
+
+/**
+ * LLM-judge test touchfiles — keyed by test description string.
+ */
+export const LLM_JUDGE_TOUCHFILES: Record<string, string[]> = {
+  'command reference table':          ['SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts'],
+  'snapshot flags reference':         ['SKILL.md', 'SKILL.md.tmpl', 'browse/src/snapshot.ts'],
+  'browse/SKILL.md reference':        ['browse/SKILL.md', 'browse/SKILL.md.tmpl', 'browse/src/**'],
+  'setup block':                      ['SKILL.md', 'SKILL.md.tmpl'],
+  'regression vs baseline':           ['SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts', 'test/fixtures/eval-baselines.json'],
+  'qa/SKILL.md workflow':             ['qa/SKILL.md', 'qa/SKILL.md.tmpl'],
+  'qa/SKILL.md health rubric':        ['qa/SKILL.md', 'qa/SKILL.md.tmpl'],
+  'qa/SKILL.md anti-refusal':         ['qa/SKILL.md', 'qa/SKILL.md.tmpl', 'qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl'],
+  'cross-skill greptile consistency': ['review/SKILL.md', 'review/SKILL.md.tmpl', 'ship/SKILL.md', 'ship/SKILL.md.tmpl', 'review/greptile-triage.md', 'retro/SKILL.md', 'retro/SKILL.md.tmpl'],
+  'baseline score pinning':           ['SKILL.md', 'SKILL.md.tmpl', 'test/fixtures/eval-baselines.json'],
+
+  // Ship & Release
+  'ship/SKILL.md workflow':               ['ship/SKILL.md', 'ship/SKILL.md.tmpl'],
+  'document-release/SKILL.md workflow':   ['document-release/SKILL.md', 'document-release/SKILL.md.tmpl'],
+
+  // Plan Reviews
+  'plan-ceo-review/SKILL.md modes':       ['plan-ceo-review/SKILL.md', 'plan-ceo-review/SKILL.md.tmpl'],
+  'plan-eng-review/SKILL.md sections':    ['plan-eng-review/SKILL.md', 'plan-eng-review/SKILL.md.tmpl'],
+  'plan-design-review/SKILL.md passes':   ['plan-design-review/SKILL.md', 'plan-design-review/SKILL.md.tmpl'],
+
+  // Design skills
+  'design-review/SKILL.md fix loop':      ['design-review/SKILL.md', 'design-review/SKILL.md.tmpl'],
+  'design-consultation/SKILL.md research': ['design-consultation/SKILL.md', 'design-consultation/SKILL.md.tmpl'],
+
+  // Office Hours
+  'office-hours/SKILL.md spec review':    ['office-hours/SKILL.md', 'office-hours/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+  'office-hours/SKILL.md design sketch':  ['office-hours/SKILL.md', 'office-hours/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
+
+  // Deploy skills
+  'land-and-deploy/SKILL.md workflow':    ['land-and-deploy/SKILL.md', 'land-and-deploy/SKILL.md.tmpl'],
+  'canary/SKILL.md monitoring loop':      ['canary/SKILL.md', 'canary/SKILL.md.tmpl'],
+  'benchmark/SKILL.md perf collection':   ['benchmark/SKILL.md', 'benchmark/SKILL.md.tmpl'],
+  'setup-deploy/SKILL.md platform setup': ['setup-deploy/SKILL.md', 'setup-deploy/SKILL.md.tmpl'],
+
+  // Other skills
+  'retro/SKILL.md instructions':          ['retro/SKILL.md', 'retro/SKILL.md.tmpl'],
+  'qa-only/SKILL.md workflow':            ['qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl'],
+  'gstack-upgrade/SKILL.md upgrade flow': ['gstack-upgrade/SKILL.md', 'gstack-upgrade/SKILL.md.tmpl'],
+};
+
+/**
+ * Changes to any of these files trigger ALL tests (both E2E and LLM-judge).
+ */
+export const GLOBAL_TOUCHFILES = [
+  'test/helpers/session-runner.ts',
+  'test/helpers/codex-session-runner.ts',
+  'test/helpers/gemini-session-runner.ts',
+  'test/helpers/eval-store.ts',
+  'test/helpers/llm-judge.ts',
+  'scripts/gen-skill-docs.ts',
+  'test/helpers/touchfiles.ts',
+  'browse/test/test-server.ts',
+];
+
+// --- Base branch detection ---
+
+/**
+ * Detect the base branch by trying refs in order.
+ * Returns the first valid ref, or null if none found.
+ */
+export function detectBaseBranch(cwd: string): string | null {
+  for (const ref of ['origin/main', 'origin/master', 'main', 'master']) {
+    const result = spawnSync('git', ['rev-parse', '--verify', ref], {
+      cwd, stdio: 'pipe', timeout: 3000,
+    });
+    if (result.status === 0) return ref;
+  }
+  return null;
+}
+
+/**
+ * Get list of files changed between base branch and HEAD.
+ */
+export function getChangedFiles(baseBranch: string, cwd: string): string[] {
+  const result = spawnSync('git', ['diff', '--name-only', `${baseBranch}...HEAD`], {
+    cwd, stdio: 'pipe', timeout: 5000,
+  });
+  if (result.status !== 0) return [];
+  return result.stdout.toString().trim().split('\n').filter(Boolean);
+}
+
+// --- Test selection ---
+
+/**
+ * Select tests to run based on changed files.
+ *
+ * Algorithm:
+ * 1. If any changed file matches a global touchfile → run ALL tests
+ * 2. Otherwise, for each test, check if any changed file matches its patterns
+ * 3. Return selected + skipped lists with reason
+ */
+export function selectTests(
+  changedFiles: string[],
+  touchfiles: Record<string, string[]>,
+  globalTouchfiles: string[] = GLOBAL_TOUCHFILES,
+): { selected: string[]; skipped: string[]; reason: string } {
+  const allTestNames = Object.keys(touchfiles);
+
+  // Global touchfile hit → run all
+  for (const file of changedFiles) {
+    if (globalTouchfiles.some(g => matchGlob(file, g))) {
+      return { selected: allTestNames, skipped: [], reason: `global: ${file}` };
+    }
+  }
+
+  // Per-test matching
+  const selected: string[] = [];
+  const skipped: string[] = [];
+  for (const [testName, patterns] of Object.entries(touchfiles)) {
+    const hit = changedFiles.some(f => patterns.some(p => matchGlob(f, p)));
+    (hit ? selected : skipped).push(testName);
+  }
+
+  return { selected, skipped, reason: 'diff' };
+}

package/.agents/skills/gstack/test/hook-scripts.test.ts

@@ -0,0 +1,373 @@
+import { describe, test, expect } from 'bun:test';
+import { spawnSync } from 'child_process';
+import * as path from 'path';
+import * as fs from 'fs';
+import * as os from 'os';
+
+const ROOT = path.resolve(import.meta.dir, '..');
+const CAREFUL_SCRIPT = path.join(ROOT, 'careful', 'bin', 'check-careful.sh');
+const FREEZE_SCRIPT = path.join(ROOT, 'freeze', 'bin', 'check-freeze.sh');
+
+function runHook(scriptPath: string, input: object, env?: Record<string, string>): { exitCode: number; output: any; raw: string } {
+  const result = spawnSync('bash', [scriptPath], {
+    input: JSON.stringify(input),
+    stdio: ['pipe', 'pipe', 'pipe'],
+    env: { ...process.env, ...env },
+    timeout: 5000,
+  });
+  const raw = result.stdout.toString().trim();
+  let output: any = {};
+  try {
+    output = JSON.parse(raw);
+  } catch {}
+  return { exitCode: result.status ?? 1, output, raw };
+}
+
+function runHookRaw(scriptPath: string, rawInput: string, env?: Record<string, string>): { exitCode: number; output: any; raw: string } {
+  const result = spawnSync('bash', [scriptPath], {
+    input: rawInput,
+    stdio: ['pipe', 'pipe', 'pipe'],
+    env: { ...process.env, ...env },
+    timeout: 5000,
+  });
+  const raw = result.stdout.toString().trim();
+  let output: any = {};
+  try {
+    output = JSON.parse(raw);
+  } catch {}
+  return { exitCode: result.status ?? 1, output, raw };
+}
+
+function carefulInput(command: string) {
+  return { tool_input: { command } };
+}
+
+function freezeInput(filePath: string) {
+  return { tool_input: { file_path: filePath } };
+}
+
+function withFreezeDir(freezePath: string, fn: (stateDir: string) => void) {
+  const stateDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-freeze-test-'));
+  fs.writeFileSync(path.join(stateDir, 'freeze-dir.txt'), freezePath);
+  try {
+    fn(stateDir);
+  } finally {
+    fs.rmSync(stateDir, { recursive: true, force: true });
+  }
+}
+
+// Detect whether the safe-rm-targets regex works on this platform.
+// macOS sed -E does not support \s, so the safe exception check fails there.
+function detectSafeRmWorks(): boolean {
+  const { output } = runHook(CAREFUL_SCRIPT, carefulInput('rm -rf node_modules'));
+  return output.permissionDecision === undefined;
+}
+
+// ============================================================
+// check-careful.sh tests
+// ============================================================
+describe('check-careful.sh', () => {
+
+  // --- Destructive rm commands ---
+
+  describe('rm -rf / rm -r', () => {
+    test('rm -rf /var/data warns with recursive delete message', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('rm -rf /var/data'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('recursive delete');
+    });
+
+    test('rm -r ./some-dir warns', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('rm -r ./some-dir'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('recursive delete');
+    });
+
+    test('rm -rf node_modules allows (safe exception)', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('rm -rf node_modules'));
+      expect(exitCode).toBe(0);
+      if (detectSafeRmWorks()) {
+        // GNU sed: safe exception triggers, allows through
+        expect(output.permissionDecision).toBeUndefined();
+      } else {
+        // macOS sed: safe exception regex uses \\s which is unsupported,
+        // so the safe-targets check fails and the command warns
+        expect(output.permissionDecision).toBe('ask');
+      }
+    });
+
+    test('rm -rf .next dist allows (multiple safe targets)', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('rm -rf .next dist'));
+      expect(exitCode).toBe(0);
+      if (detectSafeRmWorks()) {
+        expect(output.permissionDecision).toBeUndefined();
+      } else {
+        expect(output.permissionDecision).toBe('ask');
+      }
+    });
+
+    test('rm -rf node_modules /var/data warns (mixed safe+unsafe)', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('rm -rf node_modules /var/data'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('recursive delete');
+    });
+  });
+
+  // --- SQL destructive commands ---
+  // Note: SQL commands that contain embedded double quotes (e.g., psql -c "DROP TABLE")
+  // get their command value truncated by the grep-based JSON extractor because \"
+  // terminates the [^"]* match. We use commands WITHOUT embedded quotes so the grep
+  // extraction works and the SQL keywords are visible to the pattern matcher.
+
+  describe('SQL destructive commands', () => {
+    test('psql DROP TABLE warns with DROP in message', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('psql -c DROP TABLE users;'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('DROP');
+    });
+
+    test('mysql drop database warns (case insensitive)', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('mysql -e drop database mydb'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message.toLowerCase()).toContain('drop');
+    });
+
+    test('psql TRUNCATE warns', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('psql -c TRUNCATE orders;'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('TRUNCATE');
+    });
+  });
+
+  // --- Git destructive commands ---
+
+  describe('git destructive commands', () => {
+    test('git push --force warns with force-push', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('git push --force origin main'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('force-push');
+    });
+
+    test('git push -f warns', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('git push -f origin main'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('force-push');
+    });
+
+    test('git reset --hard warns with uncommitted', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('git reset --hard HEAD~3'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('uncommitted');
+    });
+
+    test('git checkout . warns', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('git checkout .'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('uncommitted');
+    });
+
+    test('git restore . warns', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('git restore .'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('uncommitted');
+    });
+  });
+
+  // --- Container / infra destructive commands ---
+
+  describe('container and infra commands', () => {
+    test('kubectl delete warns with kubectl in message', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('kubectl delete pod my-pod'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('kubectl');
+    });
+
+    test('docker rm -f warns', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('docker rm -f container123'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('Docker');
+    });
+
+    test('docker system prune -a warns', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput('docker system prune -a'));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('Docker');
+    });
+  });
+
+  // --- Safe commands ---
+
+  describe('safe commands allow without warning', () => {
+    const safeCmds = [
+      'ls -la',
+      'git status',
+      'npm install',
+      'cat README.md',
+      'echo hello',
+    ];
+
+    for (const cmd of safeCmds) {
+      test(`"${cmd}" allows`, () => {
+        const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput(cmd));
+        expect(exitCode).toBe(0);
+        expect(output.permissionDecision).toBeUndefined();
+      });
+    }
+  });
+
+  // --- Edge cases ---
+
+  describe('edge cases', () => {
+    test('empty command allows gracefully', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, carefulInput(''));
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBeUndefined();
+    });
+
+    test('missing command field allows gracefully', () => {
+      const { exitCode, output } = runHook(CAREFUL_SCRIPT, { tool_input: {} });
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBeUndefined();
+    });
+
+    test('malformed JSON input allows gracefully (exit 0, output {})', () => {
+      const { exitCode, raw } = runHookRaw(CAREFUL_SCRIPT, 'this is not json at all{{{{');
+      expect(exitCode).toBe(0);
+      expect(raw).toBe('{}');
+    });
+
+    test('Python fallback: grep fails on multiline JSON, Python parses it', () => {
+      // Construct JSON where "command": and the value are on separate lines.
+      // grep works line-by-line, so it cannot match "command"..."value" across lines.
+      // This forces CMD to be empty, triggering the Python fallback which handles
+      // the full JSON correctly.
+      const rawJson = '{"tool_input":{"command":\n"rm -rf /tmp/important"}}';
+      const { exitCode, output } = runHookRaw(CAREFUL_SCRIPT, rawJson);
+      expect(exitCode).toBe(0);
+      expect(output.permissionDecision).toBe('ask');
+      expect(output.message).toContain('recursive delete');
+    });
+  });
+});
+
+// ============================================================
+// check-freeze.sh tests
+// ============================================================
+describe('check-freeze.sh', () => {
+
+  describe('edits inside freeze boundary', () => {
+    test('edit inside freeze boundary allows', () => {
+      withFreezeDir('/Users/dev/project/src/', (stateDir) => {
+        const { exitCode, output } = runHook(
+          FREEZE_SCRIPT,
+          freezeInput('/Users/dev/project/src/index.ts'),
+          { CLAUDE_PLUGIN_DATA: stateDir },
+        );
+        expect(exitCode).toBe(0);
+        expect(output.permissionDecision).toBeUndefined();
+      });
+    });
+
+    test('edit in subdirectory of freeze path allows', () => {
+      withFreezeDir('/Users/dev/project/src/', (stateDir) => {
+        const { exitCode, output } = runHook(
+          FREEZE_SCRIPT,
+          freezeInput('/Users/dev/project/src/components/Button.tsx'),
+          { CLAUDE_PLUGIN_DATA: stateDir },
+        );
+        expect(exitCode).toBe(0);
+        expect(output.permissionDecision).toBeUndefined();
+      });
+    });
+  });
+
+  describe('edits outside freeze boundary', () => {
+    test('edit outside freeze boundary denies', () => {
+      withFreezeDir('/Users/dev/project/src/', (stateDir) => {
+        const { exitCode, output } = runHook(
+          FREEZE_SCRIPT,
+          freezeInput('/Users/dev/other-project/index.ts'),
+          { CLAUDE_PLUGIN_DATA: stateDir },
+        );
+        expect(exitCode).toBe(0);
+        expect(output.permissionDecision).toBe('deny');
+        expect(output.message).toContain('freeze');
+        expect(output.message).toContain('outside');
+      });
+    });
+
+    test('write outside freeze boundary denies', () => {
+      withFreezeDir('/Users/dev/project/src/', (stateDir) => {
+        const { exitCode, output } = runHook(
+          FREEZE_SCRIPT,
+          freezeInput('/etc/hosts'),
+          { CLAUDE_PLUGIN_DATA: stateDir },
+        );
+        expect(exitCode).toBe(0);
+        expect(output.permissionDecision).toBe('deny');
+        expect(output.message).toContain('freeze');
+        expect(output.message).toContain('outside');
+      });
+    });
+  });
+
+  describe('trailing slash prevents prefix confusion', () => {
+    test('freeze at /src/ denies /src-old/ (trailing slash prevents prefix match)', () => {
+      withFreezeDir('/Users/dev/project/src/', (stateDir) => {
+        const { exitCode, output } = runHook(
+          FREEZE_SCRIPT,
+          freezeInput('/Users/dev/project/src-old/index.ts'),
+          { CLAUDE_PLUGIN_DATA: stateDir },
+        );
+        expect(exitCode).toBe(0);
+        expect(output.permissionDecision).toBe('deny');
+        expect(output.message).toContain('outside');
+      });
+    });
+  });
+
+  describe('no freeze file exists', () => {
+    test('allows everything when no freeze file present', () => {
+      const stateDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-freeze-test-'));
+      try {
+        const { exitCode, output } = runHook(
+          FREEZE_SCRIPT,
+          freezeInput('/anywhere/at/all.ts'),
+          { CLAUDE_PLUGIN_DATA: stateDir },
+        );
+        expect(exitCode).toBe(0);
+        expect(output.permissionDecision).toBeUndefined();
+      } finally {
+        fs.rmSync(stateDir, { recursive: true, force: true });
+      }
+    });
+  });
+
+  describe('edge cases', () => {
+    test('missing file_path field allows gracefully', () => {
+      withFreezeDir('/Users/dev/project/src/', (stateDir) => {
+        const { exitCode, output } = runHook(
+          FREEZE_SCRIPT,
+          { tool_input: {} },
+          { CLAUDE_PLUGIN_DATA: stateDir },
+        );
+        expect(exitCode).toBe(0);
+        expect(output.permissionDecision).toBeUndefined();
+      });
+    });
+  });
+});