chore: import upstream snapshot with attribution

examples/claude-agent-sdk/advanced/.gitignore

@@ -0,0 +1 @@
+latest-diffs.md

examples/claude-agent-sdk/advanced/hooks.js

@@ -0,0 +1,105 @@
+const { execSync } = require('child_process');
+const path = require('path');
+const fs = require('fs');
+
+/**
+ * Extension hook that manages git workspace lifecycle
+ * @param {string} hookName - The name of the hook being called (beforeAll, beforeEach, afterEach, afterAll)
+ * @param {Object} context - Context information for the hook
+ */
+function extensionHook(hookName, context) {
+  // Resolve workspace path relative to this hook file (not the cwd)
+  const workspacePath = path.join(__dirname, 'workspace');
+  const gitPath = path.join(workspacePath, '.git');
+  const reportPath = path.join(__dirname, 'latest-diffs.md');
+
+  if (hookName === 'beforeAll') {
+    // Initialize git repo once before all tests
+    try {
+      console.log('Initializing git repository...');
+
+      // Initialize git if not already initialized
+      if (!fs.existsSync(gitPath)) {
+        execSync('git init', {
+          cwd: workspacePath,
+          stdio: 'pipe',
+        });
+      }
+
+      // Configure git user for the initial commit
+      execSync('git config user.name "Test User"', {
+        cwd: workspacePath,
+        stdio: 'pipe',
+      });
+      execSync('git config user.email "test@example.com"', {
+        cwd: workspacePath,
+        stdio: 'pipe',
+      });
+
+      // Add all files and create initial commit
+      execSync('git add -A', {
+        cwd: workspacePath,
+        stdio: 'pipe',
+      });
+
+      execSync('git commit -m "Initial commit"', {
+        cwd: workspacePath,
+        stdio: 'pipe',
+      });
+
+      // Create fresh report file
+      fs.writeFileSync(reportPath, '# Test Run Report\n\n', 'utf8');
+
+      console.log('=== Git repository initialized ===');
+      console.log('');
+    } catch (error) {
+      console.error('Git initialization failed:', error.message);
+    }
+  } else if (hookName === 'afterEach') {
+    // Capture changes and reset workspace after each test
+    try {
+      const timestamp = new Date().toISOString();
+      const gitStatus = execSync('git status --porcelain', {
+        cwd: workspacePath,
+        encoding: 'utf8',
+      });
+
+      // Build report entry
+      let reportEntry = `## Test completed at ${timestamp}\n\n`;
+
+      if (gitStatus.trim()) {
+        const gitDiff = execSync('git diff HEAD', {
+          cwd: workspacePath,
+          encoding: 'utf8',
+        });
+
+        reportEntry += '### Changes Made\n\n```diff\n' + gitDiff + '\n```\n\n';
+
+        // Reset workspace
+        execSync('git reset --hard HEAD', {
+          cwd: workspacePath,
+          stdio: 'pipe', // Silent
+        });
+      } else {
+        reportEntry += '_No changes made during test_\n\n';
+      }
+
+      // Append to report
+      fs.appendFileSync(reportPath, reportEntry, 'utf8');
+    } catch (error) {
+      console.error('Git reset failed:', error.message);
+    }
+  } else if (hookName === 'afterAll') {
+    // Clean up git repository after all tests
+    try {
+      if (fs.existsSync(gitPath)) {
+        fs.rmSync(gitPath, { recursive: true, force: true });
+      }
+      console.log('Git workspace cleaned up. View diffs: cat ' + reportPath);
+    } catch (error) {
+      console.error('Git cleanup failed:', error.message);
+    }
+  }
+}
+
+module.exports = extensionHook;

examples/claude-agent-sdk/advanced/promptfooconfig.yaml

@@ -0,0 +1,33 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: 'Claude Agent SDK with file edits and afterEach hook'
+
+prompts:
+  - |
+    Refactor the auth.js file to use async/await patterns with proper error handling. Don't make any other unrelated changes.
+
+providers:
+  - id: anthropic:claude-agent-sdk
+    config:
+      working_dir: ./workspace
+      # Add file editing tools to the default set of read-only tools
+      append_allowed_tools: ['Write', 'Edit', 'MultiEdit']
+      # Approve file edits
+      permission_mode: 'acceptEdits'
+
+# Use an extension hook to reset the working directory after each test
+extensions:
+  - file://hooks.js:extensionHook
+
+# Prevent race conditions during concurrent evals
+evaluateOptions:
+  maxConcurrency: 1
+
+tests:
+  - vars: {}
+    assert:
+      - type: llm-rubric
+        value: 'Should refactor code to use async/await patterns'
+      - type: llm-rubric
+        value: 'Should add proper error handling'
+      - type: llm-rubric
+        value: 'Should not make any other changes unrelated to async/await patterns or error handling'

examples/claude-agent-sdk/advanced/workspace/auth.js

@@ -0,0 +1,47 @@
+// Authentication module
+const users = [];
+
+function login(email, password, callback) {
+  setTimeout(() => {
+    const user = users.find((u) => u.email === email);
+    if (!user) {
+      return callback(new Error('User not found'));
+    }
+    if (user.password !== password) {
+      return callback(new Error('Invalid password'));
+    }
+    callback(null, { id: user.id, email: user.email });
+  }, 10);
+}
+
+function register(email, password, callback) {
+  setTimeout(() => {
+    const existingUser = users.find((u) => u.email === email);
+    if (existingUser) {
+      return callback(new Error('User already exists'));
+    }
+    const user = {
+      id: Math.random().toString(36).substr(2, 9),
+      email: email,
+      password: password,
+    };
+    users.push(user);
+    callback(null, { id: user.id, email: user.email });
+  }, 10);
+}
+
+function getUserById(id, callback) {
+  setTimeout(() => {
+    const user = users.find((u) => u.id === id);
+    if (!user) {
+      return callback(new Error('User not found'));
+    }
+    callback(null, { id: user.id, email: user.email });
+  }, 10);
+}
+
+module.exports = {
+  login,
+  register,
+  getUserById,
+};

examples/claude-agent-sdk/advanced/workspace/package.json

@@ -0,0 +1,13 @@
+{
+  "name": "auth-module",
+  "version": "1.0.0",
+  "license": "MIT",
+  "private": true,
+  "description": "Simple authentication module for refactoring",
+  "main": "auth.js",
+  "scripts": {
+    "start": "node auth.js"
+  },
+  "dependencies": {},
+  "devDependencies": {}
+}