fix: Handle Claude CLI unavailability gracefully in CI

- Add try-catch around pty.spawn() to prevent crashes when PTY unavailable
- Add unhandledRejection/uncaughtException handlers for graceful degradation
- Add checkBackendHealth/waitForBackendHealth utilities for tests
- Add data/.api-key and data/credentials.json to .gitignore

.gitignore

@@ -91,4 +91,7 @@ yarn.lock
 
 # Fork-specific workflow files (should never be committed)
 DEVELOPMENT_WORKFLOW.md
-check-sync.sh
+check-sync.sh
+# API key files
+data/.api-key
+data/credentials.json

apps/server/src/index.ts

@@ -597,6 +597,26 @@ const startServer = (port: number) => {
 
 startServer(PORT);
 
+// Global error handlers to prevent crashes from uncaught errors
+process.on('unhandledRejection', (reason: unknown, _promise: Promise<unknown>) => {
+  logger.error('Unhandled Promise Rejection:', {
+    reason: reason instanceof Error ? reason.message : String(reason),
+    stack: reason instanceof Error ? reason.stack : undefined,
+  });
+  // Don't exit - log the error and continue running
+  // This prevents the server from crashing due to unhandled rejections
+});
+
+process.on('uncaughtException', (error: Error) => {
+  logger.error('Uncaught Exception:', {
+    message: error.message,
+    stack: error.stack,
+  });
+  // Exit on uncaught exceptions to prevent undefined behavior
+  // The process is in an unknown state after an uncaught exception
+  process.exit(1);
+});
+
 // Graceful shutdown
 process.on('SIGTERM', () => {
   logger.info('SIGTERM received, shutting down...');

apps/server/src/services/claude-usage-service.ts

@@ -2,6 +2,7 @@ import { spawn } from 'child_process';
 import * as os from 'os';
 import * as pty from 'node-pty';
 import { ClaudeUsage } from '../routes/claude/types.js';
+import { createLogger } from '@automaker/utils';
 
 /**
  * Claude Usage Service
@@ -14,6 +15,8 @@ import { ClaudeUsage } from '../routes/claude/types.js';
  * - macOS: Uses 'expect' command for PTY
  * - Windows/Linux: Uses node-pty for PTY
  */
+const logger = createLogger('ClaudeUsage');
+
 export class ClaudeUsageService {
   private claudeBinary = 'claude';
   private timeout = 30000; // 30 second timeout
@@ -164,21 +167,40 @@ export class ClaudeUsageService {
       const shell = this.isWindows ? 'cmd.exe' : '/bin/sh';
       const args = this.isWindows ? ['/c', 'claude', '/usage'] : ['-c', 'claude /usage'];
 
-      const ptyProcess = pty.spawn(shell, args, {
-        name: 'xterm-256color',
-        cols: 120,
-        rows: 30,
-        cwd: workingDirectory,
-        env: {
-          ...process.env,
-          TERM: 'xterm-256color',
-        } as Record<string, string>,
-      });
+      let ptyProcess: any = null;
+
+      try {
+        ptyProcess = pty.spawn(shell, args, {
+          name: 'xterm-256color',
+          cols: 120,
+          rows: 30,
+          cwd: workingDirectory,
+          env: {
+            ...process.env,
+            TERM: 'xterm-256color',
+          } as Record<string, string>,
+        });
+      } catch (spawnError) {
+        // pty.spawn() can throw synchronously if the native module fails to load
+        // or if PTY is not available in the current environment (e.g., containers without /dev/pts)
+        const errorMessage = spawnError instanceof Error ? spawnError.message : String(spawnError);
+        logger.error('[executeClaudeUsageCommandPty] Failed to spawn PTY:', errorMessage);
+
+        // Return a user-friendly error instead of crashing
+        reject(
+          new Error(
+            `Unable to access terminal: ${errorMessage}. Claude CLI may not be available or PTY support is limited in this environment.`
+          )
+        );
+        return;
+      }
 
       const timeoutId = setTimeout(() => {
         if (!settled) {
           settled = true;
-          ptyProcess.kill();
+          if (ptyProcess && !ptyProcess.killed) {
+            ptyProcess.kill();
+          }
           // Don't fail if we have data - return it instead
           if (output.includes('Current session')) {
             resolve(output);
@@ -188,7 +210,7 @@ export class ClaudeUsageService {
         }
       }, this.timeout);
 
-      ptyProcess.onData((data) => {
+      ptyProcess.onData((data: string) => {
         output += data;
 
         // Check if we've seen the usage data (look for "Current session")
@@ -196,12 +218,12 @@ export class ClaudeUsageService {
           hasSeenUsageData = true;
           // Wait for full output, then send escape to exit
           setTimeout(() => {
-            if (!settled) {
+            if (!settled && ptyProcess && !ptyProcess.killed) {
               ptyProcess.write('\x1b'); // Send escape key
 
               // Fallback: if ESC doesn't exit (Linux), use SIGTERM after 2s
               setTimeout(() => {
-                if (!settled) {
+                if (!settled && ptyProcess && !ptyProcess.killed) {
                   ptyProcess.kill('SIGTERM');
                 }
               }, 2000);
@@ -212,14 +234,14 @@ export class ClaudeUsageService {
         // Fallback: if we see "Esc to cancel" but haven't seen usage data yet
         if (!hasSeenUsageData && output.includes('Esc to cancel')) {
           setTimeout(() => {
-            if (!settled) {
+            if (!settled && ptyProcess && !ptyProcess.killed) {
               ptyProcess.write('\x1b'); // Send escape key
             }
           }, 3000);
         }
       });
 
-      ptyProcess.onExit(({ exitCode }) => {
+      ptyProcess.onExit(({ exitCode }: { exitCode: number }) => {
         clearTimeout(timeoutId);
         if (settled) return;
         settled = true;

apps/ui/tests/utils/api/client.ts

@@ -368,3 +368,42 @@ export async function authenticateForTests(page: Page): Promise<boolean> {
   const apiKey = process.env.AUTOMAKER_API_KEY || 'test-api-key-for-e2e-tests';
   return authenticateWithApiKey(page, apiKey);
 }
+
+/**
+ * Check if the backend server is healthy
+ * Returns true if the server responds with status 200, false otherwise
+ */
+export async function checkBackendHealth(page: Page, timeout = 5000): Promise<boolean> {
+  try {
+    const response = await page.request.get(`${API_BASE_URL}/api/health`, {
+      timeout,
+    });
+    return response.ok();
+  } catch {
+    return false;
+  }
+}
+
+/**
+ * Wait for the backend to be healthy, with retry logic
+ * Throws an error if the backend doesn't become healthy within the timeout
+ */
+export async function waitForBackendHealth(
+  page: Page,
+  maxWaitMs = 30000,
+  checkIntervalMs = 500
+): Promise<void> {
+  const startTime = Date.now();
+
+  while (Date.now() - startTime < maxWaitMs) {
+    if (await checkBackendHealth(page, checkIntervalMs)) {
+      return;
+    }
+    await page.waitForTimeout(checkIntervalMs);
+  }
+
+  throw new Error(
+    `Backend did not become healthy within ${maxWaitMs}ms. ` +
+      `Last health check failed or timed out.`
+  );
+}