fix: Comprehensive authentication error handling

server/main.py

@@ -120,9 +120,11 @@ async def setup_status():
     # Check for Claude CLI
     claude_cli = shutil.which("claude") is not None
 
-    # Check for credentials file
-    credentials_path = Path.home() / ".claude" / ".credentials.json"
-    credentials = credentials_path.exists()
+    # Check for Claude CLI configuration directory
+    # Note: Claude CLI no longer stores credentials in ~/.claude/.credentials.json
+    # The existence of ~/.claude indicates the CLI has been configured
+    claude_dir = Path.home() / ".claude"
+    credentials = claude_dir.exists() and claude_dir.is_dir()
 
     # Check for Node.js and npm
     node = shutil.which("node") is not None

server/services/process_manager.py

@@ -36,6 +36,47 @@
     r'aws[_-]?secret[=:][^\s]+',
 ]
 
+# Patterns that indicate Claude CLI authentication errors
+AUTH_ERROR_PATTERNS = [
+    r"not\s+logged\s+in",
+    r"not\s+authenticated",
+    r"authentication\s+(failed|required|error)",
+    r"login\s+required",
+    r"please\s+(run\s+)?['\"]?claude\s+login",
+    r"unauthorized",
+    r"invalid\s+(token|credential|api.?key)",
+    r"expired\s+(token|session|credential)",
+    r"could\s+not\s+authenticate",
+    r"sign\s+in\s+(to|required)",
+]
+
+
+def is_auth_error(text: str) -> bool:
+    """Check if text contains Claude CLI authentication error messages."""
+    if not text:
+        return False
+    text_lower = text.lower()
+    for pattern in AUTH_ERROR_PATTERNS:
+        if re.search(pattern, text_lower):
+            return True
+    return False
+
+
+AUTH_ERROR_HELP = """
+================================================================================
+  AUTHENTICATION ERROR DETECTED
+================================================================================
+
+Claude CLI requires authentication to work.
+
+To fix this, run:
+  claude login
+
+This will open a browser window to sign in.
+After logging in, try starting the agent again.
+================================================================================
+"""
+
 
 def sanitize_output(line: str) -> str:
     """Remove sensitive information from output lines."""
@@ -185,6 +226,9 @@ async def _stream_output(self) -> None:
         if not self.process or not self.process.stdout:
             return
 
+        auth_error_detected = False
+        output_buffer = []  # Buffer recent lines for auth error detection
+
         try:
             loop = asyncio.get_running_loop()
             while True:
@@ -198,6 +242,18 @@ async def _stream_output(self) -> None:
                 decoded = line.decode("utf-8", errors="replace").rstrip()
                 sanitized = sanitize_output(decoded)
 
+                # Buffer recent output for auth error detection
+                output_buffer.append(decoded)
+                if len(output_buffer) > 20:
+                    output_buffer.pop(0)
+
+                # Check for auth errors
+                if not auth_error_detected and is_auth_error(decoded):
+                    auth_error_detected = True
+                    # Broadcast auth error help message
+                    for help_line in AUTH_ERROR_HELP.strip().split('\n'):
+                        await self._broadcast_output(help_line)
+
                 await self._broadcast_output(sanitized)
 
         except asyncio.CancelledError:
@@ -209,6 +265,12 @@ async def _stream_output(self) -> None:
             if self.process and self.process.poll() is not None:
                 exit_code = self.process.returncode
                 if exit_code != 0 and self.status == "running":
+                    # Check buffered output for auth errors if we haven't detected one yet
+                    if not auth_error_detected:
+                        combined_output = '\n'.join(output_buffer)
+                        if is_auth_error(combined_output):
+                            for help_line in AUTH_ERROR_HELP.strip().split('\n'):
+                                await self._broadcast_output(help_line)
                     self.status = "crashed"
                 elif self.status == "running":
                     self.status = "stopped"

start.py

@@ -9,6 +9,7 @@
 """
 
 import os
+import re
 import subprocess
 import sys
 from pathlib import Path
@@ -24,6 +25,53 @@
     register_project,
 )
 
+# Patterns that indicate Claude CLI authentication errors
+AUTH_ERROR_PATTERNS = [
+    r"not\s+logged\s+in",
+    r"not\s+authenticated",
+    r"authentication\s+(failed|required|error)",
+    r"login\s+required",
+    r"please\s+(run\s+)?['\"]?claude\s+login",
+    r"unauthorized",
+    r"invalid\s+(token|credential|api.?key)",
+    r"expired\s+(token|session|credential)",
+    r"could\s+not\s+authenticate",
+    r"sign\s+in\s+(to|required)",
+]
+
+
+def is_auth_error(output: str) -> bool:
+    """
+    Check if output contains Claude CLI authentication error messages.
+
+    Args:
+        output: Combined stdout/stderr from subprocess
+
+    Returns:
+        True if authentication error detected, False otherwise
+    """
+    if not output:
+        return False
+
+    output_lower = output.lower()
+    for pattern in AUTH_ERROR_PATTERNS:
+        if re.search(pattern, output_lower):
+            return True
+    return False
+
+
+def print_auth_error_help() -> None:
+    """Print helpful message when authentication error is detected."""
+    print("\n" + "=" * 50)
+    print("  Authentication Error Detected")
+    print("=" * 50)
+    print("\nClaude CLI requires authentication to work.")
+    print("\nTo fix this, run:")
+    print("  claude login")
+    print("\nThis will open a browser window to sign in.")
+    print("After logging in, try running this command again.")
+    print("=" * 50 + "\n")
+
 
 def check_spec_exists(project_dir: Path) -> bool:
     """
@@ -203,6 +251,7 @@ def run_spec_creation(project_dir: Path) -> bool:
     Run Claude Code with /create-spec command to create project specification.
 
     The project path is passed as an argument so create-spec knows where to write files.
+    Captures stderr to detect authentication errors and provide helpful guidance.
     """
     print("\n" + "=" * 50)
     print("  Project Specification Setup")
@@ -217,12 +266,25 @@ def run_spec_creation(project_dir: Path) -> bool:
     try:
         # Launch Claude Code with /create-spec command
         # Project path included in command string so it populates $ARGUMENTS
-        subprocess.run(
+        # Capture stderr to detect auth errors while letting stdout flow to terminal
+        result = subprocess.run(
             ["claude", f"/create-spec {project_dir}"],
             check=False,  # Don't raise on non-zero exit
-            cwd=str(Path(__file__).parent)  # Run from project root
+            cwd=str(Path(__file__).parent),  # Run from project root
+            stderr=subprocess.PIPE,
+            text=True
         )
 
+        # Check for authentication errors in stderr
+        stderr_output = result.stderr or ""
+        if result.returncode != 0 and is_auth_error(stderr_output):
+            print_auth_error_help()
+            return False
+
+        # If there was stderr output but not an auth error, show it
+        if stderr_output.strip() and result.returncode != 0:
+            print(f"\nClaude CLI error: {stderr_output.strip()}")
+
         # Check if spec was created in project prompts directory
         if check_spec_exists(project_dir):
             print("\n" + "-" * 50)
@@ -232,6 +294,9 @@ def run_spec_creation(project_dir: Path) -> bool:
             print("\n" + "-" * 50)
             print("Spec creation incomplete.")
             print(f"Please ensure app_spec.txt exists in: {get_project_prompts_dir(project_dir)}")
+            # If failed with non-zero exit and no spec, might be auth issue
+            if result.returncode != 0:
+                print("\nIf you're having authentication issues, try running: claude login")
             return False
 
     except FileNotFoundError:
@@ -348,6 +413,8 @@ def create_new_project_flow() -> tuple[str, Path] | None:
 def run_agent(project_name: str, project_dir: Path) -> None:
     """Run the autonomous agent with the given project.
 
+    Captures stderr to detect authentication errors and provide helpful guidance.
+
     Args:
         project_name: Name of the project
         project_dir: Absolute path to the project directory
@@ -367,9 +434,28 @@ def run_agent(project_name: str, project_dir: Path) -> None:
     # Build the command - pass absolute path
     cmd = [sys.executable, "autonomous_agent_demo.py", "--project-dir", str(project_dir.resolve())]
 
-    # Run the agent
+    # Run the agent with stderr capture to detect auth errors
+    # stdout goes directly to terminal for real-time output
     try:
-        subprocess.run(cmd, check=False)
+        result = subprocess.run(
+            cmd,
+            check=False,
+            stderr=subprocess.PIPE,
+            text=True
+        )
+
+        # Check for authentication errors
+        stderr_output = result.stderr or ""
+        if result.returncode != 0:
+            if is_auth_error(stderr_output):
+                print_auth_error_help()
+            elif stderr_output.strip():
+                # Show any other errors
+                print(f"\nAgent error:\n{stderr_output.strip()}")
+                # Still hint about auth if exit was unexpected
+                if "error" in stderr_output.lower() or "exception" in stderr_output.lower():
+                    print("\nIf this is an authentication issue, try running: claude login")
+
     except KeyboardInterrupt:
         print("\n\nAgent interrupted. Run again to resume.")
 

start.sh

@@ -20,40 +20,18 @@ fi
 
 echo "[OK] Claude CLI found"
 
-# Check if user has credentials
-CLAUDE_CREDS="$HOME/.claude/.credentials.json"
-if [ -f "$CLAUDE_CREDS" ]; then
-    echo "[OK] Claude credentials found"
+# Note: Claude CLI no longer stores credentials in ~/.claude/.credentials.json
+# We can't reliably check auth status without making an API call, so we just
+# verify the CLI is installed and remind the user to login if needed
+if [ -d "$HOME/.claude" ]; then
+    echo "[OK] Claude CLI directory found"
+    echo "     (If you're not logged in, run: claude login)"
 else
-    echo "[!] Not authenticated with Claude"
+    echo "[!] Claude CLI not configured"
     echo ""
-    echo "You need to run 'claude login' to authenticate."
-    echo "This will open a browser window to sign in."
+    echo "Please run 'claude login' to authenticate before continuing."
     echo ""
-    read -p "Would you like to run 'claude login' now? (y/n): " LOGIN_CHOICE
-
-    if [[ "$LOGIN_CHOICE" =~ ^[Yy]$ ]]; then
-        echo ""
-        echo "Running 'claude login'..."
-        echo "Complete the login in your browser, then return here."
-        echo ""
-        claude login
-
-        # Check if login succeeded
-        if [ -f "$CLAUDE_CREDS" ]; then
-            echo ""
-            echo "[OK] Login successful!"
-        else
-            echo ""
-            echo "[ERROR] Login failed or was cancelled."
-            echo "Please try again."
-            exit 1
-        fi
-    else
-        echo ""
-        echo "Please run 'claude login' manually, then try again."
-        exit 1
-    fi
+    read -p "Press Enter to continue anyway, or Ctrl+C to exit..."
 fi
 
 echo ""

start_ui.sh

@@ -9,6 +9,27 @@ echo "  AutoCoder UI"
 echo "===================================="
 echo ""
 
+# Check if Claude CLI is installed
+if ! command -v claude &> /dev/null; then
+    echo "[!] Claude CLI not found"
+    echo ""
+    echo "    The agent requires Claude CLI to work."
+    echo "    Install it from: https://claude.ai/download"
+    echo ""
+    echo "    After installing, run: claude login"
+    echo ""
+else
+    echo "[OK] Claude CLI found"
+    # Note: Claude CLI no longer stores credentials in ~/.claude/.credentials.json
+    # We can't reliably check auth status without making an API call
+    if [ -d "$HOME/.claude" ]; then
+        echo "     (If you're not logged in, run: claude login)"
+    else
+        echo "[!] Claude CLI not configured - run 'claude login' first"
+    fi
+fi
+echo ""
+
 # Check if Python is available
 if ! command -v python3 &> /dev/null; then
     if ! command -v python &> /dev/null; then