Migration from Docker to Standalone Python Server (#73)
* Migration from docker to standalone server Migration handling Fixed tests Use simpler in-memory storage Support for concurrent logging to disk Simplified direct connections to localhost * Migration from docker / redis to standalone script Updated tests Updated run script Fixed requirements Use dotenv Ask if user would like to install MCP in Claude Desktop once Updated docs * More cleanup and references to docker removed * Cleanup * Comments * Fixed tests * Fix GitHub Actions workflow for standalone Python architecture - Install requirements-dev.txt for pytest and testing dependencies - Remove Docker setup from simulation tests (now standalone) - Simplify linting job to use requirements-dev.txt - Update simulation tests to run directly without Docker Fixes unit test failures in CI due to missing pytest dependency. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Remove simulation tests from GitHub Actions - Removed simulation-tests job that makes real API calls - Keep only unit tests (mocked, no API costs) and linting - Simulation tests should be run manually with real API keys - Reduces CI costs and complexity GitHub Actions now only runs: - Unit tests (569 tests, all mocked) - Code quality checks (ruff, black) 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Fixed tests * Fixed tests --------- Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Beehive Innovations
committed by
GitHub
GitHub
parent
9d72545ecd
commit
4151c3c3a5
@@ -6,18 +6,18 @@ by simulating real Claude CLI communications and validating conversation
|
||||
continuity, file handling, deduplication features, and clarification scenarios.
|
||||
|
||||
Test Flow:
|
||||
1. Setup fresh Docker environment with clean containers
|
||||
1. Setup standalone server environment
|
||||
2. Load and run individual test modules
|
||||
3. Validate system behavior through logs and Redis
|
||||
3. Validate system behavior through logs and memory
|
||||
4. Cleanup and report results
|
||||
|
||||
Usage:
|
||||
python communication_simulator_test.py [--verbose] [--keep-logs] [--tests TEST_NAME...] [--individual TEST_NAME] [--rebuild]
|
||||
python communication_simulator_test.py [--verbose] [--keep-logs] [--tests TEST_NAME...] [--individual TEST_NAME] [--setup]
|
||||
|
||||
--tests: Run specific tests only (space-separated)
|
||||
--list-tests: List all available tests
|
||||
--individual: Run a single test individually
|
||||
--rebuild: Force rebuild Docker environment using run-server.sh
|
||||
--setup: Force setup standalone server environment using run-server.sh
|
||||
|
||||
Available tests:
|
||||
basic_conversation - Basic conversation flow with chat tool
|
||||
@@ -25,8 +25,8 @@ Available tests:
|
||||
per_tool_deduplication - File deduplication for individual tools
|
||||
cross_tool_continuation - Cross-tool conversation continuation scenarios
|
||||
cross_tool_comprehensive - Comprehensive cross-tool integration testing
|
||||
logs_validation - Docker logs validation
|
||||
redis_validation - Redis conversation memory validation
|
||||
line_number_validation - Line number handling validation across tools
|
||||
memory_validation - Conversation memory validation
|
||||
model_thinking_config - Model thinking configuration testing
|
||||
o3_model_selection - O3 model selection and routing testing
|
||||
ollama_custom_url - Ollama custom URL configuration testing
|
||||
@@ -45,11 +45,11 @@ Examples:
|
||||
# Run only basic conversation and content validation tests
|
||||
python communication_simulator_test.py --tests basic_conversation content_validation
|
||||
|
||||
# Run a single test individually (with full Docker setup)
|
||||
# Run a single test individually (with full standalone setup)
|
||||
python communication_simulator_test.py --individual content_validation
|
||||
|
||||
# Force rebuild Docker environment before running tests
|
||||
python communication_simulator_test.py --rebuild
|
||||
# Force setup standalone server environment before running tests
|
||||
python communication_simulator_test.py --setup
|
||||
|
||||
# List available tests
|
||||
python communication_simulator_test.py --list-tests
|
||||
@@ -68,15 +68,15 @@ class CommunicationSimulator:
|
||||
"""Simulates real-world Claude CLI communication with MCP Gemini server"""
|
||||
|
||||
def __init__(
|
||||
self, verbose: bool = False, keep_logs: bool = False, selected_tests: list[str] = None, rebuild: bool = False
|
||||
self, verbose: bool = False, keep_logs: bool = False, selected_tests: list[str] = None, setup: bool = False
|
||||
):
|
||||
self.verbose = verbose
|
||||
self.keep_logs = keep_logs
|
||||
self.selected_tests = selected_tests or []
|
||||
self.rebuild = rebuild
|
||||
self.setup = setup
|
||||
self.temp_dir = None
|
||||
self.container_name = "zen-mcp-server"
|
||||
self.redis_container = "zen-mcp-redis"
|
||||
self.server_process = None
|
||||
self.python_path = self._get_python_path()
|
||||
|
||||
# Import test registry
|
||||
from simulator_tests import TEST_REGISTRY
|
||||
@@ -96,6 +96,23 @@ class CommunicationSimulator:
|
||||
logging.basicConfig(level=log_level, format="%(asctime)s - %(levelname)s - %(message)s")
|
||||
self.logger = logging.getLogger(__name__)
|
||||
|
||||
def _get_python_path(self) -> str:
|
||||
"""Get the Python path for the virtual environment"""
|
||||
current_dir = os.getcwd()
|
||||
venv_python = os.path.join(current_dir, "venv", "bin", "python")
|
||||
|
||||
if os.path.exists(venv_python):
|
||||
return venv_python
|
||||
|
||||
# Try .zen_venv as fallback
|
||||
zen_venv_python = os.path.join(current_dir, ".zen_venv", "bin", "python")
|
||||
if os.path.exists(zen_venv_python):
|
||||
return zen_venv_python
|
||||
|
||||
# Fallback to system python if venv doesn't exist
|
||||
self.logger.warning("Virtual environment not found, using system python")
|
||||
return "python"
|
||||
|
||||
def _create_test_runner(self, test_class):
|
||||
"""Create a test runner function for a test class"""
|
||||
|
||||
@@ -118,13 +135,13 @@ class CommunicationSimulator:
|
||||
self.temp_dir = tempfile.mkdtemp(prefix="mcp_test_")
|
||||
self.logger.debug(f"Created temp directory: {self.temp_dir}")
|
||||
|
||||
# Only run run-server.sh if rebuild is requested
|
||||
if self.rebuild:
|
||||
# Only run run-server.sh if setup is requested
|
||||
if self.setup:
|
||||
if not self._run_server_script():
|
||||
return False
|
||||
|
||||
# Always verify containers are running (regardless of rebuild)
|
||||
return self._verify_existing_containers()
|
||||
# Always verify server environment is available
|
||||
return self._verify_server_environment()
|
||||
|
||||
except Exception as e:
|
||||
self.logger.error(f"Failed to setup test environment: {e}")
|
||||
@@ -160,29 +177,40 @@ class CommunicationSimulator:
|
||||
self.logger.error(f"Failed to run run-server.sh: {e}")
|
||||
return False
|
||||
|
||||
def _verify_existing_containers(self) -> bool:
|
||||
"""Verify that required containers are already running (no setup)"""
|
||||
def _verify_server_environment(self) -> bool:
|
||||
"""Verify that server environment is ready"""
|
||||
try:
|
||||
self.logger.info("Verifying existing Docker containers...")
|
||||
self.logger.info("Verifying standalone server environment...")
|
||||
|
||||
result = self._run_command(["docker", "ps", "--format", "{{.Names}}"], capture_output=True)
|
||||
running_containers = result.stdout.decode().strip().split("\n")
|
||||
# Check if server.py exists
|
||||
server_file = "server.py"
|
||||
if not os.path.exists(server_file):
|
||||
self.logger.error(f"Server file not found: {server_file}")
|
||||
self.logger.error("Please ensure you're in the correct directory and server.py exists")
|
||||
return False
|
||||
|
||||
required = [self.container_name, self.redis_container]
|
||||
for container in required:
|
||||
if container not in running_containers:
|
||||
self.logger.error(f"Required container not running: {container}")
|
||||
self.logger.error(
|
||||
"Please start Docker containers first, or use --rebuild to set them up automatically"
|
||||
)
|
||||
# Check if virtual environment is available
|
||||
if not os.path.exists(self.python_path):
|
||||
self.logger.error(f"Python executable not found: {self.python_path}")
|
||||
self.logger.error("Please run ./run-server.sh first to set up the environment")
|
||||
return False
|
||||
|
||||
# Check if required dependencies are available
|
||||
try:
|
||||
result = self._run_command([self.python_path, "-c", "import json; print('OK')"], capture_output=True)
|
||||
if result.returncode != 0:
|
||||
self.logger.error("Python environment validation failed")
|
||||
return False
|
||||
except Exception as e:
|
||||
self.logger.error(f"Python environment check failed: {e}")
|
||||
return False
|
||||
|
||||
self.logger.info(f"All required containers are running: {required}")
|
||||
self.logger.info("Standalone server environment is ready")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
self.logger.error(f"Container verification failed: {e}")
|
||||
self.logger.error("Please ensure Docker is running and containers are available, or use --rebuild")
|
||||
self.logger.error(f"Server environment verification failed: {e}")
|
||||
self.logger.error("Please ensure the server environment is set up correctly, or use --setup")
|
||||
return False
|
||||
|
||||
def simulate_claude_cli_session(self) -> bool:
|
||||
@@ -348,11 +376,20 @@ class CommunicationSimulator:
|
||||
try:
|
||||
self.logger.info("Cleaning up test environment...")
|
||||
|
||||
# Note: We don't stop Docker services ourselves - let run-server.sh handle Docker lifecycle
|
||||
# Stop any running server processes
|
||||
if self.server_process and self.server_process.poll() is None:
|
||||
self.logger.info("Stopping server process...")
|
||||
self.server_process.terminate()
|
||||
try:
|
||||
self.server_process.wait(timeout=5)
|
||||
except subprocess.TimeoutExpired:
|
||||
self.server_process.kill()
|
||||
self.server_process.wait()
|
||||
|
||||
if not self.keep_logs:
|
||||
self.logger.info("Test completed. Docker containers left running (use run-server.sh to manage)")
|
||||
self.logger.info("Test completed. Standalone server process stopped.")
|
||||
else:
|
||||
self.logger.info("Keeping logs and Docker services running for inspection")
|
||||
self.logger.info("Keeping logs for inspection")
|
||||
|
||||
# Remove temp directory
|
||||
if self.temp_dir and os.path.exists(self.temp_dir):
|
||||
@@ -374,11 +411,13 @@ def parse_arguments():
|
||||
"""Parse and validate command line arguments"""
|
||||
parser = argparse.ArgumentParser(description="Zen MCP Communication Simulator Test")
|
||||
parser.add_argument("--verbose", "-v", action="store_true", help="Enable verbose logging")
|
||||
parser.add_argument("--keep-logs", action="store_true", help="Keep Docker services running for log inspection")
|
||||
parser.add_argument("--keep-logs", action="store_true", help="Keep logs for inspection after test completion")
|
||||
parser.add_argument("--tests", "-t", nargs="+", help="Specific tests to run (space-separated)")
|
||||
parser.add_argument("--list-tests", action="store_true", help="List available tests and exit")
|
||||
parser.add_argument("--individual", "-i", help="Run a single test individually")
|
||||
parser.add_argument("--rebuild", action="store_true", help="Force rebuild Docker environment using run-server.sh")
|
||||
parser.add_argument(
|
||||
"--setup", action="store_true", help="Force setup standalone server environment using run-server.sh"
|
||||
)
|
||||
|
||||
return parser.parse_args()
|
||||
|
||||
@@ -453,7 +492,7 @@ def main():
|
||||
|
||||
# Initialize simulator consistently for all use cases
|
||||
simulator = CommunicationSimulator(
|
||||
verbose=args.verbose, keep_logs=args.keep_logs, selected_tests=args.tests, rebuild=args.rebuild
|
||||
verbose=args.verbose, keep_logs=args.keep_logs, selected_tests=args.tests, setup=args.setup
|
||||
)
|
||||
|
||||
# Determine execution mode and run
|
||||
|
||||
Reference in New Issue
Block a user