Fix test failures and improve type annotations for mypy compliance

- Fix test_notebook_magic.py: Handle widgets module import when ipywidgets unavailable
- Add Optional type annotations for function parameters with None defaults
- Fix Path object assignment issues in config.py by using separate variables
- Add null checks for optional config fields (module_loads, environment_variables)
- Add type annotations for dictionaries (futures, active_jobs)
- Add runtime check for LocalExecutor context manager usage
- Change cloud provider return types to Dict[str, Any] for mixed data types
- Install types-PyYAML and types-paramiko for better type checking
- Resolve Magics class redefinition conflicts in notebook_magic.py

All tests pass (279/279) and code formatting is clean.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

Author: jeremymanning

clustrix/config.py

@@ -88,24 +88,24 @@ def __post_init__(self):
 
     def save_to_file(self, config_path: str) -> None:
         """Save this configuration instance to a file."""
-        config_path = Path(config_path)
+        config_path_obj = Path(config_path)
         config_data = asdict(self)
 
-        with open(config_path, "w") as f:
-            if config_path.suffix.lower() in [".yml", ".yaml"]:
+        with open(config_path_obj, "w") as f:
+            if config_path_obj.suffix.lower() in [".yml", ".yaml"]:
                 yaml.dump(config_data, f, default_flow_style=False)
             else:
                 json.dump(config_data, f, indent=2)
 
     @classmethod
     def load_from_file(cls, config_path: str) -> "ClusterConfig":
         """Load configuration from a file and return a new instance."""
-        config_path = Path(config_path)
-        if not config_path.exists():
+        config_path_obj = Path(config_path)
+        if not config_path_obj.exists():
             raise FileNotFoundError(f"Configuration file not found: {config_path}")
 
-        with open(config_path, "r") as f:
-            if config_path.suffix.lower() in [".yml", ".yaml"]:
+        with open(config_path_obj, "r") as f:
+            if config_path_obj.suffix.lower() in [".yml", ".yaml"]:
                 config_data = yaml.safe_load(f)
             else:
                 config_data = json.load(f)
@@ -143,12 +143,12 @@ def load_config(config_path: str) -> None:
     """
     global _config
 
-    config_path = Path(config_path)
-    if not config_path.exists():
+    config_path_obj = Path(config_path)
+    if not config_path_obj.exists():
         raise FileNotFoundError(f"Configuration file not found: {config_path}")
 
-    with open(config_path, "r") as f:
-        if config_path.suffix.lower() in [".yml", ".yaml"]:
+    with open(config_path_obj, "r") as f:
+        if config_path_obj.suffix.lower() in [".yml", ".yaml"]:
             config_data = yaml.safe_load(f)
         else:
             config_data = json.load(f)
@@ -163,11 +163,11 @@ def save_config(config_path: str) -> None:
     Args:
         config_path: Path where to save configuration
     """
-    config_path = Path(config_path)
+    config_path_obj = Path(config_path)
     config_data = asdict(_config)
 
-    with open(config_path, "w") as f:
-        if config_path.suffix.lower() in [".yml", ".yaml"]:
+    with open(config_path_obj, "w") as f:
+        if config_path_obj.suffix.lower() in [".yml", ".yaml"]:
             yaml.dump(config_data, f, default_flow_style=False)
         else:
             json.dump(config_data, f, indent=2)

clustrix/cost_providers/aws.py

@@ -260,7 +260,7 @@ def estimate_batch_cost(
 
     def get_region_pricing_comparison(
         self, instance_type: str
-    ) -> Dict[str, Dict[str, float]]:
+    ) -> Dict[str, Dict[str, Any]]:
         """Compare pricing across AWS regions (simplified)."""
         # Regional pricing multipliers (approximate)
         region_multipliers = {

clustrix/cost_providers/azure.py

@@ -269,7 +269,7 @@ def estimate_batch_cost(
 
     def get_region_pricing_comparison(
         self, instance_type: str
-    ) -> Dict[str, Dict[str, float]]:
+    ) -> Dict[str, Dict[str, Any]]:
         """Compare pricing across Azure regions (simplified)."""
         # Regional pricing multipliers (approximate)
         region_multipliers = {

clustrix/cost_providers/gcp.py

@@ -259,7 +259,7 @@ def estimate_sustained_use_discount(self, hours_per_month: float) -> Dict[str, A
 
     def get_region_pricing_comparison(
         self, instance_type: str
-    ) -> Dict[str, Dict[str, float]]:
+    ) -> Dict[str, Dict[str, Any]]:
         """Compare pricing across GCP regions (simplified)."""
         # Regional pricing multipliers (approximate)
         region_multipliers = {

clustrix/cost_providers/lambda_cloud.py

@@ -4,7 +4,7 @@
 
 import logging
 from datetime import datetime
-from typing import Dict, List, Any
+from typing import Dict, List, Any, Optional
 
 from ..cost_monitoring import BaseCostMonitor, ResourceUsage, CostEstimate
 
@@ -128,7 +128,7 @@ def get_pricing_info(self) -> Dict[str, float]:
         return self.pricing.copy()
 
     def get_instance_recommendations(
-        self, resource_usage: ResourceUsage, current_instance: str = None
+        self, resource_usage: ResourceUsage, current_instance: Optional[str] = None
     ) -> List[str]:
         """Get instance type recommendations based on current usage."""
         recommendations = []
@@ -242,7 +242,7 @@ def get_performance_metrics(self) -> Dict[str, Any]:
 
     def estimate_monthly_cost(
         self, instance_type: str, hours_per_day: float = 8
-    ) -> Dict[str, float]:
+    ) -> Dict[str, Any]:
         """Estimate monthly costs for different usage patterns."""
         instance_type = instance_type.lower().replace("-", "_")
         hourly_rate = self.pricing.get(instance_type, self.pricing["default"])

clustrix/executor.py

@@ -20,7 +20,7 @@ def __init__(self, config: ClusterConfig):
         self.config = config
         self.ssh_client = None
         self.sftp_client = None
-        self.active_jobs = {}
+        self.active_jobs: Dict[str, Any] = {}
 
         # Connection will be established on-demand
 

clustrix/local_executor.py

@@ -24,7 +24,7 @@ def __init__(self, max_workers: Optional[int] = None, use_threads: bool = False)
             max_workers: Maximum number of worker processes/threads
             use_threads: If True, use ThreadPoolExecutor, else ProcessPoolExecutor
         """
-        self.max_workers = max_workers or os.cpu_count()
+        self.max_workers = max_workers or os.cpu_count() or 4
         self.use_threads = use_threads
         self._executor = None
 
@@ -115,10 +115,13 @@ def _execute_parallel_chunks(
         timeout: Optional[float],
     ) -> List[Any]:
         """Execute chunks in parallel using the executor."""
-        futures = {}
+        futures: Dict[Any, int] = {}
         results = [None] * len(work_chunks)
 
         # Submit all tasks
+        if self._executor is None:
+            raise RuntimeError("LocalExecutor must be used as a context manager")
+
         for i, chunk in enumerate(work_chunks):
             args = chunk.get("args", ())
             kwargs = chunk.get("kwargs", {})
@@ -183,7 +186,7 @@ def execute_loop_parallel(
         loop_var: str,
         iterable: Union[range, List, tuple],
         func_args: tuple = (),
-        func_kwargs: dict = None,
+        func_kwargs: Optional[Dict[Any, Any]] = None,
         chunk_size: Optional[int] = None,
     ) -> List[Any]:
         """
@@ -419,7 +422,7 @@ def create_local_executor(
     use_threads: Optional[bool] = None,
     func: Optional[Callable] = None,
     args: tuple = (),
-    kwargs: dict = None,
+    kwargs: Optional[Dict[Any, Any]] = None,
 ) -> LocalExecutor:
     """
     Create a LocalExecutor with appropriate settings.

clustrix/loop_analysis.py

@@ -74,7 +74,7 @@ def to_dict(self) -> Dict[str, Any]:
 class SafeRangeEvaluator(ast.NodeVisitor):
     """Safely evaluate range expressions without using eval()."""
 
-    def __init__(self, local_vars: Dict[str, Any] = None):
+    def __init__(self, local_vars: Optional[Dict[str, Any]] = None):
         self.local_vars = local_vars or {}
         self.result = None
         self.safe = True
@@ -192,8 +192,8 @@ def has_dependencies(self) -> bool:
 class LoopDetector(ast.NodeVisitor):
     """Enhanced loop detection with dependency analysis."""
 
-    def __init__(self, local_vars: Dict[str, Any] = None):
-        self.loops = []
+    def __init__(self, local_vars: Optional[Dict[str, Any]] = None):
+        self.loops: List[LoopInfo] = []
         self.current_level = 0
         self.local_vars = local_vars or {}
 
@@ -299,7 +299,7 @@ def _analyze_while_loop(self, node) -> Optional[LoopInfo]:
 
 
 def detect_loops_in_function(
-    func: Callable, args: tuple = (), kwargs: dict = None
+    func: Callable, args: tuple = (), kwargs: Optional[Dict[Any, Any]] = None
 ) -> List[LoopInfo]:
     """
     Detect and analyze loops in a function.
@@ -320,7 +320,7 @@ def detect_loops_in_function(
         tree = ast.parse(source)
 
         # Build local variables context
-        local_vars = {}
+        local_vars: Dict[str, Any] = {}
 
         # Add function arguments to context
         try:
@@ -353,7 +353,7 @@ def detect_loops_in_function(
 def find_parallelizable_loops(
     func: Callable,
     args: tuple = (),
-    kwargs: dict = None,
+    kwargs: Optional[Dict[Any, Any]] = None,
     max_nesting_level: int = 1,
 ) -> List[LoopInfo]:
     """

clustrix/notebook_magic.py

@@ -22,7 +22,7 @@
     IPYTHON_AVAILABLE = False
 
     # Create placeholder classes for non-notebook environments
-    class Magics:
+    class Magics:  # type: ignore
         pass
 
     def magics_class(cls):

clustrix/utils.py

@@ -311,7 +311,7 @@ def setup_remote_environment(
     ssh_client,
     work_dir: str,
     requirements: Dict[str, str],
-    config: ClusterConfig = None,
+    config: Optional[ClusterConfig] = None,
 ):
     """Setup environment on remote cluster via SSH."""
 
@@ -394,14 +394,17 @@ def _create_slurm_script(
         script_lines.append(f"#SBATCH --partition={job_config['partition']}")
 
     # Add environment setup
-    for module in config.module_loads:
-        script_lines.append(f"module load {module}")
+    if config.module_loads:
+        for module in config.module_loads:
+            script_lines.append(f"module load {module}")
 
-    for var, value in config.environment_variables.items():
-        script_lines.append(f"export {var}={value}")
+    if config.environment_variables:
+        for var, value in config.environment_variables.items():
+            script_lines.append(f"export {var}={value}")
 
-    for cmd in config.pre_execution_commands:
-        script_lines.append(cmd)
+    if config.pre_execution_commands:
+        for cmd in config.pre_execution_commands:
+            script_lines.append(cmd)
 
     # Add execution commands
     script_lines.extend(