Merged in bugfix/max_workers_and_batch_id (pull request #864)

Trigger error when batch_id is not specified or when max_workers is negative

* Trigger error when batch_id is not specified or when max_workers is negative


Approved-by: Katon Minhas

src/config.py

@@ -93,7 +93,7 @@ def get_arg_value(arg_name, default):
 # Run config args
 RUN_MODE = get_arg_value("run_mode", "ec2")  # Valid: local or ec2
 READ_MODE = get_arg_value("read_mode", "s3")  # Valid: local or s3
-BATCH_ID = get_arg_value("batch_id", "test_batch")
+BATCH_ID = get_arg_value("batch_id", None) # BATCH_ID is mandatory
 
 # Per-file logging settings (for debugging)
 ENABLE_PER_FILE_LOGGING = get_arg_value("enable_per_file_logging", "False") == "True"

src/pipelines/runner.py

@@ -106,6 +106,14 @@ def main(client: str = "saas", testing=False, test_params={}):
         testing: Whether running in test mode
         test_params: Test parameters if testing=True
     """
+    # Check if batch_id is specified
+    if not config.BATCH_ID:
+       raise ValueError("batch_id is required. Please specify batch_id in your command")
+    
+    # Check if max_workers is not negative
+    if config.MAX_WORKERS < 0:
+        raise ValueError(f"Invalid configuration: MAX_WORKERS must be non-negative (got {config.MAX_WORKERS})")
+    
     # Validate client
     registry = get_registry()
     if client != "saas" and not registry.has_client(client):

src/pipelines/saas/main.py

@@ -84,6 +84,14 @@ def safe_process_file(item, constants, run_timestamp):
 
 
 def main(testing=False, test_params={}):
+    # Check if batch_id is specified
+    if not config.BATCH_ID:
+       raise ValueError("batch_id is required. Please specify batch_id in your command")
+    
+    # Check if max_workers is not negative
+    if config.MAX_WORKERS < 0:
+        raise ValueError(f"Invalid configuration: MAX_WORKERS must be non-negative (got {config.MAX_WORKERS})")
+
     # Set up per-file logging (creates separate log files for each document)
     logging_utils.setup_per_file_logging()