Save the cluster IP and Samba CIFS credentials to a local configuration file. The agent should call this tool when the user provides the cluster IP and credentials.

Get the overall status of the NeuralForgeAI cluster, including health metrics, active celery workers (invokers), and the current tasks queue.

Get detailed telemetry and status of a specific YOLO training study. Returns progress, active invoker, and current trial metrics.

IMPORTANT WORKFLOW FOR AGENTS: When the user asks 'how is my training going?' (or similar) without providing a study_id:

1. DO NOT ask the user for the study_id immediately.

2. First, search the current working directory for .yaml files.

3. Read the discovered .yaml files to check if they contain a study_id field.

4. If you find a study_id inside a YAML file, automatically use this tool with that ID to check its status.

5. Only ask the user for the ID or file path if you cannot find any .yaml files with a study_id in the current directory.

Cancel a running training study by its ID. This will stop the active trials and terminate the executor containers.

Generate a NeuralForgeAI training YAML configuration file and save it to disk. This allows the user to inspect the file before launching the training. Returns the absolute path to the generated YAML file.

Submit a locally saved YOLO training YAML configuration to the NeuralForgeAI cluster. Use this after the user has reviewed and approved the YAML file generated by generate_training_yaml.

Verify if a dataset path exists on the remote Samba share by spinning up a lightweight Docker container.

Validates a YOLO dataset structure by running an inspection script inside a Docker container connected to the remote CIFS share. Supports detect/segment (yaml) and classify (directory).