> ## Documentation Index
> Fetch the complete documentation index at: https://bagel.softnanolab.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Callback

> Abstract base class for callbacks in the optimization process.

Callbacks can be used to monitor, log, or modify the optimization behavior.
All hook methods have default no-op implementations, so subclasses only need
to override the methods they care about.

## Methods

### on\_optimization\_start

Called once before the optimization loop begins.

**Parameters**

<ResponseField name="context" type="CallbackContext" required>
  Context containing initial system state and minimizer reference.
</ResponseField>

### on\_step\_end

Called after each optimization step.

This is the main hook for monitoring and logging during optimization.
All callbacks execute even if early stopping is triggered.

**Parameters**

<ResponseField name="context" type="CallbackContext" required>
  Context containing current step information, systems, and metrics.
</ResponseField>

### on\_optimization\_end

Called once after the optimization loop completes.

**Parameters**

<ResponseField name="context" type="CallbackContext" required>
  Context containing final system state and minimizer reference.
</ResponseField>

## Example

```python theme={null}
class MyCallback(Callback):
    def on_step_end(self, context: CallbackContext) -> None:
        print(f"Step {context.step}: energy = {context.metrics['system_energy']}")
```