​

Overview

Real-time traces are one of Laminar’s most powerful features, allowing you to see spans as they’re being executed without waiting for the top-level span to complete. This provides immediate visibility into trace data during development and debugging processes, which is especially valuable when:

• Working with long-running operations
• Debugging complex agent interactions
• Monitoring multiple chained LLM requests
• Testing a system in development

​

How It Works

Laminar uses OpenTelemetry for trace collection and processing. By default, it uses BatchSpanProcessor, which buffers and sends traces in batches to optimize performance:

• Traces are collected and stored temporarily on the client side
• Data is sent periodically to the Laminar backend
• There’s a small delay between span completion and dashboard visibility
• The delay depends on batch configuration (flush interval and batch size)

​

Disable Batching (Optional)

For immediate trace visibility, you can disable batching by setting disableBatch to true in the Laminar.initialize function:

Laminar.initialize({
    // ... other options
    disableBatch: true,
});

Laminar.initialize({
    // ... other options
    disableBatch: true,
});

Laminar.initialize(
    # other options
    disable_batch=True,
)

This configuration uses SimpleSpanProcessor, which processes and sends traces immediately.

​

Performance Considerations

• Development: Real-time processing provides immediate feedback, beneficial for debugging and development workflows
• Production: Batch processing is recommended for better performance and resource utilization

​

Benefits

1. Immediate Feedback: See traces as they happen, without waiting for operations to complete
2. Faster Debugging: Identify issues in real-time without waiting for batched processing
3. Progress Monitoring: Track long-running operations as they execute
4. Enhanced Development Experience: Test and iterate more quickly with instant visibility