ak-dev-new-tracing-provider

Implement BaseTrace interfaces and framework-specific traced runners for Agent Kernel.

113|60|Updated Jul 18, 2025
One-click install
npx skills add https://github.com/yaalalabs/agent-kernel --skill ak-dev-new-tracing-provider
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ak-dev-new-tracing-provider
Source: https://github.com/yaalalabs/agent-kernel/tree/main/.agents/skills/ak-dev-new-tracing-provider
Command: npx skills add https://github.com/yaalalabs/agent-kernel --skill ak-dev-new-tracing-provider

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a comprehensive guide to integrating new tracing and observability backends into the Agent Kernel framework, enhancing the ability to monitor and debug agent operations.

Core Features & Use Cases

  • Custom Tracing Integration: Implement support for new tracing providers beyond the defaults.
  • Framework-Specific Runners: Create traced versions of runners for OpenAI, LangGraph, CrewAI, and Google ADK.
  • Configuration and Testing: Details on updating configuration, managing dependencies, and writing tests for new providers.
  • Use Case: A development team needs to integrate Agent Kernel with their existing in-house tracing system, which is not natively supported. This Skill guides them through the entire process.

Quick Start

Follow the step-by-step guide to add a new tracing provider to Agent Kernel.

Frequently Asked Questions about ak-dev-new-tracing-provider

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add a new tracing provider to Agent Kernel?

To add a new tracing provider to Agent Kernel, implement the BaseTrace interface, create framework-specific traced runners for OpenAI or LangGraph, update the trace factory, and manage the necessary configuration and dependencies.

Can I integrate a custom in-house observability system with Agent Kernel?

Yes, you can integrate a custom in-house observability system by implementing the BaseTrace interface and updating the trace factory to route telemetry data to your existing backend for monitoring agent operations.

What frameworks are supported when creating traced runners for observability?

The guide covers creating traced runners for OpenAI, LangGraph, CrewAI, and Google ADK, ensuring your new tracing provider captures telemetry across these specific execution frameworks.

How does the BaseTrace interface work for custom observability integration?

The BaseTrace interface defines the contract for capturing tracing data, requiring you to implement its methods and register the implementation in the trace factory to enable monitoring for agent operations.

Do I need to update dependencies when adding a new tracing backend to Agent Kernel?

Yes, adding a new tracing backend requires updating dependencies to include the provider's SDK, modifying configuration files, and writing tests to verify the observability integration works correctly.

What is the best way to test a new tracing provider implementation in Agent Kernel?

The best way to test a new tracing provider is to follow the configuration and testing details in the guide, ensuring your custom BaseTrace implementation correctly captures telemetry from the framework-specific runners.