feat: capability to override runner

[amithad]

Description

This feature allows agent developers to plug their own observability platform by overriding AK provided runner for the particualr agentic framework.

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Refactoring (no functional changes)
• Performance improvement
• Test update
• CI/CD update
• Other (please describe):

Related Issues

Fixes #
Relates to #

Changes Made

Added a new parameter to pass the runner to Module constructor

Testing

• Unit tests pass locally
• Integration tests pass locally
• Manual testing completed
• New tests added for changes

Checklist

• My code follows the project's style guidelines
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• Any dependent changes have been merged and published

Screenshots (if applicable)

Additional Notes

[Copilot]

Pull Request Overview

This PR introduces the capability for agent developers to integrate their own observability platforms by allowing custom runner overrides for different agentic frameworks.

Key Changes:

• Added optional runner parameter to all module constructors (OpenAIModule, LangGraphModule, CrewAIModule, GoogleADKModule)
• Updated runner initialization logic to prioritize custom runners over default trace configurations
• Added comprehensive documentation and blog post content explaining how to implement custom tracing platforms

Reviewed Changes

Copilot reviewed 6 out of 6 changed files in this pull request and generated 6 comments.

Show a summary per file

File	Description
docs/docs/advanced/traceability.md	Added new section documenting how to integrate custom observability platforms with examples
docs/blog/2025-11-17-observability-support.md	Updated blog post to reflect simplified custom runner initialization approach
ak-py/src/agentkernel/openai/openai.py	Added optional runner parameter to OpenAIModule constructor with priority logic
ak-py/src/agentkernel/langgraph/langgraph.py	Added optional runner parameter to LangGraphModule constructor with priority logic
ak-py/src/agentkernel/crewai/crewai.py	Added optional runner parameter to CrewAIModule constructor with priority logic
ak-py/src/agentkernel/adk/adk.py	Added optional runner parameter to GoogleADKModule constructor with priority logic

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull Request Overview

Copilot reviewed 6 out of 6 changed files in this pull request and generated 6 comments.

Comments suppressed due to low confidence (4)

docs/docs/advanced/traceability.md:453

• Spelling error: "supercedes" should be "supersedes".

## Summary

docs/blog/2025-11-17-observability-support.md:395

• Spelling error: "supercedes" should be "supersedes".
  docs/blog/2025-11-17-observability-support.md:392
• Remove spaces around the = operator in keyword arguments. According to PEP 8, keyword arguments should not have spaces around the equals sign. Change runner = MyCustomOpenAIRunner() to runner=MyCustomOpenAIRunner().
  docs/docs/advanced/traceability.md:439
• The parameter order in the run method call is incorrect. According to the OpenAIRunner.run signature, the correct order is (agent, session, prompt), but this code shows (agent=agent, prompt=prompt, session=session) which has prompt before session. Change to: result = await super().run(agent=agent, session=session, prompt=prompt)

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.