Story (Required)

As a Platform Developer / SRE trying to quickly diagnose failing Tekton pipelines and TaskRuns from the CLI, I want a tkn-assist client that leverages OpenShift Lightspeed to perform failure analysis and return concise, human-readable explanations and actionable remediation steps.
This story delivers a CLI-first experience that calls Lightspeed (which in turn uses the Tekton MCP tools and OpenShift MCP to gather compact context), so engineers can get reliable root-cause analysis without manually collecting logs or YAML. It improves developer productivity, reduces mean time to repair, and ensures consistent analysis across CLI and console workflows.

Background (Required)

We are pivoting from direct LLM calls to using OpenShift Lightspeed (OLS) as the centralized AI assistant. Lightspeed is responsible for pulling logs/manifests/events via MCP servers, constructing token-efficient context, and invoking the LLM. The tkn-assist client should act as a lightweight CLI wrapper that sends user requests to Lightspeed and displays the returned analysis. Example user commands to support in this story:

• tkn-assist taskrun diagnose <taskrun-name> -n <namespace>

• tkn-assist pipelinerun diagnose <pipelinerun-name> -n <namespace>

Out of scope

<Defines what is not included in this story>

Approach (Required)

<Description of the general technical path on how to achieve the goal of the story. Include details like json schema, class definitions>

Dependencies

<Describes what this story depends on. Dependent Stories and EPICs should be linked to the story.>

Acceptance Criteria (Mandatory)

<Describe edge cases to consider when implementing the story and defining tests>

<Provides a required and minimum list of acceptance tests for this story. More is expected as the engineer implements this story>

INVEST Checklist

Dependencies identified

Blockers noted and expected delivery timelines set

Design is implementable

Acceptance criteria agreed upon

Story estimated

Legend

Unknown

Verified

Unsatisfied

Done Checklist

• Code is completed, reviewed, documented and checked in
• Unit and integration test automation have been delivered and running cleanly in continuous integration/staging/canary environment
• Continuous Delivery pipeline(s) is able to proceed with new code included
• Customer facing documentation, API docs etc. are produced/updated, reviewed and published
• Acceptance criteria are met