Uploaded image for project: 'OpenShift Pipelines'
  1. OpenShift Pipelines
  2. SRVKP-9149

Conversational Pipeline Debugger

XMLWordPrintable

    • Icon: Feature Feature
    • Resolution: Unresolved
    • Icon: Major Major
    • None
    • None
    • AI
    • False
    • Hide

      None

      Show
      None
    • False

      Goals

      Streamline pipeline troubleshooting by enabling users to query issues in natural language (e.g., "why is my pipelined has failed?"), eliminating the need for manual raw log analysis.

      Information: The scope is productizing what was done in the Tekton Assistant

      Requirements

      Requirements Notes IS MVP
      • Context Aware as the User selects a pipeline and interacts with the OpenShift LightSpeed Prompt, the chat automatically uses the open pipeline's content as context.
      • Natural Language Query Given a failed pipeline, a user can interactively query in natural language (e.g., “why did my image push timing out?”) within the Console.
      • Clear Language Response The system's response must be in clear, natural language and summarize the issue, eliminating the need for the user to manually read raw logs.
      • Actionable Suggestions The response provides actionable suggestions to resolve the issue, which may include code or YAML snippets with a suggested fix.

      Out of scope

      • Fine-Tuned LLM model
      • Provide domain-specific docs for a RAG (Retrieval Augmented Generation) system for pipeline analysis.
      • Backend Tool Integration The failure analysis and explanation are generated by the explain_failure tool provided by the Tekton MCP Server.

      Dependencies

      • OpenShift LightSpeed
      • OpenShift Webconsole UX Design.

      Assumptions

      Customer Considerations

      • LLM capable to produce OpenShift Pipelines YAML snippets
      • OpenShift LightSpeed enabled with a connection to a LLM

      Done Checklist

      • Requirements are met
      • Non-functional properties of the Feature have been validated (such as performance, resource, UX, security or privacy aspects)
      • User Journey automation is delivered
      • Support and SRE teams are provided with enough skills to support the feature in production environment

              Unassigned Unassigned
              rh-ee-csalinas Carlos Salinas Gancedo
              Votes:
              0 Vote for this issue
              Watchers:
              2 Start watching this issue

                Created:
                Updated: