feat(runtimes): add Pending and Running status conditions for TrainJob

[RohitYandigeri]

Fixes #2713

This PR improves TrainJob observability by adding intermediate status
conditions that reflect the lifecycle of the underlying jobs.

What’s added

• Pending condition when a TrainJob is created but underlying jobs have not started
• Running condition when underlying jobs are actively executing
• Status is derived from Job-level signals via the TrainJobStatus framework plugin
• kubectl get trainjob now reflects these states consistently

Notes

• Status is not set during TrainJob creation (controller-owned status), in line
  with Kubernetes conventions
• CRD regeneration could not be performed locally on Windows; happy to update
  manifests if requested

Why

This aligns TrainJob with standard Kubernetes resource status patterns and
provides better UX for users monitoring training lifecycle.

cc @kubeflow/kubeflow-trainer-team

[google-oss-prow]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by:
Once this PR has been reviewed and has the lgtm label, please assign tenzen-y for approval. For more information see the Kubernetes Code Review Process.

The full list of commands accepted by this bot can be found here.

Details

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[github-actions]

🎉 Welcome to the Kubeflow Trainer! 🎉

Thanks for opening your first PR! We're happy to have you as part of our community 🚀

Here's what happens next:

• If you haven't already, please check out our Contributing Guide for repo-specific guidelines and the Kubeflow Contributor Guide for general community standards.
• Our team will review your PR soon! cc @kubeflow/kubeflow-trainer-team

Join the community:

• Slack: Join our #kubeflow-trainer Slack channel.
• Meetings: Attend the Kubeflow AutoML and Training Working Group bi-weekly meetings.

Feel free to ask questions in the comments if you need any help or clarification!
Thanks again for contributing to Kubeflow! 🙏

[andreyvelich]

Thank you for this contribution @RohitYandigeri!
As we discussed before, Job Active condition doesn't indicate that training process is running. Sometime, PyTorch can stuck in initialization phase or synchronization phase. Kubernetes Batch/Job doesn't detect that.

As part of this KEP: #2905, we are working on exposing training progress to the TrainJob status. That will help us to detect that the actual model training process is happening.

cc @robert-bell @kubeflow/kubeflow-trainer-team

Let's hold this PR for now, and discuss more details in 2905
/hold

[andreyvelich]

I will close this PR since we will implement solution to detect TrainJob status as part of this KEP: #2905
/close

[google-oss-prow]

@andreyvelich: Closed this PR.

Details

In response to this:

I will close this PR since we will implement solution to detect TrainJob status as part of this KEP: #2905
/close

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository.