V2.1.0 odh rebase

[abhijeet-dhumal]

What this PR does / why we need it:
RHOAIENG-38137
Upstream Trainer v2 operator has latest release v2.1 - kubeflow#2859
This PR is to follow the upgrade and rebase midstream/downstream.

Checklist:

• Docs included if any changes are user facing

Summary by CodeRabbit

Release Notes

• New Features

  • Added GPU-enabled end-to-end testing workflow
  • Added Rust testing support
  • Added Helm chart OCI-based installation and publishing
  • Introduced Volcano PodGroup policy support for pod scheduling
  • Added pod template override capabilities and container restart rule configurations to Python API

• Documentation

  • Published security policy and vulnerability reporting guidelines
  • Expanded contributor guide with coding style standards
  • Added 2025 roadmap milestones

• Updates

  • Updated Kubernetes test versions and tool dependencies
  • Bumped Python API and Helm chart versions to 2.1.0
  • Added new notebook-based training examples to E2E tests

[coderabbitai]

Walkthrough

This pull request introduces version 2.1.0 of Kubeflow Trainer with expanded CI/CD workflows, new model definitions in the Python API, Helm chart updates, configuration enhancements, and documentation improvements. Key additions include GPU E2E testing, workflow approval automation, Rust support, Volcano CRD integration, and extensive Kubernetes API model extensions for container restart rules, pod certificates, and extended resource handling.

Changes

Cohort / File(s)	Summary
Configuration & Linting .flake8, .gitattributes, .gitignore, .pre-commit-config.yaml, .golangci-kal.yml	Extended flake8 ignore rules (E203), added linguist-generated markers for Go generated code and API client paths, expanded gitignore patterns for Helm and data_cache artifacts, configured pre-commit hooks for Rust formatting/checking, introduced kubeapilinter configuration with customized KubeAPI linting rules
GitHub Workflows – CI/CD Pipelines .github/workflows/build-and-push-images.yaml, .github/workflows/test-*.yaml, .github/workflows/publish-*.yaml, .github/workflows/template-publish-image/action.yaml, .github/workflows/trivy-scan.yaml	Extended build matrix with data-cache component (linux/amd64, linux/arm64), restricted mlx-runtime to linux/amd64 only, updated Kubernetes test versions (1.31.0 → 1.34.0), added Kubeflow SDK installation with docker extras, added new notebooks to E2E tests (local-training-mnist, local-container-mnist), added repository-scoped gating for Go jobs
GitHub Workflows – New Features .github/workflows/check-pr-title.yaml, .github/workflows/gh-workflow-approve.yaml, .github/workflows/test-e2e-gpu.yaml, .github/workflows/test-rust.yaml, .github/workflows/trivy-scan.yaml, .github/workflows/publish-helm-charts.yaml	Introduced semantic PR title validation (conventional commits), implemented workflow approval automation for Kubeflow members and labeled PRs, added GPU-enabled E2E test workflow with label gating and optional cluster cleanup, added Rust unit/integration test support, introduced Trivy vulnerability scanning, added Helm chart publication to GHCR (OCI registry)
Documentation & Governance README.md, ROADMAP.md, SECURITY.md, CONTRIBUTING.md, CHANGELOG.md, ADOPTERS.md, OWNERS	Updated README with Latest News section, replaced badges, expanded overview descriptions, added Kubeflow Trainer-specific terminology; added 2025 roadmap section; introduced security policy with versioning and vulnerability handling; restructured CONTRIBUTING guide with coding style section and conventional commit guidance; added v2.0.1 release notes; added Red Hat adopter entry; promoted astefanutti from reviewer to approver
Build Automation Makefile	Bumped Kubernetes/controller toolchain versions (K8S_VERSION 1.32.0→1.34.0, ENVTEST_VERSION release-0.20→release-0.22, CONTROLLER_GEN_VERSION v0.17.2→v0.18.0), added golangci-lint-kal target with KubeAPI linting, introduced Volcano CRD support and targets, expanded manifests generation for config/v1alpha1, added test-rust and test-e2e-setup-gpu-cluster targets, broadened test exclusion filters
Python API – Version & Models Index api/python_api/kubeflow_trainer_api/__init__.py, api/python_api/kubeflow_trainer_api/models/__init__.py	Bumped package version 2.0.0→2.1.0, added 15+ new model imports (container restart rules, extended resource handling, pod certificates, file key selector, volcano pod group policy, pod template overrides, network topology)
Python API – Kubernetes Core Models api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_*.py	Added container restart policy support (ContainerRestartRule, OnExitCodes), introduced extended resource claim handling (ContainerExtendedResourceRequest, PodExtendedResourceClaimStatus), added file-based environment variable sourcing (FileKeySelector), added pod certificate projection support, added node swap status tracking, updated pod spec with hostnameOverride field, added observed_generation and extended resource claim status to pod status, updated field descriptions to remove beta feature gate references and clarify semantics
Python API – Batch & Scheduling Models api/python_api/kubeflow_trainer_api/models/io_k8s_api_batch_v1_*.py, api/python_api/kubeflow_trainer_api/models/scheduling_v1beta1_*.py, api/python_api/kubeflow_trainer_api/models/jobset_v1alpha2_*.py	Shortened descriptions for backoffLimit, backoffLimitPerIndex, maxFailedIndexes to remove feature gate references, added message pattern matching to failure policy rules, changed JobSet restarts default from None→0, added groupName field to ReplicatedJob, introduced NetworkTopologySpec for network topology constraints
Python API – Trainer Models api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_*.py	Replaced PodSpecOverride with PodTemplateOverride (adds metadata handling), added Volcano pod group policy support (VolcanoPodGroupPolicySource), added pod template metadata overrides, extended pod spec overrides with affinity/annotations/imagePullSecrets/labels, updated field descriptions across all trainer models for clarity and consistency, made TrainingRuntimeSpec template field optional
Python API – Configuration api/python_api/pyproject.toml	Simplified license declaration from table format to string, removed wheel build targets configuration
Helm Chart charts/kubeflow-trainer/Chart.yaml, charts/kubeflow-trainer/README.md	Bumped chart version 2.0.0→2.1.0, updated jobset dependency (oci://registry.k8s.io/jobset/charts/jobset v0.8.2→oci://registry.k8s.io/jobset/charts 0.10.1), updated installation instructions to use OCI-based Helm chart from GHCR, added manager security context and controller configuration defaults, expanded documented values with new manager fields

Estimated code review effort

🎯 4 (Complex) | ⏱️ ~60 minutes

Areas requiring extra attention:

• Python API Model Updates (api/python_api/kubeflow_trainer_api/models/): Review the consistency of serialization/deserialization logic (to_dict, from_dict) across ~50 model files; verify alias handling and None-field exclusion patterns are applied correctly
• Kubernetes Version & Tooling Bumps (Makefile, workflows): Confirm compatibility of controller-gen v0.18.0, envtest release-0.22, and K8S 1.34.0 with existing code generation and manifests
• Pod Template Override Refactoring (trainer_v1alpha1_pod_template_override.py, trainer_v1alpha1_train_job_spec.py): Ensure the transition from PodSpecOverride to PodTemplateOverride is backward compatible and properly handles metadata merging
• Workflow Approval Automation (.github/workflows/gh-workflow-approve.yaml): Verify membership check logic and workflow run approval API interactions are sound and handle edge cases (404s, non-members)
• GPU E2E Workflow (.github/workflows/test-e2e-gpu.yaml): Confirm label-gating, cluster setup/teardown, and artifact handling work correctly with Kind GPU setup

🐰 With whiskers twitching in delight,
New models hop and schemas take flight,
Volcano rumbles, GPU clusters gleam,
Version 2.1 fulfills the training dream!
Workflows approve, the tests run so bright—
Kubeflow Trainer bounds forward tonight! 🚀

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title 'V2.1.0 odh rebase' refers to rebasing the repository to Trainer v2.1.0, which is the main objective described in the PR. It is specific and directly related to the core purpose of the changeset.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.

✨ Finishing touches

• 📝 Generate docstrings

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 23

🧹 Nitpick comments (6)

api/python_api/pyproject.toml (1)

35-36: Consider pinning hatchling version for reproducible builds.

The build-system requirement specifies hatchling without a version constraint, which could lead to non-deterministic builds if breaking changes are introduced in future releases. For a reproducible build pipeline, consider pinning to a specific version or a narrow version range.

Example: requires = ["hatchling>=1.0,<2.0"] or similar.

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_cluster_training_runtime.py (1)

33-34: Documentation descriptions are less informative after the upstream rebase.

The field descriptions have been simplified:

• metadata: Previously "Standard object's metadata.", now "metadata of the ClusterTrainingRuntime."
• spec: Previously "Specification of the desired ClusterTrainingRuntime.", now "spec of the ClusterTrainingRuntime."

Since this is auto-generated code from the OpenAPI specification, the less descriptive text is coming from the upstream v2.1.0 spec. If more detailed descriptions would benefit API consumers, consider proposing improvements to the upstream OpenAPI definition in the Kubeflow Trainer repository.

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_model_initializer.py (1)

30-30: Remove unused noqa directive.

Static analysis flagged the # noqa: E501 on this line as unused. Since this is generated code, you may want to verify with your code generator configuration or clean up manually if applicable.

Apply this diff to remove the unused directive:

-    ModelInitializer represents the desired configuration to initialize pre-trained model. The ModelInitializer spec will override the runtime Job template which contains this label: `trainer.kubeflow.org/trainjob-ancestor-step: dataset-initializer`
-    """ # noqa: E501
+    ModelInitializer represents the desired configuration to initialize pre-trained model. The ModelInitializer spec will override the runtime Job template which contains this label: `trainer.kubeflow.org/trainjob-ancestor-step: dataset-initializer`
+    """

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_ml_policy.py (1)

30-30: Remove unused noqa directive.

The # noqa: E501 directive is unnecessary here as the line length doesn't trigger E501.

Apply this diff:

-    """ # noqa: E501
+    """

Note: Since this is an auto-generated file, consider whether the fix should be applied to the OpenAPI generator template instead.

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule_on_exit_codes.py (2)

25-31: Consider adding field validation constraints.

The field descriptions mention specific constraints that aren't enforced in the model:

• operator: Should be "In" or "NotIn"
• values: Maximum 255 elements allowed

While server-side validation may handle these constraints, adding client-side validation would provide earlier error detection.

Example validation with Pydantic v2 features:

+from typing import Literal
+from pydantic import field_validator

 class IoK8sApiCoreV1ContainerRestartRuleOnExitCodes(BaseModel):
     """
     ContainerRestartRuleOnExitCodes describes the condition for handling an exited container based on its exit codes.
     """ # noqa: E501
-    operator: StrictStr = Field(description="Represents the relationship between the container exit code(s) and the specified values. Possible values are: - In: the requirement is satisfied if the container exit code is in the   set of specified values. - NotIn: the requirement is satisfied if the container exit code is   not in the set of specified values.")
+    operator: Literal["In", "NotIn"] = Field(description="Represents the relationship between the container exit code(s) and the specified values. Possible values are: - In: the requirement is satisfied if the container exit code is in the   set of specified values. - NotIn: the requirement is satisfied if the container exit code is   not in the set of specified values.")
     values: Optional[List[StrictInt]] = Field(default=None, description="Specifies the set of values to check for container exit codes. At most 255 elements are allowed.")
     __properties: ClassVar[List[str]] = ["operator", "values"]
+    
+    @field_validator('values')
+    @classmethod
+    def validate_values_length(cls, v):
+        if v is not None and len(v) > 255:
+            raise ValueError('values list cannot exceed 255 elements')
+        return v

---

54-72: Simplify to_dict() by removing unused excluded_fields.

The excluded_fields set is defined but remains empty and unused. This appears to be generated template code.

Apply this diff to simplify:

     def to_dict(self) -> Dict[str, Any]:
         """Return the dictionary representation of the model using alias.

         This has the following differences from calling pydantic's
         `self.model_dump(by_alias=True)`:

         * `None` is only added to the output dict for nullable fields that
           were set at model initialization. Other fields with value `None`
           are ignored.
         """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
+        return self.model_dump(
             by_alias=True,
-            exclude=excluded_fields,
             exclude_none=True,
         )
-        return _dict

Note: If this pattern is needed for consistency with other generated models in the codebase, it's acceptable to leave as-is.

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between d0c78f5 and c156297.

⛔ Files ignored due to path filters (6)

• docs/images/trainer-tech-stack.drawio.svg is excluded by !**/*.svg
• docs/proposals/2437-volcano-scheduler/user-roles-scheduler.drawio.svg is excluded by !**/*.svg
• docs/proposals/2442-jax-runtime-trainer-v2/drawing.drawio.svg is excluded by !**/*.svg
• go.sum is excluded by !**/*.sum
• pkg/data_cache/Cargo.lock is excluded by !**/*.lock
• pkg/data_cache/test/Cargo.lock is excluded by !**/*.lock

📒 Files selected for processing (107)

• .flake8 (1 hunks)
• .gitattributes (1 hunks)
• .github/ISSUE_TEMPLATE/bug_report.yaml (1 hunks)
• .github/workflows/build-and-push-images.yaml (2 hunks)
• .github/workflows/check-pr-title.yaml (1 hunks)
• .github/workflows/gh-workflow-approve.yaml (1 hunks)
• .github/workflows/publish-helm-charts.yaml (1 hunks)
• .github/workflows/template-publish-image/action.yaml (1 hunks)
• .github/workflows/test-e2e-gpu.yaml (1 hunks)
• .github/workflows/test-e2e.yaml (3 hunks)
• .github/workflows/test-go.yaml (2 hunks)
• .github/workflows/test-rust.yaml (1 hunks)
• .github/workflows/trivy-scan.yaml (1 hunks)
• .gitignore (1 hunks)
• .golangci-kal.yml (1 hunks)
• .pre-commit-config.yaml (1 hunks)
• ADOPTERS.md (1 hunks)
• CHANGELOG.md (4 hunks)
• CONTRIBUTING.md (1 hunks)
• Makefile (7 hunks)
• OWNERS (1 hunks)
• README.md (3 hunks)
• ROADMAP.md (1 hunks)
• SECURITY.md (1 hunks)
• api/python_api/kubeflow_trainer_api/__init__.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/__init__.py (7 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_autoscaling_v2_hpa_scaling_rules.py (3 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_batch_v1_job_spec.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_batch_v1_job_status.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_batch_v1_pod_failure_policy_rule.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_batch_v1_success_policy.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container.py (6 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_extended_resource_request.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule_on_exit_codes.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_status.py (3 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_endpoint_address.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_endpoint_port.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_endpoint_subset.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_endpoints.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_endpoints_list.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_env_from_source.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_env_var.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_env_var_source.py (4 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_ephemeral_container.py (6 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_ephemeral_container_common.py (6 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_file_key_selector.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_glusterfs_volume_source.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_lifecycle.py (3 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_node_swap_status.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_node_system_info.py (4 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_persistent_volume_claim_spec.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_persistent_volume_claim_status.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_persistent_volume_spec.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_affinity_term.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_anti_affinity.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_certificate_projection.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_condition.py (3 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_extended_resource_claim_status.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_spec.py (3 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_status.py (4 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_replication_controller_spec.py (2 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_resource_quota_spec.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_resource_requirements.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_scoped_resource_selector_requirement.py (2 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_service_spec.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_taint.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_topology_spread_constraint.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_volume.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_volume_projection.py (4 hunks)
• api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_volume_source.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/jobset_v1alpha2_failure_policy_rule.py (2 hunks)
• api/python_api/kubeflow_trainer_api/models/jobset_v1alpha2_job_set_status.py (2 hunks)
• api/python_api/kubeflow_trainer_api/models/jobset_v1alpha2_replicated_job.py (2 hunks)
• api/python_api/kubeflow_trainer_api/models/scheduling_v1beta1_network_topology_spec.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_cluster_training_runtime.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_container_override.py (2 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_coscheduling_pod_group_policy_source.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_dataset_initializer.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_initializer.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_job_set_template_spec.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_job_status.py (2 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_ml_policy.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_ml_policy_source.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_model_initializer.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_mpiml_policy_source.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_group_policy.py (3 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_group_policy_source.py (3 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_spec_override.py (4 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_spec_override_target_job.py (2 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_metadata_override.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override_target_job.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_spec_override.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_runtime_ref.py (2 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_torch_elastic_policy.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_torch_ml_policy_source.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_train_job.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_train_job_spec.py (4 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_train_job_status.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_trainer.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_training_runtime.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_training_runtime_spec.py (1 hunks)
• api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_volcano_pod_group_policy_source.py (1 hunks)
• api/python_api/pyproject.toml (1 hunks)
• charts/kubeflow-trainer/Chart.yaml (1 hunks)
• charts/kubeflow-trainer/README.md (3 hunks)

⛔ Files not processed due to max files limit (51)

• charts/kubeflow-trainer/README.md.gotmpl
• charts/kubeflow-trainer/crds/trainer.kubeflow.org_clustertrainingruntimes.yaml
• charts/kubeflow-trainer/crds/trainer.kubeflow.org_trainingruntimes.yaml
• charts/kubeflow-trainer/templates/_helpers.tpl
• charts/kubeflow-trainer/templates/manager/_helpers.tpl
• charts/kubeflow-trainer/templates/manager/configmap.yaml
• charts/kubeflow-trainer/templates/manager/deployment.yaml
• charts/kubeflow-trainer/templates/rbac/clusterrole.yaml
• charts/kubeflow-trainer/tests/manager/configmap_test.yaml
• charts/kubeflow-trainer/values.yaml
• cmd/data_cache/Dockerfile
• cmd/initializers/dataset/Dockerfile
• cmd/initializers/dataset/requirements.txt
• cmd/initializers/model/Dockerfile
• cmd/initializers/model/requirements.txt
• cmd/runtimes/deepspeed/Dockerfile
• cmd/runtimes/deepspeed/requirements.txt
• cmd/runtimes/mlx/Dockerfile
• cmd/runtimes/mlx/requirements.txt
• cmd/trainer-controller-manager/main.go
• cmd/trainers/torchtune/Dockerfile
• cmd/trainers/torchtune/requirements.txt
• docs/proposals/2170-kubeflow-trainer-v2/README.md
• docs/proposals/2401-llm-trainer-v2/README.md
• docs/proposals/2432-gpu-testing-on-llm-blueprints/OCI VM/bootstrap.sh
• docs/proposals/2432-gpu-testing-on-llm-blueprints/OCI VM/main.tf
• docs/proposals/2432-gpu-testing-on-llm-blueprints/OCI VM/terraform.tfvars
• docs/proposals/2432-gpu-testing-on-llm-blueprints/README.md
• docs/proposals/2437-volcano-scheduler/README.md
• docs/proposals/2442-jax-runtime-trainer-v2/README.md
• docs/release/README.md
• examples/local/local-container-mnist.ipynb
• examples/local/local-training-mnist.ipynb
• examples/mlx/language-modeling/fine-tune-llama.ipynb
• examples/pytorch/data-cache/fine-tune-with-cache.ipynb
• examples/pytorch/image-classification/mnist.ipynb
• examples/pytorch/question-answering/fine-tune-distilbert.ipynb
• examples/torchtune/llama3_2/alpaca-trainjob-yaml.ipynb
• examples/torchtune/qwen2_5/qwen2.5-1.5B-with-alpaca.ipynb
• go.mod
• hack/.custom-gcl.yaml
• hack/data_cache/run_with_remote_table.sh
• hack/e2e-run-notebook.sh
• hack/e2e-setup-cluster.sh
• hack/e2e-setup-gpu-cluster.sh
• hack/python-api/gen-api.sh
• hack/scripts/load-image-to-kind.sh
• hack/swagger/main.go
• hack/update-codegen.sh
• hack/violation_exception_v1alpha1.list
• manifests/base/crds/trainer.kubeflow.org_clustertrainingruntimes.yaml

🧰 Additional context used

🧬 Code graph analysis (44)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_volume_projection.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_certificate_projection.py (1)

• IoK8sApiCoreV1PodCertificateProjection (25-95)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule_on_exit_codes.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule.py (2)

• to_dict (55-76)
• from_dict (79-91)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_ephemeral_container.py (3)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule.py (3)

• IoK8sApiCoreV1ContainerRestartRule (26-91)
• to_dict (55-76)
• from_dict (79-91)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container.py (2)

• to_dict (108-193)
• from_dict (196-231)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule_on_exit_codes.py (2)

• to_dict (54-72)
• from_dict (75-87)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_initializer.py (2)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_dataset_initializer.py (1)

• TrainerV1alpha1DatasetInitializer (27-101)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_model_initializer.py (1)

• TrainerV1alpha1ModelInitializer (27-101)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override_target_job.py (1)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override.py (2)

• to_dict (58-89)
• from_dict (92-105)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_cluster_training_runtime.py (1)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_training_runtime_spec.py (1)

• TrainerV1alpha1TrainingRuntimeSpec (28-101)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_env_var_source.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_file_key_selector.py (3)

• IoK8sApiCoreV1FileKeySelector (25-91)
• to_dict (56-74)
• from_dict (77-91)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_model_initializer.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_env_var.py (1)

• IoK8sApiCoreV1EnvVar (26-93)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_training_runtime.py (1)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_training_runtime_spec.py (1)

• TrainerV1alpha1TrainingRuntimeSpec (28-101)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_ml_policy.py (2)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_mpiml_policy_source.py (1)

• TrainerV1alpha1MPIMLPolicySource (25-91)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_torch_ml_policy_source.py (1)

• TrainerV1alpha1TorchMLPolicySource (27-95)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_ml_policy_source.py (2)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_mpiml_policy_source.py (1)

• TrainerV1alpha1MPIMLPolicySource (25-91)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_torch_ml_policy_source.py (1)

• TrainerV1alpha1TorchMLPolicySource (27-95)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_status.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_lifecycle.py (1)

• stop_signal_validate_enum (36-43)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_volume.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_glusterfs_volume_source.py (1)

• IoK8sApiCoreV1GlusterfsVolumeSource (25-89)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_ephemeral_container_common.py (4)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule.py (3)

• IoK8sApiCoreV1ContainerRestartRule (26-91)
• to_dict (55-76)
• from_dict (79-91)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_env_from_source.py (3)

• IoK8sApiCoreV1EnvFromSource (27-97)
• to_dict (57-81)
• from_dict (84-97)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container.py (2)

• to_dict (108-193)
• from_dict (196-231)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_ephemeral_container.py (2)

• to_dict (109-194)
• from_dict (197-233)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_extended_resource_request.py (2)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_env_var.py (1)

• from_dict (80-93)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_file_key_selector.py (1)

• from_dict (77-91)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override.py (2)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override_target_job.py (6)

• TrainerV1alpha1PodTemplateOverrideTargetJob (25-85)
• to_str (39-41)
• to_json (43-46)
• to_dict (53-71)
• from_json (49-51)
• from_dict (74-85)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_spec_override.py (6)

• TrainerV1alpha1PodTemplateSpecOverride (31-152)
• to_str (53-55)
• to_json (57-60)
• to_dict (67-130)
• from_json (63-65)
• from_dict (133-152)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_group_policy.py (2)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_volcano_pod_group_policy_source.py (3)

• TrainerV1alpha1VolcanoPodGroupPolicySource (26-89)
• to_dict (54-75)
• from_dict (78-89)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_group_policy_source.py (2)

• to_dict (56-80)
• from_dict (83-95)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_torch_ml_policy_source.py (1)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_torch_elastic_policy.py (1)

• TrainerV1alpha1TorchElasticPolicy (26-99)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule_on_exit_codes.py (6)

• IoK8sApiCoreV1ContainerRestartRuleOnExitCodes (25-87)
• to_str (40-42)
• to_json (44-47)
• to_dict (54-72)
• from_json (50-52)
• from_dict (75-87)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_volcano_pod_group_policy_source.py (2)

api/python_api/kubeflow_trainer_api/models/scheduling_v1beta1_network_topology_spec.py (6)

• SchedulingV1beta1NetworkTopologySpec (25-87)
• to_str (40-42)
• to_json (44-47)
• to_dict (54-72)
• from_json (50-52)
• from_dict (75-87)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_group_policy.py (5)

• to_str (42-44)
• to_json (46-49)
• to_dict (56-80)
• from_json (52-54)
• from_dict (83-95)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_train_job_status.py (1)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_job_status.py (1)

• TrainerV1alpha1JobStatus (25-95)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_autoscaling_v2_hpa_scaling_rules.py (2)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_batch_v1_job_spec.py (2)

• to_dict (92-122)
• from_dict (125-151)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_status.py (2)

• to_dict (83-134)
• from_dict (137-167)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_spec_override.py (2)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_container_override.py (3)

• TrainerV1alpha1ContainerOverride (27-105)
• to_dict (57-89)
• from_dict (92-105)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_spec_override.py (2)

• to_dict (67-130)
• from_dict (133-152)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container.py (3)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule.py (3)

• IoK8sApiCoreV1ContainerRestartRule (26-91)
• to_dict (55-76)
• from_dict (79-91)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_env_from_source.py (3)

• IoK8sApiCoreV1EnvFromSource (27-97)
• to_dict (57-81)
• from_dict (84-97)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_ephemeral_container.py (2)

• to_dict (109-194)
• from_dict (197-233)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_status.py (2)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_condition.py (1)

• IoK8sApiCoreV1PodCondition (26-98)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_extended_resource_claim_status.py (1)

• IoK8sApiCoreV1PodExtendedResourceClaimStatus (26-95)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_node_system_info.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_node_swap_status.py (1)

• IoK8sApiCoreV1NodeSwapStatus (25-85)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_extended_resource_claim_status.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_extended_resource_request.py (6)

• IoK8sApiCoreV1ContainerExtendedResourceRequest (25-89)
• to_str (41-43)
• to_json (45-48)
• to_dict (55-73)
• from_json (51-53)
• from_dict (76-89)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_metadata_override.py (2)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override_target_job.py (3)

• to_dict (53-71)
• from_json (49-51)
• from_dict (74-85)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_train_job_spec.py (3)

• to_dict (64-98)
• from_json (60-62)
• from_dict (101-119)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_group_policy_source.py (2)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_volcano_pod_group_policy_source.py (3)

• TrainerV1alpha1VolcanoPodGroupPolicySource (26-89)
• to_dict (54-75)
• from_dict (78-89)

api/python_api/kubeflow_trainer_api/models/scheduling_v1beta1_network_topology_spec.py (2)

• to_dict (54-72)
• from_dict (75-87)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_file_key_selector.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_env_var_source.py (1)

• from_dict (98-113)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_volume_source.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_glusterfs_volume_source.py (1)

• IoK8sApiCoreV1GlusterfsVolumeSource (25-89)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_spec_override.py (2)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_volume.py (1)

• IoK8sApiCoreV1Volume (55-265)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_container_override.py (6)

• TrainerV1alpha1ContainerOverride (27-105)
• to_str (43-45)
• to_json (47-50)
• to_dict (57-89)
• from_json (53-55)
• from_dict (92-105)

api/python_api/kubeflow_trainer_api/models/scheduling_v1beta1_network_topology_spec.py (1)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_volcano_pod_group_policy_source.py (2)

• to_dict (54-75)
• from_dict (78-89)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_batch_v1_job_spec.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_batch_v1_success_policy.py (1)

• IoK8sApiBatchV1SuccessPolicy (26-93)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_lifecycle.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_status.py (2)

• stop_signal_validate_enum (53-60)
• from_dict (137-167)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_train_job.py (2)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_train_job_spec.py (1)

• TrainerV1alpha1TrainJobSpec (29-119)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_train_job_status.py (1)

• TrainerV1alpha1TrainJobStatus (27-103)

api/python_api/kubeflow_trainer_api/models/__init__.py (12)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_extended_resource_request.py (1)

• IoK8sApiCoreV1ContainerExtendedResourceRequest (25-89)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule.py (1)

• IoK8sApiCoreV1ContainerRestartRule (26-91)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule_on_exit_codes.py (1)

• IoK8sApiCoreV1ContainerRestartRuleOnExitCodes (25-87)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_file_key_selector.py (1)

• IoK8sApiCoreV1FileKeySelector (25-91)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_node_swap_status.py (1)

• IoK8sApiCoreV1NodeSwapStatus (25-85)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_certificate_projection.py (1)

• IoK8sApiCoreV1PodCertificateProjection (25-95)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_extended_resource_claim_status.py (1)

• IoK8sApiCoreV1PodExtendedResourceClaimStatus (26-95)

api/python_api/kubeflow_trainer_api/models/scheduling_v1beta1_network_topology_spec.py (1)

• SchedulingV1beta1NetworkTopologySpec (25-87)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override.py (1)

• TrainerV1alpha1PodTemplateOverride (28-105)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override_target_job.py (1)

• TrainerV1alpha1PodTemplateOverrideTargetJob (25-85)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_spec_override.py (1)

• TrainerV1alpha1PodTemplateSpecOverride (31-152)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_volcano_pod_group_policy_source.py (1)

• TrainerV1alpha1VolcanoPodGroupPolicySource (26-89)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_trainer.py (2)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_env_var.py (1)

• IoK8sApiCoreV1EnvVar (26-93)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_resource_requirements.py (1)

• IoK8sApiCoreV1ResourceRequirements (27-122)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_spec.py (2)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container.py (1)

• IoK8sApiCoreV1Container (36-231)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_resource_requirements.py (1)

• IoK8sApiCoreV1ResourceRequirements (27-122)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_dataset_initializer.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_env_var.py (1)

• IoK8sApiCoreV1EnvVar (26-93)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_training_runtime_spec.py (3)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_ml_policy.py (1)

• TrainerV1alpha1MLPolicy (27-97)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_group_policy.py (1)

• TrainerV1alpha1PodGroupPolicy (27-95)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_job_set_template_spec.py (1)

• TrainerV1alpha1JobSetTemplateSpec (27-95)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_container_override.py (1)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_env_var.py (1)

• IoK8sApiCoreV1EnvVar (26-93)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_train_job_spec.py (4)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override.py (3)

• TrainerV1alpha1PodTemplateOverride (28-105)
• to_dict (58-89)
• from_dict (92-105)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override_target_job.py (2)

• to_dict (53-71)
• from_dict (74-85)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_spec_override.py (2)

• to_dict (67-130)
• from_dict (133-152)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_metadata_override.py (2)

• to_dict (54-72)
• from_dict (75-87)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_certificate_projection.py (2)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_extended_resource_request.py (5)

• to_str (41-43)
• to_json (45-48)
• to_dict (55-73)
• from_json (51-53)
• from_dict (76-89)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_file_key_selector.py (5)

• to_str (42-44)
• to_json (46-49)
• to_dict (56-74)
• from_json (52-54)
• from_dict (77-91)

🪛 actionlint (1.7.8)

.github/workflows/test-e2e-gpu.yaml

14-14: label "oracle-vm-16cpu-a10gpu-240gb" is unknown. available labels are "windows-latest", "windows-latest-8-cores", "windows-2025", "windows-2022", "windows-11-arm", "ubuntu-latest", "ubuntu-latest-4-cores", "ubuntu-latest-8-cores", "ubuntu-latest-16-cores", "ubuntu-24.04", "ubuntu-24.04-arm", "ubuntu-22.04", "ubuntu-22.04-arm", "macos-latest", "macos-latest-xl", "macos-latest-xlarge", "macos-latest-large", "macos-26-xlarge", "macos-26", "macos-15-intel", "macos-15-xlarge", "macos-15-large", "macos-15", "macos-14-xl", "macos-14-xlarge", "macos-14-large", "macos-14", "macos-13-xl", "macos-13-xlarge", "macos-13-large", "macos-13", "self-hosted", "x64", "arm", "arm64", "linux", "macos", "windows". if it is a custom label for self-hosted runner, set list of labels in actionlint.yaml config file

(runner-label)

---

87-87: label "oracle-vm-16cpu-a10gpu-240gb" is unknown. available labels are "windows-latest", "windows-latest-8-cores", "windows-2025", "windows-2022", "windows-11-arm", "ubuntu-latest", "ubuntu-latest-4-cores", "ubuntu-latest-8-cores", "ubuntu-latest-16-cores", "ubuntu-24.04", "ubuntu-24.04-arm", "ubuntu-22.04", "ubuntu-22.04-arm", "macos-latest", "macos-latest-xl", "macos-latest-xlarge", "macos-latest-large", "macos-26-xlarge", "macos-26", "macos-15-intel", "macos-15-xlarge", "macos-15-large", "macos-15", "macos-14-xl", "macos-14-xlarge", "macos-14-large", "macos-14", "macos-13-xl", "macos-13-xlarge", "macos-13-large", "macos-13", "self-hosted", "x64", "arm", "arm64", "linux", "macos", "windows". if it is a custom label for self-hosted runner, set list of labels in actionlint.yaml config file

(runner-label)

🪛 Flake8 (7.3.0)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule_on_exit_codes.py

[error] 22-22: redefinition of unused 'Optional' from line 21

(F811)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_node_swap_status.py

[error] 22-22: redefinition of unused 'Optional' from line 21

(F811)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override.py

[error] 25-25: redefinition of unused 'Optional' from line 21

(F811)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_group_policy.py

[error] 24-24: redefinition of unused 'Optional' from line 21

(F811)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule.py

[error] 23-23: redefinition of unused 'Optional' from line 21

(F811)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_volcano_pod_group_policy_source.py

[error] 23-23: redefinition of unused 'Optional' from line 21

(F811)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_autoscaling_v2_hpa_scaling_rules.py

[error] 24-24: redefinition of unused 'Optional' from line 21

(F811)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_metadata_override.py

[error] 22-22: redefinition of unused 'Optional' from line 21

(F811)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_group_policy_source.py

[error] 24-24: redefinition of unused 'Optional' from line 21

(F811)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_file_key_selector.py

[error] 22-22: redefinition of unused 'Optional' from line 21

(F811)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_spec_override.py

[error] 28-28: redefinition of unused 'Optional' from line 21

(F811)

api/python_api/kubeflow_trainer_api/models/scheduling_v1beta1_network_topology_spec.py

[error] 22-22: redefinition of unused 'Optional' from line 21

(F811)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_certificate_projection.py

[error] 22-22: redefinition of unused 'Optional' from line 21

(F811)

🪛 LanguageTool

CONTRIBUTING.md

[uncategorized] ~114-~114: Possible missing comma found.
Context: ...res or enhancement for Kubeflow Trainer project we follow the [Kubeflow Enhancement Pro...

(AI_HYDRA_LEO_MISSING_COMMA)

SECURITY.md

[uncategorized] ~19-~19: If this is a compound adjective that modifies the following noun, use a hyphen.
Context: ... report vulnerabilities to the Kubeflow Open Source Community. All reports are thoroughly i...

(EN_COMPOUND_ADJECTIVE_INTERNAL)

---

[typographical] ~58-~58: Consider adding a comma here.
Context: ...tion Channels For the general questions please join the following resources: - Kubefl...

(PLEASE_COMMA)

README.md

[uncategorized] ~25-~25: If this is a compound adjective that modifies the following noun, use a hyphen.
Context: .../releases/tag/v2.0.0). - [2025/04] From High Performance Computing To AI Workloads on Kubernetes...

(EN_COMPOUND_ADJECTIVE_INTERNAL)

charts/kubeflow-trainer/README.md

[style] ~51-~51: Try moving the adverb to make the sentence clearer.
Context: ...ullnameOverride | string | "jobset" | String to fully override jobset release name. | | commonLabels | object | {} | Com...

(SPLIT_INFINITIVE)

🪛 markdownlint-cli2 (0.18.1)

ROADMAP.md

24-24: Bare URL used

(MD034, no-bare-urls)

CONTRIBUTING.md

136-136: Bare URL used

(MD034, no-bare-urls)

---

138-138: Bare URL used

(MD034, no-bare-urls)

🪛 Ruff (0.14.4)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule_on_exit_codes.py

12-12: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

---

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

22-22: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

---

28-28: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_resource_quota_spec.py

44-44: Avoid specifying long messages outside the exception class

(TRY003)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override_target_job.py

12-12: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

---

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

28-28: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_scoped_resource_selector_requirement.py

45-45: Avoid specifying long messages outside the exception class

(TRY003)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_node_swap_status.py

12-12: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

---

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

22-22: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

---

28-28: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_model_initializer.py

30-30: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_ml_policy.py

30-30: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_status.py

59-59: Avoid specifying long messages outside the exception class

(TRY003)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_extended_resource_request.py

12-12: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

---

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

28-28: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_override.py

12-12: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

---

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

25-25: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

---

31-31: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_group_policy.py

24-24: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

---

30-30: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule.py

12-12: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

---

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

23-23: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

---

29-29: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_volcano_pod_group_policy_source.py

12-12: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

---

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

23-23: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

---

29-29: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_autoscaling_v2_hpa_scaling_rules.py

24-24: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

---

30-30: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_extended_resource_claim_status.py

12-12: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

---

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

29-29: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_metadata_override.py

12-12: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

---

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

22-22: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

---

28-28: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_group_policy_source.py

24-24: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

---

30-30: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_file_key_selector.py

12-12: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

---

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

22-22: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

---

28-28: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_pod_template_spec_override.py

12-12: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

---

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

28-28: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

---

34-34: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/scheduling_v1beta1_network_topology_spec.py

12-12: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

---

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

22-22: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

---

28-28: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_lifecycle.py

42-42: Avoid specifying long messages outside the exception class

(TRY003)

api/python_api/kubeflow_trainer_api/models/jobset_v1alpha2_failure_policy_rule.py

28-28: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_env_from_source.py

30-30: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_pod_certificate_projection.py

12-12: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

---

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

22-22: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

---

28-28: Unused noqa directive (non-enabled: E501)

Remove unused noqa directive

(RUF100)

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

• GitHub Check: pre-commit

[coderabbitai]

⚠️ Potential issue | 🔴 Critical

Exclusion rule is inverted—KAL won't run on API folders.

The exclusion rule contradicts the stated intent. Line 66 says "KAL should only run on API folders," but path-except: "pkg/apis/*" at line 67 excludes kubeapilinter from paths matching pkg/apis/*—the opposite of the goal.

To fix, the exclusion should target paths outside the API folder. Apply this diff:

  issues:
    max-same-issues: 0
+  exclude-rules:
+    - path-except: "pkg/apis/*"
+      linters:
+        - kubeapilinter
-  exclusions:
-    generated: strict
-    rules:
-      ## KAL should only run on API folders.
-      - path-except: "pkg/apis/*"
-        linters:
-          - kubeapilinter

Alternatively, if path-except is not the intended syntax, use path: to explicitly match only API folders:

-  exclusions:
-    generated: strict
-    rules:
-      ## KAL should only run on API folders.
-      - path-except: "pkg/apis/*"
+  exclude-rules:
+    ## KAL should only run on API folders.
+    - path: "^(?!pkg/apis/)"
         linters:
           - kubeapilinter

Committable suggestion skipped: line range outside the PR's diff.

🤖 Prompt for AI Agents

.golangci-kal.yml around lines 63 to 69: the exclusion currently uses
path-except: "pkg/apis/*", which excludes API folders instead of limiting KAL to
them; change the rule to explicitly target only API folders by replacing
path-except with path: "pkg/apis/*" (or invert the pattern so excluded paths are
everything except pkg/apis/*), and keep the linters block the same so
kubeapilinter runs only on pkg/apis/*.

[coderabbitai]

⚠️ Potential issue | 🟡 Minor

Remove duplicate Optional import.

Optional is already imported on line 21. Line 24 should only import Set.

Apply this diff to fix the duplicate import:

-from typing import Optional, Set
+from typing import Set

Note: Since this file is auto-generated (line 11), consider whether this issue originates from the OpenAPI Generator templates and should be addressed there if it's a recurring pattern across generated files.

📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change

	from typing import Optional, Set
	from typing import Set

🧰 Tools

🪛 Flake8 (7.3.0)

[error] 24-24: redefinition of unused 'Optional' from line 21

(F811)

🪛 Ruff (0.14.4)

24-24: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

🤖 Prompt for AI Agents

In
api/python_api/kubeflow_trainer_api/models/io_k8s_api_autoscaling_v2_hpa_scaling_rules.py
around line 24, there is a duplicate import of Optional (it’s already imported
on line 21); remove Optional from the line and leave only Set so the import
reads only Set, and if this duplication appears across generated files consider
fixing the OpenAPI Generator template that emits duplicate imports.

[coderabbitai]

⚠️ Potential issue | 🟡 Minor

Documentation updates align with API stabilization; minor typo detected.

Lines 34–45 update field descriptions to remove feature-gate and beta references, clarifying default behaviors for interdependent fields (e.g., backoffLimit/backoffLimitPerIndex interaction). These changes are consistent with Kubernetes v2.1.0 feature stabilization and appropriate for an auto-generated model file.

However, Line 43 contains a typo: "the the only allowed value" should be "the only allowed value".

Please correct the typo on line 43:

-    pod_replacement_policy: Optional[StrictStr] = Field(default=None, description="podReplacementPolicy specifies when to create replacement Pods. Possible values are: - TerminatingOrFailed means that we recreate pods   when they are terminating (has a metadata.deletionTimestamp) or failed. - Failed means to wait until a previously created Pod is fully terminated (has phase   Failed or Succeeded) before creating a replacement Pod.  When using podFailurePolicy, Failed is the the only allowed value. TerminatingOrFailed and Failed are allowed values when podFailurePolicy is not in use.  Possible enum values:  - `\"Failed\"` means to wait until a previously created Pod is fully terminated (has phase Failed or Succeeded) before creating a replacement Pod.  - `\"TerminatingOrFailed\"` means that we recreate pods when they are terminating (has a metadata.deletionTimestamp) or failed.", alias="podReplacementPolicy")
+    pod_replacement_policy: Optional[StrictStr] = Field(default=None, description="podReplacementPolicy specifies when to create replacement Pods. Possible values are: - TerminatingOrFailed means that we recreate pods   when they are terminating (has a metadata.deletionTimestamp) or failed. - Failed means to wait until a previously created Pod is fully terminated (has phase   Failed or Succeeded) before creating a replacement Pod.  When using podFailurePolicy, Failed is the only allowed value. TerminatingOrFailed and Failed are allowed values when podFailurePolicy is not in use.  Possible enum values:  - `\"Failed\"` means to wait until a previously created Pod is fully terminated (has phase Failed or Succeeded) before creating a replacement Pod.  - `\"TerminatingOrFailed\"` means that we recreate pods when they are terminating (has a metadata.deletionTimestamp) or failed.", alias="podReplacementPolicy")

🤖 Prompt for AI Agents

In api/python_api/kubeflow_trainer_api/models/io_k8s_api_batch_v1_job_spec.py
around lines 34 to 45, fix the typo in the pod_replacement_policy Field
description where it currently reads "the the only allowed value" by removing
the duplicate "the" so it reads "the only allowed value"; make this single-word
fix inside the description string and leave all other text unchanged.

[coderabbitai]

⚠️ Potential issue | 🟡 Minor

Clean up import issues in the code generator.

The import section has several issues flagged by static analysis:

• Line 17: re is imported but never used
• Line 22: Optional is imported twice (duplicate from line 21)
• Lines 12, 17, 28: Unused noqa directives

Since this is auto-generated code (line 11 states "Do not edit the class manually"), these issues should be addressed in the OpenAPI code generator configuration or templates.

Apply this diff to manually fix the imports:

 from __future__ import annotations
 import pprint
-import re  # noqa: F401
 import json

 from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr
 from typing import Any, ClassVar, Dict, List, Optional
-from typing import Optional, Set
+from typing import Set
 from typing_extensions import Self

📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change

	from __future__ import annotations
	import pprint
	import re # noqa: F401
	import json
	from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr
	from typing import Any, ClassVar, Dict, List, Optional
	from typing import Optional, Set
	from typing_extensions import Self
	from __future__ import annotations
	import pprint
	import json
	from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr
	from typing import Any, ClassVar, Dict, List, Optional
	from typing import Set
	from typing_extensions import Self

🧰 Tools

🪛 Flake8 (7.3.0)

[error] 22-22: redefinition of unused 'Optional' from line 21

(F811)

🪛 Ruff (0.14.4)

17-17: Unused noqa directive (non-enabled: F401)

Remove unused noqa directive

(RUF100)

---

22-22: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

🤖 Prompt for AI Agents

In
api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule_on_exit_codes.py
around lines 15 to 23, the import block contains unused/duplicate imports and
unnecessary noqa directives; remove the unused "re" import, delete the duplicate
"Optional" import, and remove the redundant "# noqa: F401" and any other unused
noqa comments so only required imports remain, and update the OpenAPI generator
templates/config to prevent reintroducing these unused imports in generated
code.

[coderabbitai]

🛠️ Refactor suggestion | 🟠 Major

Address the TODO: Use Pydantic v2's model_dump_json().

The TODO comment suggests using .model_dump_json(), and since Pydantic v2.10.0 is already in use, this should be implemented. The current approach of calling json.dumps(self.to_dict()) is less efficient than the native Pydantic v2 method.

Apply this diff to use the Pydantic v2 method:

     def to_json(self) -> str:
         """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
+        return self.model_dump_json(by_alias=True, exclude_none=True)

Note: Using exclude_none=True to match the behavior of to_dict() (line 70).

🤖 Prompt for AI Agents

In
api/python_api/kubeflow_trainer_api/models/io_k8s_api_core_v1_container_restart_rule_on_exit_codes.py
around lines 44 to 47, replace the manual json.dumps(self.to_dict()) with
Pydantic v2's native JSON exporter: call self.model_dump_json(by_alias=True,
exclude_none=True) (include any additional flags like exclude_unset=True if you
want to preserve previous unset-exclusion behavior), so the method returns the
model_dump_json result instead of json.dumps(self.to_dict()).

[coderabbitai]

⚠️ Potential issue | 🟡 Minor

Fix the duplicate Optional import.

Line 23 redefines Optional, which was already imported from typing on line 21.

Apply this diff:

 from kubeflow_trainer_api.models.scheduling_v1beta1_network_topology_spec import SchedulingV1beta1NetworkTopologySpec
-from typing import Optional, Set
+from typing import Set
 from typing_extensions import Self

📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change

	from kubeflow_trainer_api.models.scheduling_v1beta1_network_topology_spec import SchedulingV1beta1NetworkTopologySpec
	from typing import Optional, Set
	from typing_extensions import Self
	from kubeflow_trainer_api.models.scheduling_v1beta1_network_topology_spec import SchedulingV1beta1NetworkTopologySpec
	from typing import Set
	from typing_extensions import Self

🧰 Tools

🪛 Flake8 (7.3.0)

[error] 23-23: redefinition of unused 'Optional' from line 21

(F811)

🪛 Ruff (0.14.4)

23-23: Redefinition of unused Optional from line 21

Remove definition: Optional

(F811)

🤖 Prompt for AI Agents

In
api/python_api/kubeflow_trainer_api/models/trainer_v1alpha1_volcano_pod_group_policy_source.py
around lines 22 to 24, the second import reintroduces Optional which is already
imported earlier; remove the duplicate by changing the line to only import the
remaining needed symbol(s) (e.g., replace "from typing import Optional, Set"
with "from typing import Set") or delete the redundant Optional so Optional is
imported only once.

[coderabbitai]

⚠️ Potential issue | 🟡 Minor

Add missing comma in sentence.

Line 114 reads: "...enhancement for Kubeflow Trainer project we follow the..." which needs a comma after "project".

Apply this diff:

-For any significant features or enhancement for Kubeflow Trainer project we follow the
+For any significant features or enhancement for Kubeflow Trainer project, we follow the

📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change

	For any significant features or enhancement for Kubeflow Trainer project we follow the
	For any significant features or enhancement for Kubeflow Trainer project, we follow the

🧰 Tools

🪛 LanguageTool

[uncategorized] ~114-~114: Possible missing comma found.
Context: ...res or enhancement for Kubeflow Trainer project we follow the [Kubeflow Enhancement Pro...

(AI_HYDRA_LEO_MISSING_COMMA)

🤖 Prompt for AI Agents

CONTRIBUTING.md around line 114: the sentence "For any significant features or
enhancement for Kubeflow Trainer project we follow the" is missing a comma after
"project"; insert a comma immediately after "project" so it reads "...Kubeflow
Trainer project, we follow the" to correct the punctuation.

[coderabbitai]

⚠️ Potential issue | 🟡 Minor

Convert bare URLs to markdown links.

Lines 136 and 138 contain bare URLs that should be formatted as markdown links for consistency and improved readability.

Apply this diff:

-The Trainer SDK can be found at https://github.com/kubeflow/sdk/tree/main/kubeflow/trainer.
+The Trainer SDK can be found at [https://github.com/kubeflow/sdk/tree/main/kubeflow/trainer](https://github.com/kubeflow/sdk/tree/main/kubeflow/trainer).

Committable suggestion skipped: line range outside the PR's diff.

🧰 Tools

🪛 markdownlint-cli2 (0.18.1)

136-136: Bare URL used

(MD034, no-bare-urls)

---

138-138: Bare URL used

(MD034, no-bare-urls)

🤖 Prompt for AI Agents

In CONTRIBUTING.md around lines 136 to 138, the two bare URLs should be
converted to markdown links; replace the plain URLs with descriptive
markdown-style links (for example, link the repo URL using text like "Kubeflow
SDK repo" and link the trainer path using text like "Trainer SDK") so both lines
read with [Link Text](URL) syntax for consistency and readability.

[coderabbitai]

⚠️ Potential issue | 🟡 Minor

Use hyphen for compound adjective.

"Kubeflow Open Source Community" should be "Kubeflow Open-Source Community" when used as a compound adjective before a noun.

Apply this diff:

-We're extremely grateful for security researchers and users that report vulnerabilities to the Kubeflow Open Source Community. All reports are thoroughly investigated by Kubeflow projects owners.
+We're extremely grateful for security researchers and users that report vulnerabilities to the Kubeflow Open-Source Community. All reports are thoroughly investigated by Kubeflow projects owners.

📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change

	Kubeflow Open Source Community. All reports are thoroughly investigated by Kubeflow projects owners.
	Kubeflow Open-Source Community. All reports are thoroughly investigated by Kubeflow projects owners.

🧰 Tools

🪛 LanguageTool

[uncategorized] ~19-~19: If this is a compound adjective that modifies the following noun, use a hyphen.
Context: ... report vulnerabilities to the Kubeflow Open Source Community. All reports are thoroughly i...

(EN_COMPOUND_ADJECTIVE_INTERNAL)

🤖 Prompt for AI Agents

In SECURITY.md around line 19, the phrase "Kubeflow Open Source Community" used
as a compound adjective should be hyphenated; update the text on line 19 to read
"Kubeflow Open-Source Community" (preserve capitalization and surrounding
punctuation) so the compound adjective is correct.

[coderabbitai]

⚠️ Potential issue | 🟡 Minor

Add comma for readability.

Line 58 needs a comma after "For the general questions".

Apply this diff:

-For the general questions please join the following resources:
+For general questions, please join the following resources:

📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change

	For the general questions please join the following resources:
	For general questions, please join the following resources:

🧰 Tools

🪛 LanguageTool

[typographical] ~58-~58: Consider adding a comma here.
Context: ...tion Channels For the general questions please join the following resources: - Kubefl...

(PLEASE_COMMA)

🤖 Prompt for AI Agents

In SECURITY.md around line 58, the sentence "For the general questions please
join the following resources:" is missing a comma; add a comma after "For the
general questions" so it reads "For the general questions, please join the
following resources:" to improve readability.

[efazal]

/lgtm