Skip to content

feat: add create-issue skill - #4338

Merged
ko3n1g merged 5 commits into
NVIDIA:mainfrom
ko3n1g:ko3n1g/feat/triage-issue
Apr 16, 2026
Merged

feat: add create-issue skill#4338
ko3n1g merged 5 commits into
NVIDIA:mainfrom
ko3n1g:ko3n1g/feat/triage-issue

Conversation

@ko3n1g

@ko3n1g ko3n1g commented Apr 16, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

Summary

  • Adds `skills/create-issue/SKILL.md`, a Claude Code skill that investigates a failing GitHub Actions run or job and files a structured bug issue against `NVIDIA/Megatron-LM`.
  • Given a run or job URL, the skill:
    1. Fetches failure logs and extracts failing test node IDs + error snippet
    2. Resolves the triggering PR from the run's head branch (`pull-request/`)
    3. Finds the GitHub login of whoever last touched the failing test file (via Commits API, using the PR's base branch) and assigns the issue to them
    4. Checks for duplicate open issues before creating a new one
    5. Files a structured `bug` issue with the PR link, run/job links, error snippet, and assignee

Example usage

```
/create-issue https://github.com/NVIDIA/Megatron-LM/actions/runs/24510353170/job/71641206557
```

This would produce an issue like:

🐛 CI failure: tests/unit_tests/transformer/moe/test_paged_stashing.py::TestPagedStashing::test_forward_backward_4_layers

CI test `...::test_forward_backward_4_layers` failed in job `tests/unit_tests/transformer/moe/**/*.py - latest`.
Tag the @mcore-oncall to get oncall's attention.

Field Value
PR #4332: ...
Run 24510353170
Job 71641206557

Error
```
AssertionError: Fused GroupedMLP is not supported for this configuration.
megatron/core/transformer/moe/experts.py:730: AssertionError
```

Assigned to the author of `test_paged_stashing.py` on the PR's base branch.

@ko3n1g @claude
feat: add triage-issue skill
2abade6 
Adds a Claude Code skill that investigates a failing GitHub Actions run
or job URL, extracts the root cause from the logs, checks for duplicate
open issues, and files a structured bug report against NVIDIA/Megatron-LM.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Signed-off-by: oliver könig <okoenig@nvidia.com>
@ko3n1g

ko3n1g commented Apr 16, 2026

Copy link
Copy Markdown
Contributor Author

/ok to test

@svcnvidia-nemo-ci
svcnvidia-nemo-ci marked this pull request as draft April 16, 2026 13:50
@github-actions

github-actions Bot commented Apr 16, 2026

Copy link
Copy Markdown
Contributor

This PR has been automatically converted to draft because all PRs must start as drafts.

When you are ready for review, click Ready for Review to begin the review process. This will:

  1. Add the oncall reviewer (optional reviewer)
  2. Add required review teams based on your changes

See the contribution guide for more details.

@copy-pr-bot

copy-pr-bot Bot commented Apr 16, 2026

Copy link
Copy Markdown

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.

@svcnvidia-nemo-ci svcnvidia-nemo-ci added this to the Core 0.16 milestone Apr 16, 2026
ko3n1g and others added 2 commits April 16, 2026 13:54
@ko3n1g @claude
feat(triage-issue): link triggering PR and assign test author
1c44376 
- Step 4 now resolves the triggering PR from the run's head branch
  (pull-request/<number>) and looks up the GitHub login of whoever last
  touched the failing test file via git log / Commits API.
- Step 7 passes --assignee and adds a PR row to the failing-run table.
- Guidelines updated to make both behaviours explicit.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Signed-off-by: oliver könig <okoenig@nvidia.com>
@ko3n1g @claude
fix(triage-issue): look up test author against PR base branch, not main
b4828a1 
The failing test file may not exist on main (e.g. introduced on a dev
branch). Step 4 now resolves the PR's baseRefName first and passes it
as ?sha= to the Commits API, with a fallback to the PR's own commits
when the file was introduced by the PR itself.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Signed-off-by: oliver könig <okoenig@nvidia.com>
@ko3n1g
ko3n1g marked this pull request as ready for review April 16, 2026 14:05
@svcnvidia-nemo-ci
svcnvidia-nemo-ci requested a review from a team April 16, 2026 14:05
@svcnvidia-nemo-ci svcnvidia-nemo-ci added the docs-only documentation only (docs or docstrings) label Apr 16, 2026
@ko3n1g
ko3n1g enabled auto-merge April 16, 2026 14:06
@ko3n1g @claude
refactor: rename triage-issue skill to create-issue
cb3c317 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Signed-off-by: oliver könig <okoenig@nvidia.com>
@ko3n1g ko3n1g changed the title feat: add triage-issue skill feat: add create-issue skill Apr 16, 2026
@ko3n1g
ko3n1g added this pull request to the merge queue Apr 16, 2026
@svcnvidia-nemo-ci

svcnvidia-nemo-ci commented Apr 16, 2026

Copy link
Copy Markdown
Contributor

🔄 Merge queue validation started!

You can track the progress here: https://github.com/NVIDIA/Megatron-LM/actions/runs/24521701340

@ko3n1g
ko3n1g removed this pull request from the merge queue due to a manual request Apr 16, 2026
@ko3n1g
ko3n1g added this pull request to the merge queue Apr 16, 2026
@svcnvidia-nemo-ci

svcnvidia-nemo-ci commented Apr 16, 2026

Copy link
Copy Markdown
Contributor

🔄 Merge queue validation started!

You can track the progress here: https://github.com/NVIDIA/Megatron-LM/actions/runs/24523257294

@github-merge-queue
github-merge-queue Bot removed this pull request from the merge queue due to failed status checks Apr 16, 2026
@ko3n1g
ko3n1g added this pull request to the merge queue Apr 16, 2026
@svcnvidia-nemo-ci

svcnvidia-nemo-ci commented Apr 16, 2026

Copy link
Copy Markdown
Contributor

🔄 Merge queue validation started!

You can track the progress here: https://github.com/NVIDIA/Megatron-LM/actions/runs/24531054570

@ko3n1g
ko3n1g removed this pull request from the merge queue due to a manual request Apr 16, 2026
@ko3n1g
ko3n1g merged commit efbe7a1 into NVIDIA:main Apr 16, 2026
9 checks passed
yangbofun pushed a commit to xlm-research/Megatron-LM that referenced this pull request May 22, 2026
@ko3n1g @claude
feat: add create-issue skill (NVIDIA#4338)
b6baead 
Signed-off-by: oliver könig <okoenig@nvidia.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
yhgalaxy pushed a commit to yhgalaxy/Megatron-LM that referenced this pull request Jun 17, 2026
@ko3n1g @claude @yhgalaxy
feat: add create-issue skill (NVIDIA#4338)
dfc153e 
Signed-off-by: oliver könig <okoenig@nvidia.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Signed-off-by: yhgalaxy <yhgalaxy@outlook.com>
jon-barker pushed a commit to jon-barker/Megatron-LM that referenced this pull request Jul 10, 2026
@ko3n1g @claude Jon Barker
feat: add create-issue skill (NVIDIA#4338)
e16e3f3 
Signed-off-by: oliver könig <okoenig@nvidia.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Signed-off-by: Jon Barker <jbarker@aws-cmh-slurm-1-vscode-02.cm.cluster>
terminator123 pushed a commit to 021ai/Megatron-LM that referenced this pull request Aug 3, 2026
@ko3n1g @claude @terminator123
feat: add create-issue skill (NVIDIA#4338)
482ab6d 
Signed-off-by: oliver könig <okoenig@nvidia.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@thomasdhc thomasdhc thomasdhc approved these changes

Assignees

No one assigned

Labels

docs-only documentation only (docs or docstrings)

Projects

None yet

Milestone

Core 0.16

Development

Successfully merging this pull request may close these issues.

3 participants

@ko3n1g @svcnvidia-nemo-ci @thomasdhc