Conversation
Signed-off-by: JC Fillion-Robin <jcfr@nvidia.com>
Dependency Review✅ No vulnerabilities or license issues or OpenSSF Scorecard issues found.Snapshot WarningsEnsure that dependencies are being submitted on PR branches. Re-running this action after a short time may resolve the issue. See the documentation for more information and troubleshooting advice. Scanned FilesNone |
Signed-off-by: JC Fillion-Robin <jcfr@nvidia.com>
WalkthroughTwo new JSON files are created under the Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 2✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. 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. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@releases/4.1.0/artifacts.json`:
- Around line 11-17: The release artifacts reference the internal staging image
tag "nvcr.io/nvstaging/holoscan/holoscan:v4.1.0.1-cuda13" for keys like
"x64-workstation" and "sbsa" (and the CPU entry), which is not publicly
accessible; update those values to the public NGC image namespace used in prior
manifests (e.g., replace "nvcr.io/nvstaging/holoscan/holoscan:v4.1.0.1-cuda13"
with the public NGC equivalent such as
"nvcr.io/nvidia/clara-holoscan/holoscan:v4.1.0.1-cuda13" or
"nvcr.io/nvidia/holoscan/holoscan:v4.1.0.1-cuda13"/"nvidia/holoscan:..."
consistent with your public tagging), ensuring every occurrence (the
"x64-workstation", "sbsa", and CPU "x64-workstation" entries) is replaced so
public users can pull the images.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: c052c0d1-a7d7-46c2-a3f1-05573036be80
📒 Files selected for processing (2)
releases/4.1.0/artifacts-cu12.jsonreleases/4.1.0/artifacts.json
| "x64-workstation": "nvcr.io/nvstaging/holoscan/holoscan:v4.1.0.1-cuda13", | ||
| "sbsa": "nvcr.io/nvstaging/holoscan/holoscan:v4.1.0.1-cuda13" | ||
| }, | ||
| "igpu": {}, | ||
| "cpu": { | ||
| "x64-workstation": "nvcr.io/nvstaging/holoscan/holoscan:v4.1.0.1-cuda13" | ||
| } |
There was a problem hiding this comment.
🧩 Analysis chain
🌐 Web query:
Are the NGC image tags nvcr.io/nvstaging/holoscan/holoscan:v4.1.0.1-cuda13publicly pullable by non-internal users? Please provide official NVIDIA/NGC documentation aboutnvstaging visibility and access requirements.
💡 Result:
No, the NGC image tag nvcr.io/nvstaging/holoscan/holoscan:v4.1.0.1-cuda13 is not publicly pullable by non-internal users. nvstaging is an internal NVIDIA staging registry used for pre-release image staging as part of the NGC publishing workflow, prior to promotion to public repositories under nvcr.io/nvidia/.... Multiple NVIDIA GitHub repositories confirm this usage: changes to CI/CD pipelines stage images specifically to nvstaging for the "new NGC Publishing workflow" (e.g., nvidia-container-toolkit PR#1033, k8s-device-plugin PR#1230, gpu-operator PR#1401). No official NGC documentation lists nvstaging repositories as publicly accessible. Public Holoscan containers appear under nvidia/holoscan-* on catalog.ngc.nvidia.com (e.g., holoscan-pb24h2, holoscan-ltsb2), not nvstaging. NGC private registry docs describe org/team-specific access requiring API keys and explicit permissions, but nvstaging is not documented for external orgs—indicating internal-only access. Non-internal users lack permissions; attempts to pull would fail with authentication/authorization errors, as nvstaging is not discoverable or listed in public NGC catalog/UI.
Citations:
- 1: https://docs.nvidia.com/ngc/latest/ngc-private-registry-user-guide.html
- 2: Updated .release:staging to stage images in nvstaging NVIDIA/nvidia-container-toolkit#1033
- 3: https://docs.nvidia.com/ngc/latest/ngc-user-guide.html
- 4: https://docs.nvidia.com/ngc/latest/ngc-catalog-user-guide.html
- 5: https://docs.nvidia.com/dgx/ngc-registry-for-dgx-user-guide/index.html
- 6: Updated .release:staging to stage device-plugin images in nvstaging NVIDIA/k8s-device-plugin#1230
- 7: Updated .release:staging to stage images in nvstaging NVIDIA/gpu-operator#1401
Replace nvstaging image tags with public NGC equivalents in 4.1.0 release artifacts.
The 4.1.0 build images reference nvcr.io/nvstaging/holoscan/holoscan:v4.1.0.1-cuda13, which is NVIDIA's internal staging registry. Non-internal users cannot pull from nvstaging; attempts will fail with authentication errors. This blocks the 4.1.0 CLI release for all public users.
Replace nvstaging references with the public NGC nvidia/holoscan namespace tags to match prior releases in this manifest (e.g., nvcr.io/nvidia/clara-holoscan/holoscan:... or appropriate public v4.1.0 public tag).
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@releases/4.1.0/artifacts.json` around lines 11 - 17, The release artifacts
reference the internal staging image tag
"nvcr.io/nvstaging/holoscan/holoscan:v4.1.0.1-cuda13" for keys like
"x64-workstation" and "sbsa" (and the CPU entry), which is not publicly
accessible; update those values to the public NGC image namespace used in prior
manifests (e.g., replace "nvcr.io/nvstaging/holoscan/holoscan:v4.1.0.1-cuda13"
with the public NGC equivalent such as
"nvcr.io/nvidia/clara-holoscan/holoscan:v4.1.0.1-cuda13" or
"nvcr.io/nvidia/holoscan/holoscan:v4.1.0.1-cuda13"/"nvidia/holoscan:..."
consistent with your public tagging), ensuring every occurrence (the
"x64-workstation", "sbsa", and CPU "x64-workstation" entries) is replaced so
public users can pull the images.
1 participant
Summary by CodeRabbit