[None][feat] Add Auto-Deploy dashboard failures analysis skill#12033
[None][feat] Add Auto-Deploy dashboard failures analysis skill#12033lucaslie merged 2 commits intoNVIDIA:mainfrom
Conversation
Signed-off-by: Tal Cherckez <127761168+tcherckez-nvidia@users.noreply.github.com>
📝 WalkthroughWalkthroughA new skill specification is introduced that defines a workflow for analyzing AutoDeploy pipeline failures, categorizing them into root-cause buckets, and creating targeted PRs or issues per bucket. The specification includes multi-phase control flow (0-4), pipeline resolution rules, bucket validation procedures, and multiple output format options. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~15 minutes 🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
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 @.claude/skills/ad-pipeline-failure-pr/SKILL.md:
- Line 8: The document uses the misspelled environment variable GITLAN_TOKEN
(e.g., in the SKILL description text and any references) which breaks GitLab
auth; update every occurrence of GITLAN_TOKEN to the correct GITLAB_TOKEN so all
mentions (including the initial auth requirement and any later examples or
instructions) consistently reference GITLAB_TOKEN.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: ead35b5c-83a8-41ca-9271-9113c5e5c687
📒 Files selected for processing (1)
.claude/skills/ad-pipeline-failure-pr/SKILL.md
|
/bot skip --comment "doc changes only" |
|
PR_Github #38300 [ skip ] triggered by Bot. Commit: |
|
PR_Github #38300 [ skip ] completed with state |
Summary by CodeRabbit
Note: This release includes internal documentation updates with no direct user-facing changes.
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
To see a list of available CI bot commands, please comment
/bot help.