feat(workflow-status): route nightly job log analysis through NVIDIA Inference Hub - #401
Open
Avinash-Raj wants to merge 4 commits into
Open
feat(workflow-status): route nightly job log analysis through NVIDIA Inference Hub#401Avinash-Raj wants to merge 4 commits into
Avinash-Raj wants to merge 4 commits into
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
workflow_status.pyClaude failure analysis through NVIDIA Inference Hub (https://inference-api.nvidia.com) instead of a claude.ai login.azure/anthropic/claude-opus-5. Auth isANTHROPIC_AUTH_TOKEN(nightly still usessecrets.ANTHROPIC_API_KEYas that bearer token), withNVIDIA_API_KEY/NGC_API_KEYas fallbacks.ANTHROPIC_AUTH_TOKEN,ANTHROPIC_BASE_URL,CLAUDE_MODEL).--bareis used so GitHub runners skip OAuth.Test plan
python3 scripts/workflow_status/workflow_status.py --helpshows hub defaults and--anthropic-base-url/--claude-model.NVIDIA_API_KEYorANTHROPIC_AUTH_TOKENset, run against a known failed nightly--run-idand confirm cause/fix text is produced (not the Claude CLI auth error).--model azure/anthropic/claude-opus-5andANTHROPIC_BASE_URL=https://inference-api.nvidia.com.workflow_dispatchnightly-status-report.ymlafter repo vars/secrets are in place; check Slack payload / artifacts. (Here is the result of Nightly status report job which was triggered manually from this PR's branch.)