Analyze saved NemoClaw CI timings to rank consistently slow command-line tests and compare base-image publication with reuse. Read-only analyzers report execution times, runner queues, and sample coverage as bounded JSON output.
Analyze retained NemoClaw CI timings for slow CLI tests, runner queues, or base-image publication.
Review the instructions the agent will receive before you install.
Run one read-only standalone analyzer from a NemoClaw checkout. Both commands use authenticated gh reads and print bounded JSON to stdout. They perform no GitHub writes.
Use retained cli-vitest-results artifacts to rank consistently slow tests and files. The CI workflow retains this historical input for 14 days:
node --no-warnings \
.agents/skills/nemoclaw-maintainer-analyze-ci-performance/scripts/analyze-recent-cli-timings.mts \
--workdir "$PWD"
Defaults preserve the former timing tool contract: repository NVIDIA/NemoClaw, 10 reports, 15 results, a 0.7 minimum sample ratio, and artifact name cli-vitest-results. Optional flags are --repo, --limit, --top, --min-sample-ratio, and --artifact-name.
The analyzer requires at least two usable retained reports. It rejects compressed artifacts above 25,000,000 bytes and bounds ZIP entries, expanded content, listings, and report content. It requires Bash, GNU dd and find, Info-ZIP zipinfo and unzip, awk, base64, mktemp, stat, and wc on Linux.
Compare main-push E2E runs that publish a same-commit base image with runs that reuse a prior publication:
node --no-warnings \
.agents/skills/nemoclaw-maintainer-analyze-ci-performance/scripts/analyze-base-image-publication-timings.mts \
--workdir "$PWD"
Defaults preserve the former timing tool contract: repository NVIDIA/NemoClaw, 300 E2E runs, 500 base-image runs, and up to 150 systematic samples per stratum. Optional flags are --repo, --e2e-limit, --base-limit, and --max-per-stratum.
Report the population window and stratum sizes before statistics. Treat atLeast30SuccessfulJobs: false as insufficient evidence for stable inference. Job execution, verifier, workflow completion, runner queue, and matrix-boundary measurements use successful publication jobs only.
Do not combine this workflow with pull request value-stream analysis. Load nemoclaw-maintainer-analyze-pr-value-stream for a complete PR lifetime trace. Stop on GitHub authentication or authorization failure and follow the repository GitHub access hard stop.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Publish or update a NemoClaw pull request and track automated checks and reviews through completion. It preserves the requested scope, coordinates repairs for valid findings, and reports the latest commit’s results and remaining blockers.
Implement an accepted NemoClaw issue or repair a classified pull request finding. Keep changes within the agreed scope, run focused checks for affected behavior, and review the final changes before handing evidence to an authorized publication workflow.
Prepare a local NemoClaw development environment, repair setup problems, or check readiness. It also handles explicitly requested command-line access, runtime onboarding, and launching the coding agent pinned by the project.
Turn a named NemoClaw issue into an implementation plan with clear ownership, scope, completion criteria, and validation evidence. For larger changes, define independently useful steps, their dependencies, and delivery order.
Audit and upgrade NemoClaw dependencies, including Hermes and base images. Trace upstream changes to affected code, implement required migrations, and verify tests, distributed artifacts, and the versions actually selected for use.
Update NemoClaw documentation after merged changes or audit it for outdated guidance. Verify current behavior against source and tests, edit the pages responsible for that guidance, and check affected links and generated variants.