docs: refresh 0.0.56 release documentation#4618
Merged
Merged
Conversation
miyoungc
added
documentation
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Enterprise Run ID: 📒 Files selected for processing (3)
✅ Files skipped from review due to trivial changes (3)
📝 WalkthroughWalkthroughDocumentation-only PR updating NemoClaw v0.0.56 references: model router configuration, host immutability/security guidance, NemoClaw positioning, sandbox lifecycle and messaging, expanded CLI command docs, integration/policy entries, and release notes across skill and public MDX files. Changesv0.0.56 Documentation Updates
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
Contributor
|
🌿 Preview your docs: https://nvidia-preview-pr-4618.docs.buildwithfern.com/nemoclaw |
Contributor
E2E Advisor RecommendationRequired E2E: None Full advisor summaryE2E Recommendation AdvisorBase: Required E2E
Optional E2E
New E2E recommendations
|
Contributor
E2E Scenario Advisor RecommendationRequired scenario E2E: None Full scenario advisor summaryE2E Scenario AdvisorBase: Required scenario E2E
Optional scenario E2E
Relevant changed files
|
Contributor
PR Review AdvisorFindings: 0 needs attention, 4 worth checking, 0 nice ideas Review findings🛠️ Needs attention
🔎 Worth checking
🌱 Nice ideas
Since last review detailsCurrent findings:
This is an automated advisory review. A human maintainer must make the final merge decision. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 3
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
.agents/skills/nemoclaw-user-configure-inference/references/inference-options.md (2)
77-143:⚠️ Potential issue | 🔴 Critical | 🏗️ Heavy liftDo not edit autogenerated user skill files directly.
This file is under
.agents/skills/nemoclaw-user-*/*.md, which is designated as autogenerated content and should be updated via its generator/source workflow instead of manual edits.As per coding guidelines, “Autogenerated user skills under
.agents/skills/nemoclaw-user-*/*.mdmust never be edited directly”.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In @.agents/skills/nemoclaw-user-configure-inference/references/inference-options.md around lines 77 - 143, The markdown under the autogenerated user-skill (containing the routing, models, and tolerance examples and the NEMOCLAW_PROVIDER hints) was edited directly but must not be changed in-place; revert this file to the generated state and instead update the generator/source that outputs this content (the template or generator that emits the routing, models, tolerance, Host Python requirement, and NEMOCLAW_MODEL_ROUTER_PYTHON sections), then re-run the generation pipeline so changes appear in the file; ensure the generator modifies the routing block (routing, checkpoint, tolerance, encoder) and the models list (name, litellm_model, cost_per_m_input_tokens, api_base) and commit the regenerated artifact rather than manual edits.
119-121:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winUse copyable shell code blocks instead of
consolewith prompts.These command examples are copyable CLI commands, so they should use a shell language tag (for example,
bash) and omit$prompt markers.As per coding guidelines, “Copyable CLI code blocks must use language-specific tags such as
bash,sh, orpowershell, and must not include prompt markers such as$.”Also applies to: 136-138
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In @.agents/skills/nemoclaw-user-configure-inference/references/inference-options.md around lines 119 - 121, Replace the fenced code blocks that currently use the "console" language and include a leading "$" prompt with copyable shell blocks: change the language tag from ```console to ```bash (or ```sh) and remove the "$ " prompt marker so the snippet reads like a plain command (e.g., NEMOCLAW_PROVIDER=routed NVIDIA_API_KEY=<your-key> nemoclaw onboard --non-interactive). Apply the same change to the other similar example containing the NEMOCLAW_PROVIDER ... nemoclaw onboard command referenced in the file.
🧹 Nitpick comments (1)
docs/about/release-notes.mdx (1)
18-24: ⚡ Quick winSplit each bullet to one sentence per source line.
Several bullets here place multiple sentences on the same line, which breaks the docs source readability rule for sentence-per-line formatting.
As per coding guidelines, "One sentence per line in source (makes diffs readable)."
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs/about/release-notes.mdx` around lines 18 - 24, The release-notes bullets contain multiple sentences per line which violates the one-sentence-per-line docs rule; edit each bulleted item so every sentence is on its own source line (e.g., split the "Public installer..." bullet, the "nemoclaw <name> status..." bullet, and the other bullets such that each sentence begins on a new line), preserving existing wording and punctuation and leaving markdown list markers and links intact; ensure no bullet line contains more than one sentence and run the docs linter to verify compliance.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In
@.agents/skills/nemoclaw-user-manage-policy/references/integration-policy-examples.md:
- Around line 202-213: This change edits an autogenerated user-skill markdown
(the content matching the rule "Autogenerated user skills under
`.agents/skills/nemoclaw-user-*/*.md` must never be edited directly"); revert
the manual edit in that markdown and instead make the update in the source that
generates it (or update the generation pipeline/template) so the file is
regenerated; ensure the change is applied to the generator input (or pipeline
config) that produces integration-policy-examples.md and run the generation job
locally/CI to produce the updated autogenerated file; if needed, add or update a
CI/lint check to reject direct edits to autogenerated
`.agents/skills/nemoclaw-user-*/*.md` files.
In @.agents/skills/nemoclaw-user-overview/references/overview.md:
- Line 8: Replace the unhyphenated compound adjective "on prem" in the sentence
that reads "This enables self-evolving agents to run more safely in clouds, on
prem, RTX PCs, and DGX Spark." with the correctly hyphenated form "on-prem" so
the sentence uses "on-prem" as the compound modifier.
In @.agents/skills/nemoclaw-user-reference/references/commands.md:
- Line 78: Revert any direct edits to the autogenerated
.agents/skills/nemoclaw-user-*/*.md file and instead update the upstream
documentation source/template that generates the onboarding command text (the
source that emits the "Use `--fresh` to ignore any saved onboarding session..."
line for the nemoclaw onboard command), then run the skill
generator/regeneration process to produce a new artifact so the change lands in
the generated commands.md rather than editing the generated file directly.
---
Outside diff comments:
In
@.agents/skills/nemoclaw-user-configure-inference/references/inference-options.md:
- Around line 77-143: The markdown under the autogenerated user-skill
(containing the routing, models, and tolerance examples and the
NEMOCLAW_PROVIDER hints) was edited directly but must not be changed in-place;
revert this file to the generated state and instead update the generator/source
that outputs this content (the template or generator that emits the routing,
models, tolerance, Host Python requirement, and NEMOCLAW_MODEL_ROUTER_PYTHON
sections), then re-run the generation pipeline so changes appear in the file;
ensure the generator modifies the routing block (routing, checkpoint, tolerance,
encoder) and the models list (name, litellm_model, cost_per_m_input_tokens,
api_base) and commit the regenerated artifact rather than manual edits.
- Around line 119-121: Replace the fenced code blocks that currently use the
"console" language and include a leading "$" prompt with copyable shell blocks:
change the language tag from ```console to ```bash (or ```sh) and remove the "$
" prompt marker so the snippet reads like a plain command (e.g.,
NEMOCLAW_PROVIDER=routed NVIDIA_API_KEY=<your-key> nemoclaw onboard
--non-interactive). Apply the same change to the other similar example
containing the NEMOCLAW_PROVIDER ... nemoclaw onboard command referenced in the
file.
---
Nitpick comments:
In `@docs/about/release-notes.mdx`:
- Around line 18-24: The release-notes bullets contain multiple sentences per
line which violates the one-sentence-per-line docs rule; edit each bulleted item
so every sentence is on its own source line (e.g., split the "Public
installer..." bullet, the "nemoclaw <name> status..." bullet, and the other
bullets such that each sentence begins on a new line), preserving existing
wording and punctuation and leaving markdown list markers and links intact;
ensure no bullet line contains more than one sentence and run the docs linter to
verify compliance.
🪄 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: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 98c71f94-2a48-4f58-8dea-bd8a0f977b8f
📒 Files selected for processing (19)
.agents/skills/nemoclaw-user-configure-inference/references/inference-options.md.agents/skills/nemoclaw-user-configure-security/references/best-practices.md.agents/skills/nemoclaw-user-get-started/SKILL.md.agents/skills/nemoclaw-user-get-started/references/quickstart-hermes.md.agents/skills/nemoclaw-user-manage-policy/references/integration-policy-examples.md.agents/skills/nemoclaw-user-manage-sandboxes/SKILL.md.agents/skills/nemoclaw-user-manage-sandboxes/evals/evals.json.agents/skills/nemoclaw-user-manage-sandboxes/references/messaging-channels.md.agents/skills/nemoclaw-user-overview/SKILL.md.agents/skills/nemoclaw-user-overview/references/how-it-works.md.agents/skills/nemoclaw-user-overview/references/overview.md.agents/skills/nemoclaw-user-overview/references/release-notes.md.agents/skills/nemoclaw-user-reference/references/commands.md.agents/skills/nemoclaw-user-reference/references/troubleshooting.mddocs/about/release-notes.mdxdocs/manage-sandboxes/messaging-channels.mdxdocs/network-policy/integration-policy-examples.mdxdocs/reference/commands.mdxdocs/security/best-practices.mdx
💤 Files with no reviewable changes (1)
- .agents/skills/nemoclaw-user-get-started/references/quickstart-hermes.md
cv
approved these changes
Jun 1, 2026
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
2 participants
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
uvin the PyPI preset, compact WhatsApp pairing guidance, andnemoclaw inference setcommand boundaries.nemoclaw-user-*skills and removes skipped experimental command terms from generated skill surfaces.Source summary
docs/manage-sandboxes/lifecycle.mdx,docs/reference/commands.mdx,docs/about/release-notes.mdx: Documents that public installs andnemoclaw updatefollow the maintainedlkgtag by default.docs/about/release-notes.mdx: Notes that non-interactive Linux installs can reactivate Docker group membership and continue in one installer run whensg dockeris available.docs/reference/commands.mdx,docs/about/release-notes.mdx: Captures live sandbox agent-version probing for status, connect, and upgrade checks.docs/inference/use-local-inference.mdx,docs/about/release-notes.mdx: Captures the GPU Docker-driver host-network local-inference reachability gate.docs/manage-sandboxes/messaging-channels.mdx,docs/reference/commands.mdx,docs/about/release-notes.mdx: Documents compact WhatsApp QR pairing guidance and gateway/session diagnostics.docs/manage-sandboxes/messaging-channels.mdx,docs/reference/commands.mdx,docs/about/release-notes.mdx: Reflects Slack credential validation before enabling the channel.docs/manage-sandboxes/messaging-channels.mdx,docs/reference/troubleshooting.mdx,docs/about/release-notes.mdx: Keeps Telegram allowlist alias guidance in the generated user skills and release notes.docs/reference/commands.mdx,docs/about/release-notes.mdx: Includes the newnemoclaw <name> skill remove <skill>command in command docs and release notes.inference setto openshell #4566 ->docs/reference/commands.mdx,docs/about/release-notes.mdx: Documents thenemoclaw inference setredirect boundary when--provideror--modelis missing.docs/reference/commands.mdx,docs/about/release-notes.mdx: Captures per-sandbox status JSON support.docs/reference/commands.mdx,docs/about/release-notes.mdx: Captures debug command sandbox-name validation and safer tarball writing.docs/network-policy/integration-policy-examples.mdx,docs/about/release-notes.mdx: Documents that thepypipreset allows/usr/local/bin/uv.docs/network-policy/integration-policy-examples.mdx,docs/about/release-notes.mdx: Captures observable Jira preset validation guidance.docs/manage-sandboxes/lifecycle.mdx,docs/reference/commands.mdx,docs/about/release-notes.mdx: Documents user-data preservation defaults for uninstall.docs/reference/commands.mdx,docs/about/release-notes.mdx: Captures CPU-only sandbox intent preservation across rebuilds.docs/reference/commands.mdx,docs/about/release-notes.mdx: Captures safer snapshot restore behavior around existing destinations.docs/.docs-skip: Removed skipped experimental command terms from source docs and generated skill evals instead of documenting those features.Verification
python3 scripts/docs-to-skills.py docs/ .agents/skills/ --prefix nemoclaw-user --doc-platform fern-mdxnpm run docs(passes; Fern reports the pre-existing light-mode accent contrast warning)rg "permissive mode|shields down|shields up|shields status|config rotate-token|rotate-token" .agents/skills(no matches)npm run build:cli(run to refresh local CLI artifacts for the pre-push TypeScript hook)NEMOCLAW_* env-var documentation gate,Verify docs-to-skills output,markdownlint-cli2,gitleaks, andTest (skills YAML).Summary by CodeRabbit
Documentation
New Features
channels statuswith JSON),skill removedocs; Hermes unflagged as experimental; DGX Spark quickstart sandbox-name note.