docs: refresh documentation and user-skills for 0.0.34#3003
Merged
Conversation
Co-authored-by: Cursor <cursoragent@cursor.com>
Contributor
📝 WalkthroughWalkthroughDocumentation-only changes: clarified Ollama/WSL/Windows local-inference behavior and proxy, standardized sandbox-name validation and default, documented scripted-installer env vars and CLI behavior (status/logs/rebuild), replaced workspace skill with a manage-sandboxes skill, added reference guides, and bumped docs version to 0.0.34. ChangesDocs: Local Inference, Sandbox Naming, CLI References, and Day‑Two Skills
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested labels
Poem
🚥 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)
Tip 💬 Introducing Slack Agent: The best way for teams to turn conversations into code.Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.
Built for teams:
One agent for your entire SDLC. Right inside Slack. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (5)
docs/get-started/windows-preparation.md (1)
106-106: 💤 Low valueConsider using consistent terminology for the onboarding wizard.
Other documentation files refer to the "
onboardwizard" with inline code formatting.
For consistency, consider:-If Ollama is installed but not already running in WSL, the onboarding process starts it for you. +If Ollama is installed but not already running in WSL, the `onboard` wizard starts it for you.As per coding guidelines, CLI commands and component names should use inline
codeformatting, and consistent terminology improves clarity across documentation.🤖 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/get-started/windows-preparation.md` at line 106, The sentence uses plain text "onboarding process" but other docs refer to the `onboard` wizard with inline code formatting; update this sentence to use the same terminology and inline code formatting (e.g., replace "the onboarding process starts it for you" with "the `onboard` wizard starts it for you") to keep CLI/component names consistent across docs.docs/get-started/quickstart.md (2)
188-188: ⚡ Quick winUse one sentence per line in source.
Line 188 contains two sentences.
Split them for better diff readability.-Routes inference to a local Ollama instance. Depending on your platform, the wizard can use an existing daemon, start an installed daemon, or offer an install action. +Routes inference to a local Ollama instance. +Depending on your platform, the wizard can use an existing daemon, start an installed daemon, or offer an install action.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/get-started/quickstart.md` at line 188, The sentence pair "Routes inference to a local Ollama instance. Depending on your platform, the wizard can use an existing daemon, start an installed daemon, or offer an install action." should be split into two separate lines in the source so each sentence is on its own line; edit the paragraph in quickstart.md to place "Routes inference to a local Ollama instance." on its own line and the following sentence "Depending on your platform, the wizard can use an existing daemon, start an installed daemon, or offer an install action." on the next line to follow the one-sentence-per-line guideline.
190-190: ⚡ Quick winUse one sentence per line in source.
Line 190 contains two sentences.
Split them for better diff readability.-No API key is required. On non-WSL hosts, NemoClaw generates a token and starts an authenticated proxy so containers can reach Ollama without exposing the daemon directly to your network. +No API key is required. +On non-WSL hosts, NemoClaw generates a token and starts an authenticated proxy so containers can reach Ollama without exposing the daemon directly to your network.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/get-started/quickstart.md` at line 190, The sentence "No API key is required. On non-WSL hosts, NemoClaw generates a token and starts an authenticated proxy so containers can reach Ollama without exposing the daemon directly to your network." should be split into two lines so each sentence is on its own line in docs/get-started/quickstart.md; edit the paragraph containing that sentence (search for the exact text "No API key is required.") and place a newline after the first sentence so "No API key is required." is one line and the remaining sentence starts the next line.docs/inference/use-local-inference.md (2)
83-83: ⚡ Quick winUse inline code formatting for CLI commands.
The term
onboardshould use inline code formatting since it refers to the CLI wizard command.-For non-WSL Ollama setups, the onboard wizard manages the proxy automatically: +For non-WSL Ollama setups, the `onboard` wizard manages the proxy automatically:As per coding guidelines, CLI commands, file paths, flags, parameter names, and values must use inline
codeformatting.🤖 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/inference/use-local-inference.md` at line 83, Replace the plain text "onboard wizard" with inline code formatting for the CLI command by changing it to "`onboard` wizard" in the sentence "For non-WSL Ollama setups, the onboard wizard manages the proxy automatically:" and ensure any other CLI commands, flags, file paths or parameter names in that sentence use inline `code` formatting to follow the documentation style guide.
38-38: ⚡ Quick winUse inline code formatting for CLI commands and component names.
The term
onboardshould use inline code formatting since it refers to the CLI wizard command.-- A local model server running, or an Ollama setup that the NemoClaw onboard wizard can use, start, or install. +- A local model server running, or an Ollama setup that the NemoClaw `onboard` wizard can use, start, or install.As per coding guidelines, CLI commands, file paths, flags, parameter names, and values must use inline
codeformatting.🤖 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/inference/use-local-inference.md` at line 38, Update the sentence "A local model server running, or an Ollama setup that the NemoClaw onboard wizard can use, start, or install." to use inline code formatting for CLI commands and component names: wrap `onboard` (the CLI wizard command) in backticks, and also wrap component/CLI references like `Ollama` and `NemoClaw` or any CLI flags/paths mentioned in code style; ensure the sentence reads with those names and commands formatted as inline `code`.
🤖 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.
Nitpick comments:
In `@docs/get-started/quickstart.md`:
- Line 188: The sentence pair "Routes inference to a local Ollama instance.
Depending on your platform, the wizard can use an existing daemon, start an
installed daemon, or offer an install action." should be split into two separate
lines in the source so each sentence is on its own line; edit the paragraph in
quickstart.md to place "Routes inference to a local Ollama instance." on its own
line and the following sentence "Depending on your platform, the wizard can use
an existing daemon, start an installed daemon, or offer an install action." on
the next line to follow the one-sentence-per-line guideline.
- Line 190: The sentence "No API key is required. On non-WSL hosts, NemoClaw
generates a token and starts an authenticated proxy so containers can reach
Ollama without exposing the daemon directly to your network." should be split
into two lines so each sentence is on its own line in
docs/get-started/quickstart.md; edit the paragraph containing that sentence
(search for the exact text "No API key is required.") and place a newline after
the first sentence so "No API key is required." is one line and the remaining
sentence starts the next line.
In `@docs/get-started/windows-preparation.md`:
- Line 106: The sentence uses plain text "onboarding process" but other docs
refer to the `onboard` wizard with inline code formatting; update this sentence
to use the same terminology and inline code formatting (e.g., replace "the
onboarding process starts it for you" with "the `onboard` wizard starts it for
you") to keep CLI/component names consistent across docs.
In `@docs/inference/use-local-inference.md`:
- Line 83: Replace the plain text "onboard wizard" with inline code formatting
for the CLI command by changing it to "`onboard` wizard" in the sentence "For
non-WSL Ollama setups, the onboard wizard manages the proxy automatically:" and
ensure any other CLI commands, flags, file paths or parameter names in that
sentence use inline `code` formatting to follow the documentation style guide.
- Line 38: Update the sentence "A local model server running, or an Ollama setup
that the NemoClaw onboard wizard can use, start, or install." to use inline code
formatting for CLI commands and component names: wrap `onboard` (the CLI wizard
command) in backticks, and also wrap component/CLI references like `Ollama` and
`NemoClaw` or any CLI flags/paths mentioned in code style; ensure the sentence
reads with those names and commands formatted as inline `code`.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 5daa80ac-914c-45d5-9246-24253c793428
📒 Files selected for processing (6)
docs/deployment/deploy-to-remote-gpu.mddocs/get-started/quickstart.mddocs/get-started/windows-preparation.mddocs/inference/use-local-inference.mddocs/reference/commands.mddocs/reference/troubleshooting.md
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
cv
approved these changes
May 4, 2026
miyoungc
changed the title
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
docs/reference/commands.md (1)
308-316:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winFix the state-count mismatch in the
statussection.Line 308 says the command reports “one of three states,” but the table now lists four states (
healthy,unreachable,not probed,not verified). Please update the sentence to avoid contradictory behavior docs.Suggested edit
-The command probes every inference provider and reports one of three states on the `Inference` line: +The command probes every inference provider and reports one of four states on the `Inference` line:🤖 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/reference/commands.md` around lines 308 - 316, Update the sentence that currently states the command "probes every inference provider and reports one of three states on the `Inference` line" to reflect the four entries in the table; specifically change it to say "one of four states" (or reword to "one of several states") so it matches the listed states `healthy`, `unreachable`, `not probed`, and `not verified` shown under the `Inference` line in the status section.
🧹 Nitpick comments (1)
.agents/skills/nemoclaw-user-manage-policy/SKILL.md (1)
1-288: 💤 Low valueAutogenerated skill documentation updated as expected.
This file was correctly regenerated from
docs/source per the PR workflow. The comprehensive network policy customization guide is well-structured and covers static changes, dynamic updates, presets, and custom preset authoring.Minor capitalization issue in preset table: Line 171 uses lowercase "github" in the table; it should be "GitHub" per the official brand name. Since this file is autogenerated, apply the fix to the corresponding source file in
docs/and regenerate. Based on learnings, changes to.agents/skills/files are autogenerated fromdocs/bydocs-to-skills.pyand should be fixed at the source.🤖 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-manage-policy/SKILL.md around lines 1 - 288, The autogenerated skill doc has a lowercase preset entry "github" in the "Available presets" table that should use the official capitalization "GitHub"; update the corresponding source docs entry (the preset name/label in the docs source that generates the presets table, e.g., the preset key/value for github) to "GitHub" and then re-run the docs-to-skills.py generation so the change propagates into .agents/skills/nemoclaw-user-manage-policy/SKILL.md; ensure the preset identifier remains the same for programmatic use but fix the human-facing display text to "GitHub" in the source.
🤖 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 `@docs/manage-sandboxes/workspace-files.md`:
- Around line 100-102: The doc and code disagree: the implementation in
src/nemoclaw.ts checks backup.success and always aborts (calls bail()) even when
backup.backedUpDirs.length > 0, so update the documentation in
docs/manage-sandboxes/workspace-files.md to reflect that rebuild aborts on any
backup failure (i.e., NemoClaw does not continue with partial backups) and
reword the sentence to use active voice (replace "was saved" with "saved" or
similar active phrasing); alternatively, if you prefer to change behavior
instead, modify the logic around backup.success in the rebuild flow to allow
continuation when backup.backedUpDirs.length > 0 by skipping bail() and
proceeding with restoring only verified entries—but pick one approach and make
the doc and code consistent.
---
Outside diff comments:
In `@docs/reference/commands.md`:
- Around line 308-316: Update the sentence that currently states the command
"probes every inference provider and reports one of three states on the
`Inference` line" to reflect the four entries in the table; specifically change
it to say "one of four states" (or reword to "one of several states") so it
matches the listed states `healthy`, `unreachable`, `not probed`, and `not
verified` shown under the `Inference` line in the status section.
---
Nitpick comments:
In @.agents/skills/nemoclaw-user-manage-policy/SKILL.md:
- Around line 1-288: The autogenerated skill doc has a lowercase preset entry
"github" in the "Available presets" table that should use the official
capitalization "GitHub"; update the corresponding source docs entry (the preset
name/label in the docs source that generates the presets table, e.g., the preset
key/value for github) to "GitHub" and then re-run the docs-to-skills.py
generation so the change propagates into
.agents/skills/nemoclaw-user-manage-policy/SKILL.md; ensure the preset
identifier remains the same for programmatic use but fix the human-facing
display text to "GitHub" in the source.
🪄 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: ff78b0b9-9c54-43b9-aeac-2bcc6c906d66
📒 Files selected for processing (27)
.agents/skills/nemoclaw-skills-guide/SKILL.md.agents/skills/nemoclaw-user-agent-skills/references/agent-skills.md.agents/skills/nemoclaw-user-configure-inference/SKILL.md.agents/skills/nemoclaw-user-configure-inference/references/inference-options.md.agents/skills/nemoclaw-user-configure-inference/references/set-up-sub-agent.md.agents/skills/nemoclaw-user-configure-inference/references/switch-inference-providers.md.agents/skills/nemoclaw-user-deploy-remote/SKILL.md.agents/skills/nemoclaw-user-get-started/SKILL.md.agents/skills/nemoclaw-user-get-started/references/quickstart-hermes.md.agents/skills/nemoclaw-user-get-started/references/windows-preparation.md.agents/skills/nemoclaw-user-manage-policy/SKILL.md.agents/skills/nemoclaw-user-manage-policy/references/approve-network-requests.md.agents/skills/nemoclaw-user-manage-sandboxes/SKILL.md.agents/skills/nemoclaw-user-manage-sandboxes/references/backup-restore.md.agents/skills/nemoclaw-user-manage-sandboxes/references/messaging-channels.md.agents/skills/nemoclaw-user-manage-sandboxes/references/workspace-files.md.agents/skills/nemoclaw-user-reference/SKILL.md.agents/skills/nemoclaw-user-reference/references/cli-selection-guide.md.agents/skills/nemoclaw-user-reference/references/commands.md.agents/skills/nemoclaw-user-reference/references/network-policies.md.agents/skills/nemoclaw-user-reference/references/troubleshooting.mddocs/manage-sandboxes/lifecycle.mddocs/manage-sandboxes/workspace-files.mddocs/project.jsondocs/reference/commands.mddocs/resources/agent-skills.mddocs/versions1.json
✅ Files skipped from review due to trivial changes (13)
- docs/project.json
- docs/versions1.json
- .agents/skills/nemoclaw-user-reference/SKILL.md
- docs/resources/agent-skills.md
- .agents/skills/nemoclaw-user-reference/references/network-policies.md
- .agents/skills/nemoclaw-user-configure-inference/references/switch-inference-providers.md
- .agents/skills/nemoclaw-user-get-started/references/windows-preparation.md
- .agents/skills/nemoclaw-user-manage-policy/references/approve-network-requests.md
- .agents/skills/nemoclaw-user-get-started/references/quickstart-hermes.md
- .agents/skills/nemoclaw-user-configure-inference/references/inference-options.md
- docs/manage-sandboxes/lifecycle.md
- .agents/skills/nemoclaw-skills-guide/SKILL.md
- .agents/skills/nemoclaw-user-manage-sandboxes/SKILL.md
Co-authored-by: Cursor <cursoragent@cursor.com>
Contributor
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
docs/manage-sandboxes/lifecycle.md (2)
256-258:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winUse
consolelanguage tag with$prompt for CLI examples.This CLI command example uses the
bashlanguage identifier, but the style guide requiresconsolewith a$prompt prefix for all CLI examples.As per coding guidelines, CLI code blocks must use the
consolelanguage tag with$prompt prefix.Proposed fix
-```bash -nemoclaw uninstall -``` +```console +$ nemoclaw uninstall +```🤖 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/manage-sandboxes/lifecycle.md` around lines 256 - 258, Replace the bash code block containing the CLI example for the command "nemoclaw uninstall" with a console code block and add the prompt prefix; specifically, change the fenced block language from bash to console and prepend the command with "$ " so the block shows "$ nemoclaw uninstall" instead of just "nemoclaw uninstall".
270-272:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winUse
consolelanguage tag with$prompt for CLI examples.This CLI command example uses the
bashlanguage identifier, but the style guide requiresconsolewith a$prompt prefix for all CLI examples.As per coding guidelines, CLI code blocks must use the
consolelanguage tag with$prompt prefix.Proposed fix
-```bash -curl -fsSL https://raw.githubusercontent.com/NVIDIA/NemoClaw/refs/heads/main/uninstall.sh | bash -``` +```console +$ curl -fsSL https://raw.githubusercontent.com/NVIDIA/NemoClaw/refs/heads/main/uninstall.sh | bash +```🤖 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/manage-sandboxes/lifecycle.md` around lines 270 - 272, Replace the code block language tag "bash" with "console" and prefix the command line with a "$" prompt in the snippet shown in docs/manage-sandboxes/lifecycle.md so the CLI example follows the style guide; specifically change the fenced code block header from ```bash to ```console and add a leading "$ " before the curl command inside the block.
🧹 Nitpick comments (1)
docs/manage-sandboxes/lifecycle.md (1)
239-239: ⚡ Quick winUse active voice.
The phrase "if any manifest-defined state path cannot be copied" uses passive voice.
As per coding guidelines, active voice is required throughout documentation.
Suggested rewrite
-The flow refuses to proceed past preflight if a credential is missing or past backup if any manifest-defined state path cannot be copied, so a failed run leaves the original sandbox intact and ready to retry. +The flow refuses to proceed past preflight if a credential is missing or past backup if NemoClaw cannot copy any manifest-defined state path, so a failed run leaves the original sandbox intact and ready to retry.🤖 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/manage-sandboxes/lifecycle.md` at line 239, Rewrite the passive clause "if any manifest-defined state path cannot be copied" into active voice; update the sentence to read something like: "The flow refuses to proceed past preflight if a credential is missing or past backup if we cannot copy any manifest-defined state path." Edit the line in lifecycle.md replacing the passive fragment with an active-subject construction ("we cannot copy" or "the process cannot copy") while preserving the original meaning.
🤖 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.
Outside diff comments:
In `@docs/manage-sandboxes/lifecycle.md`:
- Around line 256-258: Replace the bash code block containing the CLI example
for the command "nemoclaw uninstall" with a console code block and add the
prompt prefix; specifically, change the fenced block language from bash to
console and prepend the command with "$ " so the block shows "$ nemoclaw
uninstall" instead of just "nemoclaw uninstall".
- Around line 270-272: Replace the code block language tag "bash" with "console"
and prefix the command line with a "$" prompt in the snippet shown in
docs/manage-sandboxes/lifecycle.md so the CLI example follows the style guide;
specifically change the fenced code block header from ```bash to ```console and
add a leading "$ " before the curl command inside the block.
---
Nitpick comments:
In `@docs/manage-sandboxes/lifecycle.md`:
- Line 239: Rewrite the passive clause "if any manifest-defined state path
cannot be copied" into active voice; update the sentence to read something like:
"The flow refuses to proceed past preflight if a credential is missing or past
backup if we cannot copy any manifest-defined state path." Edit the line in
lifecycle.md replacing the passive fragment with an active-subject construction
("we cannot copy" or "the process cannot copy") while preserving the original
meaning.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: d1c4f212-2baa-45ab-87c0-a83bd3ea8ea5
📒 Files selected for processing (6)
.agents/skills/nemoclaw-user-manage-sandboxes/SKILL.md.agents/skills/nemoclaw-user-manage-sandboxes/references/workspace-files.md.agents/skills/nemoclaw-user-reference/references/commands.mddocs/manage-sandboxes/lifecycle.mddocs/manage-sandboxes/workspace-files.mddocs/reference/commands.md
✅ Files skipped from review due to trivial changes (3)
- docs/reference/commands.md
- .agents/skills/nemoclaw-user-reference/references/commands.md
- .agents/skills/nemoclaw-user-manage-sandboxes/references/workspace-files.md
🚧 Files skipped from review as they are similar to previous changes (1)
- .agents/skills/nemoclaw-user-manage-sandboxes/SKILL.md
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
Catch up the docs for user-facing changes that landed over the weekend and today, so the published guidance matches current installer, onboarding, status, logs, local inference, rebuild backup behavior, the next docs version selector, and refreshed generated user skills.
Related Issue
None.
Changes
host.docker.internalmodel pulls from feat(onboard): add WSL Windows-host Ollama install/start/restart flow #2800; clarify that onboard owns Ollama install and model pulls from fix(install): drop Ollama bootstrap, let onboard own install and pulls #2952.nemoclaw <name> logs --tail/--sincecoverage from fix(logs): honor tail and since flags #2825.nemoclaw status --jsoncoverage from fix(status): emit JSON for status flag (Fixes #2790) #2822..agents/skills/nemoclaw-user-*from docs, including the newnemoclaw-user-manage-sandboxesgenerated skill and removal of the stalenemoclaw-user-workspaceoutput.Type of Change
Verification
npx prek run --all-filespassesnpm testpassesmake docsbuilds without warnings (doc changes only)Signed-off-by: Miyoung Choi miyoungc@nvidia.com
Made with Cursor
Summary by CodeRabbit