docs: add agent runtime primer

[mnajafian-nv]

Overview

Adds a first-time Agent Runtime Primer so users can understand what NeMo Relay adds before running Quick Start.

• I confirm this contribution is my own work, or I have the right to submit it under this project's license.
• I searched existing issues and open pull requests, and this does not duplicate existing work.

Details

• Adds docs/getting-started/agent-runtime-primer.md to explain scopes, managed tool and LLM calls, middleware, events, subscribers/exporters, and plugins.
• Clarifies that NeMo Relay does not replace agent frameworks, model providers, application logic, observability backends, or NeMo Agent Toolkit.
• Links the page from the docs overview and Getting Started navigation.

Validation: just docs, just docs-linkcheck, git diff --check. uv run pre-commit run --all-files was also run; all unrelated hooks passed.

Where should the reviewer start?

docs/getting-started/agent-runtime-primer.md

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

• N/A

Summary by CodeRabbit

• Documentation
  • Added an Agent Runtime Primer detailing the agent runtime execution model: scopes, managed tool/LLM calls, middleware, lifecycle events, and plugins.
  • Clarifies what NeMo Relay does not replace and offers guidance on selecting instrumentation boundaries (application-owned, framework-owned, or reusable plugin behavior).
  • Updated docs navigation to include the new Getting Started entry for the primer.

[coderabbitai]

Walkthrough

This PR adds a new "Agent Runtime Primer" documentation page explaining NeMo Relay's execution model and instrumentation boundaries, and integrates it into the docs index (initial reading path table and Getting Started toctree).

Changes

Agent Runtime Primer Documentation

Layer / File(s)	Summary
Agent Runtime Primer content and index integration docs/getting-started/agent-runtime-primer.md, docs/index.md	New primer page explaining what NeMo Relay's execution model adds (scopes, managed calls, middleware, events, plugins), what it does not replace, how to choose instrumentation boundaries, and recommended next reads. Integrated into the documentation index via a table entry and toctree addition for discoverability.

🎯 1 (Trivial) | ⏱️ ~5 minutes

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	Title follows Conventional Commits format with 'docs' type and concise imperative summary under 72 characters.
Description check	✅ Passed	Description includes all required sections: Overview with confirmations, Details of changes, reviewer start point, and Related Issues field.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 3

🤖 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/getting-started/agent-runtime-primer.md`:
- Around line 87-100: Add a complete lead-in sentence before the bulleted "Read
Next" list under the "## Read Next" heading that briefly explains the purpose of
the list (e.g., "The following links provide next steps and related topics to
explore.") so the list has a full sentence introducing it and satisfies the
guideline that lists must start with a complete lead-in; ensure the sentence
precedes the existing bullets and matches the list tone.
- Around line 89-100: Make the list items parallel by changing the first item
from "Run [Quick Start](quick-start.md) for the smallest binding-specific
example." to match the others—e.g., "Use [Quick Start](quick-start.md) for the
smallest binding-specific example."; ensure the rest of the five items starting
with "Use" remain unchanged (the items referencing "Instrument Applications",
"Integrate into Frameworks", "Build Plugins", "Observability", and "Adaptive")
and preserve punctuation and link targets.
- Line 10: Replace the lowercase phrase "the quick start" with title-cased
"Quick Start" and convert the first mention into an internal link to the Quick
Start page (i.e., change the plain text "the quick start" to a Markdown link
labeled "Quick Start" pointing to the Quick Start document) so readers can
navigate directly from the first reference.

🪄 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: ASSERTIVE

Plan: Enterprise

Run ID: c14e2364-696d-4f69-bffa-f7049f83889c

📥 Commits

Reviewing files that changed from the base of the PR and between 8f096e7 and 1f4241b.

📒 Files selected for processing (2)

• docs/getting-started/agent-runtime-primer.md
• docs/index.md

📜 Review details

🧰 Additional context used

📓 Path-based instructions (20)

**/*.{md,rst,html,txt}

📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-brand-terminology.md)

**/*.{md,rst,html,txt}: Always spell NVIDIA in all caps. Do not use Nvidia, nvidia, nVidia, nVIDIA, or NV.
Use an NVIDIA before a noun because the name starts with an 'en' sound.
Do not add a registered trademark symbol after NVIDIA when referring to the company.
Use trademark symbols with product names only when the document type or legal guidance requires them.
Verify official capitalization, spacing, and hyphenation for product names.
Precede NVIDIA product names with NVIDIA on first mention when it is natural and accurate.
Do not rewrite product names for grammar or title-case rules.
Preserve third-party product names according to the owner's spelling.
Include the company name and full model qualifier on first use when it helps identify the model.
Preserve the official capitalization and punctuation of model names.
Use shorter family names only after the full name is established.
Spell out a term on first use and put the acronym in parentheses unless the acronym is widely understood by the intended audience.
Use the acronym on later mentions after it has been defined.
For long documents, reintroduce the full term if readers might lose context.
Form plurals of acronyms with s, not an apostrophe, such as GPUs.
In headings, common acronyms can remain abbreviated. Spell out the term in the first or second sentence of the body.
Common terms such as CPU, GPU, PC, API, and UI usually do not need to be spelled out for developer audiences.

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

**/*.{md,rst,html}

📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-brand-terminology.md)

Link the first mention of a product name when the destination helps the reader.

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

**/*.{rs,py,js,ts,mjs,go,sh,toml,yml,yaml,md,json,css,html}

📄 CodeRabbit inference engine (AGENTS.md)

Keep SPDX headers on source, docs, scripts, and configuration files. The project is Apache-2.0.

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

**/*.{html,md}

📄 CodeRabbit inference engine (CONTRIBUTING.md)

Include SPDX license header with format: <!-- SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. SPDX-License-Identifier: Apache-2.0 --> in HTML and Markdown files

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

{README.md,docs/index.md}

📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)

{README.md,docs/index.md}: Update entry-point docs when examples or reading paths change
README.md or docs/index.md must be updated when entry points change

Files:

• docs/index.md

**/*.md

📄 CodeRabbit inference engine (.agents/skills/contribute-integration/SKILL.md)

Documentation must be updated if activation or usage changed

**/*.md: Use title case consistently in technical documentation headings
Avoid quotation marks, ampersands, and exclamation marks in headings
Keep product, event, research, and whitepaper names in their official title case
Use title case for table headers
Do not force social-media sentence case into technical docs
Format code elements, commands, parameters, package names, and expressions in monospace
Format directories, file names, and paths in monospace using backticks
Use angle brackets inside monospace for variables inside paths, such as /home/<username>/.login
Format error messages and strings in quotation marks, keeping literal code strings in code formatting when clearer
Format UI buttons, menus, fields, and labels in bold
Use angle brackets between UI labels for menu paths, such as File > Save As
Use italics for new terms on first use, sparingly and only when introducing the term
Use italics for publication titles
Format keyboard shortcuts in plain text, such as Press Ctrl+Alt+Delete
Use owner/repo link text for GitHub repositories, preferring [NVIDIA/NeMo](link) over prose references like 'the GitHub repo'
Introduce every code block with a complete sentence
Do not make a code block complete the grammar of the previous sentence
Do not continue a sentence after a code block
Use syntax highlighting when the format supports it for code blocks
Avoid the word 'snippet' unless the surrounding docs already use it as a term of art
Keep inline method, function, and class references consistent with nearby docs, omitting empty parentheses for prose readability when no call is shown
Use descriptive anchor text that matches the destination title when possible for links
Avoid raw URLs in running text
Avoid generic anchor text such as 'here,' 'this page,' and 'read more'
Include acronyms in link text when a linked term includes an acronym
Do not link long sentences or multiple sentences
Avoid links ...

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

{CHANGELOG.md,RELEASING.md,docs/**/*.md}

📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)

Release history and release notes must reference GitHub Releases, not CHANGELOG.md or docs pages

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

**/{docs,examples,**/*.md,*.patch,*.diff,.github,*.sh,*.yaml,*.yml}

📄 CodeRabbit inference engine (.agents/skills/rename-surfaces/SKILL.md)

Update documentation, examples, CI configuration, and patch artifacts when performing rename operations

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

{README.md,docs/index.md,**/README.md,python/*/README.md,crates/*/README.md}

📄 CodeRabbit inference engine (.agents/skills/review-doc-style/SKILL.md)

Update entry-point documentation including README.md, docs/index.md, package or crate READMEs, and binding-level source READMEs when public behavior changes

Files:

• docs/index.md

{**/*.md,**/*.rst,**/*.txt}

📄 CodeRabbit inference engine (.agents/skills/review-doc-style/SKILL.md)

{**/*.md,**/*.rst,**/*.txt}: Commands, package names, file paths, or APIs must be correct and not stale in documentation
Do not claim support for bindings, features, or workflows in documentation that the repo no longer provides
Examples and procedures must not fail as written in documentation
User-facing naming must be consistent with current repo terminology throughout documentation
NVIDIA must be capitalized correctly in all documentation
Prefer active voice, present tense, and short sentences in documentation
Prefer 'after' over 'once' for temporal references in documentation
Use 'can' instead of 'may' when describing possibility rather than permission in documentation

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

{**/*.md,**/*.rst}

📄 CodeRabbit inference engine (.agents/skills/review-doc-style/SKILL.md)

{**/*.md,**/*.rst}: Code, commands, paths, and filenames must be formatted as inline code in documentation
Headings in technical documentation must use title case consistently
Code blocks, tables, and lists must be introduced with complete lead-in sentences in documentation
Use descriptive anchor text in links rather than bare URLs or weak labels such as 'here' in documentation
Procedures must use imperative voice and parallel structure in documentation

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

**/*.{md,rst,txt}

📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-guide.md)

Spell NVIDIA in all caps. Do not use Nvidia, nvidia, or NV.

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

**/*.{md,rst}

📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-guide.md)

**/*.{md,rst}: Format commands, code elements, expressions, package names, file names, and paths as inline code.
Use descriptive link text. Avoid raw URLs and weak anchors such as "here" or "read more."
Use title case consistently for technical documentation headings.
Introduce code blocks, lists, tables, and images with complete sentences.
Write procedures as imperative steps. Keep steps parallel and split long procedures into smaller tasks.
Prefer active voice, present tense, short sentences, contractions, and plain English.
Use can for possibility and reserve may for permission.
Use after for temporal relationships instead of once.
Prefer refer to over see when the wording points readers to another resource.
Avoid culture-specific idioms, unnecessary Latinisms, jokes, and marketing exaggeration in technical docs.
Spell out months in body text, avoid ordinal dates, and use clear time zones.
Spell out whole numbers from zero through nine unless they are technical values, parameters, versions, or UI values.
Use numerals for 10 or greater and include commas in thousands.
Do not add trademark symbols to learning-oriented docs unless the source, platform, or legal guidance explicitly requires them.

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

{docs/**,README.md,CONTRIBUTING.md}

📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)

{docs/**,README.md,CONTRIBUTING.md}: For docs-only changes, run targeted checks only if commands, package names, or examples changed. Use just docs for docs-site builds and just docs-linkcheck when links changed
Run docs site build with just docs

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

{docs/**,README.md,CONTRIBUTING.md,**/*.md}

📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)

Run docs link validation with just docs-linkcheck when links change

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

{docs/**,README.md}

📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)

Verify README and docs entry points still match current package names and paths for large or public-facing changes

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

{docs/**,examples/**,README.md}

📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)

Verify examples still run with documented commands for large or public-facing changes

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

{docs/**,README.md,**/Cargo.toml,**/package.json,**/*.md}

📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)

Ensure renamed public surfaces are reflected consistently in manifests and docs for large or public-facing changes

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

{docs/**,README.md,CONTRIBUTING.md,RELEASING.md,SECURITY.md}

⚙️ CodeRabbit configuration file

{docs/**,README.md,CONTRIBUTING.md,RELEASING.md,SECURITY.md}: Review documentation for technical accuracy against the current API, command correctness, and consistency across language bindings.
Flag stale examples, missing SPDX headers where required, and instructions that no longer match CI or pre-commit behavior.

Files:

• docs/index.md
• docs/getting-started/agent-runtime-primer.md

{README.md,docs/getting-started/**/*.md}

📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)

Update README.md, docs/getting-started/, or binding-level READMEs if behavior differs by language or usage changed

Files:

• docs/getting-started/agent-runtime-primer.md

🔇 Additional comments (5)

docs/getting-started/agent-runtime-primer.md (3)

20-42: LGTM!

---

44-68: LGTM!

---

70-86: LGTM!

docs/index.md (2)

60-60: LGTM!

---

147-147: LGTM!

[coderabbitai]

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 (2)

docs/getting-started/agent-runtime-primer.md (2)

65-65: ⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

Add NVIDIA prefix to NeMo Agent Toolkit on first mention.

This is the first mention of NeMo Agent Toolkit in the document and should include the company prefix for consistency with product naming guidelines.

🔧 Proposed fix

-- NeMo Agent Toolkit
+- NVIDIA NeMo Agent Toolkit

As per coding guidelines: "Precede NVIDIA product names with NVIDIA on first mention when it is natural and accurate."

🤖 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/getting-started/agent-runtime-primer.md` at line 65, Replace the first
occurrence of the product name "NeMo Agent Toolkit" with the full branded name
"NVIDIA NeMo Agent Toolkit" (keep subsequent mentions unchanged); locate the
inline text "NeMo Agent Toolkit" in the document (e.g., the heading or first
mention) and update it to include the "NVIDIA" prefix to comply with the naming
guideline.

---

100-100: ⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

Clarify ATOF vs ATIF and expand ATIF on first use in this page.

docs/getting-started/agent-runtime-primer.md intentionally references ATOF at lines 37-38 (Agent Trajectory Observability Format) and ATIF at line 100 (Agent Trajectory Interchange Format); both formats are documented separately in docs/plugins/observability/atof.md and docs/plugins/observability/atif.md. Expand ATIF at line 100 to Agent Trajectory Interchange Format (ATIF) for first-mention consistency on this page.

🤖 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/getting-started/agent-runtime-primer.md` at line 100, The page uses both
ATOF and ATIF—please disambiguate and expand ATIF on its first occurrence:
replace the first instance of "ATIF" (the phrase "runtime events to ATIF,
OpenTelemetry, or OpenInference") with "Agent Trajectory Interchange Format
(ATIF)" and, if ATOF is present elsewhere, ensure ATOF is expanded as "Agent
Trajectory Observability Format (ATOF)" at its first mention so both acronyms
are introduced consistently across the document.

🤖 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/getting-started/agent-runtime-primer.md`:
- Line 8: Update the first occurrence of the product name "NeMo Relay" to
include the vendor prefix so it reads "NVIDIA NeMo Relay" (i.e., change the
initial phrase "NeMo Relay is a portable runtime layer..." to "NVIDIA NeMo Relay
is a portable runtime layer...") so the document follows the branding guideline
on first mention.

---

Outside diff comments:
In `@docs/getting-started/agent-runtime-primer.md`:
- Line 65: Replace the first occurrence of the product name "NeMo Agent Toolkit"
with the full branded name "NVIDIA NeMo Agent Toolkit" (keep subsequent mentions
unchanged); locate the inline text "NeMo Agent Toolkit" in the document (e.g.,
the heading or first mention) and update it to include the "NVIDIA" prefix to
comply with the naming guideline.
- Line 100: The page uses both ATOF and ATIF—please disambiguate and expand ATIF
on its first occurrence: replace the first instance of "ATIF" (the phrase
"runtime events to ATIF, OpenTelemetry, or OpenInference") with "Agent
Trajectory Interchange Format (ATIF)" and, if ATOF is present elsewhere, ensure
ATOF is expanded as "Agent Trajectory Observability Format (ATOF)" at its first
mention so both acronyms are introduced consistently across the document.

🪄 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: ASSERTIVE

Plan: Enterprise

Run ID: d7bf8b6b-ac3b-4f49-ba80-ee83ccb2dbce

📥 Commits

Reviewing files that changed from the base of the PR and between 1f4241b and eeb8711.

📒 Files selected for processing (1)

• docs/getting-started/agent-runtime-primer.md

📜 Review details

🧰 Additional context used

📓 Path-based instructions (18)

**/*.{md,rst,html,txt}

📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-brand-terminology.md)

**/*.{md,rst,html,txt}: Always spell NVIDIA in all caps. Do not use Nvidia, nvidia, nVidia, nVIDIA, or NV.
Use an NVIDIA before a noun because the name starts with an 'en' sound.
Do not add a registered trademark symbol after NVIDIA when referring to the company.
Use trademark symbols with product names only when the document type or legal guidance requires them.
Verify official capitalization, spacing, and hyphenation for product names.
Precede NVIDIA product names with NVIDIA on first mention when it is natural and accurate.
Do not rewrite product names for grammar or title-case rules.
Preserve third-party product names according to the owner's spelling.
Include the company name and full model qualifier on first use when it helps identify the model.
Preserve the official capitalization and punctuation of model names.
Use shorter family names only after the full name is established.
Spell out a term on first use and put the acronym in parentheses unless the acronym is widely understood by the intended audience.
Use the acronym on later mentions after it has been defined.
For long documents, reintroduce the full term if readers might lose context.
Form plurals of acronyms with s, not an apostrophe, such as GPUs.
In headings, common acronyms can remain abbreviated. Spell out the term in the first or second sentence of the body.
Common terms such as CPU, GPU, PC, API, and UI usually do not need to be spelled out for developer audiences.

Files:

• docs/getting-started/agent-runtime-primer.md

**/*.{md,rst,html}

📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-brand-terminology.md)

Link the first mention of a product name when the destination helps the reader.

Files:

• docs/getting-started/agent-runtime-primer.md

**/*.{rs,py,js,ts,mjs,go,sh,toml,yml,yaml,md,json,css,html}

📄 CodeRabbit inference engine (AGENTS.md)

Keep SPDX headers on source, docs, scripts, and configuration files. The project is Apache-2.0.

Files:

• docs/getting-started/agent-runtime-primer.md

**/*.{html,md}

📄 CodeRabbit inference engine (CONTRIBUTING.md)

Include SPDX license header with format: <!-- SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. SPDX-License-Identifier: Apache-2.0 --> in HTML and Markdown files

Files:

• docs/getting-started/agent-runtime-primer.md

{README.md,docs/getting-started/**/*.md}

📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)

Update README.md, docs/getting-started/, or binding-level READMEs if behavior differs by language or usage changed

Files:

• docs/getting-started/agent-runtime-primer.md

**/*.md

📄 CodeRabbit inference engine (.agents/skills/contribute-integration/SKILL.md)

Documentation must be updated if activation or usage changed

**/*.md: Use title case consistently in technical documentation headings
Avoid quotation marks, ampersands, and exclamation marks in headings
Keep product, event, research, and whitepaper names in their official title case
Use title case for table headers
Do not force social-media sentence case into technical docs
Format code elements, commands, parameters, package names, and expressions in monospace
Format directories, file names, and paths in monospace using backticks
Use angle brackets inside monospace for variables inside paths, such as /home/<username>/.login
Format error messages and strings in quotation marks, keeping literal code strings in code formatting when clearer
Format UI buttons, menus, fields, and labels in bold
Use angle brackets between UI labels for menu paths, such as File > Save As
Use italics for new terms on first use, sparingly and only when introducing the term
Use italics for publication titles
Format keyboard shortcuts in plain text, such as Press Ctrl+Alt+Delete
Use owner/repo link text for GitHub repositories, preferring [NVIDIA/NeMo](link) over prose references like 'the GitHub repo'
Introduce every code block with a complete sentence
Do not make a code block complete the grammar of the previous sentence
Do not continue a sentence after a code block
Use syntax highlighting when the format supports it for code blocks
Avoid the word 'snippet' unless the surrounding docs already use it as a term of art
Keep inline method, function, and class references consistent with nearby docs, omitting empty parentheses for prose readability when no call is shown
Use descriptive anchor text that matches the destination title when possible for links
Avoid raw URLs in running text
Avoid generic anchor text such as 'here,' 'this page,' and 'read more'
Include acronyms in link text when a linked term includes an acronym
Do not link long sentences or multiple sentences
Avoid links ...

Files:

• docs/getting-started/agent-runtime-primer.md

{CHANGELOG.md,RELEASING.md,docs/**/*.md}

📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)

Release history and release notes must reference GitHub Releases, not CHANGELOG.md or docs pages

Files:

• docs/getting-started/agent-runtime-primer.md

**/{docs,examples,**/*.md,*.patch,*.diff,.github,*.sh,*.yaml,*.yml}

📄 CodeRabbit inference engine (.agents/skills/rename-surfaces/SKILL.md)

Update documentation, examples, CI configuration, and patch artifacts when performing rename operations

Files:

• docs/getting-started/agent-runtime-primer.md

{**/*.md,**/*.rst,**/*.txt}

📄 CodeRabbit inference engine (.agents/skills/review-doc-style/SKILL.md)

{**/*.md,**/*.rst,**/*.txt}: Commands, package names, file paths, or APIs must be correct and not stale in documentation
Do not claim support for bindings, features, or workflows in documentation that the repo no longer provides
Examples and procedures must not fail as written in documentation
User-facing naming must be consistent with current repo terminology throughout documentation
NVIDIA must be capitalized correctly in all documentation
Prefer active voice, present tense, and short sentences in documentation
Prefer 'after' over 'once' for temporal references in documentation
Use 'can' instead of 'may' when describing possibility rather than permission in documentation

Files:

• docs/getting-started/agent-runtime-primer.md

{**/*.md,**/*.rst}

📄 CodeRabbit inference engine (.agents/skills/review-doc-style/SKILL.md)

{**/*.md,**/*.rst}: Code, commands, paths, and filenames must be formatted as inline code in documentation
Headings in technical documentation must use title case consistently
Code blocks, tables, and lists must be introduced with complete lead-in sentences in documentation
Use descriptive anchor text in links rather than bare URLs or weak labels such as 'here' in documentation
Procedures must use imperative voice and parallel structure in documentation

Files:

• docs/getting-started/agent-runtime-primer.md

**/*.{md,rst,txt}

📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-guide.md)

Spell NVIDIA in all caps. Do not use Nvidia, nvidia, or NV.

Files:

• docs/getting-started/agent-runtime-primer.md

**/*.{md,rst}

📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-guide.md)

**/*.{md,rst}: Format commands, code elements, expressions, package names, file names, and paths as inline code.
Use descriptive link text. Avoid raw URLs and weak anchors such as "here" or "read more."
Use title case consistently for technical documentation headings.
Introduce code blocks, lists, tables, and images with complete sentences.
Write procedures as imperative steps. Keep steps parallel and split long procedures into smaller tasks.
Prefer active voice, present tense, short sentences, contractions, and plain English.
Use can for possibility and reserve may for permission.
Use after for temporal relationships instead of once.
Prefer refer to over see when the wording points readers to another resource.
Avoid culture-specific idioms, unnecessary Latinisms, jokes, and marketing exaggeration in technical docs.
Spell out months in body text, avoid ordinal dates, and use clear time zones.
Spell out whole numbers from zero through nine unless they are technical values, parameters, versions, or UI values.
Use numerals for 10 or greater and include commas in thousands.
Do not add trademark symbols to learning-oriented docs unless the source, platform, or legal guidance explicitly requires them.

Files:

• docs/getting-started/agent-runtime-primer.md

{docs/**,README.md,CONTRIBUTING.md}

📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)

{docs/**,README.md,CONTRIBUTING.md}: For docs-only changes, run targeted checks only if commands, package names, or examples changed. Use just docs for docs-site builds and just docs-linkcheck when links changed
Run docs site build with just docs

Files:

• docs/getting-started/agent-runtime-primer.md

{docs/**,README.md,CONTRIBUTING.md,**/*.md}

📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)

Run docs link validation with just docs-linkcheck when links change

Files:

• docs/getting-started/agent-runtime-primer.md

{docs/**,README.md}

📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)

Verify README and docs entry points still match current package names and paths for large or public-facing changes

Files:

• docs/getting-started/agent-runtime-primer.md

{docs/**,examples/**,README.md}

📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)

Verify examples still run with documented commands for large or public-facing changes

Files:

• docs/getting-started/agent-runtime-primer.md

{docs/**,README.md,**/Cargo.toml,**/package.json,**/*.md}

📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)

Ensure renamed public surfaces are reflected consistently in manifests and docs for large or public-facing changes

Files:

• docs/getting-started/agent-runtime-primer.md

{docs/**,README.md,CONTRIBUTING.md,RELEASING.md,SECURITY.md}

⚙️ CodeRabbit configuration file

{docs/**,README.md,CONTRIBUTING.md,RELEASING.md,SECURITY.md}: Review documentation for technical accuracy against the current API, command correctness, and consistency across language bindings.
Flag stale examples, missing SPDX headers where required, and instructions that no longer match CI or pre-commit behavior.

Files:

• docs/getting-started/agent-runtime-primer.md

🔇 Additional comments (2)

docs/getting-started/agent-runtime-primer.md (2)

20-43: LGTM!

---

70-85: LGTM!

[willkill07]

/merge