feat(cli): add nemo-flow plugins edit#98
Conversation
Signed-off-by: Will Killian <wkillian@nvidia.com>
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
WalkthroughReplaces legacy exporter flags/env/TOML with plugin-based observability: ChangesPlugin-Based Observability Configuration
Estimated code review effort🎯 4 (Complex) | ⏱️ ~75 minutes Possibly related PRs
✨ Finishing Touches🧪 Generate unit tests (beta)
|
github-actions
Bot
added
size:XL
Signed-off-by: Will Killian <wkillian@nvidia.com>
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
crates/cli/src/launcher.rs (1)
505-510: 🧹 Nitpick | 🔵 Trivial | ⚡ Quick winUpdate stale live-status doc comment to match plugin-based output.
The comment still says the banner shows ATIF/OpenInference fields, but the implementation now shows plugin configuration status.
Proposed doc-comment fix
- // Prints a compact pre-launch status banner so users see at a glance where their observability - // data is going (gateway URL, ATIF dir, OpenInference endpoint) before the agent's own UI takes + // Prints a compact pre-launch status banner so users see at a glance where their observability + // data is going (gateway URL and plugin configuration status) before the agent's own UI takes🤖 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 `@crates/cli/src/launcher.rs` around lines 505 - 510, Update the stale doc comment above the compact pre-launch status banner in launcher.rs to reflect that the output now shows plugin configuration status (plugin names and enabled/disabled state) rather than ATIF/OpenInference fields; keep the details that the banner is emitted on stderr, is compact and pre-launch, and is suppressed when stdout is not a TTY, and mention that it’s distinct from the verbose `print()`/`--print` output. Reference the existing comment block that documents the banner behavior near the banner-printing code so you update its wording to describe "plugin configuration status" instead of "ATIF/OpenInference" while preserving the notes about stderr/TTY and distinction from `print()`.crates/cli/tests/coverage/session_tests.rs (1)
137-159: 🧹 Nitpick | 🔵 Trivial | ⚡ Quick winRemove the disconnected filesystem assertion from this test.
This test now verifies unknown terminal events are ignored in memory, but the temp-dir ATIF assertion is unrelated to configured output paths and always passes.
Suggested cleanup
#[tokio::test] async fn terminal_retry_for_unknown_session_is_ignored() { - let temp = tempfile::tempdir().unwrap(); let config = session_test_config(); let manager = SessionManager::new(config); @@ assert!(manager.inner.lock().await.is_empty()); - assert!(!temp.path().join("retry-session.atif.json").exists()); }🤖 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 `@crates/cli/tests/coverage/session_tests.rs` around lines 137 - 159, The test terminal_retry_for_unknown_session_is_ignored currently creates a temp dir and asserts a nonexistent ATIF file doesn't exist, which is unrelated; remove the disconnected filesystem assertion and its temp dir setup: delete the let temp = tempfile::tempdir().unwrap(); line and the final assert!(!temp.path().join("retry-session.atif.json").exists()); line so the test only verifies the in-memory SessionManager behavior (references: terminal_retry_for_unknown_session_is_ignored, tempfile::tempdir, the path join and existence assert).
🤖 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 `@ATTRIBUTIONS-Rust.md`:
- Around line 6360-6364: The attribution blocks (e.g., the "## console - 0.16.3"
heading and its license fence) violate markdown lint rules by lacking
surrounding blank lines and using unlabeled fenced blocks; fix by inserting a
blank line before and after each heading and before and after each fenced
license block, and change the fence from ``` to ```text so the license block is
labeled. Apply the same normalization to the other new sections called out
(lines referenced in the review: 8330-8334, 25853-25857, 25882-25886,
27100-27104) and any other newly added attribution sections in
ATTRIBUTIONS-Rust.md.
In `@crates/cli/src/doctor.rs`:
- Around line 513-521: The observability component probe collection should be
skipped when the component is explicitly disabled: update the code path that
currently does `if let Some(config) =
observability_component_config(plugin_value) {
collect_observability_component_checks(&mut checks, config).await; } else { ...
}` to first check `config.enabled` (treating absence as true) and only call
`collect_observability_component_checks` when `enabled == true`; if `enabled ==
false` push an Info check like "Observability plugin" with "component disabled"
details. Apply the same enabled-guard logic to the other occurrence that calls
`collect_observability_component_checks` (the analogous block later in the file)
so disabled components no longer run endpoint/directory probes.
In `@crates/cli/src/plugins.rs`:
- Around line 255-261: The ensure_tty function currently only checks stdin;
update it to verify both stdin and stdout are TTYs before enabling interactive
plugin editing by calling the same terminal check used for stdin on stdout
(e.g., std::io::stdout().is_terminal()) and return the same
CliError::Config("interactive plugin editing requires a TTY".into()) if either
is not a TTY; modify the ensure_tty function to perform both checks so the menu
renderer (Term::stdout()) cannot fail mid-session.
In `@crates/cli/tests/coverage/doctor_tests.rs`:
- Around line 262-263: The test currently only asserts the presence of any
warning (assert!(checks.iter().any(|check| check.status == Status::Warn))) which
allows unrelated warnings to satisfy the expectation; update this to assert that
the specific ATIF-directory check is the one with Status::Warn by locating the
check in checks (e.g., using checks.iter().find(|c| c.name.contains("ATIF") ||
c.name.contains("ATIF directory")) or matching the check's unique identifier)
and then assert that that check.status == Status::Warn while keeping the
assert!(!missing.exists()) as-is.
---
Outside diff comments:
In `@crates/cli/src/launcher.rs`:
- Around line 505-510: Update the stale doc comment above the compact pre-launch
status banner in launcher.rs to reflect that the output now shows plugin
configuration status (plugin names and enabled/disabled state) rather than
ATIF/OpenInference fields; keep the details that the banner is emitted on
stderr, is compact and pre-launch, and is suppressed when stdout is not a TTY,
and mention that it’s distinct from the verbose `print()`/`--print` output.
Reference the existing comment block that documents the banner behavior near the
banner-printing code so you update its wording to describe "plugin configuration
status" instead of "ATIF/OpenInference" while preserving the notes about
stderr/TTY and distinction from `print()`.
In `@crates/cli/tests/coverage/session_tests.rs`:
- Around line 137-159: The test terminal_retry_for_unknown_session_is_ignored
currently creates a temp dir and asserts a nonexistent ATIF file doesn't exist,
which is unrelated; remove the disconnected filesystem assertion and its temp
dir setup: delete the let temp = tempfile::tempdir().unwrap(); line and the
final assert!(!temp.path().join("retry-session.atif.json").exists()); line so
the test only verifies the in-memory SessionManager behavior (references:
terminal_retry_for_unknown_session_is_ignored, tempfile::tempdir, the path join
and existence assert).
🪄 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: 1c1c99bd-d2a0-4f8e-bd52-e4ec0721bd0f
⛔ Files ignored due to path filters (1)
Cargo.lockis excluded by!**/*.lock
📒 Files selected for processing (43)
ATTRIBUTIONS-Rust.mdcrates/cli/Cargo.tomlcrates/cli/README.mdcrates/cli/src/config.rscrates/cli/src/doctor.rscrates/cli/src/gateway.rscrates/cli/src/installer.rscrates/cli/src/launcher.rscrates/cli/src/main.rscrates/cli/src/plugins.rscrates/cli/src/session.rscrates/cli/src/setup.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/config_tests.rscrates/cli/tests/coverage/doctor_tests.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/tests/coverage/launcher_tests.rscrates/cli/tests/coverage/plugins_tests.rscrates/cli/tests/coverage/server_tests.rscrates/cli/tests/coverage/session_tests.rscrates/cli/tests/coverage/setup_tests.rscrates/core/Cargo.tomlcrates/core/src/config_editor.rscrates/core/src/lib.rscrates/core/src/observability/plugin_component.rscrates/core/src/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rsdocs/about/concepts/plugins.mddocs/build-plugins/about.mddocs/build-plugins/plugin-configuration-files.mddocs/export-observability-data/observability-plugin.mddocs/getting-started/configuration.mddocs/index.mddocs/integrate-frameworks/coding-agent-claude-code.mddocs/integrate-frameworks/coding-agent-codex.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-hermes.mdintegrations/coding-agents/README.mdintegrations/coding-agents/claude-code/README.mdintegrations/coding-agents/codex/README.mdintegrations/coding-agents/cursor/README.md
💤 Files with no reviewable changes (3)
- crates/cli/tests/coverage/server_tests.rs
- crates/cli/src/installer.rs
- crates/cli/tests/coverage/launcher_tests.rs
📜 Review details
🧰 Additional context used
📓 Path-based instructions (39)
**/*.{md,rst,html,txt}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-brand-terminology.md)
**/*.{md,rst,html,txt}: Always spellNVIDIAin all caps. Do not useNvidia,nvidia,nVidia,nVIDIA, orNV.
Usean NVIDIAbefore a noun because the name starts with an 'en' sound.
Do not add a registered trademark symbol afterNVIDIAwhen 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 withNVIDIAon 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 withs, not an apostrophe, such asGPUs.
In headings, common acronyms can remain abbreviated. Spell out the term in the first or second sentence of the body.
Common terms such asCPU,GPU,PC,API, andUIusually do not need to be spelled out for developer audiences.
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mdcrates/cli/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mdintegrations/coding-agents/README.mdintegrations/coding-agents/cursor/README.mdATTRIBUTIONS-Rust.mdintegrations/coding-agents/claude-code/README.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.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/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mdcrates/cli/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mdintegrations/coding-agents/README.mdintegrations/coding-agents/cursor/README.mdATTRIBUTIONS-Rust.mdintegrations/coding-agents/claude-code/README.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{md,rst,txt}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-guide.md)
**/*.{md,rst,txt}: SpellNVIDIAin all caps. Do not useNvidia,nvidia, orNV.
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.
Usecanfor possibility and reservemayfor permission.
Useafterfor temporal relationships instead ofonce.
Preferrefer tooverseewhen the wording points readers to another resource.
Avoid culture-specific idioms, unnecessary Latinisms, jokes, and marketing exaggeration in technical documentation.
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 documentation unless the source, platform, or legal guidance explicitly requires them.
Do not add trademark symbols to NeMo Flow learning documentation by default.
Do not rewrite API names, package names, command flags, or code literals for style reasons.
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mdcrates/cli/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mdintegrations/coding-agents/README.mdintegrations/coding-agents/cursor/README.mdATTRIBUTIONS-Rust.mdintegrations/coding-agents/claude-code/README.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{md,markdown,rst}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-technical-docs.md)
**/*.{md,markdown,rst}: 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
Use monospace formatting for code elements, commands, parameters, package names, and expressions
Use monospace formatting for directories, file names, and paths
Use angle brackets inside monospace for variables inside paths, such as/home/<username>/.login
Use quotation marks for error messages and strings in documentation
Use bold formatting for UI buttons, menus, fields, and labels in documentation
Use angle brackets between UI labels for menu paths, such as File > Save As
Use italics for new terms on first use in documentation
Use italics for publication titles in documentation
Use plain text formatting for keyboard shortcuts in documentation
Prefer[NVIDIA/NeMo](link)format for GitHub repository references over generic phrases 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 in documentation
Avoid generic link anchors such as 'here,' 'this page,' and 'read more' in documentation
Include the acronym in link text if a linked term includes an acronym
Do not link long sentences or multiple sentences in documentation
Avoid links that pull readers away from a procedure unles...
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mdcrates/cli/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mdintegrations/coding-agents/README.mdintegrations/coding-agents/cursor/README.mdATTRIBUTIONS-Rust.mdintegrations/coding-agents/claude-code/README.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{html,md}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license headers in HTML and Markdown files using HTML comment syntax
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mdcrates/cli/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mdintegrations/coding-agents/README.mdintegrations/coding-agents/cursor/README.mdATTRIBUTIONS-Rust.mdintegrations/coding-agents/claude-code/README.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
docs/**/*.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Run
./scripts/build-docs.shfor documentation site changes
docs/**/*.md: Relevant getting-started or reference docs must be updated when examples change
Release-policy docs must point to GitHub Releases as the only release-history source of truth
docs/**/*.md: Use title case for headings in technical documentation
Introduce code blocks, tables, and lists with complete lead-in sentences in documentation
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Run Markdown link checking via
lycheeforREADME.md,CONTRIBUTING.md, anddocs/through pre-commit hooks
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mdcrates/cli/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mdintegrations/coding-agents/README.mdintegrations/coding-agents/cursor/README.mdATTRIBUTIONS-Rust.mdintegrations/coding-agents/claude-code/README.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{md,markdown,py,sh,bash,js,ts,java,cpp,go,rust}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Keep package names, repo references, and build commands current in documentation
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mdcrates/cli/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mdintegrations/coding-agents/README.mdintegrations/coding-agents/cursor/README.mdATTRIBUTIONS-Rust.mdintegrations/coding-agents/claude-code/README.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
{RELEASING.md,CHANGELOG.md,docs/**/*.md}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Keep release-process and release-notes guidance in repo-maintainer docs such as RELEASING.md, not as user-facing docs pages or CHANGELOG.md
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{md,markdown,py,sh,bash}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Keep stable user-facing wrappers at scripts/ root in docs and examples; only point at namespaced helper paths when documenting internal maintenance work
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mdcrates/cli/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mdintegrations/coding-agents/README.mdintegrations/coding-agents/cursor/README.mdATTRIBUTIONS-Rust.mdintegrations/coding-agents/claude-code/README.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{md,markdown,py,sh,bash,js,ts,example}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Example commands must match current package names and paths
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mdcrates/cli/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mdintegrations/coding-agents/README.mdintegrations/coding-agents/cursor/README.mdATTRIBUTIONS-Rust.mdintegrations/coding-agents/claude-code/README.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
{scripts/*.sh,docs/**/*.md}
📄 CodeRabbit inference engine (.agents/skills/contribute-integration/SKILL.md)
Use root
./scripts/*.shcommands in docs and contributor guidance as documented, with implementations underscripts/third-party/
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
{docs/**,examples/**,crates/adaptive/**,python/nemo_flow/**,go/nemo_flow/**,**/{example,component}.{ts,tsx,js,rs,py,go}}
📄 CodeRabbit inference engine (.agents/skills/maintain-optimizer/SKILL.md)
Any new adaptive component kind must have documentation, examples, and binding coverage across all supported languages
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
{README*,CHANGELOG*,docs/**/*.{md,rst,txt},examples/**/*,*.md}
📄 CodeRabbit inference engine (.agents/skills/rename-surfaces/SKILL.md)
Update documentation, examples, and getting-started guides with new package/module/crate names after rename operations
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mdATTRIBUTIONS-Rust.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{md,txt,rst}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/SKILL.md)
**/*.{md,txt,rst}: Ensure commands, package names, file paths, and APIs in documentation are correct and not stale; flag incorrect or outdated information as blocking issues
Ensure examples and procedures in documentation will execute successfully with current APIs and commands
Use consistent user-facing terminology throughout documentation that matches current repo terminology
Capitalize NVIDIA correctly in all documentation and public-facing text
Format code, commands, paths, and filenames as inline code (monospace) in documentation
Use descriptive anchor text for links instead of bare URLs or weak labels like 'here' in documentation
Prefer active voice, present tense, short sentences, and plain English in documentation
Structure documentation procedures as imperative steps that are easy to scan and not too long for a single sequence
Prefer 'after' instead of 'once' for temporal references in documentation
Use 'can' instead of 'may' when describing possibility (rather than permission) in documentation
Avoid ambiguous numeric dates and ordinal dates in documentation body text
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mdcrates/cli/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mdintegrations/coding-agents/README.mdintegrations/coding-agents/cursor/README.mdATTRIBUTIONS-Rust.mdintegrations/coding-agents/claude-code/README.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
{README.md,docs/**/*.md,examples/**/*.{js,ts,py,go,rs}}
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
Keep documentation and examples synchronized with current install, import, and build commands
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{py,js,ts,tsx,go,rs,md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Format changed files with the language-native formatter before the final lint/test pass
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mdcrates/core/src/lib.rscrates/cli/src/main.rsdocs/export-observability-data/observability-plugin.mdcrates/cli/tests/coverage/plugins_tests.rscrates/cli/README.mdcrates/cli/tests/coverage/doctor_tests.rscrates/cli/src/gateway.rsintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-gateway.mdcrates/core/src/plugin.rscrates/core/src/observability/plugin_component.rscrates/cli/src/launcher.rsdocs/integrate-frameworks/coding-agent-claude-code.mdintegrations/coding-agents/README.mdcrates/core/tests/unit/observability/plugin_component_tests.rsintegrations/coding-agents/cursor/README.mdATTRIBUTIONS-Rust.mdintegrations/coding-agents/claude-code/README.mdcrates/core/src/config_editor.rscrates/cli/src/doctor.rsdocs/integrate-frameworks/coding-agent-cursor.mdcrates/cli/tests/cli_tests.rscrates/cli/src/plugins.rscrates/cli/tests/coverage/gateway_tests.rsdocs/integrate-frameworks/coding-agent-hermes.mdcrates/cli/tests/coverage/installer_tests.rsdocs/integrate-frameworks/coding-agent-codex.mdcrates/cli/src/setup.rscrates/cli/src/session.rscrates/cli/tests/coverage/config_tests.rscrates/cli/tests/coverage/setup_tests.rscrates/cli/tests/coverage/session_tests.rscrates/cli/src/config.rs
{README.md,CONTRIBUTING.md,docs/**/*.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
For docs-only changes, run targeted checks only if commands, package names, or examples changed. Use
just docsfor docs-site builds andjust docs-linkcheckwhen links changed
Files:
docs/getting-started/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.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/configuration.mddocs/index.mddocs/about/concepts/plugins.mddocs/build-plugins/plugin-configuration-files.mddocs/build-plugins/about.mddocs/export-observability-data/observability-plugin.mddocs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
**/Cargo.{toml,lock}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Run
cargo deny checkfor Rust dependency auditing as configured indeny.toml
Files:
crates/core/Cargo.tomlcrates/cli/Cargo.toml
**/*.toml
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license headers in TOML files using TOML comment syntax
Files:
crates/core/Cargo.tomlcrates/cli/Cargo.toml
crates/{core,adaptive}/**
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changes to
crates/coreorcrates/adaptivemust run the full language matrix
Files:
crates/core/Cargo.tomlcrates/core/src/lib.rscrates/core/src/plugin.rscrates/core/src/observability/plugin_component.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/config_editor.rs
{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
{README.md,docs/index.md,**/README.md}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/SKILL.md)
Update entry-point documentation (README.md, docs/index.md, package READMEs, binding-level source READMEs) whenever public behavior changes
Files:
docs/index.mdcrates/cli/README.mdintegrations/coding-agents/codex/README.mdintegrations/coding-agents/README.mdintegrations/coding-agents/cursor/README.mdintegrations/coding-agents/claude-code/README.md
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-ffi-surface/SKILL.md)
**/*.rs: Runcargo fmt --allfor FFI work as it is Rust work
Runjust test-rustfor FFI validation
Runcargo clippy --workspace --all-targets -- -D warningsto enforce warnings-as-errors linting
**/*.rs: Runcargo fmt --allfor Rust code formatting
Runcargo clippy --workspace --all-targets -- -D warningsto enforce Rust linting with no warnings
Runjust test-rustas the shared-runtime build/test wrapper for Rust changesUse Rust snake_case naming convention for Rust code
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor Rust code formatting when Node changes touch Rust files
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting when Rust files changed as part of Node work
**/*.rs: Always runjust test-rustwhen any Rust code changes
Always runcargo fmt --allwhen any Rust code changes
Always runcargo clippy --workspace --all-targets -- -D warningswhen any Rust code changes
Files:
crates/core/src/lib.rscrates/cli/src/main.rscrates/cli/tests/coverage/plugins_tests.rscrates/cli/tests/coverage/doctor_tests.rscrates/cli/src/gateway.rscrates/core/src/plugin.rscrates/core/src/observability/plugin_component.rscrates/cli/src/launcher.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/config_editor.rscrates/cli/src/doctor.rscrates/cli/tests/cli_tests.rscrates/cli/src/plugins.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/src/setup.rscrates/cli/src/session.rscrates/cli/tests/coverage/config_tests.rscrates/cli/tests/coverage/setup_tests.rscrates/cli/tests/coverage/session_tests.rscrates/cli/src/config.rs
**/*.{rs,go,js,ts,tsx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license headers in all Rust, Go, JavaScript, and TypeScript source files using C-style comment syntax
Files:
crates/core/src/lib.rscrates/cli/src/main.rscrates/cli/tests/coverage/plugins_tests.rscrates/cli/tests/coverage/doctor_tests.rscrates/cli/src/gateway.rscrates/core/src/plugin.rscrates/core/src/observability/plugin_component.rscrates/cli/src/launcher.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/config_editor.rscrates/cli/src/doctor.rscrates/cli/tests/cli_tests.rscrates/cli/src/plugins.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/src/setup.rscrates/cli/src/session.rscrates/cli/tests/coverage/config_tests.rscrates/cli/tests/coverage/setup_tests.rscrates/cli/tests/coverage/session_tests.rscrates/cli/src/config.rs
**/*.{rs,py,go,js,ts,tsx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Use
SONAR_IGNORE_START/SONAR_IGNORE_ENDmarkers only for documented false positives that cannot be resolved in code; keep ignored blocks small, add explanatory comments, and require reviewer sign-off
Files:
crates/core/src/lib.rscrates/cli/src/main.rscrates/cli/tests/coverage/plugins_tests.rscrates/cli/tests/coverage/doctor_tests.rscrates/cli/src/gateway.rscrates/core/src/plugin.rscrates/core/src/observability/plugin_component.rscrates/cli/src/launcher.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/config_editor.rscrates/cli/src/doctor.rscrates/cli/tests/cli_tests.rscrates/cli/src/plugins.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/src/setup.rscrates/cli/src/session.rscrates/cli/tests/coverage/config_tests.rscrates/cli/tests/coverage/setup_tests.rscrates/cli/tests/coverage/session_tests.rscrates/cli/src/config.rs
**/*.{js,ts,tsx,jsx,py,rs,go,java,c,cpp,h,cc,cxx,cs,rb,php,swift,kt}
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changed files must be formatted with the language-native formatter
Files:
crates/core/src/lib.rscrates/cli/src/main.rscrates/cli/tests/coverage/plugins_tests.rscrates/cli/tests/coverage/doctor_tests.rscrates/cli/src/gateway.rscrates/core/src/plugin.rscrates/core/src/observability/plugin_component.rscrates/cli/src/launcher.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/config_editor.rscrates/cli/src/doctor.rscrates/cli/tests/cli_tests.rscrates/cli/src/plugins.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/src/setup.rscrates/cli/src/session.rscrates/cli/tests/coverage/config_tests.rscrates/cli/tests/coverage/setup_tests.rscrates/cli/tests/coverage/session_tests.rscrates/cli/src/config.rs
{crates/core,crates/adaptive}/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-wasm-binding/SKILL.md)
If the change touched shared runtime semantics in
crates/coreorcrates/adaptive, also usevalidate-change
Files:
crates/core/src/lib.rscrates/core/src/plugin.rscrates/core/src/observability/plugin_component.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/config_editor.rs
crates/core/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
When
crates/corechanges, run the full validation matrix across Rust, Python, Go, Node.js, and WebAssembly
crates/core/**/*.rs: UseJson = serde_json::Valuein Rust-facing runtime APIs where the existing code expects JSON payloads.
UseResult<T>withFlowErrorin core runtime paths. Keep errors explicit and binding-appropriate at the wrapper layer.
Files:
crates/core/src/lib.rscrates/core/src/plugin.rscrates/core/src/observability/plugin_component.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/config_editor.rs
**/*.{rs,py,js,ts,tsx,go}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
During iteration, prefer
uv run pre-commit run --files <changed files...>for targeted validation
Files:
crates/core/src/lib.rscrates/cli/src/main.rscrates/cli/tests/coverage/plugins_tests.rscrates/cli/tests/coverage/doctor_tests.rscrates/cli/src/gateway.rscrates/core/src/plugin.rscrates/core/src/observability/plugin_component.rscrates/cli/src/launcher.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/config_editor.rscrates/cli/src/doctor.rscrates/cli/tests/cli_tests.rscrates/cli/src/plugins.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/src/setup.rscrates/cli/src/session.rscrates/cli/tests/coverage/config_tests.rscrates/cli/tests/coverage/setup_tests.rscrates/cli/tests/coverage/session_tests.rscrates/cli/src/config.rs
crates/{core,adaptive}/**/*.rs
⚙️ CodeRabbit configuration file
crates/{core,adaptive}/**/*.rs: Review the Rust runtime for async correctness, scope isolation, middleware ordering, and event lifecycle regressions.
Pay close attention to task-local/thread-local scope propagation, callback lifetimes, stream finalization, and root_uuid isolation.
Public API changes should preserve existing behavior unless tests and docs show the intended migration path.
Files:
crates/core/src/lib.rscrates/core/src/plugin.rscrates/core/src/observability/plugin_component.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/config_editor.rs
{crates/**/tests/**,python/tests/**,go/nemo_flow/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_flow/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/cli/tests/coverage/plugins_tests.rscrates/cli/tests/coverage/doctor_tests.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/cli/tests/cli_tests.rscrates/cli/tests/coverage/gateway_tests.rscrates/cli/tests/coverage/installer_tests.rscrates/cli/tests/coverage/config_tests.rscrates/cli/tests/coverage/setup_tests.rscrates/cli/tests/coverage/session_tests.rs
**/README.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Update relevant crate or package README when that surface changed
Relevant package or crate README.md files must be updated when examples or binding guidance changes
Files:
crates/cli/README.mdintegrations/coding-agents/codex/README.mdintegrations/coding-agents/README.mdintegrations/coding-agents/cursor/README.mdintegrations/coding-agents/claude-code/README.md
**/{integrations,integration,*-integration}/**
📄 CodeRabbit inference engine (.agents/skills/contribute-integration/SKILL.md)
**/{integrations,integration,*-integration}/**: Keep NeMo Flow optional in framework integrations
Preserve the framework's original behavior when NeMo Flow is absent
Wrap tool and LLM paths at the correct framework boundary
Integration pattern must followdocs/integrate-frameworks/adding-scopes.md
Files:
integrations/coding-agents/codex/README.mdintegrations/coding-agents/README.mdintegrations/coding-agents/cursor/README.mdintegrations/coding-agents/claude-code/README.md
docs/integrate-frameworks/**/*.md
📄 CodeRabbit inference engine (.agents/skills/contribute-integration/SKILL.md)
Documentation must be updated if activation or usage of the integration changed
Files:
docs/integrate-frameworks/coding-agent-gateway.mddocs/integrate-frameworks/coding-agent-claude-code.mddocs/integrate-frameworks/coding-agent-cursor.mddocs/integrate-frameworks/coding-agent-hermes.mddocs/integrate-frameworks/coding-agent-codex.md
{crates/adaptive/**/*.rs,python/nemo_flow/plugin.py,go/nemo_flow/**/*.go,**/{context,plugin}.{ts,tsx,js,rs}}
📄 CodeRabbit inference engine (.agents/skills/maintain-optimizer/SKILL.md)
Keep plugin context surfaces aligned across all language implementations
Files:
crates/core/src/plugin.rs
ATTRIBUTIONS-Rust.md
📄 CodeRabbit inference engine (.agents/skills/update-project-version/SKILL.md)
Regenerate
ATTRIBUTIONS-Rust.mdwith./scripts/generate_attributions.sh rustif Cargo metadata changed and committed attribution files must stay fresh
Files:
ATTRIBUTIONS-Rust.md
**/{config,schema,adaptive}.{yaml,yml,json,ts,tsx,py,go,rs}
📄 CodeRabbit inference engine (.agents/skills/maintain-optimizer/SKILL.md)
Ensure dynamic config shape matches the documented canonical model in docs/use-adaptive-optimization/configure.md
Files:
crates/cli/src/config.rs
🪛 LanguageTool
docs/build-plugins/plugin-configuration-files.md
[style] ~125-~125: The double modal “requires elevated” is nonstandard (only accepted in certain dialects). Consider “to be elevated”.
Context: ...flow/plugins.toml` and usually requires elevated filesystem permissions. The editor men...
(NEEDS_FIXED)
🪛 markdownlint-cli2 (0.22.1)
ATTRIBUTIONS-Rust.md
[warning] 6360-6360: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 6363-6363: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Above
(MD022, blanks-around-headings)
[warning] 6363-6363: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 6364-6364: Fenced code blocks should be surrounded by blank lines
(MD031, blanks-around-fences)
[warning] 6364-6364: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
[warning] 8330-8330: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 8333-8333: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Above
(MD022, blanks-around-headings)
[warning] 8333-8333: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 8334-8334: Fenced code blocks should be surrounded by blank lines
(MD031, blanks-around-fences)
[warning] 8334-8334: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
[warning] 25853-25853: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 25856-25856: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Above
(MD022, blanks-around-headings)
[warning] 25856-25856: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 25857-25857: Fenced code blocks should be surrounded by blank lines
(MD031, blanks-around-fences)
[warning] 25857-25857: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
[warning] 25882-25882: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 25885-25885: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Above
(MD022, blanks-around-headings)
[warning] 25885-25885: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 25886-25886: Fenced code blocks should be surrounded by blank lines
(MD031, blanks-around-fences)
[warning] 25886-25886: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
[warning] 27100-27100: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 27103-27103: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Above
(MD022, blanks-around-headings)
[warning] 27103-27103: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below
(MD022, blanks-around-headings)
[warning] 27104-27104: Fenced code blocks should be surrounded by blank lines
(MD031, blanks-around-fences)
[warning] 27104-27104: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🔇 Additional comments (49)
crates/core/Cargo.toml (1)
18-18: LGTM!Also applies to: 51-51
crates/cli/src/gateway.rs (1)
580-588: LGTM!Also applies to: 866-884, 875-884
integrations/coding-agents/codex/README.md (1)
44-45: LGTM!Also applies to: 56-60, 72-85, 99-100
docs/build-plugins/plugin-configuration-files.md (1)
1-259: LGTM!docs/index.md (1)
185-185: LGTM!docs/about/concepts/plugins.md (1)
158-160: LGTM!docs/build-plugins/about.md (1)
36-36: LGTM!docs/getting-started/configuration.md (1)
31-35: LGTM!docs/export-observability-data/observability-plugin.md (1)
62-147: LGTM!crates/core/src/config_editor.rs (1)
1-158: LGTM!crates/core/src/lib.rs (1)
60-60: LGTM!crates/cli/src/main.rs (1)
16-16: LGTM!Also applies to: 25-25, 71-76
crates/cli/Cargo.toml (1)
26-26: ⚡ Quick winNo action needed. The version specification
console = "0.16"is valid and will resolve to the latest compatible version (0.16.3) via semantic versioning. Patch-level updates are handled automatically by Cargo.crates/cli/README.md (1)
106-117: LGTM!Also applies to: 118-130
crates/cli/tests/coverage/installer_tests.rs (1)
118-119: LGTM!crates/cli/src/launcher.rs (1)
568-575: LGTM!integrations/coding-agents/README.md (1)
47-50: LGTM!Also applies to: 88-106
crates/core/src/plugin.rs (1)
78-79: LGTM!Also applies to: 103-104, 131-132, 149-150, 167-168, 178-179, 201-219, 223-224, 900-905
docs/integrate-frameworks/coding-agent-hermes.md (1)
24-25: LGTM!Also applies to: 58-79, 100-101
crates/cli/tests/coverage/gateway_tests.rs (1)
5-5: LGTM!Also applies to: 83-83, 108-136
integrations/coding-agents/cursor/README.md (1)
42-43: LGTM!Also applies to: 69-82, 96-97
integrations/coding-agents/claude-code/README.md (1)
36-37: LGTM!Also applies to: 63-77, 90-91
crates/cli/tests/coverage/doctor_tests.rs (1)
188-189: LGTM!Also applies to: 243-257
docs/integrate-frameworks/coding-agent-codex.md (1)
25-26: LGTM!Also applies to: 56-57, 62-79, 86-87, 151-152
crates/cli/tests/coverage/setup_tests.rs (1)
78-92: LGTM!Also applies to: 145-146, 189-190, 201-205
crates/cli/tests/coverage/plugins_tests.rs (1)
1-122: LGTM!crates/core/tests/unit/observability/plugin_component_tests.rs (1)
11-13: LGTM!Also applies to: 58-79, 112-154, 201-281
crates/core/src/observability/plugin_component.rs (1)
102-103: LGTM!Also applies to: 144-145, 157-158, 179-180, 228-229, 235-236, 280-354, 408-445
docs/integrate-frameworks/coding-agent-gateway.md (1)
98-99: LGTM!Also applies to: 115-133, 145-147
docs/integrate-frameworks/coding-agent-cursor.md (1)
27-28: LGTM!Also applies to: 61-77, 85-86, 135-136
crates/cli/src/session.rs (1)
157-158: LGTM!Also applies to: 359-359, 465-467, 471-471, 496-500
crates/cli/tests/cli_tests.rs (1)
112-113: LGTM!Also applies to: 139-141, 156-157, 238-239
docs/integrate-frameworks/coding-agent-claude-code.md (1)
18-19: LGTM!Also applies to: 51-72, 79-80, 132-133
crates/cli/src/doctor.rs (1)
639-665: LGTM!crates/cli/tests/coverage/config_tests.rs (1)
151-191: LGTM!Also applies to: 193-260, 263-300, 303-518, 706-717, 726-761
crates/cli/src/plugins.rs (1)
63-145: LGTM!Also applies to: 147-253, 264-946
crates/cli/src/setup.rs (5)
14-14: LGTM!
6-8: LGTM!Also applies to: 86-89, 122-126, 288-289
186-188: LGTM!
299-299: LGTM!Also applies to: 303-303, 506-506, 658-658
410-412: LGTM!crates/cli/src/config.rs (8)
4-4: LGTM!Also applies to: 6-6, 9-9
80-82: LGTM!Also applies to: 151-182
192-201: LGTM!
525-526: LGTM!
543-551: LGTM!Also applies to: 949-965
659-674: LGTM!
915-940: LGTM!
247-248: LGTM!Also applies to: 415-416, 422-422, 456-457, 561-561, 605-607, 829-829, 863-863
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 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 `@crates/cli/src/plugins.rs`:
- Around line 482-487: The Reset shortcut currently calls reset_section whenever
reset_selected_field returns false, which wipes the section even if the "Back"
row is highlighted; change the handling inside the
MenuResponse::Shortcut(MenuShortcut::Reset, selected) arm so you only call
reset_section when the selected index actually corresponds to a real field
(i.e., not the "Back" entry). Concretely, either check that fields.get(selected)
is Some (or selected < fields.len()) before calling reset_section, or add a
small helper like is_field_selected(config, section, fields, selected) and only
call reset_section when that guard is true; otherwise just continue without
making destructive changes.
🪄 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: b4eb50ce-0bd1-4d15-bb12-6ba6bf1ba4c1
📒 Files selected for processing (2)
crates/cli/src/plugins.rscrates/cli/tests/coverage/plugins_tests.rs
📜 Review details
🧰 Additional context used
📓 Path-based instructions (7)
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-ffi-surface/SKILL.md)
**/*.rs: Runcargo fmt --allfor FFI work as it is Rust work
Runjust test-rustfor FFI validation
Runcargo clippy --workspace --all-targets -- -D warningsto enforce warnings-as-errors linting
**/*.rs: Runcargo fmt --allfor Rust code formatting
Runcargo clippy --workspace --all-targets -- -D warningsto enforce Rust linting with no warnings
Runjust test-rustas the shared-runtime build/test wrapper for Rust changesUse Rust snake_case naming convention for Rust code
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor Rust code formatting when Node changes touch Rust files
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting when Rust files changed as part of Node work
**/*.rs: Always runjust test-rustwhen any Rust code changes
Always runcargo fmt --allwhen any Rust code changes
Always runcargo clippy --workspace --all-targets -- -D warningswhen any Rust code changes
Files:
crates/cli/tests/coverage/plugins_tests.rscrates/cli/src/plugins.rs
**/*.{rs,go,js,ts,tsx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license headers in all Rust, Go, JavaScript, and TypeScript source files using C-style comment syntax
Files:
crates/cli/tests/coverage/plugins_tests.rscrates/cli/src/plugins.rs
**/*.{rs,py,go,js,ts,tsx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Use
SONAR_IGNORE_START/SONAR_IGNORE_ENDmarkers only for documented false positives that cannot be resolved in code; keep ignored blocks small, add explanatory comments, and require reviewer sign-off
Files:
crates/cli/tests/coverage/plugins_tests.rscrates/cli/src/plugins.rs
**/*.{js,ts,tsx,jsx,py,rs,go,java,c,cpp,h,cc,cxx,cs,rb,php,swift,kt}
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changed files must be formatted with the language-native formatter
Files:
crates/cli/tests/coverage/plugins_tests.rscrates/cli/src/plugins.rs
**/*.{py,js,ts,tsx,go,rs,md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Format changed files with the language-native formatter before the final lint/test pass
Files:
crates/cli/tests/coverage/plugins_tests.rscrates/cli/src/plugins.rs
**/*.{rs,py,js,ts,tsx,go}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
During iteration, prefer
uv run pre-commit run --files <changed files...>for targeted validation
Files:
crates/cli/tests/coverage/plugins_tests.rscrates/cli/src/plugins.rs
{crates/**/tests/**,python/tests/**,go/nemo_flow/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_flow/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/cli/tests/coverage/plugins_tests.rs
🔇 Additional comments (1)
crates/cli/tests/coverage/plugins_tests.rs (1)
1-139: LGTM!
Signed-off-by: Will Killian <wkillian@nvidia.com>
github-actions
Bot
added
size:XXL
There was a problem hiding this comment.
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/integrate-frameworks/coding-agent-codex.md`:
- Around line 127-130: The TOML examples use the invalid token “[features].hooks
= true”; fix by replacing every occurrence of that token with a valid TOML
form—either a single-line dotted key "features.hooks = true" or an explicit
table header "[features]" followed by "hooks = true" on the next line—so that
the hooks flag is properly nested under the features table in the docs.
In `@integrations/coding-agents/codex/README.md`:
- Around line 34-35: The README shows an invalid TOML key `[features].hooks =
true`; update the documentation and any setup logic that writes to
.codex/config.toml so it uses the correct dotted-key form (features.hooks =
true) when enabling hooks and ensure the text still references merging hook
entries into .codex/hooks.json; change any occurrence of `[features].hooks` to
`features.hooks` (e.g., in the README and the setup description that writes to
.codex/config.toml) to match the features.hooks flag referenced earlier.
In `@integrations/coding-agents/README.md`:
- Around line 28-29: The README contains an invalid TOML example using
`[features].hooks = true`; update the snippet to use valid TOML either by
converting it to a dotted key `features.hooks = true` or by using a table block
with `[features]` on one line and `hooks = true` on the next, so users copying
the example won't encounter TOML parse errors.
🪄 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: 36b481ab-5241-48fd-bf55-8c0529d72cc4
📒 Files selected for processing (7)
crates/cli/src/launcher.rscrates/cli/src/plugins.rscrates/cli/tests/coverage/launcher_tests.rscrates/cli/tests/coverage/plugins_tests.rsdocs/integrate-frameworks/coding-agent-codex.mdintegrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
📜 Review details
🧰 Additional context used
📓 Path-based instructions (29)
**/*.{md,rst,html,txt}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-brand-terminology.md)
**/*.{md,rst,html,txt}: Always spellNVIDIAin all caps. Do not useNvidia,nvidia,nVidia,nVIDIA, orNV.
Usean NVIDIAbefore a noun because the name starts with an 'en' sound.
Do not add a registered trademark symbol afterNVIDIAwhen 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 withNVIDIAon 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 withs, not an apostrophe, such asGPUs.
In headings, common acronyms can remain abbreviated. Spell out the term in the first or second sentence of the body.
Common terms such asCPU,GPU,PC,API, andUIusually do not need to be spelled out for developer audiences.
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-codex.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:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{md,rst,txt}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-guide.md)
**/*.{md,rst,txt}: SpellNVIDIAin all caps. Do not useNvidia,nvidia, orNV.
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.
Usecanfor possibility and reservemayfor permission.
Useafterfor temporal relationships instead ofonce.
Preferrefer tooverseewhen the wording points readers to another resource.
Avoid culture-specific idioms, unnecessary Latinisms, jokes, and marketing exaggeration in technical documentation.
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 documentation unless the source, platform, or legal guidance explicitly requires them.
Do not add trademark symbols to NeMo Flow learning documentation by default.
Do not rewrite API names, package names, command flags, or code literals for style reasons.
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{md,markdown,rst}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-technical-docs.md)
**/*.{md,markdown,rst}: 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
Use monospace formatting for code elements, commands, parameters, package names, and expressions
Use monospace formatting for directories, file names, and paths
Use angle brackets inside monospace for variables inside paths, such as/home/<username>/.login
Use quotation marks for error messages and strings in documentation
Use bold formatting for UI buttons, menus, fields, and labels in documentation
Use angle brackets between UI labels for menu paths, such as File > Save As
Use italics for new terms on first use in documentation
Use italics for publication titles in documentation
Use plain text formatting for keyboard shortcuts in documentation
Prefer[NVIDIA/NeMo](link)format for GitHub repository references over generic phrases 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 in documentation
Avoid generic link anchors such as 'here,' 'this page,' and 'read more' in documentation
Include the acronym in link text if a linked term includes an acronym
Do not link long sentences or multiple sentences in documentation
Avoid links that pull readers away from a procedure unles...
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{html,md}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license headers in HTML and Markdown files using HTML comment syntax
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-codex.md
**/README.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Update relevant crate or package README when that surface changed
Relevant package or crate README.md files must be updated when examples or binding guidance changes
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
**/*.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Run Markdown link checking via
lycheeforREADME.md,CONTRIBUTING.md, anddocs/through pre-commit hooks
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{md,markdown,py,sh,bash,js,ts,java,cpp,go,rust}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Keep package names, repo references, and build commands current in documentation
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{md,markdown,py,sh,bash}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Keep stable user-facing wrappers at scripts/ root in docs and examples; only point at namespaced helper paths when documenting internal maintenance work
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-codex.md
**/*.{md,markdown,py,sh,bash,js,ts,example}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Example commands must match current package names and paths
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-codex.md
**/{integrations,integration,*-integration}/**
📄 CodeRabbit inference engine (.agents/skills/contribute-integration/SKILL.md)
**/{integrations,integration,*-integration}/**: Keep NeMo Flow optional in framework integrations
Preserve the framework's original behavior when NeMo Flow is absent
Wrap tool and LLM paths at the correct framework boundary
Integration pattern must followdocs/integrate-frameworks/adding-scopes.md
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
**/*.{md,txt,rst}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/SKILL.md)
**/*.{md,txt,rst}: Ensure commands, package names, file paths, and APIs in documentation are correct and not stale; flag incorrect or outdated information as blocking issues
Ensure examples and procedures in documentation will execute successfully with current APIs and commands
Use consistent user-facing terminology throughout documentation that matches current repo terminology
Capitalize NVIDIA correctly in all documentation and public-facing text
Format code, commands, paths, and filenames as inline code (monospace) in documentation
Use descriptive anchor text for links instead of bare URLs or weak labels like 'here' in documentation
Prefer active voice, present tense, short sentences, and plain English in documentation
Structure documentation procedures as imperative steps that are easy to scan and not too long for a single sequence
Prefer 'after' instead of 'once' for temporal references in documentation
Use 'can' instead of 'may' when describing possibility (rather than permission) in documentation
Avoid ambiguous numeric dates and ordinal dates in documentation body text
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.mddocs/integrate-frameworks/coding-agent-codex.md
{README.md,docs/index.md,**/README.md}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/SKILL.md)
Update entry-point documentation (README.md, docs/index.md, package READMEs, binding-level source READMEs) whenever public behavior changes
Files:
integrations/coding-agents/README.mdintegrations/coding-agents/codex/README.md
**/*.{py,js,ts,tsx,go,rs,md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Format changed files with the language-native formatter before the final lint/test pass
Files:
integrations/coding-agents/README.mdcrates/cli/tests/coverage/plugins_tests.rsintegrations/coding-agents/codex/README.mdcrates/cli/tests/coverage/launcher_tests.rscrates/cli/src/launcher.rsdocs/integrate-frameworks/coding-agent-codex.mdcrates/cli/src/plugins.rs
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-ffi-surface/SKILL.md)
**/*.rs: Runcargo fmt --allfor FFI work as it is Rust work
Runjust test-rustfor FFI validation
Runcargo clippy --workspace --all-targets -- -D warningsto enforce warnings-as-errors linting
**/*.rs: Runcargo fmt --allfor Rust code formatting
Runcargo clippy --workspace --all-targets -- -D warningsto enforce Rust linting with no warnings
Runjust test-rustas the shared-runtime build/test wrapper for Rust changesUse Rust snake_case naming convention for Rust code
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor Rust code formatting when Node changes touch Rust files
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting when Rust files changed as part of Node work
**/*.rs: Always runjust test-rustwhen any Rust code changes
Always runcargo fmt --allwhen any Rust code changes
Always runcargo clippy --workspace --all-targets -- -D warningswhen any Rust code changes
Files:
crates/cli/tests/coverage/plugins_tests.rscrates/cli/tests/coverage/launcher_tests.rscrates/cli/src/launcher.rscrates/cli/src/plugins.rs
**/*.{rs,go,js,ts,tsx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license headers in all Rust, Go, JavaScript, and TypeScript source files using C-style comment syntax
Files:
crates/cli/tests/coverage/plugins_tests.rscrates/cli/tests/coverage/launcher_tests.rscrates/cli/src/launcher.rscrates/cli/src/plugins.rs
**/*.{rs,py,go,js,ts,tsx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Use
SONAR_IGNORE_START/SONAR_IGNORE_ENDmarkers only for documented false positives that cannot be resolved in code; keep ignored blocks small, add explanatory comments, and require reviewer sign-off
Files:
crates/cli/tests/coverage/plugins_tests.rscrates/cli/tests/coverage/launcher_tests.rscrates/cli/src/launcher.rscrates/cli/src/plugins.rs
**/*.{js,ts,tsx,jsx,py,rs,go,java,c,cpp,h,cc,cxx,cs,rb,php,swift,kt}
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changed files must be formatted with the language-native formatter
Files:
crates/cli/tests/coverage/plugins_tests.rscrates/cli/tests/coverage/launcher_tests.rscrates/cli/src/launcher.rscrates/cli/src/plugins.rs
**/*.{rs,py,js,ts,tsx,go}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
During iteration, prefer
uv run pre-commit run --files <changed files...>for targeted validation
Files:
crates/cli/tests/coverage/plugins_tests.rscrates/cli/tests/coverage/launcher_tests.rscrates/cli/src/launcher.rscrates/cli/src/plugins.rs
{crates/**/tests/**,python/tests/**,go/nemo_flow/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_flow/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/cli/tests/coverage/plugins_tests.rscrates/cli/tests/coverage/launcher_tests.rs
docs/**/*.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Run
./scripts/build-docs.shfor documentation site changes
docs/**/*.md: Relevant getting-started or reference docs must be updated when examples change
Release-policy docs must point to GitHub Releases as the only release-history source of truth
docs/**/*.md: Use title case for headings in technical documentation
Introduce code blocks, tables, and lists with complete lead-in sentences in documentation
Files:
docs/integrate-frameworks/coding-agent-codex.md
{RELEASING.md,CHANGELOG.md,docs/**/*.md}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Keep release-process and release-notes guidance in repo-maintainer docs such as RELEASING.md, not as user-facing docs pages or CHANGELOG.md
Files:
docs/integrate-frameworks/coding-agent-codex.md
docs/integrate-frameworks/**/*.md
📄 CodeRabbit inference engine (.agents/skills/contribute-integration/SKILL.md)
Documentation must be updated if activation or usage of the integration changed
Files:
docs/integrate-frameworks/coding-agent-codex.md
{scripts/*.sh,docs/**/*.md}
📄 CodeRabbit inference engine (.agents/skills/contribute-integration/SKILL.md)
Use root
./scripts/*.shcommands in docs and contributor guidance as documented, with implementations underscripts/third-party/
Files:
docs/integrate-frameworks/coding-agent-codex.md
{docs/**,examples/**,crates/adaptive/**,python/nemo_flow/**,go/nemo_flow/**,**/{example,component}.{ts,tsx,js,rs,py,go}}
📄 CodeRabbit inference engine (.agents/skills/maintain-optimizer/SKILL.md)
Any new adaptive component kind must have documentation, examples, and binding coverage across all supported languages
Files:
docs/integrate-frameworks/coding-agent-codex.md
{README*,CHANGELOG*,docs/**/*.{md,rst,txt},examples/**/*,*.md}
📄 CodeRabbit inference engine (.agents/skills/rename-surfaces/SKILL.md)
Update documentation, examples, and getting-started guides with new package/module/crate names after rename operations
Files:
docs/integrate-frameworks/coding-agent-codex.md
{README.md,docs/**/*.md,examples/**/*.{js,ts,py,go,rs}}
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
Keep documentation and examples synchronized with current install, import, and build commands
Files:
docs/integrate-frameworks/coding-agent-codex.md
{README.md,CONTRIBUTING.md,docs/**/*.md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
For docs-only changes, run targeted checks only if commands, package names, or examples changed. Use
just docsfor docs-site builds andjust docs-linkcheckwhen links changed
Files:
docs/integrate-frameworks/coding-agent-codex.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/integrate-frameworks/coding-agent-codex.md
🔇 Additional comments (5)
crates/cli/src/launcher.rs (1)
8-9: LGTM!Also applies to: 296-298, 526-540, 581-587, 602-683, 757-777
crates/cli/tests/coverage/launcher_tests.rs (1)
229-249: LGTM!Also applies to: 252-309
crates/cli/src/plugins.rs (2)
334-340: Interactive mode still does not guard the output terminal stream.
ensure_ttychecks only stdin, but the menu renderer usesTerm::stderr(). Redirected stderr can still fail mid-session.
492-497: Reset shortcut still clears the whole section from non-field rows.When
reset_selected_fieldreturnsfalse, the code still callsreset_section, so pressingron rows like Back remains unexpectedly destructive.crates/cli/tests/coverage/plugins_tests.rs (1)
6-158: LGTM!
Signed-off-by: Will Killian <wkillian@nvidia.com>
PR NVIDIA#98 moved gateway LLM traffic onto the managed core execution APIs. Non-streaming calls still close before returning, but streaming calls now rely on LlmStreamWrapper to emit the LLM end event. When Codex drops or cancels a streaming response before the stream is fully polled, the wrapper was dropped without closing the LLM span. Close streaming LLM spans from LlmStreamWrapper::drop so partial streams still emit an end event. Also close any remaining CLI sessions before gateway plugin teardown so Codex transparent runs that do not emit a native SessionEnd still pop active tool, subagent, and agent scopes while exporters are registered. Add focused regression coverage for partial stream drops and Codex gateway shutdown without a SessionEnd hook. Signed-off-by: Ajay Thorve <athorve@nvidia.com>
AjayThorve
force-pushed
the
wkk_nemo-flow-plugins-edit
branch
from
9d2a885 to
74a30c5
Compare
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 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 `@crates/cli/src/session.rs`:
- Around line 333-343: close_all currently aborts teardown on the first
close_for_shutdown error, leaving remaining sessions unclosed; change close_all
to iterate all sessions returned from self.inner.lock().await.drain() and
attempt session.close_for_shutdown(reason).await for each, capturing errors but
not returning immediately; after the loop, if any session close returned Err,
return that error (or aggregate/convert to a single CliError), otherwise return
Ok(()). Reference the close_all method and the close_for_shutdown call to locate
where to implement per-session error capture and deferred return.
🪄 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: 8ae40c19-033e-415f-8389-18e5772a3b0d
📒 Files selected for processing (5)
crates/cli/src/server.rscrates/cli/src/session.rscrates/cli/tests/coverage/session_tests.rscrates/core/src/stream.rscrates/core/tests/integration/stream_tests.rs
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (28)
- GitHub Check: WebAssembly / Test (windows-arm64)
- GitHub Check: WebAssembly / Test (linux-arm64)
- GitHub Check: Python / Test (linux-amd64)
- GitHub Check: WebAssembly / Test (windows-amd64)
- GitHub Check: Go / Test (macos-arm64)
- GitHub Check: WebAssembly / Test (macos-arm64)
- GitHub Check: Node.js / Test (windows-amd64)
- GitHub Check: WebAssembly / Test (linux-amd64)
- GitHub Check: Python / Test (windows-amd64)
- GitHub Check: Python / Test (windows-arm64)
- GitHub Check: License Diff / Run
- GitHub Check: Python / Test (linux-arm64)
- GitHub Check: Node.js / Test (linux-arm64)
- GitHub Check: Node.js / Test (windows-arm64)
- GitHub Check: Python / Test (macos-arm64)
- GitHub Check: Node.js / Test (linux-amd64)
- GitHub Check: Rust / Test (windows-arm64)
- GitHub Check: Rust / Test (linux-arm64)
- GitHub Check: Go / Test (linux-amd64)
- GitHub Check: Rust / Test (windows-amd64)
- GitHub Check: Node.js / Test (macos-arm64)
- GitHub Check: Rust / Test (linux-amd64)
- GitHub Check: Documentation / Build
- GitHub Check: Rust / Test (macos-arm64)
- GitHub Check: Go / Test (linux-arm64)
- GitHub Check: Go / Test (windows-arm64)
- GitHub Check: Go / Test (windows-amd64)
- GitHub Check: OpenClaw / Test
🧰 Additional context used
📓 Path-based instructions (12)
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-ffi-surface/SKILL.md)
**/*.rs: Runcargo fmt --allfor FFI work as it is Rust work
Runjust test-rustfor FFI validation
Runcargo clippy --workspace --all-targets -- -D warningsto enforce warnings-as-errors linting
**/*.rs: Runcargo fmt --allfor Rust code formatting
Runcargo clippy --workspace --all-targets -- -D warningsto enforce Rust linting with no warnings
Runjust test-rustas the shared-runtime build/test wrapper for Rust changesUse Rust snake_case naming convention for Rust code
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor Rust code formatting when Node changes touch Rust files
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting when Rust files changed as part of Node work
**/*.rs: Always runjust test-rustwhen any Rust code changes
Always runcargo fmt --allwhen any Rust code changes
Always runcargo clippy --workspace --all-targets -- -D warningswhen any Rust code changes
Files:
crates/core/src/stream.rscrates/core/tests/integration/stream_tests.rscrates/cli/src/server.rscrates/cli/src/session.rscrates/cli/tests/coverage/session_tests.rs
**/*.{rs,go,js,ts,tsx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license headers in all Rust, Go, JavaScript, and TypeScript source files using C-style comment syntax
Files:
crates/core/src/stream.rscrates/core/tests/integration/stream_tests.rscrates/cli/src/server.rscrates/cli/src/session.rscrates/cli/tests/coverage/session_tests.rs
**/*.{rs,py,go,js,ts,tsx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Use
SONAR_IGNORE_START/SONAR_IGNORE_ENDmarkers only for documented false positives that cannot be resolved in code; keep ignored blocks small, add explanatory comments, and require reviewer sign-off
Files:
crates/core/src/stream.rscrates/core/tests/integration/stream_tests.rscrates/cli/src/server.rscrates/cli/src/session.rscrates/cli/tests/coverage/session_tests.rs
**/*.{js,ts,tsx,jsx,py,rs,go,java,c,cpp,h,cc,cxx,cs,rb,php,swift,kt}
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changed files must be formatted with the language-native formatter
Files:
crates/core/src/stream.rscrates/core/tests/integration/stream_tests.rscrates/cli/src/server.rscrates/cli/src/session.rscrates/cli/tests/coverage/session_tests.rs
crates/{core,adaptive}/**
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changes to
crates/coreorcrates/adaptivemust run the full language matrix
Files:
crates/core/src/stream.rscrates/core/tests/integration/stream_tests.rs
{crates/core,crates/adaptive}/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-wasm-binding/SKILL.md)
If the change touched shared runtime semantics in
crates/coreorcrates/adaptive, also usevalidate-change
Files:
crates/core/src/stream.rscrates/core/tests/integration/stream_tests.rs
crates/core/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
When
crates/corechanges, run the full validation matrix across Rust, Python, Go, Node.js, and WebAssembly
crates/core/**/*.rs: UseJson = serde_json::Valuein Rust-facing runtime APIs where the existing code expects JSON payloads.
UseResult<T>withFlowErrorin core runtime paths. Keep errors explicit and binding-appropriate at the wrapper layer.
Files:
crates/core/src/stream.rscrates/core/tests/integration/stream_tests.rs
**/*.{py,js,ts,tsx,go,rs,md}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
Format changed files with the language-native formatter before the final lint/test pass
Files:
crates/core/src/stream.rscrates/core/tests/integration/stream_tests.rscrates/cli/src/server.rscrates/cli/src/session.rscrates/cli/tests/coverage/session_tests.rs
**/*.{rs,py,js,ts,tsx,go}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
During iteration, prefer
uv run pre-commit run --files <changed files...>for targeted validation
Files:
crates/core/src/stream.rscrates/core/tests/integration/stream_tests.rscrates/cli/src/server.rscrates/cli/src/session.rscrates/cli/tests/coverage/session_tests.rs
crates/{core,adaptive}/**/*.rs
⚙️ CodeRabbit configuration file
crates/{core,adaptive}/**/*.rs: Review the Rust runtime for async correctness, scope isolation, middleware ordering, and event lifecycle regressions.
Pay close attention to task-local/thread-local scope propagation, callback lifetimes, stream finalization, and root_uuid isolation.
Public API changes should preserve existing behavior unless tests and docs show the intended migration path.
Files:
crates/core/src/stream.rscrates/core/tests/integration/stream_tests.rs
**/{integrations,integration,*-integration}/**
📄 CodeRabbit inference engine (.agents/skills/contribute-integration/SKILL.md)
**/{integrations,integration,*-integration}/**: Keep NeMo Flow optional in framework integrations
Preserve the framework's original behavior when NeMo Flow is absent
Wrap tool and LLM paths at the correct framework boundary
Integration pattern must followdocs/integrate-frameworks/adding-scopes.md
Files:
crates/core/tests/integration/stream_tests.rs
{crates/**/tests/**,python/tests/**,go/nemo_flow/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_flow/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/core/tests/integration/stream_tests.rscrates/cli/tests/coverage/session_tests.rs
🔇 Additional comments (2)
crates/core/src/stream.rs (1)
213-217: LGTM!crates/core/tests/integration/stream_tests.rs (1)
207-257: LGTM!
Document nemo-flow-cli as the published install path and keep the README wording concise. Lead the coding-agent gateway docs with the new agent shortcut commands while keeping the explicit run form for custom launchers. Remove the benchmark/eval recipe from user-facing docs. Signed-off-by: Ajay Thorve <athorve@nvidia.com>
close_all drained every session but returned on the first close_for_shutdown failure, so any later drained sessions skipped shutdown cleanup. Capture the first close error, keep closing the remaining sessions, and return the captured error after the loop. Add a regression test that proves a later valid session still closes after an earlier close fails. Signed-off-by: Ajay Thorve <athorve@nvidia.com>
Salonijain27
left a comment
Salonijain27
left a comment
There was a problem hiding this comment.
Approved from a dependency point of view
|
/merge |
3 participants
Overview
Adds a plugin-driven observability configuration flow centered on
plugins.toml, including an interactive editor for the built-in Observability component and a clean removal of legacy exporter configuration surfaces.Details
nemo-flow plugins editwith user/project/global scope handling, keyboard-driven menus, preview, save, reset, clear, and schema/type-backed editor metadata from core config types.plugins.toml, removes legacy exporter flags/config parsing, and updates doctor/setup/session handling accordingly.plugins.toml, including layered system/project/user merge behavior, duplicate component-kind checks, and clearer legacy config errors.Validation run locally:
cargo fmt --checkcargo clippy -p nemo-flow-cli -- -D warningscargo test -p nemo-flow-clicargo test -p nemo-flow --features schemajust docsjust test-rustWhere should the reviewer start?
Start with
crates/cli/src/plugins.rsfor the interactiveplugins.tomleditor, then reviewcrates/cli/src/config.rsfor plugin file discovery and merge behavior, anddocs/build-plugins/plugin-configuration-files.mdfor the documented operator contract.Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)
Summary by CodeRabbit
New Features
Documentation
Breaking Changes
Other