feat: add core observability plugin#89
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:
WalkthroughThis PR adds a built-in ChangesBuilt-In Observability Plugin Implementation and Bindings
Estimated code review effort🎯 4 (Complex) | ⏱️ ~60 minutes 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
github-actions
Bot
added
size:XL
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 5
🤖 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/core/README.md`:
- Around line 47-48: Replace the bare acronym "ATOF" in the README's
observability bullet with its expanded form on first mention (i.e., write the
full term followed by " (ATOF)"), so the line reads something like "Built-in
observability plugin: Configure first-party <Full Term> (ATOF), ATIF,
OpenTelemetry, and OpenInference exporters from the core crate," and thereafter
continue using "ATOF"; update only the first occurrence of ATOF in the sentence
that lists ATOF, ATIF, OpenTelemetry, and OpenInference exporters.
In `@crates/core/src/observability/plugin_component.rs`:
- Around line 525-539: When a top-level agent End event is successfully
processed, finalize and evict its per-agent state instead of keeping it forever:
in observe_scope (and after the write_atif_file(agent) succeeds in the branch
where event.uuid() == agent_uuid && event.scope_category() ==
Some(ScopeCategory::End)), remove the agent entry from self.agents and also
remove any related entry in self.scope_subscribers (and drop/clear
agent.observed_events) so completed agents don’t accumulate; keep the existing
behavior when write_atif_file returns Err (it already sets self.last_error).
In `@crates/core/src/plugin.rs`:
- Around line 736-738: The built-in registration
(ensure_builtin_plugins_registered) must be run only once to avoid taking the
registry write lock on every call; replace the current direct call to
register_observability_component() with a one-time guard using a static
synchronization primitive (e.g., std::sync::OnceLock or
once_cell::sync::OnceCell) that stores the Result<()> from
register_observability_component so subsequent calls to
ensure_builtin_plugins_registered simply return the stored Result; update
ensure_builtin_plugins_registered, and ensure callers list_plugin_kinds,
lookup_plugin, and validate_plugin_config keep calling
ensure_builtin_plugins_registered but now incur no repeated registration work.
In `@docs/getting-started/configuration.md`:
- Around line 37-39: The "Export Observability Data" link currently points to
../export-observability-data/code-examples.md but the link text implies the
section landing/about page; update the link target so the anchor text matches
the destination by changing the href for "Export Observability Data" to
../export-observability-data/about.md (alternatively, if you prefer to keep
code-examples.md, rename the anchor text to "Observability Code Examples") so
the documentation navigation is accurate.
In `@README.md`:
- Around line 67-68: Update the README top-level description to spell out ATOF
on first use: replace the standalone "ATOF" in the sentence containing "Built-in
observability plugin" with its full form followed by the acronym in parentheses
(e.g., "Automated Telemetry Observability Framework (ATOF)"), then keep using
"ATOF" thereafter; edit the line that mentions "ATOF, ATIF, OpenTelemetry, and
OpenInference exporters" to use the spelled-out term for ATOF while preserving
the rest of the phrasing.
🪄 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: 6b15eb86-d758-49b1-855c-390df166f7a7
📒 Files selected for processing (40)
README.mdcrates/core/README.mdcrates/core/src/observability/mod.rscrates/core/src/observability/plugin_component.rscrates/core/src/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/ffi/nemo_flow.hcrates/ffi/src/api/observability.rscrates/ffi/tests/unit/api/core_tests.rscrates/node/README.mdcrates/node/observability.d.tscrates/node/observability.jscrates/node/package.jsoncrates/node/tests/observability_plugin_tests.mjscrates/wasm/scripts/prepare_pkg.mjscrates/wasm/tests-js/observability_tests.mjscrates/wasm/wrappers/esm/observability.d.tscrates/wasm/wrappers/esm/observability.jscrates/wasm/wrappers/nodejs/observability.jsdocs/about/concepts/plugins.mddocs/about/concepts/subscribers.mddocs/export-observability-data/about.mddocs/export-observability-data/atif.mddocs/export-observability-data/basic-guide.mddocs/export-observability-data/code-examples.mddocs/export-observability-data/observability-plugin.mddocs/getting-started/configuration.mddocs/index.mddocs/reference/api/nodejs/index.mddocs/reference/api/python/index.mddocs/reference/api/rust/index.mdgo/nemo_flow/observability_plugin.gogo/nemo_flow/observability_plugin_test.gopython/nemo_flow/README.mdpython/nemo_flow/__init__.pypython/nemo_flow/__init__.pyipython/nemo_flow/observability.pypython/nemo_flow/observability.pyipython/tests/test_observability_plugin.pyscripts/docs/build_node_docs_artifacts.mjs
📜 Review details
🧰 Additional context used
📓 Path-based instructions (68)
**/*.{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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mdcrates/core/README.mdpython/nemo_flow/README.mdcrates/node/README.mddocs/export-observability-data/basic-guide.mdREADME.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mdcrates/core/README.mdpython/nemo_flow/README.mdcrates/node/README.mddocs/export-observability-data/basic-guide.mdREADME.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mdcrates/core/README.mdpython/nemo_flow/README.mdcrates/node/README.mddocs/export-observability-data/basic-guide.mdREADME.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mdcrates/core/README.mdpython/nemo_flow/README.mdcrates/node/README.mddocs/export-observability-data/basic-guide.mdREADME.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.md
**/*.{html,md}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license headers in HTML and Markdown files using HTML comment syntax
Files:
docs/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mdcrates/core/README.mdpython/nemo_flow/README.mdcrates/node/README.mddocs/export-observability-data/basic-guide.mdREADME.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.md
docs/reference/**/*.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Update relevant reference documentation for any public API changes
Files:
docs/reference/api/rust/index.mddocs/reference/api/python/index.mddocs/reference/api/nodejs/index.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mddocs/export-observability-data/basic-guide.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.md
**/*.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Run Markdown link checking via
lycheeforREADME.md,CONTRIBUTING.md, anddocs/through pre-commit hooks
Files:
docs/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mdcrates/core/README.mdpython/nemo_flow/README.mdcrates/node/README.mddocs/export-observability-data/basic-guide.mdREADME.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mdcrates/core/README.mdpython/nemo_flow/README.mdcrates/node/README.mddocs/export-observability-data/basic-guide.mdREADME.mdcrates/node/observability.d.tscrates/node/observability.jsdocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mdpython/nemo_flow/observability.pypython/nemo_flow/__init__.pycrates/wasm/wrappers/nodejs/observability.jscrates/wasm/wrappers/esm/observability.d.tsgo/nemo_flow/observability_plugin.gocrates/wasm/wrappers/esm/observability.jsdocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mdpython/tests/test_observability_plugin.pygo/nemo_flow/observability_plugin_test.godocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mddocs/export-observability-data/basic-guide.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mdcrates/core/README.mdpython/nemo_flow/README.mdcrates/node/README.mddocs/export-observability-data/basic-guide.mdREADME.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mdpython/nemo_flow/observability.pypython/nemo_flow/__init__.pydocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mdpython/tests/test_observability_plugin.pydocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mdcrates/core/README.mdpython/nemo_flow/README.mdcrates/node/README.mddocs/export-observability-data/basic-guide.mdREADME.mdcrates/node/observability.d.tscrates/node/observability.jsdocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mdpython/nemo_flow/observability.pypython/nemo_flow/__init__.pycrates/wasm/wrappers/nodejs/observability.jscrates/wasm/wrappers/esm/observability.d.tscrates/wasm/wrappers/esm/observability.jsdocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mdpython/tests/test_observability_plugin.pydocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mddocs/export-observability-data/basic-guide.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mdpython/nemo_flow/__init__.pyipython/nemo_flow/README.mddocs/export-observability-data/basic-guide.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mdpython/nemo_flow/observability.pypython/nemo_flow/__init__.pygo/nemo_flow/observability_plugin.godocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mdpython/nemo_flow/observability.pyigo/nemo_flow/observability_plugin_test.godocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mddocs/export-observability-data/basic-guide.mdREADME.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mdcrates/core/README.mdpython/nemo_flow/README.mdcrates/node/README.mddocs/export-observability-data/basic-guide.mdREADME.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mddocs/export-observability-data/basic-guide.mdREADME.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mdcrates/core/README.mdpython/nemo_flow/README.mdcrates/node/README.mddocs/export-observability-data/basic-guide.mdREADME.mdcrates/node/observability.d.tscrates/core/src/observability/mod.rscrates/node/observability.jsdocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mdcrates/core/src/plugin.rspython/nemo_flow/observability.pypython/nemo_flow/__init__.pycrates/wasm/wrappers/nodejs/observability.jscrates/wasm/wrappers/esm/observability.d.tsgo/nemo_flow/observability_plugin.gocrates/wasm/wrappers/esm/observability.jsdocs/about/concepts/subscribers.mdcrates/ffi/src/api/observability.rsdocs/about/concepts/plugins.mdcrates/core/tests/unit/observability/plugin_component_tests.rspython/tests/test_observability_plugin.pycrates/ffi/tests/unit/api/core_tests.rsgo/nemo_flow/observability_plugin_test.godocs/export-observability-data/code-examples.mdcrates/core/src/observability/plugin_component.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mddocs/export-observability-data/basic-guide.mdREADME.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.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/reference/api/rust/index.mddocs/index.mddocs/reference/api/python/index.mddocs/export-observability-data/atif.mddocs/getting-started/configuration.mddocs/export-observability-data/about.mddocs/export-observability-data/basic-guide.mdREADME.mddocs/reference/api/nodejs/index.mddocs/export-observability-data/observability-plugin.mddocs/about/concepts/subscribers.mddocs/about/concepts/plugins.mddocs/export-observability-data/code-examples.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.mdREADME.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/core/README.mdpython/nemo_flow/README.mdcrates/node/README.mdREADME.md
crates/{python,ffi,node,wasm}/**/*
⚙️ CodeRabbit configuration file
crates/{python,ffi,node,wasm}/**/*: Treat binding changes as public API changes. Check for parity with the other language bindings, FFI ownership/lifetime safety,
callback error propagation, stable type conversion, and consistent async/stream semantics.
Flag changes that update one binding without corresponding tests or documentation for the same surface elsewhere.
Files:
crates/wasm/tests-js/observability_tests.mjscrates/node/README.mdcrates/node/observability.d.tscrates/node/observability.jscrates/ffi/nemo_flow.hcrates/node/package.jsoncrates/wasm/wrappers/nodejs/observability.jscrates/wasm/wrappers/esm/observability.d.tscrates/wasm/wrappers/esm/observability.jscrates/node/tests/observability_plugin_tests.mjscrates/ffi/src/api/observability.rscrates/ffi/tests/unit/api/core_tests.rscrates/wasm/scripts/prepare_pkg.mjs
docs/{about/concepts/subscribers,export-observability-data/about}.md
📄 CodeRabbit inference engine (.agents/skills/maintain-observability/SKILL.md)
Ensure examples and documentation in
docs/about/concepts/subscribers.mdanddocs/export-observability-data/about.mdreflect the same lifecycle: create, register, run, deregister, flush, shutdown
Files:
docs/export-observability-data/about.mddocs/about/concepts/subscribers.md
docs/{about/concepts/subscribers,export-observability-data/{about,code-examples}}.md
📄 CodeRabbit inference engine (.agents/skills/maintain-observability/SKILL.md)
Update documentation and examples in
docs/about/concepts/subscribers.md,docs/export-observability-data/about.md, anddocs/export-observability-data/code-examples.mdin the same branch when making observability changes
Files:
docs/export-observability-data/about.mddocs/about/concepts/subscribers.mddocs/export-observability-data/code-examples.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:
crates/core/README.mdpython/nemo_flow/README.mdcrates/node/README.mdREADME.md
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/README.mdcrates/core/src/observability/mod.rscrates/core/src/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.rs
python/nemo_flow/**/*.pyi
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Update Python type stubs in the relevant
python/nemo_flow/*.pyimodules when adding public API surface
Files:
python/nemo_flow/__init__.pyipython/nemo_flow/observability.pyi
python/nemo_flow/**/*
⚙️ CodeRabbit configuration file
python/nemo_flow/**/*: Review Python wrapper changes for typed API consistency, contextvars-based scope isolation, async behavior, and parity with the native extension.
Stubs and runtime implementations should stay aligned.
Files:
python/nemo_flow/__init__.pyipython/nemo_flow/README.mdpython/nemo_flow/observability.pypython/nemo_flow/__init__.pypython/nemo_flow/observability.pyi
crates/node/**
📄 CodeRabbit inference engine (.agents/skills/test-node-binding/SKILL.md)
Run
just test-nodefor the normal dev/test loop when working on Node binding changes
Files:
crates/node/README.mdcrates/node/observability.d.tscrates/node/observability.jscrates/node/package.jsoncrates/node/tests/observability_plugin_tests.mjs
README.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Update README.md to reflect current workspace members and top-level documentation for changes affecting public behavior, bindings, examples, or workspace structure
Files:
README.md
**/*.{js,ts,tsx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Use camelCase naming convention for Node.js code
Files:
crates/node/observability.d.tscrates/node/observability.jscrates/wasm/wrappers/nodejs/observability.jscrates/wasm/wrappers/esm/observability.d.tscrates/wasm/wrappers/esm/observability.js
**/*.{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/node/observability.d.tscrates/core/src/observability/mod.rscrates/node/observability.jscrates/core/src/plugin.rscrates/wasm/wrappers/nodejs/observability.jscrates/wasm/wrappers/esm/observability.d.tsgo/nemo_flow/observability_plugin.gocrates/wasm/wrappers/esm/observability.jscrates/ffi/src/api/observability.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/ffi/tests/unit/api/core_tests.rsgo/nemo_flow/observability_plugin_test.gocrates/core/src/observability/plugin_component.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/node/observability.d.tscrates/core/src/observability/mod.rscrates/node/observability.jscrates/core/src/plugin.rspython/nemo_flow/observability.pypython/nemo_flow/__init__.pycrates/wasm/wrappers/nodejs/observability.jscrates/wasm/wrappers/esm/observability.d.tsgo/nemo_flow/observability_plugin.gocrates/wasm/wrappers/esm/observability.jscrates/ffi/src/api/observability.rscrates/core/tests/unit/observability/plugin_component_tests.rspython/tests/test_observability_plugin.pycrates/ffi/tests/unit/api/core_tests.rsgo/nemo_flow/observability_plugin_test.gocrates/core/src/observability/plugin_component.rs
{crates/adaptive/**,python/nemo_flow/{adaptive,plugin}.py,go/nemo_flow/{adaptive,**}/*.go,**/*.{ts,js,wasm}}
📄 CodeRabbit inference engine (.agents/skills/maintain-optimizer/SKILL.md)
Keep adaptive config schema, plugin lifecycle, and bindings in sync across crates/adaptive, core, bindings, Python (python/nemo_flow/adaptive.py and python/nemo_flow/plugin.py), Go (go/nemo_flow/adaptive and go/nemo_flow), and Node/WebAssembly helpers
Files:
crates/node/observability.d.tscrates/node/observability.jscrates/wasm/wrappers/nodejs/observability.jscrates/wasm/wrappers/esm/observability.d.tsgo/nemo_flow/observability_plugin.gocrates/wasm/wrappers/esm/observability.jsgo/nemo_flow/observability_plugin_test.go
**/*.{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/node/observability.d.tscrates/core/src/observability/mod.rscrates/node/observability.jscrates/ffi/nemo_flow.hcrates/core/src/plugin.rspython/nemo_flow/observability.pypython/nemo_flow/__init__.pycrates/wasm/wrappers/nodejs/observability.jscrates/wasm/wrappers/esm/observability.d.tsgo/nemo_flow/observability_plugin.gocrates/wasm/wrappers/esm/observability.jscrates/ffi/src/api/observability.rscrates/core/tests/unit/observability/plugin_component_tests.rspython/tests/test_observability_plugin.pycrates/ffi/tests/unit/api/core_tests.rsgo/nemo_flow/observability_plugin_test.gocrates/core/src/observability/plugin_component.rs
crates/node/**/*.{ts,tsx,js,jsx,json}
📄 CodeRabbit inference engine (.agents/skills/test-node-binding/SKILL.md)
Format changed Node files with
npm run format --workspace=nemo-flow-node
Files:
crates/node/observability.d.tscrates/node/observability.jscrates/node/package.json
crates/node/**/*.{ts,tsx}
📄 CodeRabbit inference engine (.agents/skills/test-node-binding/SKILL.md)
Run
npm run check:docstrings --workspace=nemo-flow-nodeto validate public API docstrings when Node surface documentation changes
Files:
crates/node/observability.d.ts
**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If Node.js language surface changed, always run Node.js test target even when Rust core did not change
Files:
crates/node/observability.d.tscrates/node/observability.jscrates/wasm/wrappers/nodejs/observability.jscrates/wasm/wrappers/esm/observability.d.tscrates/wasm/wrappers/esm/observability.js
**/*.{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/node/observability.d.tscrates/core/src/observability/mod.rscrates/node/observability.jscrates/core/src/plugin.rspython/nemo_flow/observability.pypython/nemo_flow/__init__.pycrates/wasm/wrappers/nodejs/observability.jscrates/wasm/wrappers/esm/observability.d.tsgo/nemo_flow/observability_plugin.gocrates/wasm/wrappers/esm/observability.jscrates/ffi/src/api/observability.rscrates/core/tests/unit/observability/plugin_component_tests.rspython/tests/test_observability_plugin.pycrates/ffi/tests/unit/api/core_tests.rsgo/nemo_flow/observability_plugin_test.gocrates/core/src/observability/plugin_component.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 lintingWhen Rust files changed as part of Python work, run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.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/observability/mod.rscrates/core/src/plugin.rscrates/ffi/src/api/observability.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/ffi/tests/unit/api/core_tests.rscrates/core/src/observability/plugin_component.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/observability/mod.rscrates/core/src/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/observability/mod.rscrates/core/src/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/observability/mod.rscrates/core/src/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.rs
crates/ffi/**
📄 CodeRabbit inference engine (.agents/skills/test-ffi-surface/SKILL.md)
Rebuild the FFI crate in release mode so the shared library and header stay in sync
Files:
crates/ffi/nemo_flow.hcrates/ffi/src/api/observability.rscrates/ffi/tests/unit/api/core_tests.rs
{crates/ffi/nemo_flow.h,crates/ffi/src/**/*.rs}
📄 CodeRabbit inference engine (.agents/skills/test-ffi-surface/SKILL.md)
Check the generated header diff when any exported symbol or type changed in the FFI surface
Files:
crates/ffi/nemo_flow.hcrates/ffi/src/api/observability.rs
**/*.h
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Prefix C FFI exports with
nemo_flow_
Files:
crates/ffi/nemo_flow.h
crates/ffi/nemo_flow.h
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Synchronize FFI header
crates/ffi/nemo_flow.hthrough Cargo/build.rs; pre-commit hooks enforce thisUse
nemo_flow_prefix naming convention for C FFI functions
Files:
crates/ffi/nemo_flow.h
{Cargo.toml,pyproject.toml,go/nemo_flow/go.mod,package.json,package-lock.json,crates/node/package.json}
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
Maintain consistent package names, import paths, and module names across Rust, Python, Go, Node, and WebAssembly workspaces in NeMo Flow
Files:
crates/node/package.json
{crates/node/package.json,package-lock.json}
📄 CodeRabbit inference engine (.agents/skills/update-project-version/SKILL.md)
Maintain alignment between
crates/node/package.jsonnpm package version and workspace-rootpackage-lock.json
Files:
crates/node/package.json
{.github/**/*.{yml,yaml},*.patch,scripts/**/*,*.sh,*.bat,Dockerfile*}
📄 CodeRabbit inference engine (.agents/skills/rename-surfaces/SKILL.md)
Update CI configuration, patch files, and build scripts with new functional identifiers after rename operations
Files:
scripts/docs/build_node_docs_artifacts.mjs
{.github/**,.gitlab-ci.yml,.pre-commit-config.yaml,justfile,scripts/**}
⚙️ CodeRabbit configuration file
{.github/**,.gitlab-ci.yml,.pre-commit-config.yaml,justfile,scripts/**}: Review automation changes for reproducibility, pinned versions where appropriate, secret handling, and consistency with the documented validation matrix.
Pay attention to commands that need generated native artifacts, FFI libraries, or platform-specific environment variables.
Files:
scripts/docs/build_node_docs_artifacts.mjs
{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.rsgo/nemo_flow/observability_plugin.gogo/nemo_flow/observability_plugin_test.go
**/*.py
📄 CodeRabbit inference engine (.agents/skills/test-python-binding/SKILL.md)
Format changed Python wrapper and test files with
uv run ruff format python
**/*.py: Use Ruff with rule sets E, F, W, I for Python linting
Use Ruff formatter for Python code with line length 120 and double quotes
Usetyfor Python type checking
Use snake_case naming convention for Python code
Include SPDX license headers in all Python source files using Python comment syntax
Files:
python/nemo_flow/observability.pypython/nemo_flow/__init__.pypython/tests/test_observability_plugin.py
python/nemo_flow/**/*.py
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Use
snake_casenaming convention for Python API implementations and wrappers
Files:
python/nemo_flow/observability.pypython/nemo_flow/__init__.py
python/**/*.py
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
python/**/*.py: If Python language surface changed, always run Python test target even when Rust core did not change
For Python changes, useuv run ruff format pythonto format Python files
Files:
python/nemo_flow/observability.pypython/nemo_flow/__init__.pypython/tests/test_observability_plugin.py
crates/wasm/{wrappers,tests-js,scripts}/**/*.{js,ts,jsx,tsx}
📄 CodeRabbit inference engine (.agents/skills/test-wasm-binding/SKILL.md)
Format changed WebAssembly JS/TS wrapper files with
npm run precommit:format --workspace=nemo-flow-node -- crates/wasm/wrappers crates/wasm/tests-js crates/wasm/scripts
Files:
crates/wasm/wrappers/nodejs/observability.jscrates/wasm/wrappers/esm/observability.d.tscrates/wasm/wrappers/esm/observability.js
crates/wasm/**/*.{ts,tsx,js,jsx}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
crates/wasm/**/*.{ts,tsx,js,jsx}: If WebAssembly language surface changed, always run WebAssembly test target even when Rust core did not change
For WebAssembly TypeScript/JavaScript changes, runnpm run precommit:format --workspace=nemo-flow-node -- crates/wasm/wrappers crates/wasm/tests-js crates/wasm/scripts
Files:
crates/wasm/wrappers/nodejs/observability.jscrates/wasm/wrappers/esm/observability.d.tscrates/wasm/wrappers/esm/observability.js
go/nemo_flow/**/*.go
📄 CodeRabbit inference engine (.agents/skills/test-go-binding/SKILL.md)
Format changed Go packages with
cd go/nemo_flow && go fmt ./...Use
PascalCasenaming convention for Go API implementationsFor Go binding changes, run
go fmt ./...within the Go module to format all Go files
Files:
go/nemo_flow/observability_plugin.gogo/nemo_flow/observability_plugin_test.go
**/*.go
📄 CodeRabbit inference engine (CONTRIBUTING.md)
**/*.go: Usegofmtfor Go code formatting
Usego vet ./...for Go static analysis
Use PascalCase naming convention for Go code
Files:
go/nemo_flow/observability_plugin.gogo/nemo_flow/observability_plugin_test.go
{crates/adaptive/**/*.rs,python/nemo_flow/adaptive.py,python/nemo_flow/plugin.py,go/nemo_flow/**/*.go,**/{helper,constructor,builder}.{ts,tsx,js}}
📄 CodeRabbit inference engine (.agents/skills/maintain-optimizer/SKILL.md)
Ensure typed helper constructors map cleanly to the same config document without divergence
Files:
go/nemo_flow/observability_plugin.gogo/nemo_flow/observability_plugin_test.go
{crates/adaptive/**/*.rs,python/nemo_flow/plugin.py,go/nemo_flow/**/*.go,**/{plugin,lifecycle}.{ts,tsx,js}}
📄 CodeRabbit inference engine (.agents/skills/maintain-optimizer/SKILL.md)
Maintain consistent plugin lifecycle across all language bindings (Rust, Python, Go, Node/WebAssembly)
Files:
go/nemo_flow/observability_plugin.gogo/nemo_flow/observability_plugin_test.go
go/**/*.go
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If Go language surface changed, always run Go test target even when Rust core did not change
Files:
go/nemo_flow/observability_plugin.gogo/nemo_flow/observability_plugin_test.go
go/nemo_flow/**/*
⚙️ CodeRabbit configuration file
go/nemo_flow/**/*: Review Go binding changes for cgo memory ownership, race safety, callback cleanup, idiomatic exported APIs, and parity with Rust/FFI behavior.
Any API change should include focused Go tests and consider race-test behavior.
Files:
go/nemo_flow/observability_plugin.gogo/nemo_flow/observability_plugin_test.go
{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/node/tests/observability_plugin_tests.mjscrates/core/tests/unit/observability/plugin_component_tests.rspython/tests/test_observability_plugin.pycrates/ffi/tests/unit/api/core_tests.rsgo/nemo_flow/observability_plugin_test.go
crates/ffi/src/api/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Add or update FFI wrappers in the relevant
crates/ffi/src/api/*.rsmodule withnemo_flow_prefix naming convention, re-export throughcrates/ffi/src/api/mod.rs, and ensure generatedcrates/ffi/nemo_flow.hstays correct
Files:
crates/ffi/src/api/observability.rs
**/test_*.py
📄 CodeRabbit inference engine (.agents/skills/test-python-binding/SKILL.md)
Run focused
pytestfirst when you know the affected area usingpytest -k "<pattern>"
Files:
python/tests/test_observability_plugin.py
{crates/wasm/package.json,crates/wasm/Cargo.toml,crates/wasm/scripts/prepare_pkg.mjs}
📄 CodeRabbit inference engine (.agents/skills/update-project-version/SKILL.md)
Do not treat
crates/wasm/package.jsonas the publishable WebAssembly package manifest unless it has an explicitversionfield; derive the published version fromcrates/wasm/Cargo.tomlthrough wasm-pack output andcrates/wasm/scripts/prepare_pkg.mjs
Files:
crates/wasm/scripts/prepare_pkg.mjs
🧠 Learnings (1)
📚 Learning: 2026-05-07T18:04:44.387Z
Learnt from: mnajafian-nv
Repo: NVIDIA/NeMo-Flow PR: 67
File: integrations/openclaw/src/modules.ts:1-2
Timestamp: 2026-05-07T18:04:44.387Z
Learning: In NVIDIA/NeMo-Flow, TypeScript source files should use `//` line comments for SPDX headers (e.g., `// SPDX-FileCopyrightText: ...` and `// SPDX-License-Identifier: ...`) rather than C-style block comments (`/* ... */`). The repo’s copyright checker enforces this mapping, so `//` SPDX headers in `.ts` files should not be flagged as a style violation.
Applied to files:
crates/node/observability.d.tscrates/wasm/wrappers/esm/observability.d.ts
🪛 markdownlint-cli2 (0.22.1)
docs/export-observability-data/code-examples.md
[warning] 212-212: Fenced code blocks should be surrounded by blank lines
(MD031, blanks-around-fences)
[warning] 241-241: Fenced code blocks should be surrounded by blank lines
(MD031, blanks-around-fences)
[warning] 275-275: Fenced code blocks should be surrounded by blank lines
(MD031, blanks-around-fences)
🪛 Ruff (0.15.12)
python/nemo_flow/observability.py
[warning] 183-191: __all__ is not sorted
Apply an isort-style sorting to __all__
(RUF022)
🔇 Additional comments (15)
README.md (1)
52-53: Good scope update for plugin capabilities.This addition clearly reflects that plugin configuration now includes observability exporters.
crates/node/observability.js (1)
15-89: Solid helper surface for the new observability component.The config factories and
ComponentSpecwrapper are consistent and provide a clean Node entry point for this plugin kind.crates/node/observability.d.ts (1)
9-71: Type surface is well-aligned with the runtime helper API.Interfaces and declared functions are coherent and expose the observability plugin contract clearly.
crates/node/package.json (1)
43-46: Export map update looks correct.
./observabilityis properly exposed with both runtime and type entry points.crates/node/README.md (1)
35-36: Documentation updates are consistent with the new Node export surface.The added
nemo-flow-node/observabilityreferences are aligned with package exports and usage guidance.Also applies to: 47-48, 90-91
scripts/docs/build_node_docs_artifacts.mjs (1)
51-57: Docs artifact pipeline changes are coherent.The new module registration and declaration rewrites follow the established normalization approach for generated Node API pages.
Also applies to: 118-142
crates/wasm/wrappers/esm/observability.d.ts (1)
9-71: Wasm observability typings look well-structured and aligned.The exported config/types and
ComponentSpecdeclaration fit the intended wrapper surface.python/nemo_flow/__init__.pyi (1)
33-33: Stub facade stays aligned with the new publicobservabilitysurface.This re-export keeps the top-level typing facade consistent with the runtime package surface.
python/nemo_flow/README.md (1)
47-47: README surface updates correctly include observability.The updated feature list and package surface list match the new public module exposure.
Also applies to: 97-97
crates/core/src/observability/mod.rs (1)
20-20: Module export is correctly wired for the new observability plugin component.crates/wasm/tests-js/observability_tests.mjs (1)
10-72: Good coverage for Wasm observability helper defaults and validation behavior.crates/node/tests/observability_plugin_tests.mjs (1)
20-178: Strong Node binding coverage for observability initialization and ATIF isolation semantics.crates/core/tests/unit/observability/plugin_component_tests.rs (1)
86-531: Comprehensive core test coverage for config validation, lifecycle teardown, and exporter behavior.python/tests/test_observability_plugin.py (1)
66-160: ⚡ Quick winAsync tests are properly handled under current configuration.
The repository uses
asyncio_mode = "auto"in pyproject.toml (line 104), which automatically detects and executes async test functions without requiring@pytest.mark.asynciodecorators. These tests will be collected and run as intended.docs/export-observability-data/code-examples.md (1)
212-212: Static analysis false positive: MyST syntax is valid.The markdownlint warnings about missing blank lines around fenced code blocks are false positives. The
:::markers are MyST directive closers for the tab-set syntax, not regular Markdown content. This pattern is correct for Sphinx-based documentation.Also applies to: 241-241, 275-275
mnajafian-nv
left a comment
mnajafian-nv
left a comment
There was a problem hiding this comment.
Thanks for the detailed implementation and cross-binding coverage. I focused on the ATIF dispatcher lifecycle, binding parity, and docs consistency.
The main issues I found are around ATIF behavior under long-running workloads: filesystem writes happen under the dispatcher mutex, completed agents appear to remain retained after write, raw observed_events is unbounded, and last_error globally stops future collection. I also found one concrete Go binding parity issue where enabled:false is omitted and therefore becomes enabled again in Rust due to the default.
One non-blocking follow-up: ensure_builtin_plugins_registered is called from list/lookup/validate/initialize flows, and idempotency currently depends on matching "already registered" in an error string. A Once/OnceLock-style registration path would avoid repeated registry write-lock work and remove the dependency on error-message wording.
The docs/API comments are smaller and should be straightforward.
|
One small follow-up on the Go enabled:false comment: |
There was a problem hiding this comment.
♻️ Duplicate comments (1)
README.md (1)
67-68:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winSpell out ATIF on first use; ATOF already flagged.
ATIFis introduced at line 46 and reused here without being spelled out. Since this PR adds both ATOF and ATIF exporter configuration, spell out ATIF either at its first mention (line 46) or reintroduce the full term here. As per coding guidelines, "Spell out a term on first use and put the acronym in parentheses unless the acronym is widely understood by the intended audience."The
ATOFissue is already covered by the existing review comment.Suggested fix for line 67
-- ✅ **Built-in observability plugin**: Configure ATOF, ATIF, OpenTelemetry, +- ✅ **Built-in observability plugin**: Configure ATOF, Agent Trajectory Interchange Format (ATIF), OpenTelemetry,Or spell out ATIF at line 46 and keep the acronym here.
🤖 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 `@README.md` around lines 67 - 68, The README currently uses the acronym ATIF without spelling it out; update the documentation so ATIF is spelled out on first use (e.g., "Azure Telemetry Ingestion Framework (ATIF)") either where ATIF is first introduced or by expanding it in the sentence with the "Built-in observability plugin" mention that also lists ATOF and OpenTelemetry; ensure the acronym appears in parentheses on first mention and leave subsequent mentions as ATIF.
🤖 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.
Duplicate comments:
In `@README.md`:
- Around line 67-68: The README currently uses the acronym ATIF without spelling
it out; update the documentation so ATIF is spelled out on first use (e.g.,
"Azure Telemetry Ingestion Framework (ATIF)") either where ATIF is first
introduced or by expanding it in the sentence with the "Built-in observability
plugin" mention that also lists ATOF and OpenTelemetry; ensure the acronym
appears in parentheses on first mention and leave subsequent mentions as ATIF.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Enterprise
Run ID: c7ae642e-890c-4a3e-9089-d2c58b025829
📒 Files selected for processing (2)
README.mddocs/index.md
📜 Review details
🧰 Additional context used
📓 Path-based instructions (23)
**/*.{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/index.mdREADME.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.mdREADME.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/index.mdREADME.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/index.mdREADME.md
**/*.{html,md}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license headers in HTML and Markdown files using HTML comment syntax
Files:
docs/index.mdREADME.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/index.md
**/*.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Run Markdown link checking via
lycheeforREADME.md,CONTRIBUTING.md, anddocs/through pre-commit hooks
Files:
docs/index.mdREADME.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/index.mdREADME.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.mdREADME.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/index.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/index.mdREADME.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/index.mdREADME.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/index.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/index.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/index.mdREADME.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/index.mdREADME.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.mdREADME.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/index.mdREADME.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/index.mdREADME.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/index.mdREADME.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.mdREADME.md
README.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Update README.md to reflect current workspace members and top-level documentation for changes affecting public behavior, bindings, examples, or workspace structure
Files:
README.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:
README.md
🔇 Additional comments (2)
docs/index.md (1)
198-198: Good docs navigation update.This entry is clear, correctly placed under Export Observability Data, and uses descriptive title-case link text that matches the new guide path.
README.md (1)
52-53: LGTM: observability exporters added to plugin capabilities.The addition of "observability exporters" to the reusable runtime behavior list is accurate and aligns with the new built-in observability plugin surface.
coderabbitai
Bot
added
the
DO NOT MERGE
willkill07
force-pushed
the
wkk_observability-plugin
branch
from
dee4f7d to
da59841
Compare
Signed-off-by: Will Killian <wkillian@nvidia.com>
willkill07
force-pushed
the
wkk_observability-plugin
branch
from
da59841 to
4151567
Compare
mnajafian-nv
left a comment
mnajafian-nv
left a comment
There was a problem hiding this comment.
LGTM overall. Only remaining suggestion from my review is docs consistency: advanced-guide.md still has the old OpenInference gRPC note. Updating that to match the new observability plugin doc should close out my comment.
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 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/core/README.md`:
- Around line 47-49: The README line containing "ATOF, ATIF, OpenTelemetry" uses
the acronym ATIF without expansion; update that phrase to spell out Agent
Trajectory Interchange Format (ATIF) on first mention (e.g., "ATOF, Agent
Trajectory Interchange Format (ATIF), OpenTelemetry") so ATIF is defined before
subsequent uses—edit the text containing "ATOF, ATIF, OpenTelemetry"
accordingly.
In `@README.md`:
- Around line 67-69: Update the README line that mentions ATOF and ATIF to spell
out ATIF on first use—e.g., change "ATIF" to "Agent Trajectory Interoperability
Format (ATIF)" so it mirrors the existing expansion for ATOF; modify the
sentence containing "Agent Trajectory Observability Format (ATOF), ATIF,
OpenTelemetry, and OpenInference exporters" to include the full phrase for ATIF
before the acronym.
🪄 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: 2763a936-f661-4361-a9ac-62e9346aa366
📒 Files selected for processing (5)
README.mdcrates/core/README.mdcrates/core/src/observability/plugin_component.rscrates/core/src/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rs
📜 Review details
🧰 Additional context used
📓 Path-based instructions (30)
**/*.{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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.md
**/*.{html,md}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license headers in HTML and Markdown files using HTML comment syntax
Files:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.md
**/*.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Run Markdown link checking via
lycheeforREADME.md,CONTRIBUTING.md, anddocs/through pre-commit hooks
Files:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.md
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/README.mdcrates/core/src/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/README.mdREADME.mdcrates/core/src/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.rs
README.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Update README.md to reflect current workspace members and top-level documentation for changes affecting public behavior, bindings, examples, or workspace structure
Files:
README.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:
README.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:
README.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:
README.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:
README.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:
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 lintingWhen Rust files changed as part of Python work, run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.rs
{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
**/*.{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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/unit/observability/plugin_component_tests.rs
There was a problem hiding this comment.
♻️ Duplicate comments (2)
README.md (1)
67-69:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winSpell out ATIF on first mention.
ATIF is used without expansion. For consistency with ATOF and per coding guidelines, spell out the full term on first use.
As per coding guidelines, "Spell out a term on first use and put the acronym in parentheses unless the acronym is widely understood by the intended audience."
📝 Suggested fix
-- ✅ **Built-in observability plugin**: Configure Agent Trajectory Observability - Format (ATOF), ATIF, OpenTelemetry, and OpenInference exporters without - registering subscribers by hand. +- ✅ **Built-in observability plugin**: Configure Agent Trajectory Observability + Format (ATOF), Agent Trajectory Interchange Format (ATIF), OpenTelemetry, and + OpenInference exporters without registering subscribers by hand.🤖 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 `@README.md` around lines 67 - 69, The README line mentions the acronym ATIF without expansion; update the first occurrence of "ATIF" in the sentence listing "Agent Trajectory Observability Format (ATOF), ATIF, OpenTelemetry, and OpenInference exporters" to spell out the full term for ATIF followed by the acronym in parentheses (e.g., "Agent Telemetry Interchange Format (ATIF)") so it matches the existing ATOF expansion and coding guidelines; edit the phrase containing ATOF/ATIF/OpenTelemetry/OpenInference to replace the bare "ATIF" with its expanded form and keep the acronym in parentheses.crates/core/README.md (1)
47-49:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winSpell out ATIF on first mention.
ATIF appears without expansion. The acronym should be spelled out on first use, matching the pattern used for ATOF.
As per coding guidelines, "Spell out a term on first use and put the acronym in parentheses unless the acronym is widely understood by the intended audience."
📝 Suggested fix
-- ✅ **Built-in observability plugin**: Configure first-party Agent Trajectory - Observability Format (ATOF), ATIF, OpenTelemetry, and OpenInference exporters - from the core crate. +- ✅ **Built-in observability plugin**: Configure first-party Agent Trajectory + Observability Format (ATOF), Agent Trajectory Interchange Format (ATIF), + OpenTelemetry, and OpenInference exporters from the core crate.🤖 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/core/README.md` around lines 47 - 49, The README line that lists observability formats uses the acronym "ATIF" without expanding it; update the sentence that currently mentions "Agent Trajectory Observability Format (ATOF), ATIF, OpenTelemetry, and OpenInference exporters" so that ATIF is spelled out on first use and followed by the acronym in parentheses (matching how ATOF is presented). Locate the list in the "Built-in observability plugin" sentence and replace the bare "ATIF" with its full form followed by "(ATIF)" so the pattern matches ATOF.
🤖 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.
Duplicate comments:
In `@crates/core/README.md`:
- Around line 47-49: The README line that lists observability formats uses the
acronym "ATIF" without expanding it; update the sentence that currently mentions
"Agent Trajectory Observability Format (ATOF), ATIF, OpenTelemetry, and
OpenInference exporters" so that ATIF is spelled out on first use and followed
by the acronym in parentheses (matching how ATOF is presented). Locate the list
in the "Built-in observability plugin" sentence and replace the bare "ATIF" with
its full form followed by "(ATIF)" so the pattern matches ATOF.
In `@README.md`:
- Around line 67-69: The README line mentions the acronym ATIF without
expansion; update the first occurrence of "ATIF" in the sentence listing "Agent
Trajectory Observability Format (ATOF), ATIF, OpenTelemetry, and OpenInference
exporters" to spell out the full term for ATIF followed by the acronym in
parentheses (e.g., "Agent Telemetry Interchange Format (ATIF)") so it matches
the existing ATOF expansion and coding guidelines; edit the phrase containing
ATOF/ATIF/OpenTelemetry/OpenInference to replace the bare "ATIF" with its
expanded form and keep the acronym in parentheses.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Enterprise
Run ID: b96dda0d-835d-4be9-b961-edd24ee39ced
📒 Files selected for processing (6)
README.mdcrates/core/README.mdcrates/core/src/observability/plugin_component.rscrates/core/src/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rsdocs/export-observability-data/advanced-guide.md
💤 Files with no reviewable changes (1)
- docs/export-observability-data/advanced-guide.md
📜 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). (14)
- GitHub Check: Rust / Test (windows-arm64)
- GitHub Check: Go / Test (windows-arm64)
- GitHub Check: Rust / Test (windows-amd64)
- GitHub Check: WebAssembly / Test (windows-arm64)
- GitHub Check: Python / Test (windows-arm64)
- GitHub Check: Python / Test (windows-amd64)
- GitHub Check: WebAssembly / Test (macos-arm64)
- GitHub Check: WebAssembly / Test (linux-arm64)
- GitHub Check: WebAssembly / Test (windows-amd64)
- GitHub Check: Go / Test (windows-amd64)
- GitHub Check: WebAssembly / Test (linux-amd64)
- GitHub Check: Documentation / Build
- GitHub Check: Node.js / Test (windows-arm64)
- GitHub Check: Node.js / Test (macos-arm64)
🧰 Additional context used
📓 Path-based instructions (30)
**/*.{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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.md
**/*.{html,md}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include SPDX license headers in HTML and Markdown files using HTML comment syntax
Files:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.md
**/*.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Run Markdown link checking via
lycheeforREADME.md,CONTRIBUTING.md, anddocs/through pre-commit hooks
Files:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.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:
crates/core/README.mdREADME.md
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/README.mdcrates/core/src/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/README.mdREADME.mdcrates/core/src/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.rs
README.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Update README.md to reflect current workspace members and top-level documentation for changes affecting public behavior, bindings, examples, or workspace structure
Files:
README.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:
README.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:
README.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:
README.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:
README.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:
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 lintingWhen Rust files changed as part of Python work, run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.rs
{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
**/*.{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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/plugin.rscrates/core/tests/unit/observability/plugin_component_tests.rscrates/core/src/observability/plugin_component.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/unit/observability/plugin_component_tests.rs
🔇 Additional comments (3)
crates/core/src/observability/plugin_component.rs (1)
1-1180: LGTM! Comprehensive observability plugin implementation.The built-in observability component is well-structured:
- ATIF filesystem I/O moved outside the dispatcher mutex (lines 681-706)
- Completed agent state evicted after successful write (lines 578-590)
- Config validation with policy-driven diagnostics
- Per-agent ATIF isolation and safe template enforcement
The architecture cleanly separates validation, registration, and runtime wiring across ATOF/ATIF/OTLP sections.
crates/core/src/plugin.rs (1)
47-47: LGTM! One-time built-in registration correctly implemented.The
OnceLock<Result<()>>gate ensuresregister_observability_component()runs exactly once, withclone_cached_plugin_error()reusing the stored result on subsequent calls. The entry-point calls at lines 793, 814, 837, and 999 ensure automatic registration before registry queries.Also applies to: 733-756
crates/core/tests/unit/observability/plugin_component_tests.rs (1)
1-606: LGTM! Comprehensive test coverage for observability plugin.The test suite covers:
- Default config and component conversion (lines 88-130)
- Built-in auto-registration (lines 133-142)
- Disabled sections producing no subscribers/files (lines 145-189)
- Singleton validation and policy-driven diagnostics (lines 192-289)
- ATOF JSONL and ATIF trajectory file generation (lines 323-524)
- Agent state eviction after write (lines 417-487)
- OTLP subscriber registration (lines 561-605)
Thorough validation and lifecycle coverage.
|
@mnajafian-nv i will address as a follow up separately due to being out of scope |
|
/merge |
2 participants
Overview
Adds a built-in core
observabilityplugin that configures first-party ATOF, ATIF, OpenTelemetry, and OpenInference exporters through the existing plugin lifecycle. The plugin is auto-registered by core plugin APIs and keeps every exporter section disabled unless that section explicitly setsenabled: true.Details
nemo_flow::observability::plugin_componentwith public config structs, singleton component registration, inferred subscriber names, ATOF/ATIF/OTLP wiring, and ATIF per-top-level-agent file splitting.Validation run locally:
cargo test -p nemo-flow observability::plugin_component -- --test-threads=1just test-rustjust test-pythonjust test-nodejust test-gojust test-wasmjust docsuv run pytest python/tests/test_observability_plugin.pynode --test --test-force-exit tests/observability_plugin_tests.mjsgo test -v -run 'Observability.*Atif|ObservabilityPluginAtofAndAtif|ObservabilityPluginAtif|ObservabilityAtif' ./...cargo test -p nemo-flow-ffi test_ffi_observability_plugin -- --test-threads=1uv run pre-commit run --all-filesWhere should the reviewer start?
Start with
crates/core/src/observability/plugin_component.rs, then reviewcrates/core/tests/unit/observability/plugin_component_tests.rsand the binding-specific observability plugin tests.Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)
Summary by CodeRabbit
New Features
Documentation
Tests