feat: Add Deep Agents integration by dagardner-nv · Pull Request #90 · NVIDIA/NeMo-Flow

dagardner-nv · 2026-05-12T21:03:35Z

Overview

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

Details

Where should the reviewer start?

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

Closes #

Summary by CodeRabbit

New Features
- Deep Agents integration: observability for agent runs, tool calls, filesystem/sandbox ops, and human-in-the-loop events; backend instrumentation and middleware emitting start/error/end marks.
Documentation
- Added setup and usage guide for the Deep Agents integration with observability examples.
Tests
- New integration and end-to-end tests covering Deep Agents flows, middleware, and backend instrumentation.
Chores
- Added optional dependency group for Deep Agents; regenerated third-party attribution/licenses.

Signed-off-by: David Gardner <dagardner@nvidia.com>

… interupts Signed-off-by: David Gardner <dagardner@nvidia.com>

Signed-off-by: David Gardner <dagardner@nvidia.com>

coderabbitai · 2026-05-12T21:03:43Z

Walkthrough

Adds a Deep Agents observability integration: event utilities, middleware, backend wrappers, LangGraph callback handler, package wiring (add_nemo_flow_integration), docs, tests, and updated attributions and CI/build syncs.

Changes

Deep Agents NeMo Flow Integration

Layer / File(s)	Summary
Observability event data and emission `python/nemo_flow/integrations/deepagents/_events.py`	Tool/backend categorization; JSON-safe summarization; builders for tool/backend event payloads; unified emit_mark to send standardized NeMo Flow marks.
Backend observability wrapper `python/nemo_flow/integrations/deepagents/backend.py`	`NemoFlowDeepAgentsBackend` and `NemoFlowDeepAgentsSandboxBackend` proxy filesystem and execute methods, emitting start/error/end marks; observe_backend factory selects appropriate wrapper and validates sandbox timeouts.
LangGraph callback handler `python/nemo_flow/integrations/deepagents/callbacks.py`	`NemoFlowDeepAgentsCallbackHandler` correlates Graph Interrupt/Resume events for HITL, tracks pending keys, and emits human_in_the_loop marks with phase and payload metadata.
Tool call middleware `python/nemo_flow/integrations/deepagents/middleware.py`	`NemoFlowDeepAgentsMiddleware` emits skill/configured marks and wraps sync/async tool calls to emit start/error/end marks with normalized args, tool kind, and result/error payloads.
Package integration and helper `python/nemo_flow/integrations/deepagents/__init__.py`	`add_nemo_flow_integration` merges kwargs/overrides, normalizes skills/subagent summaries, optionally instruments subagents, wraps backends via `observe_backend`, injects middleware, and re-exports integration symbols.
Integration documentation `python/nemo_flow/integrations/deepagents/README.md`	New README with setup, usage example, and enumerated observable events captured by the integration.
Test fixtures and integration tests `python/tests/conftest.py`, `python/tests/integrations/deepagents/test_deepagents_integration.py`	Shared `subscribed_events` fixture and comprehensive tests covering middleware, callback HITL handling, backend observation (sync/async), sandbox behavior, wiring, and an end-to-end agent test.
Dependencies and license attributions `pyproject.toml`, `ATTRIBUTIONS-Python.md`	Adds `deepagents` optional-dependency (includes `nemo-flow[langgraph]`); regenerates attributions with many new/updated entries and license formatting adjustments.
CI and build sync updates `.github/workflows/*`, `justfile`	Pre-commit/CI/justfile `uv sync` now includes `langgraph` and `deepagents` extras; CI Test job adds Windows ARM64 vcpkg OpenSSL provisioning step.
Existing test module updates `python/tests/integrations/langchain/test_middleware.py`, `python/tests/integrations/langgraph/test_langgraph_integration.py`	Moves `subscribed_events` fixture to shared conftest, updates `BaseChatModel` import path, and removes unused `Iterator` import.

Estimated code review effort

🎯 4 (Complex) | ⏱️ ~45 minutes

🚥 Pre-merge checks | ✅ 3 | ❌ 2

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description includes required checklist confirmations but lacks substantive content in Details, reviewer guidance, and related issues sections.	Add details about the Deep Agents integration changes, point reviewer to key files (e.g., middleware.py, backend.py), and link the related issue number.
Docstring Coverage	⚠️ Warning	Docstring coverage is 16.48% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (3 passed)

Check name	Status	Explanation
Title check	✅ Passed	The PR title follows Conventional Commits format with type 'feat', a clear and concise summary, under 72 characters, and no trailing period.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

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

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests

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

Signed-off-by: David Gardner <dagardner@nvidia.com>

[skip ci] Signed-off-by: David Gardner <dagardner@nvidia.com>

Signed-off-by: David Gardner <dagardner@nvidia.com>

dagardner-nv · 2026-05-12T21:45:01Z

@coderabbitai review

coderabbitai · 2026-05-12T21:45:06Z

✅ Actions performed

Review triggered.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

Signed-off-by: David Gardner <dagardner@nvidia.com>

coderabbitai

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 `@ATTRIBUTIONS-Python.md`:
- Around line 645-659: Several attribution blocks (e.g., the "## anthropic
(0.101.0)" section and its LICENSE code fence) violate MD022/MD031/MD040; update
the generator/template that emits these blocks to ensure a blank line before and
after each heading and before/after fenced code blocks, and emit fenced code
blocks with an explicit language (e.g., use ```text for LICENSE contents) so
lint rules are satisfied; then re-generate the affected sections (including
other listed ranges) and run the repo formatter on changed Markdown files (per
the project rule for **/*.{py,js,ts,tsx,go,rs,md}) to ensure consistent
formatting.

In `@python/nemo_flow/integrations/deepagents/middleware.py`:
- Around line 122-139: The method _emit_tool_mark is missing an explicit return
type annotation; update its signature to include a return type of None (e.g.,
def _emit_tool_mark(... ) -> None:) so the function's void nature is explicit
for linters and type checkers; locate the _emit_tool_mark method in
middleware.py and add the -> None annotation to its signature without changing
the body.

🪄 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: 1b49494b-9580-43bf-8ffc-d78d6a068946

📥 Commits

Reviewing files that changed from the base of the PR and between 3e09970 and aa3b66e.

⛔ Files ignored due to path filters (1)

uv.lock is excluded by !**/*.lock

📒 Files selected for processing (12)

ATTRIBUTIONS-Python.md
pyproject.toml
python/nemo_flow/integrations/deepagents/README.md
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/middleware.py
python/tests/conftest.py
python/tests/integrations/deepagents/test_deepagents_integration.py
python/tests/integrations/langchain/test_middleware.py
python/tests/integrations/langgraph/test_langgraph_integration.py

💤 Files with no reviewable changes (1)

python/tests/integrations/langgraph/test_langgraph_integration.py

📜 Review details

🧰 Additional context used

📓 Path-based instructions (29)

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

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

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

Files:

python/nemo_flow/integrations/deepagents/README.md
ATTRIBUTIONS-Python.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:

python/nemo_flow/integrations/deepagents/README.md
ATTRIBUTIONS-Python.md

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

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

**/*.{md,rst,txt}: Spell NVIDIA in all caps. Do not use Nvidia, nvidia, or NV.
Format commands, code elements, expressions, package names, file names, and paths as inline code.
Use descriptive link text. Avoid raw URLs and weak anchors such as 'here' or 'read more.'
Use title case consistently for technical documentation headings.
Introduce code blocks, lists, tables, and images with complete sentences.
Write procedures as imperative steps. Keep steps parallel and split long procedures into smaller tasks.
Prefer active voice, present tense, short sentences, contractions, and plain English.
Use can for possibility and reserve may for permission.
Use after for temporal relationships instead of once.
Prefer refer to over see when the wording points readers to another resource.
Avoid culture-specific idioms, unnecessary Latinisms, jokes, and marketing exaggeration in technical 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:

python/nemo_flow/integrations/deepagents/README.md
ATTRIBUTIONS-Python.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:

python/nemo_flow/integrations/deepagents/README.md
ATTRIBUTIONS-Python.md

**/*.{html,md}

📄 CodeRabbit inference engine (CONTRIBUTING.md)

Include SPDX license headers in HTML and Markdown files using HTML comment syntax

Files:

python/nemo_flow/integrations/deepagents/README.md
ATTRIBUTIONS-Python.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:

python/nemo_flow/integrations/deepagents/README.md

**/*.md

📄 CodeRabbit inference engine (CONTRIBUTING.md)

Run Markdown link checking via lychee for README.md, CONTRIBUTING.md, and docs/ through pre-commit hooks

Files:

python/nemo_flow/integrations/deepagents/README.md
ATTRIBUTIONS-Python.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:

python/nemo_flow/integrations/deepagents/README.md
python/tests/integrations/langchain/test_middleware.py
python/tests/conftest.py
python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/middleware.py
ATTRIBUTIONS-Python.md
python/tests/integrations/deepagents/test_deepagents_integration.py

**/*.{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:

python/nemo_flow/integrations/deepagents/README.md
python/tests/integrations/langchain/test_middleware.py
python/tests/conftest.py
python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/middleware.py
ATTRIBUTIONS-Python.md
python/tests/integrations/deepagents/test_deepagents_integration.py

**/*.{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:

python/nemo_flow/integrations/deepagents/README.md
python/tests/integrations/langchain/test_middleware.py
python/tests/conftest.py
python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/middleware.py
ATTRIBUTIONS-Python.md
python/tests/integrations/deepagents/test_deepagents_integration.py

**/{integrations,integration,*-integration}/**

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

**/{integrations,integration,*-integration}/**: Keep NeMo Flow optional in framework integrations
Preserve the framework's original behavior when NeMo Flow is absent
Wrap tool and LLM paths at the correct framework boundary
Integration pattern must follow docs/integrate-frameworks/adding-scopes.md

Files:

python/nemo_flow/integrations/deepagents/README.md
python/tests/integrations/langchain/test_middleware.py
python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/middleware.py
python/tests/integrations/deepagents/test_deepagents_integration.py

{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:

python/nemo_flow/integrations/deepagents/README.md
python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/middleware.py

**/*.{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:

python/nemo_flow/integrations/deepagents/README.md
ATTRIBUTIONS-Python.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:

python/nemo_flow/integrations/deepagents/README.md

**/*.{py,js,ts,tsx,go,rs,md}

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

Format changed files with the language-native formatter before the final lint/test pass

Files:

python/nemo_flow/integrations/deepagents/README.md
python/tests/integrations/langchain/test_middleware.py
python/tests/conftest.py
python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/middleware.py
ATTRIBUTIONS-Python.md
python/tests/integrations/deepagents/test_deepagents_integration.py

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/integrations/deepagents/README.md
python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/middleware.py

**/*.toml

📄 CodeRabbit inference engine (CONTRIBUTING.md)

Include SPDX license headers in TOML files using TOML comment syntax

Files:

pyproject.toml

{Cargo.toml,setup.py,setup.cfg,pyproject.toml,go.mod,go.sum,package.json,package-lock.json,yarn.lock,pom.xml,*.gradle}

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

Update repository manifest files (Cargo.toml, setup.py, go.mod, package.json, etc.) with new package/crate names during rename operations

Files:

pyproject.toml

{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:

pyproject.toml

**/*.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
Use ty for 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/tests/integrations/langchain/test_middleware.py
python/tests/conftest.py
python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/middleware.py
python/tests/integrations/deepagents/test_deepagents_integration.py

**/test_*.py

📄 CodeRabbit inference engine (.agents/skills/test-python-binding/SKILL.md)

Run focused pytest first when you know the affected area using pytest -k "<pattern>"

Files:

python/tests/integrations/langchain/test_middleware.py
python/tests/integrations/deepagents/test_deepagents_integration.py

**/*.{rs,py,go,js,ts,tsx}

📄 CodeRabbit inference engine (CONTRIBUTING.md)

Use SONAR_IGNORE_START / SONAR_IGNORE_END markers only for documented false positives that cannot be resolved in code; keep ignored blocks small, add explanatory comments, and require reviewer sign-off

Files:

python/tests/integrations/langchain/test_middleware.py
python/tests/conftest.py
python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/middleware.py
python/tests/integrations/deepagents/test_deepagents_integration.py

**/*.{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:

python/tests/integrations/langchain/test_middleware.py
python/tests/conftest.py
python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/middleware.py
python/tests/integrations/deepagents/test_deepagents_integration.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, use uv run ruff format python to format Python files

Files:

python/tests/integrations/langchain/test_middleware.py
python/tests/conftest.py
python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/middleware.py
python/tests/integrations/deepagents/test_deepagents_integration.py

**/*.{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:

python/tests/integrations/langchain/test_middleware.py
python/tests/conftest.py
python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/middleware.py
python/tests/integrations/deepagents/test_deepagents_integration.py

{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:

python/tests/integrations/langchain/test_middleware.py
python/tests/conftest.py
python/tests/integrations/deepagents/test_deepagents_integration.py

python/nemo_flow/**/*.py

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

Use snake_case naming convention for Python API implementations and wrappers

Files:

python/nemo_flow/integrations/deepagents/callbacks.py
python/nemo_flow/integrations/deepagents/_events.py
python/nemo_flow/integrations/deepagents/__init__.py
python/nemo_flow/integrations/deepagents/backend.py
python/nemo_flow/integrations/deepagents/middleware.py

{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:

ATTRIBUTIONS-Python.md

**/{tests,test}/**/*{integration,smoke}*.py

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

Relevant integration tests or smoke path must pass before contribution

Files:

python/tests/integrations/deepagents/test_deepagents_integration.py

🪛 markdownlint-cli2 (0.22.1)

ATTRIBUTIONS-Python.md

[warning] 647-647: Headings should be surrounded by blank lines
Expected: 1; Actual: 0; Below