feat: move Hermes agent adapter to v1alpha2 - #193
Conversation
|
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:
WalkthroughThe Hermes adapter now consumes validated ChangesHermes AgentConfig Integration
Estimated code review effort: 4 (Complex) | ~45 minutes Sequence Diagram(s)sequenceDiagram
participant Lifecycle
participant AgentConfig
participant HermesAdapter
participant MCPServers
participant AIAgent
Lifecycle->>AgentConfig: Load and validate configuration
Lifecycle->>HermesAdapter: Start with AgentConfig and RuntimeContext
HermesAdapter->>MCPServers: Discover configured MCP servers
MCPServers-->>HermesAdapter: Return MCP tools
HermesAdapter->>AIAgent: Create agent with typed settings
HermesAdapter->>AIAgent: Invoke request with RuntimeContext request ID
AIAgent-->>HermesAdapter: Return response and model metadata
HermesAdapter->>Lifecycle: Clear typed state on cleanup
Possibly related PRs
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
|
Fern docs preview: https://nvidia-preview-pull-request-193.docs.buildwithfern.com/nemo/fabric |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 7
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py (1)
197-213: 🔒 Security & Privacy | 🟠 Major | ⚡ Quick winDo not silently discard MCP tool policy.
AgentMcpServerConfigincludesallowed_toolsandblocked_tools, but this conversion emits neither field. A configured allowlist or blocklist therefore has no effect, and Hermes can expose tools that the configuration excludes.Map the policy to supported Hermes fields. If Hermes cannot enforce it, reject nonempty
allowed_toolsorblocked_toolswith an actionable error. Add coverage for both cases.🤖 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 `@adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py` around lines 197 - 213, The hermes_mcp_server_config conversion currently drops AgentMcpServerConfig.allowed_tools and blocked_tools. Map both policies to the supported Hermes configuration fields; if Hermes does not support either policy, raise an actionable ValueError whenever the corresponding collection is nonempty instead of silently ignoring it. Add coverage for nonempty allowlist and blocklist configurations.Source: Path instructions
🤖 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 `@adapter-contract/pyproject.toml`:
- Around line 27-32: Update the test environment dependency configuration so the
root adapters group installs nemo-fabric-adapter-contract with its pydantic
extra, ensuring the named tests can import pydantic_support without a separate
direct dependency. Regenerate uv.lock after modifying the dependency entry.
In `@adapter-contract/src/nemo_fabric_adapter_contract/codec.py`:
- Around line 43-46: Update the return annotation on
ContractValidationError.prepend to reference ContractValidationError directly
instead of using a quoted string, preserving the existing return behavior.
In `@adapter-contract/src/nemo_fabric_adapter_contract/pydantic_support.py`:
- Line 18: Introduce a separate bounded TypeVar for set_pydantic_extensions,
constrained to the supported contract dataclass type, and use it for that
function’s block parameter and return type. Keep the existing unbounded _T for
type_adapter so its generic behavior remains unchanged.
In `@adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py`:
- Around line 152-158: Update the configuration builder containing the
skill_dirs construction to accept the configuration root, resolve each relative
skill path against that root, and preserve absolute paths unchanged before
assigning config["skills"]["external_dirs"]. Do not expand home-directory
shorthand.
In `@docs/adapter-contract/normalized-configuration.md`:
- Around line 83-84: Update step 3 in the normalized configuration documentation
to name the set_pydantic_extensions helper from
nemo_fabric_adapter_contract.pydantic_support, and mention that it requires the
optional pydantic extra while retaining the existing set_extensions guidance.
In `@tests/adapter_contract/test_agent_execution.py`:
- Around line 120-155: Change
test_agent_execution_dataclasses_track_rust_schema_block_fields to parametrize
individual (filename, model) pairs instead of passing model tuples and looping
inside the test. Keep both field-name and required-field assertions unchanged,
so pytest reports the specific model that diverges from its Rust schema.
In `@tests/adapter_contract/test_dependency_boundary.py`:
- Line 44: Update the subprocess invocation in the dependency-boundary test to
capture the child process’s stdout and stderr, then assert using the captured
output so failures include the traceback and identify the failing import while
preserving the existing non-zero exit validation.
---
Outside diff comments:
In `@adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py`:
- Around line 197-213: The hermes_mcp_server_config conversion currently drops
AgentMcpServerConfig.allowed_tools and blocked_tools. Map both policies to the
supported Hermes configuration fields; if Hermes does not support either policy,
raise an actionable ValueError whenever the corresponding collection is nonempty
instead of silently ignoring it. Add coverage for nonempty allowlist and
blocklist configurations.
🪄 Autofix
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: e76832f5-b51c-42de-810c-6634f56dd134
⛔ Files ignored due to path filters (3)
adapter-contract/uv.lockis excluded by!**/*.lockadapters/hermes/uv.lockis excluded by!**/*.lockuv.lockis excluded by!**/*.lock
📒 Files selected for processing (27)
adapter-contract/pypi.mdadapter-contract/pyproject.tomladapter-contract/src/nemo_fabric_adapter_contract/codec.pyadapter-contract/src/nemo_fabric_adapter_contract/models.pyadapter-contract/src/nemo_fabric_adapter_contract/pydantic_support.pyadapters/common/README.mdadapters/common/src/nemo_fabric_adapters/common/lifecycle.pyadapters/hermes/fabric-adapter.jsonadapters/hermes/pyproject.tomladapters/hermes/src/nemo_fabric_adapters/hermes/adapter.pycrates/fabric-cli/assets/adapters/hermes/fabric-adapter.jsondocs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.mdexamples/harbor/swebench/adapters/hermes/fabric-adapter.jsonexternal/nat/README.mdexternal/nat/src/nemo_fabric_adapters/nat/adapter.pyskills/nemo-fabric-build-adapter/SKILL.mdtests/adapter_contract/test_agent_config.pytests/adapter_contract/test_agent_execution.pytests/adapter_contract/test_dependency_boundary.pytests/adapters/test_adapter_package_metadata.pytests/adapters/test_adapters_common_lifecycle.pytests/adapters/test_external_nat_adapter.pytests/adapters/test_hermes_adapter.pytests/adapters/test_hermes_config_builder.pytests/adapters/test_hermes_streaming.pytests/e2e/test_hermes_config_mapping.py
📜 Review details
⏰ Context from checks skipped due to timeout. (14)
- GitHub Check: Preview docs
- GitHub Check: Test (Python 3.12, linux-amd64)
- GitHub Check: Test (Python 3.11, macos-arm64)
- GitHub Check: Test (Python 3.11, windows-amd64)
- GitHub Check: Test (Python 3.13, linux-amd64)
- GitHub Check: Test (Python 3.13, macos-arm64)
- GitHub Check: Test (Python 3.12, macos-arm64)
- GitHub Check: Test (Python 3.11, linux-amd64)
- GitHub Check: Test (Python 3.13, windows-amd64)
- GitHub Check: Test (Python 3.12, windows-amd64)
- GitHub Check: Test (Python 3.14, windows-amd64)
- GitHub Check: Test (Python 3.13, linux-arm64)
- GitHub Check: Test (Python 3.11, linux-arm64)
- GitHub Check: Pre-commit
🧰 Additional context used
📓 Path-based instructions (43)
**/*.{md,rst}
📄 CodeRabbit inference engine (.agents/skills/contribute-api/SKILL.md)
Update documentation and examples in the same branch as the public API change.
Files:
adapters/common/README.mddocs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.mdadapter-contract/pypi.mdskills/nemo-fabric-build-adapter/SKILL.mdexternal/nat/README.md
**/*
📄 CodeRabbit inference engine (.agents/skills/karpathy-guidelines/SKILL.md)
**/*: Before implementing, explicitly state assumptions, surface ambiguity and tradeoffs, present multiple interpretations when relevant, and ask for clarification rather than silently deciding or proceeding when requirements are unclear.
Prefer the minimum code needed to solve the requested problem: avoid speculative features, unnecessary abstractions, unrequested flexibility, and handling of impossible scenarios; simplify overcomplicated solutions.
When editing existing code, make surgical changes only: do not modify unrelated code, comments, formatting, or pre-existing dead code; match the existing style, and remove only unused imports, variables, or functions introduced by your changes.
Define verifiable success criteria for each task, such as writing regression tests for bugs and invalid-input tests for validation, then verify the implementation against those criteria. For multi-step work, state a brief plan with a verification check for each step.
**/*: Always spellNVIDIAin all caps; do not useNvidia,nvidia,nVidia,nVIDIA, orNV.
Usean NVIDIAbefore a noun, because the name begins with an “en” sound.
Do not add a registered trademark symbol afterNVIDIAwhen referring to the company; use trademark symbols with product names only when required by the document type or legal guidance.
Verify official capitalization, spacing, hyphenation, and spelling for NVIDIA and third-party product names; do not rewrite official product names for grammar or title-case rules.
Precede NVIDIA product names withNVIDIAon first mention when natural and accurate, and link the first mention when the destination helps the reader.
On first use, include the company name and full model qualifier when it helps identify the model; preserve official capitalization and punctuation, and use shorter family names only after establishing the full name.
For learning-oriented and developer content, do not force trademark symbols unless explicitly required; for press, ...
Files:
adapters/common/README.mdtests/adapter_contract/test_dependency_boundary.pydocs/adapter-contract/execution.mdadapter-contract/src/nemo_fabric_adapter_contract/pydantic_support.pydocs/adapter-contract/normalized-configuration.mdadapter-contract/pyproject.tomladapter-contract/pypi.mdtests/adapters/test_adapters_common_lifecycle.pyskills/nemo-fabric-build-adapter/SKILL.mdcrates/fabric-cli/assets/adapters/hermes/fabric-adapter.jsonadapters/hermes/fabric-adapter.jsonexamples/harbor/swebench/adapters/hermes/fabric-adapter.jsontests/adapters/test_hermes_config_builder.pyexternal/nat/src/nemo_fabric_adapters/nat/adapter.pyadapters/hermes/pyproject.tomltests/adapters/test_hermes_streaming.pytests/e2e/test_hermes_config_mapping.pytests/adapters/test_adapter_package_metadata.pytests/adapter_contract/test_agent_config.pyexternal/nat/README.mdadapter-contract/src/nemo_fabric_adapter_contract/codec.pytests/adapters/test_external_nat_adapter.pytests/adapter_contract/test_agent_execution.pyadapter-contract/src/nemo_fabric_adapter_contract/models.pyadapters/hermes/src/nemo_fabric_adapters/hermes/adapter.pytests/adapters/test_hermes_adapter.pyadapters/common/src/nemo_fabric_adapters/common/lifecycle.py
**/*.{md,mdx,rst}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-guide.md)
**/*.{md,mdx,rst}: For NeMo Fabric documentation, verify technical claims against the current repository, public API, or documented command before reviewing style.
Always 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 ashereorread more.
Use title case consistently for technical documentation headings.
Introduce code blocks, lists, tables, and images with complete sentences.
Write procedures as imperative, parallel steps; split long procedures into smaller tasks.
Prefer active voice, present tense, short sentences, contractions, and plain English while preserving necessary technical precision.
Usecanfor possibility and reservemayfor permission.
Useafterfor temporal relationships instead ofonce, and preferrefer tooverseewhen directing 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 commas in thousands.
Do not add trademark symbols to learning-oriented documentation unless the source, platform, or legal guidance explicitly requires them.
Do not replace precise technical terms with simpler words when doing so would lose precision.
Do not flag passive voice when the actor is unknown or the action is the important part.
Do not rewrite API names, package names, command flags, or code literals for style.
**/*.{md,mdx,rst}: Use consistent title case for technical-document headings and table headers; avoid quotation marks, ampersands, and exclamation marks in headings, while preserving official product, event, research, and whitepaper title ...
Files:
adapters/common/README.mddocs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.mdadapter-contract/pypi.mdskills/nemo-fabric-build-adapter/SKILL.mdexternal/nat/README.md
**/*.{md,rst,txt,adoc}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/assets/nvidia-style-language-mechanics.md)
**/*.{md,rst,txt,adoc}: For technical documentation, use professional, active, conversational, engaging, precise, and plain-English prose. Prefer active voice, present tense, short sentences, and scannable paragraphs. Avoid casual or imprecise language, swearing, threats, insults, jokes, puns, culture-specific idioms, marketing exaggeration, and unsupported third-party comparisons.
Usecanfor possibility and reservemayfor permission; useafterfor temporal order; userefer tofor cross-references; prefer short direct sentences and specific verbs; avoid unnecessarypleasein technical documentation.
Prefer active voice when the actor matters. Passive voice is acceptable when the actor is unknown or irrelevant, when the action or result is the focus, or in programmer documentation.
Use natural contractions in conversational technical prose, but do not force them in formal legal copy, API references, or generated text.
Prefer simpler English over Latinisms: usefor exampleorsuch asinstead ofe.g.,and so oninstead ofetc.,that isinstead ofi.e.,compared toinstead ofvs., andby,through, orusinginstead ofvia. Use industry-standard terms such as in silico, in vitro, and in vivo when appropriate, and italicize them in running text.
Usethatwithout commas for essential clauses, andwhichwith commas for nonessential clauses.
Format dates and times clearly: spell out months in body text; use forms such asJune 12, 2025; avoid numeric or ordinal dates; capitalize days; use 12-hour time when appropriate; include a space beforea.m.orp.m.; useETandPTfor needed time zones; avoid24/7; and preferfrom 12:30 to 1:00 p.m.for prose ranges.
Format numbers consistently: spell out zero through nine in body text, use numerals for 10 or greater and for technical values, use commas in thousands, do not begin a sentence with a numeral, spell out ordinals, and use numerals consistently within a category wh...
Files:
adapters/common/README.mddocs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.mdadapter-contract/pypi.mdskills/nemo-fabric-build-adapter/SKILL.mdexternal/nat/README.md
**/*.{md,mdx,yml,py,rs,sh}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/SKILL.md)
Keep documentation aligned with current NeMo Fabric behavior, repository layout, entry points, commands, package names, APIs, bindings, and support claims.
Files:
adapters/common/README.mdtests/adapter_contract/test_dependency_boundary.pydocs/adapter-contract/execution.mdadapter-contract/src/nemo_fabric_adapter_contract/pydantic_support.pydocs/adapter-contract/normalized-configuration.mdadapter-contract/pypi.mdtests/adapters/test_adapters_common_lifecycle.pyskills/nemo-fabric-build-adapter/SKILL.mdtests/adapters/test_hermes_config_builder.pyexternal/nat/src/nemo_fabric_adapters/nat/adapter.pytests/adapters/test_hermes_streaming.pytests/e2e/test_hermes_config_mapping.pytests/adapters/test_adapter_package_metadata.pytests/adapter_contract/test_agent_config.pyexternal/nat/README.mdadapter-contract/src/nemo_fabric_adapter_contract/codec.pytests/adapters/test_external_nat_adapter.pytests/adapter_contract/test_agent_execution.pyadapter-contract/src/nemo_fabric_adapter_contract/models.pyadapters/hermes/src/nemo_fabric_adapters/hermes/adapter.pytests/adapters/test_hermes_adapter.pyadapters/common/src/nemo_fabric_adapters/common/lifecycle.py
**/*.{md,mdx}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/SKILL.md)
**/*.{md,mdx}: Use the full product nameNVIDIA NeMo Fabricon first use, typically in the title and H1; useNeMo Fabricthereafter. Usefabricalone only for the CLI tool and surround it with backticks.
Treat incorrect or stale commands, package names, paths, APIs, support claims, procedures, examples, terminology, or public behavior documentation as blocking issues.
CapitalizeNVIDIAcorrectly and format code, commands, paths, and filenames as inline code where needed.
Use title case for technical-documentation headings.
Introduce code blocks, tables, and lists with complete lead-in sentences; ensure examples match current APIs and build commands.
Use descriptive anchor text, avoid raw URLs and generic labels such ashere, and use repository-relative.mdxpaths for links withindocs/.
Prefer active voice, present tense, short sentences, plain English, consistent terminology, and imperative, parallel, scannable procedures.
Useafterinstead ofoncewhen expressing temporal sequence, and usecanrather thanmaywhen describing possibility rather than permission.
Avoid ambiguous numeric dates and ordinal dates in body text.
For learning-oriented documentation, do not force trademark symbols unless the source document explicitly requires them.
When reporting documentation-review findings, lead withMust fix,Should fix, andNice to havecategories; include file path, line reference, current problem, rationale, and a concrete rewrite or direction.
Files:
adapters/common/README.mddocs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.mdadapter-contract/pypi.mdskills/nemo-fabric-build-adapter/SKILL.mdexternal/nat/README.md
**/*.md
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Update relevant SDK, API reference, adapter, example, integration, and support documentation when the corresponding public surface changes.
Files:
adapters/common/README.mddocs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.mdadapter-contract/pypi.mdskills/nemo-fabric-build-adapter/SKILL.mdexternal/nat/README.md
**/*.{html,md}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
HTML and Markdown files must use the specified SPDX HTML-comment header.
Files:
adapters/common/README.mddocs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.mdadapter-contract/pypi.mdskills/nemo-fabric-build-adapter/SKILL.mdexternal/nat/README.md
adapters/*/{README.md,fabric-adapter.json}
📄 CodeRabbit inference engine (.agents/skills/contribute-adapter/SKILL.md)
Document installation, supported configuration, harness-only settings, credentials, lifecycle, telemetry, artifacts, limitations, and focused test commands; keep documentation consistent with descriptor claims.
Files:
adapters/common/README.mdadapters/hermes/fabric-adapter.json
adapters/*/README.md
📄 CodeRabbit inference engine (.agents/skills/contribute-adapter/SKILL.md)
Provide a credential-free fixture covering
plan,doctor, andrun, plus a canonical typed SDK example and, when required, a canonical harness-native YAML fixture.
Files:
adapters/common/README.md
{adapters/**,examples/**}
⚙️ CodeRabbit configuration file
{adapters/**,examples/**}: Review adapter and example changes for command correctness, config/schema consistency, artifact handling, and compatibility with the public NeMo Fabric contracts.
Files:
adapters/common/README.mdadapters/hermes/fabric-adapter.jsonexamples/harbor/swebench/adapters/hermes/fabric-adapter.jsonadapters/hermes/pyproject.tomladapters/hermes/src/nemo_fabric_adapters/hermes/adapter.pyadapters/common/src/nemo_fabric_adapters/common/lifecycle.py
{*.md,**/*.md,**/*.mdx,**/*.ipynb}
⚙️ CodeRabbit configuration file
{*.md,**/*.md,**/*.mdx,**/*.ipynb}: Enforce the product name in user-facing prose: use "NVIDIA NeMo Fabric" on first use and "NeMo Fabric" thereafter. Flag standalone capitalized "Fabric" when it refers to the product. Do not flag the lowercasefabricCLI command, package/import/crate names, code identifiers, API symbols, configuration keys, file paths, or unrelated generic uses of the word.
Files:
adapters/common/README.mddocs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.mdadapter-contract/pypi.mdskills/nemo-fabric-build-adapter/SKILL.mdexternal/nat/README.md
**/*.{rs,py,pyi,json,yaml,yml}
📄 CodeRabbit inference engine (.agents/skills/contribute-api/SKILL.md)
Determine and update every affected public surface, including the CLI, PyO3 bindings, Python SDK, type stubs, schemas, and adapter contract, so they remain in parity.
Files:
tests/adapter_contract/test_dependency_boundary.pyadapter-contract/src/nemo_fabric_adapter_contract/pydantic_support.pytests/adapters/test_adapters_common_lifecycle.pycrates/fabric-cli/assets/adapters/hermes/fabric-adapter.jsonadapters/hermes/fabric-adapter.jsonexamples/harbor/swebench/adapters/hermes/fabric-adapter.jsontests/adapters/test_hermes_config_builder.pyexternal/nat/src/nemo_fabric_adapters/nat/adapter.pytests/adapters/test_hermes_streaming.pytests/e2e/test_hermes_config_mapping.pytests/adapters/test_adapter_package_metadata.pytests/adapter_contract/test_agent_config.pyadapter-contract/src/nemo_fabric_adapter_contract/codec.pytests/adapters/test_external_nat_adapter.pytests/adapter_contract/test_agent_execution.pyadapter-contract/src/nemo_fabric_adapter_contract/models.pyadapters/hermes/src/nemo_fabric_adapters/hermes/adapter.pytests/adapters/test_hermes_adapter.pyadapters/common/src/nemo_fabric_adapters/common/lifecycle.py
**/*.{rs,py}
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
For native binding changes, run
cargo check -p fabric-python --locked.Use
snake_casefor functions and variables; usePascalCasefor Rust types and Python classes.
Files:
tests/adapter_contract/test_dependency_boundary.pyadapter-contract/src/nemo_fabric_adapter_contract/pydantic_support.pytests/adapters/test_adapters_common_lifecycle.pytests/adapters/test_hermes_config_builder.pyexternal/nat/src/nemo_fabric_adapters/nat/adapter.pytests/adapters/test_hermes_streaming.pytests/e2e/test_hermes_config_mapping.pytests/adapters/test_adapter_package_metadata.pytests/adapter_contract/test_agent_config.pyadapter-contract/src/nemo_fabric_adapter_contract/codec.pytests/adapters/test_external_nat_adapter.pytests/adapter_contract/test_agent_execution.pyadapter-contract/src/nemo_fabric_adapter_contract/models.pyadapters/hermes/src/nemo_fabric_adapters/hermes/adapter.pytests/adapters/test_hermes_adapter.pyadapters/common/src/nemo_fabric_adapters/common/lifecycle.py
**/*.{py,pyi}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If Python code or a Python-facing adapter changes, run
just test-python.In Python SDK, adapters, examples, and tests, follow the existing style, use type annotations for public APIs, and keep native binding declarations synchronized with their Rust implementations.
Files:
tests/adapter_contract/test_dependency_boundary.pyadapter-contract/src/nemo_fabric_adapter_contract/pydantic_support.pytests/adapters/test_adapters_common_lifecycle.pytests/adapters/test_hermes_config_builder.pyexternal/nat/src/nemo_fabric_adapters/nat/adapter.pytests/adapters/test_hermes_streaming.pytests/e2e/test_hermes_config_mapping.pytests/adapters/test_adapter_package_metadata.pytests/adapter_contract/test_agent_config.pyadapter-contract/src/nemo_fabric_adapter_contract/codec.pytests/adapters/test_external_nat_adapter.pytests/adapter_contract/test_agent_execution.pyadapter-contract/src/nemo_fabric_adapter_contract/models.pyadapters/hermes/src/nemo_fabric_adapters/hermes/adapter.pytests/adapters/test_hermes_adapter.pyadapters/common/src/nemo_fabric_adapters/common/lifecycle.py
**/*.{rs,py,pyi}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
**/*.{rs,py,pyi}: If public configuration types change, confirm schema snapshot tests injust test-rustpass and review generated schema diffs.
For schema or public contract changes, run both language suites and review changes underschemas/and generated API references.
Files:
tests/adapter_contract/test_dependency_boundary.pyadapter-contract/src/nemo_fabric_adapter_contract/pydantic_support.pytests/adapters/test_adapters_common_lifecycle.pytests/adapters/test_hermes_config_builder.pyexternal/nat/src/nemo_fabric_adapters/nat/adapter.pytests/adapters/test_hermes_streaming.pytests/e2e/test_hermes_config_mapping.pytests/adapters/test_adapter_package_metadata.pytests/adapter_contract/test_agent_config.pyadapter-contract/src/nemo_fabric_adapter_contract/codec.pytests/adapters/test_external_nat_adapter.pytests/adapter_contract/test_agent_execution.pyadapter-contract/src/nemo_fabric_adapter_contract/models.pyadapters/hermes/src/nemo_fabric_adapters/hermes/adapter.pytests/adapters/test_hermes_adapter.pyadapters/common/src/nemo_fabric_adapters/common/lifecycle.py
**/*.{py,pyi,rs}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
For Python SDK or PyO3 binding changes, use
python-tests, run focused pytest tests first, thenjust test-python; rebuild withjust build-pythonwhen native code or packaging changes.Public contract changes must keep native Python binding declarations synchronized with their Rust implementations.
Files:
tests/adapter_contract/test_dependency_boundary.pyadapter-contract/src/nemo_fabric_adapter_contract/pydantic_support.pytests/adapters/test_adapters_common_lifecycle.pytests/adapters/test_hermes_config_builder.pyexternal/nat/src/nemo_fabric_adapters/nat/adapter.pytests/adapters/test_hermes_streaming.pytests/e2e/test_hermes_config_mapping.pytests/adapters/test_adapter_package_metadata.pytests/adapter_contract/test_agent_config.pyadapter-contract/src/nemo_fabric_adapter_contract/codec.pytests/adapters/test_external_nat_adapter.pytests/adapter_contract/test_agent_execution.pyadapter-contract/src/nemo_fabric_adapter_contract/models.pyadapters/hermes/src/nemo_fabric_adapters/hermes/adapter.pytests/adapters/test_hermes_adapter.pyadapters/common/src/nemo_fabric_adapters/common/lifecycle.py
**/*.{rs,py,toml}
📄 CodeRabbit inference engine (.agents/skills/update-project-version/SKILL.md)
When editing version helpers, verify every
nemo-fabric-*workspace package through Cargo metadata and reject a static version inpython/pyproject.toml.
Files:
tests/adapter_contract/test_dependency_boundary.pyadapter-contract/src/nemo_fabric_adapter_contract/pydantic_support.pyadapter-contract/pyproject.tomltests/adapters/test_adapters_common_lifecycle.pytests/adapters/test_hermes_config_builder.pyexternal/nat/src/nemo_fabric_adapters/nat/adapter.pyadapters/hermes/pyproject.tomltests/adapters/test_hermes_streaming.pytests/e2e/test_hermes_config_mapping.pytests/adapters/test_adapter_package_metadata.pytests/adapter_contract/test_agent_config.pyadapter-contract/src/nemo_fabric_adapter_contract/codec.pytests/adapters/test_external_nat_adapter.pytests/adapter_contract/test_agent_execution.pyadapter-contract/src/nemo_fabric_adapter_contract/models.pyadapters/hermes/src/nemo_fabric_adapters/hermes/adapter.pytests/adapters/test_hermes_adapter.pyadapters/common/src/nemo_fabric_adapters/common/lifecycle.py
**/*.{toml,rs,py}
📄 CodeRabbit inference engine (.agents/skills/update-project-version/SKILL.md)
Avoid blind repository-wide replacement of version-like strings; distinguish package-version references from examples and unrelated dependency versions.
Files:
tests/adapter_contract/test_dependency_boundary.pyadapter-contract/src/nemo_fabric_adapter_contract/pydantic_support.pyadapter-contract/pyproject.tomltests/adapters/test_adapters_common_lifecycle.pytests/adapters/test_hermes_config_builder.pyexternal/nat/src/nemo_fabric_adapters/nat/adapter.pyadapters/hermes/pyproject.tomltests/adapters/test_hermes_streaming.pytests/e2e/test_hermes_config_mapping.pytests/adapters/test_adapter_package_metadata.pytests/adapter_contract/test_agent_config.pyadapter-contract/src/nemo_fabric_adapter_contract/codec.pytests/adapters/test_external_nat_adapter.pytests/adapter_contract/test_agent_execution.pyadapter-contract/src/nemo_fabric_adapter_contract/models.pyadapters/hermes/src/nemo_fabric_adapters/hermes/adapter.pytests/adapters/test_hermes_adapter.pyadapters/common/src/nemo_fabric_adapters/common/lifecycle.py
tests/**/*.{rs,py}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
When adding functionality, include tests in the corresponding Rust crate or the relevant area under
tests/.
Files:
tests/adapter_contract/test_dependency_boundary.pytests/adapters/test_adapters_common_lifecycle.pytests/adapters/test_hermes_config_builder.pytests/adapters/test_hermes_streaming.pytests/e2e/test_hermes_config_mapping.pytests/adapters/test_adapter_package_metadata.pytests/adapter_contract/test_agent_config.pytests/adapters/test_external_nat_adapter.pytests/adapter_contract/test_agent_execution.pytests/adapters/test_hermes_adapter.py
tests/**/*.py
📄 CodeRabbit inference engine (.agents/skills/python-tests/SKILL.md)
tests/**/*.py: Use pytest to run Python tests.
Do not add@pytest.mark.asyncioto tests; async tests are automatically detected by the async runner.
Do not add-> Nonereturn type annotations to test functions.
When mocking a class, useunittest.mock.MagicMockorAsyncMock, using thespecargument when necessary, rather than defining a new class.
Prefix mocked class names withmock, notfake.
Prefer pytest fixtures over helper methods.
If a fixture is needed in multiple test files, define it once inconftest.pyrather than repeating it.
Define fixtures using@pytest.fixture(name="<fixture_name>"[, scope="<scope>"])and a<fixture_name>_fixturefunction; specifyscopeonly when it is notfunction.
Preferpytest.mark.parametrizeover separate tests for different input types.
Use@pytest.mark.usefixtureswhen a fixture is needed but its returned value is unused or it returns no value.
Avoid defensive programming in tests; access expected values directly so missing data raises a clear failure, such as usingresults["data"]instead ofresults.get("data").
When adapter installation metadata changes, packaging metadata tests must directly assert that the root project depends unconditionally on the exact-versionnemo-fabric-runtimedistribution.
Packaging metadata tests must verify that each root harness extra delegates to the matching version of the leaf adapter'sharnessextra.
Packaging metadata tests must verify that bare leaf dependencies remain adapter-owned and that the rootadapter-testsdependency group installs each leaf through itsharnessextra.
Packaging metadata tests must verify that every leaf providesfull; only adapters importing NeMo Relay Python APIs providerelay, while adapters using an external Relay executable havefullequal toharness.
Files:
tests/adapter_contract/test_dependency_boundary.pytests/adapters/test_adapters_common_lifecycle.pytests/adapters/test_hermes_config_builder.pytests/adapters/test_hermes_streaming.pytests/e2e/test_hermes_config_mapping.pytests/adapters/test_adapter_package_metadata.pytests/adapter_contract/test_agent_config.pytests/adapters/test_external_nat_adapter.pytests/adapter_contract/test_agent_execution.pytests/adapters/test_hermes_adapter.py
{tests/**,python/tests/**}
⚙️ CodeRabbit configuration file
{tests/**,python/tests/**}: Tests should cover the behavior promised by the changed API surface, including error paths, lifecycle cleanup, and SDK/native parity where relevant.
Files:
tests/adapter_contract/test_dependency_boundary.pytests/adapters/test_adapters_common_lifecycle.pytests/adapters/test_hermes_config_builder.pytests/adapters/test_hermes_streaming.pytests/e2e/test_hermes_config_mapping.pytests/adapters/test_adapter_package_metadata.pytests/adapter_contract/test_agent_config.pytests/adapters/test_external_nat_adapter.pytests/adapter_contract/test_agent_execution.pytests/adapters/test_hermes_adapter.py
{README.md,docs/**/*.{md,mdx,yml},examples/**/*.{md,mdx,yml}}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Keep package names, repository references, and build commands current in documentation and examples.
Files:
docs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.md
{docs/**/*.{md,mdx,yml},examples/**/*.{md,mdx,yml}}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Update relevant getting-started, reference, adapter, and example documentation when the corresponding examples or adapters change.
Files:
docs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.md
docs/**/*.{md,mdx,yml}
📄 CodeRabbit inference engine (.agents/skills/contribute-docs/SKILL.md)
Run
just docswhen the documentation site changes.
Files:
docs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.md
docs/**
📄 CodeRabbit inference engine (AGENTS.md)
Run just docs after changing the documentation site.
Files:
docs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.md
{docs/**,README.md,AGENTS.md}
⚙️ CodeRabbit configuration file
{docs/**,README.md,AGENTS.md}: Review documentation for technical accuracy against the current API, command correctness, and consistency with generated schemas.
For links between files under docs/, require paths relative to the source file with the target file's .mdx extension so they work in both Fern builds and repository browsers. Flag Fern site-root links such as NeMo Fabric overview; use the repository-relative equivalent, such as NeMo Fabric overview.
Files:
docs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.md
**/*.{rs,toml}
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
For any Rust change, run
just test-rustandcargo fmt --all -- --check.For Rust core, CLI, or shared runtime semantic changes, run Rust formatting and tests, and add Python tests when behavior is exposed through the SDK.
Use Rust stable tooling; format Rust code with
cargo fmt --all, verify formatting withcargo fmt --all -- --check, and compile withcargo check --workspace --locked.
Files:
adapter-contract/pyproject.tomladapters/hermes/pyproject.toml
**/{Cargo.toml,Cargo.lock,pyproject.toml,package.json}
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
For new or updated dependencies, document the functional need, alternatives considered, and why the selected dependency is the narrowest fit.
Files:
adapter-contract/pyproject.tomladapters/hermes/pyproject.toml
**/*.{toml,lock}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If a manifest or lockfile changes, run the license-diff script against
origin/main, review transitive license changes, and run theattributions-rustandattributions-pythonpre-commit hooks.
Files:
adapter-contract/pyproject.tomladapters/hermes/pyproject.toml
**/*.{yml,yaml,toml,lock}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
For CI or packaging changes, use
maintain-ciormaintain-packaging, then run recipes and checks whose behavior changed.
Files:
adapter-contract/pyproject.tomladapters/hermes/pyproject.toml
**/*.{toml,yaml,yml,sh,bash}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
TOML, YAML, and shell files must use the specified
#SPDX copyright and Apache-2.0 license headers.
Files:
adapter-contract/pyproject.tomladapters/hermes/pyproject.toml
**/{Cargo.toml,pyproject.toml}
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
**/{Cargo.toml,pyproject.toml}: Keep package names, dependency declarations, import paths, module names, and workspace or Python package metadata internally consistent.
Prefer the standard library, an existing dependency, or a small local implementation before adding a new direct dependency.
When multiple dependencies satisfy the requirement, prefer a maintained OSS option with clear SPDX metadata, a smaller transitive graph, and permissive licensing such as Apache-2.0, MIT, BSD, or ISC.
Files:
adapter-contract/pyproject.tomladapters/hermes/pyproject.toml
**/{Cargo.toml,pyproject.toml,Cargo.lock,uv.lock}
📄 CodeRabbit inference engine (.agents/skills/maintain-packaging/SKILL.md)
**/{Cargo.toml,pyproject.toml,Cargo.lock,uv.lock}: For new dependencies, record the functional need, viable alternatives considered, why the selected dependency is the narrowest fit, and any unresolved licensing question.
After updating manifests or lockfiles, runuv run --no-project python scripts/licensing/license_diff.py --base-ref origin/mainand review added packages and license changes.
Keep workspace, Python package, and lockfile versions aligned wherever the packaging contract requires alignment.
Files:
adapter-contract/pyproject.tomladapters/hermes/pyproject.toml
tests/adapters/**/*.py
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
tests/adapters/**/*.py: If an adapter or integration changes, run its focused tests.
For adapter behavior changes, run focused adapter tests undertests/adapters, then runjust test-python.
Files:
tests/adapters/test_adapters_common_lifecycle.pytests/adapters/test_hermes_config_builder.pytests/adapters/test_hermes_streaming.pytests/adapters/test_adapter_package_metadata.pytests/adapters/test_external_nat_adapter.pytests/adapters/test_hermes_adapter.py
**/SKILL.md
📄 CodeRabbit inference engine (.agents/skills/README.md)
Each maintainer skill file must begin with YAML frontmatter containing at least
nameanddescription.
Files:
skills/nemo-fabric-build-adapter/SKILL.md
⚙️ CodeRabbit configuration file
**/SKILL.md: Do not flag SKILL.md files for missing SPDX headers. Skill entrypoints intentionally start with YAML frontmatter instead.
Verify that every SKILL.md keeps valid YAML frontmatter with at least name and description fields before the Markdown body.
Files:
skills/nemo-fabric-build-adapter/SKILL.md
skills/**
📄 CodeRabbit inference engine (AGENTS.md)
skills/**: Keep consumer skills self-contained and dependent only on supported public Python SDK contracts and published documentation; do not include repository internals.
Do not add repository-internal contribution guidance to consumer skills.
Consumer skills must link to public GitHub documentation and example URLs rather than a docs-site domain so they remain portable when exported.
Files:
skills/nemo-fabric-build-adapter/SKILL.md
**/*.{json,jsonschema}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Public contract changes must keep checked-in JSON Schema snapshots synchronized.
Files:
crates/fabric-cli/assets/adapters/hermes/fabric-adapter.jsonadapters/hermes/fabric-adapter.jsonexamples/harbor/swebench/adapters/hermes/fabric-adapter.json
adapters/*/fabric-adapter.json
📄 CodeRabbit inference engine (.agents/skills/contribute-adapter/SKILL.md)
Define a narrow, truthful adapter descriptor; keep
config.accepts,config.generates, requirements, telemetry declarations, lifecycle capabilities, and advertised capabilities synchronized with implementation and tests.
Files:
adapters/hermes/fabric-adapter.json
{pyproject.toml,adapters/**/pyproject.toml}
📄 CodeRabbit inference engine (.agents/skills/update-project-version/SKILL.md)
{pyproject.toml,adapters/**/pyproject.toml}: Update the literalproject.versionin the root setuptools project and every adapterpyproject.toml.
Keep internal exact-version requirements aligned: rootnemo-fabric-* == <version>optional dependencies and each adapter'snemo-fabric-adapters-common == <version>dependency.
Files:
adapters/hermes/pyproject.toml
adapters/*/pyproject.toml
📄 CodeRabbit inference engine (.agents/skills/contribute-adapter/SKILL.md)
adapters/*/pyproject.toml: Keep leaf adapter runtime dependencies razor-thin and adapter-owned. Do not declare the wrapped harness/SDK or dependencies already declared by its supported package; provide dependency-free fallbacks for optional libraries.
Provide every installable Python leaf adapter with aharnessextra and afullextra for package-installable integrations; provide arelayextra when importing NeMo Relay Python APIs, but not when Relay is an external executable.
For packaged harnesses, declare and document aharnessversion constraint supported by upstream contracts and test evidence; do not claim a broader range than the evidence supports.
Files:
adapters/hermes/pyproject.toml
adapters/*/{pyproject.toml,uv.lock}
📄 CodeRabbit inference engine (.agents/skills/contribute-adapter/SKILL.md)
Keep each adapter package independent and small, using Python package metadata and lock files as applicable.
Files:
adapters/hermes/pyproject.toml
adapters/*/src/**/*.py
📄 CodeRabbit inference engine (.agents/skills/contribute-adapter/SKILL.md)
adapters/*/src/**/*.py: Implement adapters using the existing Fabricpythonorprocessrunner and normalized request/result contracts; do not add a runner or one-off abstraction for a single adapter.
Treat normalizedconfig, Fabric-resolved plans, andruntime_contextas authoritative; reserveharness.settingsfor adapter-wide behavior and apply precedence in the order: normalized config, plans/context, harness settings, descriptor/default values.
Reject conflicting duplicate declarations and unsupported behavior with actionable errors naming the field and supported alternatives; never silently drop configuration.
Validate dependency versions, hooks, and credentials before harness invocation, and never expose credential values in outputs, errors, events, logs, or fixtures.
Forward only required system, selected credential, telemetry, and documented harness-specific environment variables; never forward or log unrelated environment values.
Maintain one local adapter host per Fabric runtime across orderedstart→invoke*→stopoperations. Emit one JSON lifecycle response per request on stdout and diagnostics on stderr.
Return harness-level invocation failures as successful lifecycle responses containingresponse: null,failed: true, and structurederrorfields (code,message,retryable, and optionalmetadata).
Do not emit NeMo Relay stream records on adapter stdout; return exactly one terminal lifecycle response while streaming occurs through the SDK-owned out-of-band endpoint.
Scope workspace, generated configuration, state, sessions, and artifacts to the resolved runtime context, and isolate stateful adapter instances by Fabric runtime ID.
Usestartto initialize adapter-owned harness state, retain it for continuation across repeatedinvokecalls on the same runtime, and release it instop.
Files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.pyadapters/common/src/nemo_fabric_adapters/common/lifecycle.py
🧠 Learnings (4)
📚 Learning: 2026-08-07T07:15:59.993Z
Learnt from: AnuradhaKaruppiah
Repo: NVIDIA/NeMo-Fabric PR: 186
File: docs/adapter-contract/registration-and-discovery.md:103-104
Timestamp: 2026-08-07T07:15:59.993Z
Learning: Keep documentation files under docs/adapter-contract/ in portable Markdown (.md), not MDX. GitHub and the public authoring skill consume these files directly, and the NVIDIA NeMo Fabric documentation pipeline accepts them without conversion; do not flag the lack of MDX conversion for these files.
Applied to files:
docs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.md
📚 Learning: 2026-08-07T16:20:01.603Z
Learnt from: AnuradhaKaruppiah
Repo: NVIDIA/NeMo-Fabric PR: 186
File: docs/adapter-contract/README.md:1-4
Timestamp: 2026-08-07T16:20:01.603Z
Learning: For maintained Markdown files under docs/adapter-contract/, Fern parses content as MDX. Write SPDX license headers as JSX comments (`{/* ... */}`), not HTML comments, because HTML comments cause Fern parsing failures. This JSX form is accepted by the repository copyright checker and validated by Docs Preview.
Applied to files:
docs/adapter-contract/execution.mddocs/adapter-contract/normalized-configuration.md
📚 Learning: 2026-06-29T22:34:52.407Z
Learnt from: AjayThorve
Repo: NVIDIA/NeMo-Fabric PR: 27
File: adapters/codex-cli/fabric-adapter.json:13-15
Timestamp: 2026-06-29T22:34:52.407Z
Learning: In NeMo-Fabric adapter manifest files (e.g., `*/fabric-adapter.json`), keep `config.accepts` limited to the top-level Fabric capability sections that `resolve_capability_plan` consumes (such as `models`, `tools`, `mcp`, `skills`, `telemetry`). Do not add adapter-owned `harness.settings` keys to `config.accepts`; `harness.settings` should remain adapter-owned and be passed through unchanged.
Applied to files:
crates/fabric-cli/assets/adapters/hermes/fabric-adapter.jsonadapters/hermes/fabric-adapter.jsonexamples/harbor/swebench/adapters/hermes/fabric-adapter.json
📚 Learning: 2026-07-09T22:28:51.689Z
Learnt from: AjayThorve
Repo: NVIDIA/NeMo-Fabric PR: 43
File: adapters/claude-sdk/src/nemo_fabric_adapters/claude_sdk/adapter.py:164-168
Timestamp: 2026-07-09T22:28:51.689Z
Learning: In the NeMo-Fabric adapters, treat path values used in Fabric adapter configuration (including logic like `_resolve_path` in adapter.py) as config-root-relative. Do not apply `Path.expanduser()` (or otherwise apply `~`/home or shell-style expansion), because it will make the resolved paths normalize inconsistently across adapters. Also, do not rely on or add any resolution behavior that uses `harness.settings.cwd` as an override point for these adapter paths—`harness.settings.cwd` is explicitly unsupported in this adapter context.
Applied to files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
🪛 ast-grep (0.45.0)
tests/adapter_contract/test_dependency_boundary.py
[error] 43-43: Command coming from incoming request
Context: subprocess.run([sys.executable, "-c", script], check=True, env=env)
Note: [CWE-78] Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection').
(subprocess-from-request)
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
[info] 428-428: use jsonify instead of json.dumps for JSON output
Context: json.dumps(user_message, sort_keys=True)
Note: [CWE-116] Improper Encoding or Escaping of Output.
(use-jsonify)
🪛 Ruff (0.16.1)
tests/adapter_contract/test_dependency_boundary.py
[error] 44-44: subprocess call: check for execution of untrusted input
(S603)
adapter-contract/src/nemo_fabric_adapter_contract/pydantic_support.py
[warning] 40-40: Avoid specifying long messages outside the exception class
(TRY003)
tests/e2e/test_hermes_config_mapping.py
[error] 66-66: Probable insecure usage of temporary file or directory: "/tmp/fabric-skills/code-review"
(S108)
adapter-contract/src/nemo_fabric_adapter_contract/codec.py
[warning] 43-43: Remove quotes from type annotation
Remove quotes
(UP037)
[warning] 49-49: Dynamically typed expressions (typing.Any) are disallowed in value
(ANN401)
[warning] 58-58: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 69-71: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 74-74: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 84-84: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 88-88: Dynamically typed expressions (typing.Any) are disallowed in value
(ANN401)
[warning] 94-94: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 96-96: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 101-104: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 113-116: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 129-129: Dynamically typed expressions (typing.Any) are disallowed in instance
(ANN401)
[warning] 144-144: Dynamically typed expressions (typing.Any) are disallowed in instance
(ANN401)
[warning] 158-158: Too many return statements (18 > 6)
(PLR0911)
[warning] 158-158: Too many branches (33 > 12)
(PLR0912)
[warning] 158-158: Too many statements (58 > 50)
(PLR0915)
[warning] 159-159: Dynamically typed expressions (typing.Any) are disallowed in annotation
(ANN401)
[warning] 160-160: Dynamically typed expressions (typing.Any) are disallowed in value
(ANN401)
[warning] 164-164: Dynamically typed expressions (typing.Any) are disallowed in _decode_value
(ANN401)
[warning] 185-187: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 194-194: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 199-199: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 207-207: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 223-223: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 231-234: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 239-239: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 243-243: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 247-247: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 251-251: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 254-254: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 258-258: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 262-262: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 265-265: Dynamically typed expressions (typing.Any) are disallowed in value
(ANN401)
[warning] 265-265: Dynamically typed expressions (typing.Any) are disallowed in _encode_value
(ANN401)
adapter-contract/src/nemo_fabric_adapter_contract/models.py
[warning] 27-27: Missing return type annotation for private function _optional
(ANN202)
[warning] 27-27: Dynamically typed expressions (typing.Any) are disallowed in default
(ANN401)
[warning] 31-31: Missing return type annotation for private function _empty_dict
(ANN202)
[warning] 35-35: Missing return type annotation for private function _json_dict
(ANN202)
[warning] 39-39: Missing return type annotation for private function _empty_list
(ANN202)
[warning] 43-43: Missing return type annotation for private function _json_value_field
(ANN202)
[warning] 43-43: Dynamically typed expressions (typing.Any) are disallowed in default
(ANN401)
[warning] 54-54: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 59-62: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 84-84: Dynamically typed expressions (typing.Any) are disallowed in value
(ANN401)
[warning] 99-99: Do not perform function call _json_dict in dataclass defaults
(RUF009)
[warning] 105-105: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 117-117: Do not perform function call _json_dict in dataclass defaults
(RUF009)
[warning] 129-129: Do not perform function call _json_dict in dataclass defaults
(RUF009)
[warning] 137-140: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 163-163: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 174-177: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 184-184: Do not perform function call _empty_list in dataclass defaults
(RUF009)
[warning] 189-192: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 201-201: Do not perform function call _empty_list in dataclass defaults
(RUF009)
[warning] 202-202: Do not perform function call _empty_dict in dataclass defaults
(RUF009)
[warning] 203-203: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 204-204: Do not perform function call _empty_list in dataclass defaults
(RUF009)
[warning] 215-217: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 224-224: Do not perform function call _empty_dict in dataclass defaults
(RUF009)
[warning] 233-233: Do not perform function call _json_dict in dataclass defaults
(RUF009)
[warning] 244-244: Do not perform function call _empty_dict in dataclass defaults
(RUF009)
[warning] 245-245: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 246-246: Do not perform function call _empty_list in dataclass defaults
(RUF009)
[warning] 255-257: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 277-277: Do not perform function call _json_dict in dataclass defaults
(RUF009)
[warning] 284-284: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 285-285: Do not perform function call _empty_dict in dataclass defaults
(RUF009)
[warning] 286-286: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 287-287: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 288-288: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 289-289: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 290-290: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 291-291: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 298-298: Do not perform function call _json_value_field in dataclass defaults
(RUF009)
[warning] 299-299: Do not perform function call _json_dict in dataclass defaults
(RUF009)
[warning] 335-338: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 372-374: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 382-382: Do not perform function call _json_value_field in dataclass defaults
(RUF009)
[warning] 383-383: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 384-384: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 385-385: Do not perform function call _empty_list in dataclass defaults
(RUF009)
[warning] 389-389: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 391-391: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 415-415: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 416-416: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 417-417: Do not perform function call _empty_dict in dataclass defaults
(RUF009)
[warning] 419-419: Do not perform function call _json_dict in dataclass defaults
(RUF009)
[warning] 420-420: Do not perform function call _json_dict in dataclass defaults
(RUF009)
[warning] 435-435: Do not perform function call _json_dict in dataclass defaults
(RUF009)
[warning] 448-448: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 449-449: Do not perform function call _empty_list in dataclass defaults
(RUF009)
[warning] 457-457: Do not perform function call _optional in dataclass defaults
(RUF009)
[warning] 458-458: Do not perform function call _empty_dict in dataclass defaults
(RUF009)
[warning] 459-459: Do not perform function call _json_dict in dataclass defaults
(RUF009)
[warning] 471-471: Do not perform function call _optional in dataclass defaults
(RUF009)
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
[warning] 52-52: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 295-298: Abstract raise to an inner function
(TRY301)
[warning] 339-339: Abstract raise to an inner function
(TRY301)
[warning] 339-339: Avoid specifying long messages outside the exception class
(TRY003)
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
tests/adapters/test_hermes_adapter.py (1)
67-87: 🗄️ Data Integrity & Integration | 🟡 Minor | ⚡ Quick winValidate all Hermes descriptor copies in the test. Assert
contract_version,config.input, andconfig.acceptsfor all three descriptor paths. The current test reads onlyadapters/hermes/fabric-adapter.json, so packaged copies can drift undetected.🤖 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 `@tests/adapters/test_hermes_adapter.py` around lines 67 - 87, Update test_descriptor_uses_the_typed_agent_config_contract to load and validate all three Hermes descriptor paths, including packaged copies, rather than only adapters/hermes/fabric-adapter.json. For each descriptor, assert contract_version, config.input, and the complete expected config.accepts list using the same values already defined in the test.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@tests/adapters/test_hermes_adapter.py`:
- Around line 67-87: Update test_descriptor_uses_the_typed_agent_config_contract
to load and validate all three Hermes descriptor paths, including packaged
copies, rather than only adapters/hermes/fabric-adapter.json. For each
descriptor, assert contract_version, config.input, and the complete expected
config.accepts list using the same values already defined in the test.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Enterprise
Run ID: 63c8dbfc-1f3c-4c29-bd51-b76d774b2a93
📒 Files selected for processing (1)
tests/adapters/test_hermes_adapter.py
📜 Review details
⏰ Context from checks skipped due to timeout. (18)
- GitHub Check: Preview docs
- GitHub Check: Test (Python 3.13, windows-amd64)
- GitHub Check: Test (Python 3.12, windows-amd64)
- GitHub Check: Test (Python 3.11, windows-amd64)
- GitHub Check: Test (Python 3.14, windows-amd64)
- GitHub Check: Test (Python 3.12, macos-arm64)
- GitHub Check: Test (Python 3.11, macos-arm64)
- GitHub Check: Test (Python 3.12, linux-arm64)
- GitHub Check: Test (Python 3.14, macos-arm64)
- GitHub Check: Test (Python 3.13, macos-arm64)
- GitHub Check: Test (Python 3.12, linux-amd64)
- GitHub Check: Test (Python 3.13, linux-arm64)
- GitHub Check: Test (Python 3.13, linux-amd64)
- GitHub Check: Test (Python 3.14, linux-arm64)
- GitHub Check: Test (Python 3.11, linux-arm64)
- GitHub Check: Test (Python 3.14, linux-amd64)
- GitHub Check: Test (Python 3.11, linux-amd64)
- GitHub Check: Pre-commit
🧰 Additional context used
📓 Path-based instructions (13)
**/*.{rs,py,pyi,json,yaml,yml}
📄 CodeRabbit inference engine (.agents/skills/contribute-api/SKILL.md)
Determine and update every affected public surface, including the CLI, PyO3 bindings, Python SDK, type stubs, schemas, and adapter contract, so they remain in parity.
Files:
tests/adapters/test_hermes_adapter.py
**/*
📄 CodeRabbit inference engine (.agents/skills/karpathy-guidelines/SKILL.md)
**/*: Before implementing, explicitly state assumptions, surface ambiguity and tradeoffs, present multiple interpretations when relevant, and ask for clarification rather than silently deciding or proceeding when requirements are unclear.
Prefer the minimum code needed to solve the requested problem: avoid speculative features, unnecessary abstractions, unrequested flexibility, and handling of impossible scenarios; simplify overcomplicated solutions.
When editing existing code, make surgical changes only: do not modify unrelated code, comments, formatting, or pre-existing dead code; match the existing style, and remove only unused imports, variables, or functions introduced by your changes.
Define verifiable success criteria for each task, such as writing regression tests for bugs and invalid-input tests for validation, then verify the implementation against those criteria. For multi-step work, state a brief plan with a verification check for each step.
**/*: Always spellNVIDIAin all caps; do not useNvidia,nvidia,nVidia,nVIDIA, orNV.
Usean NVIDIAbefore a noun, because the name begins with an “en” sound.
Do not add a registered trademark symbol afterNVIDIAwhen referring to the company; use trademark symbols with product names only when required by the document type or legal guidance.
Verify official capitalization, spacing, hyphenation, and spelling for NVIDIA and third-party product names; do not rewrite official product names for grammar or title-case rules.
Precede NVIDIA product names withNVIDIAon first mention when natural and accurate, and link the first mention when the destination helps the reader.
On first use, include the company name and full model qualifier when it helps identify the model; preserve official capitalization and punctuation, and use shorter family names only after establishing the full name.
For learning-oriented and developer content, do not force trademark symbols unless explicitly required; for press, ...
Files:
tests/adapters/test_hermes_adapter.py
**/*.{rs,py}
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
For native binding changes, run
cargo check -p fabric-python --locked.Use
snake_casefor functions and variables; usePascalCasefor Rust types and Python classes.
Files:
tests/adapters/test_hermes_adapter.py
**/*.{py,pyi}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If Python code or a Python-facing adapter changes, run
just test-python.In Python SDK, adapters, examples, and tests, follow the existing style, use type annotations for public APIs, and keep native binding declarations synchronized with their Rust implementations.
Files:
tests/adapters/test_hermes_adapter.py
**/*.{rs,py,pyi}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
**/*.{rs,py,pyi}: If public configuration types change, confirm schema snapshot tests injust test-rustpass and review generated schema diffs.
For schema or public contract changes, run both language suites and review changes underschemas/and generated API references.
Files:
tests/adapters/test_hermes_adapter.py
tests/adapters/**/*.py
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
tests/adapters/**/*.py: If an adapter or integration changes, run its focused tests.
For adapter behavior changes, run focused adapter tests undertests/adapters, then runjust test-python.
Files:
tests/adapters/test_hermes_adapter.py
**/*.{py,pyi,rs}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
For Python SDK or PyO3 binding changes, use
python-tests, run focused pytest tests first, thenjust test-python; rebuild withjust build-pythonwhen native code or packaging changes.Public contract changes must keep native Python binding declarations synchronized with their Rust implementations.
Files:
tests/adapters/test_hermes_adapter.py
**/*.{rs,py,toml}
📄 CodeRabbit inference engine (.agents/skills/update-project-version/SKILL.md)
When editing version helpers, verify every
nemo-fabric-*workspace package through Cargo metadata and reject a static version inpython/pyproject.toml.
Files:
tests/adapters/test_hermes_adapter.py
**/*.{toml,rs,py}
📄 CodeRabbit inference engine (.agents/skills/update-project-version/SKILL.md)
Avoid blind repository-wide replacement of version-like strings; distinguish package-version references from examples and unrelated dependency versions.
Files:
tests/adapters/test_hermes_adapter.py
**/*.{md,mdx,yml,py,rs,sh}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/SKILL.md)
Keep documentation aligned with current NeMo Fabric behavior, repository layout, entry points, commands, package names, APIs, bindings, and support claims.
Files:
tests/adapters/test_hermes_adapter.py
tests/**/*.{rs,py}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
When adding functionality, include tests in the corresponding Rust crate or the relevant area under
tests/.
Files:
tests/adapters/test_hermes_adapter.py
tests/**/*.py
📄 CodeRabbit inference engine (.agents/skills/python-tests/SKILL.md)
tests/**/*.py: Use pytest to run Python tests.
Do not add@pytest.mark.asyncioto tests; async tests are automatically detected by the async runner.
Do not add-> Nonereturn type annotations to test functions.
When mocking a class, useunittest.mock.MagicMockorAsyncMock, using thespecargument when necessary, rather than defining a new class.
Prefix mocked class names withmock, notfake.
Prefer pytest fixtures over helper methods.
If a fixture is needed in multiple test files, define it once inconftest.pyrather than repeating it.
Define fixtures using@pytest.fixture(name="<fixture_name>"[, scope="<scope>"])and a<fixture_name>_fixturefunction; specifyscopeonly when it is notfunction.
Preferpytest.mark.parametrizeover separate tests for different input types.
Use@pytest.mark.usefixtureswhen a fixture is needed but its returned value is unused or it returns no value.
Avoid defensive programming in tests; access expected values directly so missing data raises a clear failure, such as usingresults["data"]instead ofresults.get("data").
When adapter installation metadata changes, packaging metadata tests must directly assert that the root project depends unconditionally on the exact-versionnemo-fabric-runtimedistribution.
Packaging metadata tests must verify that each root harness extra delegates to the matching version of the leaf adapter'sharnessextra.
Packaging metadata tests must verify that bare leaf dependencies remain adapter-owned and that the rootadapter-testsdependency group installs each leaf through itsharnessextra.
Packaging metadata tests must verify that every leaf providesfull; only adapters importing NeMo Relay Python APIs providerelay, while adapters using an external Relay executable havefullequal toharness.
Files:
tests/adapters/test_hermes_adapter.py
{tests/**,python/tests/**}
⚙️ CodeRabbit configuration file
{tests/**,python/tests/**}: Tests should cover the behavior promised by the changed API surface, including error paths, lifecycle cleanup, and SDK/native parity where relevant.
Files:
tests/adapters/test_hermes_adapter.py
🔇 Additional comments (3)
tests/adapters/test_hermes_adapter.py (3)
32-35: LGTM!Also applies to: 193-230, 280-303, 343-378, 412-440, 502-509, 519-529, 545-555, 627-640, 654-665, 744-756, 767-768, 826-826, 847-850
18-19: 🩺 Stability & AvailabilityRemove this comment
> Likely an incorrect or invalid review comment.
567-596: 🗄️ Data Integrity & IntegrationRetain the current coverage.
AgentConfig.from_mappingis the intended normalization boundary. Lifecycle tests cover valid conversion and invalid mappings before runtime creation, and Hermes tests cover direct rejection of untyped configuration. No additional nested-mapping rejection test is required here.
Signed-off-by: Zhongxuan Wang <daniewang@nvidia.com>
Signed-off-by: Zhongxuan Wang <daniewang@nvidia.com>
81044d8 to
af9716f
Compare
Signed-off-by: Zhongxuan Wang <daniewang@nvidia.com>
Signed-off-by: Zhongxuan Wang <daniewang@nvidia.com>
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py`:
- Around line 302-305: Update the environment setup in the Hermes adapter
initialization to assign TERMINAL_TIMEOUT from the normalized runtime
configuration, replacing setdefault so each runtime’s
harness.settings.terminal_timeout or default value is authoritative. Add a
regression test that starts two runtimes sequentially with different timeout
values and verifies the second runtime applies its own timeout.
🪄 Autofix
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: cb72a2fe-5a31-420c-a27b-8acb4e068931
📒 Files selected for processing (1)
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
📜 Review details
⏰ Context from checks skipped due to timeout. (19)
- GitHub Check: Preview docs
- GitHub Check: Test (Python 3.13, macos-arm64)
- GitHub Check: Test (Python 3.13, windows-amd64)
- GitHub Check: Test (Python 3.14, macos-arm64)
- GitHub Check: Test (Python 3.11, linux-amd64)
- GitHub Check: Test (Python 3.12, macos-arm64)
- GitHub Check: Test (Python 3.13, linux-amd64)
- GitHub Check: Test (Python 3.11, macos-arm64)
- GitHub Check: Test (Python 3.12, windows-amd64)
- GitHub Check: Test (Python 3.11, windows-amd64)
- GitHub Check: Test (Python 3.11, linux-arm64)
- GitHub Check: Test (Python 3.12, linux-arm64)
- GitHub Check: Test (Python 3.12, linux-amd64)
- GitHub Check: Test (Python 3.14, linux-amd64)
- GitHub Check: Test (Python 3.14, windows-amd64)
- GitHub Check: Test (Python 3.13, linux-arm64)
- GitHub Check: Test (arm64)
- GitHub Check: Test (Python 3.14, linux-arm64)
- GitHub Check: Pre-commit
🧰 Additional context used
📓 Path-based instructions (11)
**/*.{rs,py,pyi,json,yaml,yml}
📄 CodeRabbit inference engine (.agents/skills/contribute-api/SKILL.md)
Determine and update every affected public surface, including the CLI, PyO3 bindings, Python SDK, type stubs, schemas, and adapter contract, so they remain in parity.
Files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
**/*
📄 CodeRabbit inference engine (.agents/skills/karpathy-guidelines/SKILL.md)
**/*: Before implementing, explicitly state assumptions, surface ambiguity and tradeoffs, present multiple interpretations when relevant, and ask for clarification rather than silently deciding or proceeding when requirements are unclear.
Prefer the minimum code needed to solve the requested problem: avoid speculative features, unnecessary abstractions, unrequested flexibility, and handling of impossible scenarios; simplify overcomplicated solutions.
When editing existing code, make surgical changes only: do not modify unrelated code, comments, formatting, or pre-existing dead code; match the existing style, and remove only unused imports, variables, or functions introduced by your changes.
Define verifiable success criteria for each task, such as writing regression tests for bugs and invalid-input tests for validation, then verify the implementation against those criteria. For multi-step work, state a brief plan with a verification check for each step.
**/*: Always spellNVIDIAin all caps; do not useNvidia,nvidia,nVidia,nVIDIA, orNV.
Usean NVIDIAbefore a noun, because the name begins with an “en” sound.
Do not add a registered trademark symbol afterNVIDIAwhen referring to the company; use trademark symbols with product names only when required by the document type or legal guidance.
Verify official capitalization, spacing, hyphenation, and spelling for NVIDIA and third-party product names; do not rewrite official product names for grammar or title-case rules.
Precede NVIDIA product names withNVIDIAon first mention when natural and accurate, and link the first mention when the destination helps the reader.
On first use, include the company name and full model qualifier when it helps identify the model; preserve official capitalization and punctuation, and use shorter family names only after establishing the full name.
For learning-oriented and developer content, do not force trademark symbols unless explicitly required; for press, ...
Files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
**/*.{rs,py}
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
For native binding changes, run
cargo check -p fabric-python --locked.Use
snake_casefor functions and variables; usePascalCasefor Rust types and Python classes.
Files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
**/*.{py,pyi}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If Python code or a Python-facing adapter changes, run
just test-python.In Python SDK, adapters, examples, and tests, follow the existing style, use type annotations for public APIs, and keep native binding declarations synchronized with their Rust implementations.
Files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
**/*.{rs,py,pyi}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
**/*.{rs,py,pyi}: If public configuration types change, confirm schema snapshot tests injust test-rustpass and review generated schema diffs.
For schema or public contract changes, run both language suites and review changes underschemas/and generated API references.
Files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
**/*.{py,pyi,rs}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
For Python SDK or PyO3 binding changes, use
python-tests, run focused pytest tests first, thenjust test-python; rebuild withjust build-pythonwhen native code or packaging changes.Public contract changes must keep native Python binding declarations synchronized with their Rust implementations.
Files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
**/*.{rs,py,toml}
📄 CodeRabbit inference engine (.agents/skills/update-project-version/SKILL.md)
When editing version helpers, verify every
nemo-fabric-*workspace package through Cargo metadata and reject a static version inpython/pyproject.toml.
Files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
**/*.{toml,rs,py}
📄 CodeRabbit inference engine (.agents/skills/update-project-version/SKILL.md)
Avoid blind repository-wide replacement of version-like strings; distinguish package-version references from examples and unrelated dependency versions.
Files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
**/*.{md,mdx,yml,py,rs,sh}
📄 CodeRabbit inference engine (.agents/skills/review-doc-style/SKILL.md)
Keep documentation aligned with current NeMo Fabric behavior, repository layout, entry points, commands, package names, APIs, bindings, and support claims.
Files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
adapters/*/src/**/*.py
📄 CodeRabbit inference engine (.agents/skills/contribute-adapter/SKILL.md)
adapters/*/src/**/*.py: Implement adapters using the existing Fabricpythonorprocessrunner and normalized request/result contracts; do not add a runner or one-off abstraction for a single adapter.
Treat normalizedconfig, Fabric-resolved plans, andruntime_contextas authoritative; reserveharness.settingsfor adapter-wide behavior and apply precedence in the order: normalized config, plans/context, harness settings, descriptor/default values.
Reject conflicting duplicate declarations and unsupported behavior with actionable errors naming the field and supported alternatives; never silently drop configuration.
Validate dependency versions, hooks, and credentials before harness invocation, and never expose credential values in outputs, errors, events, logs, or fixtures.
Forward only required system, selected credential, telemetry, and documented harness-specific environment variables; never forward or log unrelated environment values.
Maintain one local adapter host per Fabric runtime across orderedstart→invoke*→stopoperations. Emit one JSON lifecycle response per request on stdout and diagnostics on stderr.
Return harness-level invocation failures as successful lifecycle responses containingresponse: null,failed: true, and structurederrorfields (code,message,retryable, and optionalmetadata).
Do not emit NeMo Relay stream records on adapter stdout; return exactly one terminal lifecycle response while streaming occurs through the SDK-owned out-of-band endpoint.
Scope workspace, generated configuration, state, sessions, and artifacts to the resolved runtime context, and isolate stateful adapter instances by Fabric runtime ID.
Usestartto initialize adapter-owned harness state, retain it for continuation across repeatedinvokecalls on the same runtime, and release it instop.
Files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
{adapters/**,examples/**}
⚙️ CodeRabbit configuration file
{adapters/**,examples/**}: Review adapter and example changes for command correctness, config/schema consistency, artifact handling, and compatibility with the public NeMo Fabric contracts.
Files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
🧠 Learnings (1)
📚 Learning: 2026-07-09T22:28:51.689Z
Learnt from: AjayThorve
Repo: NVIDIA/NeMo-Fabric PR: 43
File: adapters/claude-sdk/src/nemo_fabric_adapters/claude_sdk/adapter.py:164-168
Timestamp: 2026-07-09T22:28:51.689Z
Learning: In the NeMo-Fabric adapters, treat path values used in Fabric adapter configuration (including logic like `_resolve_path` in adapter.py) as config-root-relative. Do not apply `Path.expanduser()` (or otherwise apply `~`/home or shell-style expansion), because it will make the resolved paths normalize inconsistently across adapters. Also, do not rely on or add any resolution behavior that uses `harness.settings.cwd` as an override point for these adapter paths—`harness.settings.cwd` is explicitly unsupported in this adapter context.
Applied to files:
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
🪛 Ruff (0.16.1)
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py
[warning] 330-330: Abstract raise to an inner function
(TRY301)
[warning] 330-330: Avoid specifying long messages outside the exception class
(TRY003)
[warning] 612-612: Dynamically typed expressions (typing.Any) are disallowed in func
(ANN401)
[warning] 612-612: Dynamically typed expressions (typing.Any) are disallowed in **kwargs
(ANN401)
🔇 Additional comments (1)
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py (1)
284-286: LGTM!Also applies to: 324-331, 359-384, 420-428, 468-468, 598-612
77cc52f to
6866910
Compare
2086a36 to
77cc52f
Compare
Signed-off-by: Zhongxuan Wang <daniewang@nvidia.com>
Signed-off-by: Zhongxuan Wang <daniewang@nvidia.com>
Signed-off-by: Zhongxuan Wang <daniewang@nvidia.com>
Signed-off-by: Zhongxuan Wang <daniewang@nvidia.com>
Signed-off-by: Zhongxuan Wang <daniewang@nvidia.com>
zhongxuanwang-nv
changed the title
AjayThorve
left a comment
AjayThorve
left a comment
There was a problem hiding this comment.
Looks pretty good, approved!
2 participants
Overview
Moves the Hermes Agent adapter onto the typed
fabric.adapter/v1alpha2agent_configinput, now available onmainthrough #190.Hermes directly imports the internal
nemo-fabric-adapter-contractpackage because it owns the typed lifecycle boundary. This adds no third-party dependency or license change.Details
AgentConfigat the lifecycle boundary and maps typed models, instructions, runtime settings, tools, MCP servers, and skills into Hermes configuration.Validation
uv run --no-sync pytest tests/adapters/test_hermes_adapter.py tests/adapters/test_hermes_config_builder.py tests/adapters/test_hermes_streaming.py tests/e2e/test_hermes_config_mapping.py tests/adapters/test_adapter_package_metadata.py(49 passed)just test-python(722 passed, 16 skipped)just test-rustWhere should the reviewer start?
Start with
adapters/hermes/src/nemo_fabric_adapters/hermes/adapter.py, especiallymain,build_hermes_config, andHermesRuntime.start.tests/adapters/test_hermes_adapter.pycovers the typed lifecycle boundary;tests/e2e/test_hermes_config_mapping.pycovers generated configuration portability.Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)
Relates to FABRIC-187
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.
Summary by CodeRabbit
New Features
Bug Fixes