feat(codec): add OCI Generative AI provider support - #554
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:
WalkthroughAdds OCI GenAI request and response variants, codecs for GENERIC, COHERE, and COHEREV2 formats, provider registration, middleware integrations, language bindings, observability mapping, and validation coverage. ChangesOCI GenAI provider support
Estimated code review effort: 5 (Critical) | ~100 minutes Sequence Diagram(s)sequenceDiagram
participant Client as Client request
participant Resolver as Provider resolver
participant Codec as OCIGenAIChatCodec
participant Middleware as Guardrails or PII redaction
participant Pipeline as LLM pipeline
participant Binding as Python or Node binding
Client->>Resolver: submit OCI payload
Resolver->>Codec: select OCIGenAI provider surface
Codec->>Middleware: normalize request or response
Middleware->>Pipeline: apply policy and annotations
Binding->>Codec: invoke decode, encode, or decode_response
Codec-->>Binding: return normalized JSON or error
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches 💡 1⚔️ Resolve merge conflicts 💡
🧪 Generate unit tests (beta)
Comment |
How this series fits togetherThis PR is layer 1 of 4. Each layer adds one capability, each is independently buildable and testable, and each later branch is a pure superset of the previous — so review feedback here rebases cleanly through the rest of the stack.
Branch links and the full plan of record are on #548. Lineage: #549 (Python approach, closed per review) → #552 (this same content as a single Rust PR, closed in favor of this reviewable split). Verification provenanceEvery branch in the stack passes the full local gate on its own: |
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@crates/core/src/codec/oci_genai.rs`:
- Around line 124-162: Update flatten_all_text_parts to return None for an empty
parts slice, while preserving Text concatenation for non-empty arrays containing
only valid TEXT parts. This ensures decode_generic_content returns None for
content: [] and does not mark tool-call-only messages as containing text.
In `@crates/core/tests/unit/codec/oci_genai_tests.rs`:
- Around line 131-167: Add error-path coverage alongside the existing OCI GenAI
codec tests for GENERIC responses: create a test such as
test_invalid_generic_content_shape_errors that passes a numeric or object
message.content to OCIGenAIChatCodec.decode_response and asserts it returns an
error. Also cover an array containing a non-object part if practical, ensuring
decode_generic_content rejects each invalid shape with
FlowError::InvalidArgument.
🪄 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: a9645a77-4c88-4c9e-8a1c-90f1492e291a
📒 Files selected for processing (5)
crates/core/src/codec/mod.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/types/src/codec/request.rscrates/types/src/codec/response.rs
📜 Review details
🧰 Additional context used
📓 Path-based instructions (17)
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor all FFI work since it is Rust work
Runjust test-rustto validate FFI changes
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting on FFI workWhen Rust files changed as part of Go work, also run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allwhen Rust files are changed as part of Node work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files are changed as part of Node work
Runjust test-rustwhen Rust files are changed as part of Node workWhen changing the core Rust runtime or Rust-facing API surface, format Rust code with
cargo fmt(rustfmt defaults), keepcargo clippy -- -D warningsclean, and satisfycargo deny checkperdeny.toml.
**/*.rs: If any Rust code changed, always runjust test-rust.
If any Rust code changed, also runcargo fmt --all.
If any Rust code changed, also runcargo clippy --workspace --all-targets -- -D warnings.
For Rust changes headed for review, runcargo fmt --allandcargo clippy --workspace --all-targets -- -D warningseven if relying on pre-commit.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rs
{crates/core,crates/adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changes to
crates/coreorcrates/adaptivemust run the full language matrix
Files:
crates/core/src/codec/mod.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rs
crates/core/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-go-binding/SKILL.md)
If the change touched
crates/coreor shared runtime semantics, also usevalidate-changefor broader validation
Files:
crates/core/src/codec/mod.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rs
**/*.{rs,py}
📄 CodeRabbit inference engine (AGENTS.md)
Follow binding naming conventions in Rust and Python: use
snake_case.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rs
**/*.{rs,py,js,mjs,cjs,ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
**/*.{rs,py,js,mjs,cjs,ts,tsx}: UseJson = serde_json::Valuein Rust-facing runtime APIs where the existing code expects JSON payloads.
UseResult<T>withFlowErrorin core runtime paths, and keep errors explicit and binding-appropriate at the wrapper layer.
Keep async behavior on the existing tokio-based model; bindings should preserve callback and future lifetimes rather than blocking or hiding async work unexpectedly.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rs
**/*.{rs,py,go,js,ts,c,h}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Use language-appropriate naming conventions: Rust
snake_case, C FFI exports prefixednemo_relay_, GoPascalCase, Node.jscamelCase, and Pythonsnake_case.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rs
**/*.{rs,go,js,ts}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Add the SPDX license header to all Rust, Go, JavaScript, and TypeScript source files using the corresponding
//comment form.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rs
crates/core/src/{api/**/*.rs,api/runtime/**/*.rs,codec/**/*.rs,json.rs}
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Implement the new or changed public runtime behavior first in the Rust core, especially under
crates/core/src/api/and related core modules such ascrates/core/src/api/runtime/,crates/core/src/codec/, andcrates/core/src/json.rs.
Files:
crates/core/src/codec/mod.rscrates/core/src/codec/oci_genai.rs
{crates/**/src/**/*.rs,python/**/*.py}
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Do not add tests under
src; Rust tests belong in cratetests/trees, and Python SDK tests belong underpython/tests.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/src/codec/oci_genai.rs
**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
**/*: Format changed files with the language-native formatter before the final lint/test pass.
If dynamic plugin behavior changed, usemaintain-dynamic-pluginsand include the native SDK, worker protocol, Python SDK, docs, packaging, and Codecov surfaces in the validation plan.
If code changes alter APIs, bindings, commands, paths, packaging behavior, observability/adaptive semantics, or documented best practices, update any dependent maintainer or consumer skills in the same branch.
During iteration, preferuv run pre-commit run --files <changed files...>.
Before review or handoff, runuv run pre-commit run --all-files.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rs
crates/{core,adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If
crates/coreorcrates/adaptivechanged, run the full validation matrix across Rust, Python, Go, and Node.js.
Files:
crates/core/src/codec/mod.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rs
**/*.{rs,py,go,js,ts}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If a language surface changed, always run that language's test target even when Rust core did not change.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rs
**/*.{rs,py,js,ts,tsx,go,java,kt,swift}
📄 CodeRabbit inference engine (.agents/skills/add-middleware/SKILL.md)
Add tests covering registration and duplicate names, deregistration and missing names, priority ordering, callback failure policy, scope-local inheritance and cleanup, event payload semantics, immutable mark and scope fields, and parity across affected bindings.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rs
crates/{core,adaptive}/**/*.rs
⚙️ CodeRabbit configuration file
crates/{core,adaptive}/**/*.rs: Review the Rust runtime for async correctness, scope isolation, middleware ordering, and event lifecycle regressions.
Pay close attention to task-local/thread-local scope propagation, callback lifetimes, stream finalization, and root_uuid isolation.
Public API changes should preserve existing behavior unless tests and docs show the intended migration path.
Files:
crates/core/src/codec/mod.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rs
{crates/core/src/plugin/dynamic/**,crates/plugin/**,crates/worker/**,crates/worker-proto/**,crates/types/**,python/plugin/**,examples/rust-native-plugin/**,examples/python-grpc-worker-plugin/**,docs/build-plugins/**}
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Keep the stable boundary explicit: native plugins cross a C ABI, and worker plugins cross
grpc-v1.
Files:
crates/types/src/codec/response.rscrates/types/src/codec/request.rs
crates/types/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Runtime helpers must cover marks, scopes, continuations, and isolated scope stacks.
Files:
crates/types/src/codec/response.rscrates/types/src/codec/request.rs
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rs
🔇 Additional comments (8)
crates/types/src/codec/request.rs (1)
537-549: LGTM!crates/types/src/codec/response.rs (1)
329-339: LGTM!crates/core/src/codec/mod.rs (1)
19-19: LGTM!crates/core/src/codec/oci_genai.rs (3)
197-254: LGTM!
262-329: LGTM!
90-101: LGTM!Also applies to: 332-341
crates/core/tests/unit/codec/oci_genai_tests.rs (2)
16-129: LGTM!
169-188: LGTM!
ccb3281 to
21d6e18
Compare
|
Both review findings addressed in the updated commit:
Full workspace build and test suite re-run green after the change; the fix is propagated through the staged follow-up branches of the series. |
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@crates/core/src/codec/oci_genai.rs`:
- Around line 313-333: The decode_response_tool_call path silently discards
malformed tool calls when the name is missing or non-string. Add an appropriate
debug or warning log before returning None for this validation failure,
including enough context to identify the malformed OCI payload while preserving
the existing successful decoding behavior.
In `@crates/core/tests/unit/codec/oci_genai_tests.rs`:
- Around line 1-210: Add a test near test_invalid_generic_content_shape_errors
that decodes a GENERIC response with mixed TEXT and non-TEXT content through
OCIGenAIChatCodec::decode_response. Assert the message is MessageContent::Parts,
contains both parts, and specifically verify the non-TEXT part is represented as
ContentPart::ProviderNative with its original payload preserved.
🪄 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: 09237b3d-efcb-4116-9173-2272097f9a8c
📒 Files selected for processing (5)
crates/core/src/codec/mod.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/types/src/codec/request.rscrates/types/src/codec/response.rs
📜 Review details
🧰 Additional context used
📓 Path-based instructions (17)
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor all FFI work since it is Rust work
Runjust test-rustto validate FFI changes
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting on FFI workWhen Rust files changed as part of Go work, also run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allwhen Rust files are changed as part of Node work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files are changed as part of Node work
Runjust test-rustwhen Rust files are changed as part of Node workWhen changing the core Rust runtime or Rust-facing API surface, format Rust code with
cargo fmt(rustfmt defaults), keepcargo clippy -- -D warningsclean, and satisfycargo deny checkperdeny.toml.
**/*.rs: If any Rust code changed, always runjust test-rust.
If any Rust code changed, also runcargo fmt --all.
If any Rust code changed, also runcargo clippy --workspace --all-targets -- -D warnings.
For Rust changes headed for review, runcargo fmt --allandcargo clippy --workspace --all-targets -- -D warningseven if relying on pre-commit.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/core,crates/adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changes to
crates/coreorcrates/adaptivemust run the full language matrix
Files:
crates/core/src/codec/mod.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/core/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-go-binding/SKILL.md)
If the change touched
crates/coreor shared runtime semantics, also usevalidate-changefor broader validation
Files:
crates/core/src/codec/mod.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py}
📄 CodeRabbit inference engine (AGENTS.md)
Follow binding naming conventions in Rust and Python: use
snake_case.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,mjs,cjs,ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
**/*.{rs,py,js,mjs,cjs,ts,tsx}: UseJson = serde_json::Valuein Rust-facing runtime APIs where the existing code expects JSON payloads.
UseResult<T>withFlowErrorin core runtime paths, and keep errors explicit and binding-appropriate at the wrapper layer.
Keep async behavior on the existing tokio-based model; bindings should preserve callback and future lifetimes rather than blocking or hiding async work unexpectedly.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,ts,c,h}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Use language-appropriate naming conventions: Rust
snake_case, C FFI exports prefixednemo_relay_, GoPascalCase, Node.jscamelCase, and Pythonsnake_case.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,go,js,ts}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Add the SPDX license header to all Rust, Go, JavaScript, and TypeScript source files using the corresponding
//comment form.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/core/src/{api/**/*.rs,api/runtime/**/*.rs,codec/**/*.rs,json.rs}
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Implement the new or changed public runtime behavior first in the Rust core, especially under
crates/core/src/api/and related core modules such ascrates/core/src/api/runtime/,crates/core/src/codec/, andcrates/core/src/json.rs.
Files:
crates/core/src/codec/mod.rscrates/core/src/codec/oci_genai.rs
{crates/**/src/**/*.rs,python/**/*.py}
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Do not add tests under
src; Rust tests belong in cratetests/trees, and Python SDK tests belong underpython/tests.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/src/codec/oci_genai.rs
**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
**/*: Format changed files with the language-native formatter before the final lint/test pass.
If dynamic plugin behavior changed, usemaintain-dynamic-pluginsand include the native SDK, worker protocol, Python SDK, docs, packaging, and Codecov surfaces in the validation plan.
If code changes alter APIs, bindings, commands, paths, packaging behavior, observability/adaptive semantics, or documented best practices, update any dependent maintainer or consumer skills in the same branch.
During iteration, preferuv run pre-commit run --files <changed files...>.
Before review or handoff, runuv run pre-commit run --all-files.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If
crates/coreorcrates/adaptivechanged, run the full validation matrix across Rust, Python, Go, and Node.js.
Files:
crates/core/src/codec/mod.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,ts}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If a language surface changed, always run that language's test target even when Rust core did not change.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,ts,tsx,go,java,kt,swift}
📄 CodeRabbit inference engine (.agents/skills/add-middleware/SKILL.md)
Add tests covering registration and duplicate names, deregistration and missing names, priority ordering, callback failure policy, scope-local inheritance and cleanup, event payload semantics, immutable mark and scope fields, and parity across affected bindings.
Files:
crates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/types/src/codec/request.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive}/**/*.rs
⚙️ CodeRabbit configuration file
crates/{core,adaptive}/**/*.rs: Review the Rust runtime for async correctness, scope isolation, middleware ordering, and event lifecycle regressions.
Pay close attention to task-local/thread-local scope propagation, callback lifetimes, stream finalization, and root_uuid isolation.
Public API changes should preserve existing behavior unless tests and docs show the intended migration path.
Files:
crates/core/src/codec/mod.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/core/src/plugin/dynamic/**,crates/plugin/**,crates/worker/**,crates/worker-proto/**,crates/types/**,python/plugin/**,examples/rust-native-plugin/**,examples/python-grpc-worker-plugin/**,docs/build-plugins/**}
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Keep the stable boundary explicit: native plugins cross a C ABI, and worker plugins cross
grpc-v1.
Files:
crates/types/src/codec/response.rscrates/types/src/codec/request.rs
crates/types/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Runtime helpers must cover marks, scopes, continuations, and isolated scope stacks.
Files:
crates/types/src/codec/response.rscrates/types/src/codec/request.rs
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rs
🔇 Additional comments (4)
crates/types/src/codec/request.rs (1)
537-549: LGTM!crates/types/src/codec/response.rs (1)
329-339: LGTM!crates/core/src/codec/oci_genai.rs (1)
1-113: LGTM!Also applies to: 201-258, 266-345
crates/core/src/codec/mod.rs (1)
19-19: LGTM!
|
End-to-end validation re-run on the updated series content (including the empty-content fix above), via the Python binding built from the stack tip:
Unit suite on the same tip: 33 OCI codec tests green, full workspace build and tests passing, clippy zero warnings. |
Introduce the first layer of the OCI Generative AI provider codec:
typed ApiSpecificRequest::OCIGenAI and ApiSpecificResponse::OCIGenAI
variants, plus an OCIGenAIChatCodec implementing LlmResponseCodec.
Response decode covers ChatResult ({modelId, chatResponse}) and bare
chat responses in both apiFormat variants (GENERIC choices-based and
COHERE text-based), tolerates camelCase, kebab-case, and snake_case
key conventions (SDK vs CLI shapes), parses GENERIC string-encoded
tool-call arguments, maps promptTokens/completionTokens/totalTokens
into Usage, and maps finish reasons (stop/COMPLETE -> complete,
length/MAX_TOKENS -> length, tool_calls -> tool_use, else unknown).
Request encode/decode, streaming, and provider-surface registration
follow in subsequent changes.
Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
21d6e18 to
1b8a31f
Compare
|
Second CodeRabbit pass triaged:
Suite on the updated tip: 34 OCI codec tests green, clippy zero warnings, full stack rebased. |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@crates/core/src/codec/oci_genai.rs`:
- Around line 313-333: The decode_response_tool_call function currently assigns
an empty string when the OCI response omits id, causing parallel Cohere tool
calls to collide. Replace the unwrap_or_default fallback with a stable, unique
per-call identifier derived from the available tool-call data, while preserving
the provided id unchanged when present.
🪄 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: bb97e075-db42-4f75-be55-471c3f8be155
📒 Files selected for processing (5)
crates/core/src/codec/mod.rscrates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/types/src/codec/request.rscrates/types/src/codec/response.rs
📜 Review details
🧰 Additional context used
📓 Path-based instructions (17)
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor all FFI work since it is Rust work
Runjust test-rustto validate FFI changes
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting on FFI workWhen Rust files changed as part of Go work, also run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allwhen Rust files are changed as part of Node work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files are changed as part of Node work
Runjust test-rustwhen Rust files are changed as part of Node workWhen changing the core Rust runtime or Rust-facing API surface, format Rust code with
cargo fmt(rustfmt defaults), keepcargo clippy -- -D warningsclean, and satisfycargo deny checkperdeny.toml.
**/*.rs: If any Rust code changed, always runjust test-rust.
If any Rust code changed, also runcargo fmt --all.
If any Rust code changed, also runcargo clippy --workspace --all-targets -- -D warnings.
For Rust changes headed for review, runcargo fmt --allandcargo clippy --workspace --all-targets -- -D warningseven if relying on pre-commit.
Files:
crates/types/src/codec/request.rscrates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py}
📄 CodeRabbit inference engine (AGENTS.md)
Follow binding naming conventions in Rust and Python: use
snake_case.
Files:
crates/types/src/codec/request.rscrates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,mjs,cjs,ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
**/*.{rs,py,js,mjs,cjs,ts,tsx}: UseJson = serde_json::Valuein Rust-facing runtime APIs where the existing code expects JSON payloads.
UseResult<T>withFlowErrorin core runtime paths, and keep errors explicit and binding-appropriate at the wrapper layer.
Keep async behavior on the existing tokio-based model; bindings should preserve callback and future lifetimes rather than blocking or hiding async work unexpectedly.
Files:
crates/types/src/codec/request.rscrates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,ts,c,h}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Use language-appropriate naming conventions: Rust
snake_case, C FFI exports prefixednemo_relay_, GoPascalCase, Node.jscamelCase, and Pythonsnake_case.
Files:
crates/types/src/codec/request.rscrates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,go,js,ts}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Add the SPDX license header to all Rust, Go, JavaScript, and TypeScript source files using the corresponding
//comment form.
Files:
crates/types/src/codec/request.rscrates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/core/src/plugin/dynamic/**,crates/plugin/**,crates/worker/**,crates/worker-proto/**,crates/types/**,python/plugin/**,examples/rust-native-plugin/**,examples/python-grpc-worker-plugin/**,docs/build-plugins/**}
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Keep the stable boundary explicit: native plugins cross a C ABI, and worker plugins cross
grpc-v1.
Files:
crates/types/src/codec/request.rscrates/types/src/codec/response.rs
{crates/**/src/**/*.rs,python/**/*.py}
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Do not add tests under
src; Rust tests belong in cratetests/trees, and Python SDK tests belong underpython/tests.
Files:
crates/types/src/codec/request.rscrates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/core/src/codec/oci_genai.rs
crates/types/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Runtime helpers must cover marks, scopes, continuations, and isolated scope stacks.
Files:
crates/types/src/codec/request.rscrates/types/src/codec/response.rs
**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
**/*: Format changed files with the language-native formatter before the final lint/test pass.
If dynamic plugin behavior changed, usemaintain-dynamic-pluginsand include the native SDK, worker protocol, Python SDK, docs, packaging, and Codecov surfaces in the validation plan.
If code changes alter APIs, bindings, commands, paths, packaging behavior, observability/adaptive semantics, or documented best practices, update any dependent maintainer or consumer skills in the same branch.
During iteration, preferuv run pre-commit run --files <changed files...>.
Before review or handoff, runuv run pre-commit run --all-files.
Files:
crates/types/src/codec/request.rscrates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,ts}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If a language surface changed, always run that language's test target even when Rust core did not change.
Files:
crates/types/src/codec/request.rscrates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,ts,tsx,go,java,kt,swift}
📄 CodeRabbit inference engine (.agents/skills/add-middleware/SKILL.md)
Add tests covering registration and duplicate names, deregistration and missing names, priority ordering, callback failure policy, scope-local inheritance and cleanup, event payload semantics, immutable mark and scope fields, and parity across affected bindings.
Files:
crates/types/src/codec/request.rscrates/core/src/codec/mod.rscrates/types/src/codec/response.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/core,crates/adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changes to
crates/coreorcrates/adaptivemust run the full language matrix
Files:
crates/core/src/codec/mod.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/core/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-go-binding/SKILL.md)
If the change touched
crates/coreor shared runtime semantics, also usevalidate-changefor broader validation
Files:
crates/core/src/codec/mod.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/core/src/{api/**/*.rs,api/runtime/**/*.rs,codec/**/*.rs,json.rs}
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Implement the new or changed public runtime behavior first in the Rust core, especially under
crates/core/src/api/and related core modules such ascrates/core/src/api/runtime/,crates/core/src/codec/, andcrates/core/src/json.rs.
Files:
crates/core/src/codec/mod.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If
crates/coreorcrates/adaptivechanged, run the full validation matrix across Rust, Python, Go, and Node.js.
Files:
crates/core/src/codec/mod.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive}/**/*.rs
⚙️ CodeRabbit configuration file
crates/{core,adaptive}/**/*.rs: Review the Rust runtime for async correctness, scope isolation, middleware ordering, and event lifecycle regressions.
Pay close attention to task-local/thread-local scope propagation, callback lifetimes, stream finalization, and root_uuid isolation.
Public API changes should preserve existing behavior unless tests and docs show the intended migration path.
Files:
crates/core/src/codec/mod.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rs
🔇 Additional comments (5)
crates/types/src/codec/request.rs (1)
537-549: LGTM!crates/types/src/codec/response.rs (1)
329-339: LGTM!crates/core/src/codec/oci_genai.rs (1)
1-354: Rest of the file (key-convention helpers, GENERIC content decoding, envelope/chat_response split, usage mapping, finish-reason mapping) is correct and the previously-flagged empty-content and error-path issues are now addressed.crates/core/src/codec/mod.rs (1)
19-19: LGTM!crates/core/tests/unit/codec/oci_genai_tests.rs (1)
1-247: LGTM! Both previously-flagged gaps (invalid-content error path, mixed-partsProviderNativecoverage) are now covered.
|
@fede-kamel A few questions:
If Oracle strictly adheres to Cohere, then I'd expect separate CohereV1 and CohereV2 Codecs rather than an Oracle-specific codec.
This seems generally problematic to me. Schema specifications should be concrete and well-defined. If Oracle is extending the Cohere schema to be case/format insensitive, I really need good justification as to why a vendor-specific schema should live in Relay itself. Cohere's API is clearly defined with |
Validated the codec against live OCI Generative AI responses across
model families (Meta, OpenAI, Google, xAI, Cohere) and the three
renderings Oracle tooling emits for the documented camelCase schema.
Changes from that sweep:
- Unwrap the OCI CLI data envelope so captured CLI output decodes like
wire and SDK payloads; document the transport matrix in the module
doc (REST wire/SDKs camelCase, oci.util.to_dict() snake_case, CLI
kebab-case in a data envelope)
- Map the lowercase max_tokens finish reason emitted by Gemini models
to FinishReason::Length
- Map promptTokensDetails.cachedTokens (OpenAI/xAI models) to
cache_read_tokens instead of dropping it
- Synthesize positional call_{index} ids for COHERE tool calls, which
carry no id on the wire, so parallel calls stay distinguishable
- Add unit tests for each live-observed shape and a pipeline
integration test decoding an OCI GENERIC tool-call response through
llm_call_execute
Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
|
Thanks for the careful review @willkill07 — these are exactly the right questions. Rather than answer from the docs alone, I captured live responses from the service (us-chicago-1, one model from each family: Meta, OpenAI, Google, xAI, Cohere) and checked every claim below against them. 1. Cohere v1 or v2? Neither, and that's the crux: Oracle does not strictly adhere to Cohere. The COHERE format borrows Cohere v1 semantics (single top-level {
"modelId": "cohere.command-r-08-2024",
"modelVersion": "2.0",
"chatResponse": {
"apiFormat": "COHERE",
"text": "...",
"chatHistory": [{"role": "USER", "message": "..."}, {"role": "CHATBOT", "message": "..."}],
"finishReason": "COMPLETE",
"toolCalls": [{"name": "get_weather", "parameters": {"city": "Paris"}}],
"usage": {"promptTokens": 29, "completionTokens": 37, "totalTokens": 66}
}
}A native CohereV1 codec (snake_case, no envelope) would decode none of this. If Relay later adds Cohere's own API as a provider surface, CohereV1/V2 codecs make sense there — but they'd be decoding a different wire format than this one. I also checked the newest Cohere model on OCI ( 2. Streaming Intentional for this layer — streaming is layer 3 of the series ( 3. GENERIC spec It's Oracle's own documented schema:
So routing GENERIC through the OpenAI codec isn't an option; it hard-errors on the tool-call shape and misses the envelope and usage fields. I also verified GENERIC is what every non-Cohere family returns on OCI ( 4. Key conventions Agreed that a case/format-insensitive schema would be a smell, and the module doc described this poorly — I've reworded it in the latest push. To state it precisely: Oracle's schema is concrete, and the REST wire is strictly camelCase, always. The three spellings exist because Oracle's own tooling re-keys the same schema deterministically at different capture points:
I verified all three by running the same call through each path; the test fixtures now mirror those captures. The lookup is not fuzzy matching — the codec derives the kebab/snake spelling mechanically from the documented camelCase key, so there's exactly one accepted rendering per convention and no ambiguity. The snake_case path matters most in practice: Python is Relay's biggest binding, and That said, if you'd rather the built-in codec accept only the wire format and leave CLI/SDK-dict renderings to the caller, I'm happy to trim to camelCase-only — small diff, and I'd rather match the project's conventions than defend a preference. The live sweep also surfaced a few real-world shapes the first cut missed, all fixed with tests in the latest commit: Gemini models emit a lowercase |
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
crates/core/src/codec/oci_genai.rs (1)
245-249: 🎯 Functional Correctness | 🟠 Major | ⚡ Quick winHandle
COHEREV2as a Cohere response
COHEREV2also carries its generated text inmessage, but this branch sends it to the generic parser, which expectschoicesand drops valid V2 responses. Add an explicitCOHEREV2case here, or reject unsupported formats instead of treating them as generic.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@crates/core/src/codec/oci_genai.rs` around lines 245 - 249, Update the api_format branch in the response decoding flow to route both "COHERE" and "COHEREV2" through decode_cohere_response_body; ensure COHEREV2 no longer reaches decode_generic_response_body, which expects choices.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@crates/core/tests/integration/pipeline_tests.rs`:
- Around line 1442-1515: Make subscriber cleanup in the OCI response codec test
panic-safe by introducing an RAII guard immediately after registering the
subscriber, using its drop behavior to call deregister_subscriber for
"oci_resp_codec_sub". Remove the explicit cleanup dependency at the end of the
test while preserving deregistration on successful completion and during
assertion unwinding.
---
Outside diff comments:
In `@crates/core/src/codec/oci_genai.rs`:
- Around line 245-249: Update the api_format branch in the response decoding
flow to route both "COHERE" and "COHEREV2" through decode_cohere_response_body;
ensure COHEREV2 no longer reaches decode_generic_response_body, which expects
choices.
🪄 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: d86502fa-3656-483c-99da-0672bf8768be
📒 Files selected for processing (3)
crates/core/src/codec/oci_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rs
📜 Review details
🧰 Additional context used
📓 Path-based instructions (15)
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor all FFI work since it is Rust work
Runjust test-rustto validate FFI changes
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting on FFI workWhen Rust files changed as part of Go work, also run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allwhen Rust files are changed as part of Node work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files are changed as part of Node work
Runjust test-rustwhen Rust files are changed as part of Node workWhen changing the core Rust runtime or Rust-facing API surface, format Rust code with
cargo fmt(rustfmt defaults), keepcargo clippy -- -D warningsclean, and satisfycargo deny checkperdeny.toml.
**/*.rs: If any Rust code changed, always runjust test-rust.
If any Rust code changed, also runcargo fmt --all.
If any Rust code changed, also runcargo clippy --workspace --all-targets -- -D warnings.
For Rust changes headed for review, runcargo fmt --allandcargo clippy --workspace --all-targets -- -D warningseven if relying on pre-commit.
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/core,crates/adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changes to
crates/coreorcrates/adaptivemust run the full language matrix
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/core/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-go-binding/SKILL.md)
If the change touched
crates/coreor shared runtime semantics, also usevalidate-changefor broader validation
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py}
📄 CodeRabbit inference engine (AGENTS.md)
Follow binding naming conventions in Rust and Python: use
snake_case.
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,mjs,cjs,ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
**/*.{rs,py,js,mjs,cjs,ts,tsx}: UseJson = serde_json::Valuein Rust-facing runtime APIs where the existing code expects JSON payloads.
UseResult<T>withFlowErrorin core runtime paths, and keep errors explicit and binding-appropriate at the wrapper layer.
Keep async behavior on the existing tokio-based model; bindings should preserve callback and future lifetimes rather than blocking or hiding async work unexpectedly.
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,ts,c,h}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Use language-appropriate naming conventions: Rust
snake_case, C FFI exports prefixednemo_relay_, GoPascalCase, Node.jscamelCase, and Pythonsnake_case.
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,go,js,ts}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Add the SPDX license header to all Rust, Go, JavaScript, and TypeScript source files using the corresponding
//comment form.
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
**/*: Format changed files with the language-native formatter before the final lint/test pass.
If dynamic plugin behavior changed, usemaintain-dynamic-pluginsand include the native SDK, worker protocol, Python SDK, docs, packaging, and Codecov surfaces in the validation plan.
If code changes alter APIs, bindings, commands, paths, packaging behavior, observability/adaptive semantics, or documented best practices, update any dependent maintainer or consumer skills in the same branch.
During iteration, preferuv run pre-commit run --files <changed files...>.
Before review or handoff, runuv run pre-commit run --all-files.
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If
crates/coreorcrates/adaptivechanged, run the full validation matrix across Rust, Python, Go, and Node.js.
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,ts}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If a language surface changed, always run that language's test target even when Rust core did not change.
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,ts,tsx,go,java,kt,swift}
📄 CodeRabbit inference engine (.agents/skills/add-middleware/SKILL.md)
Add tests covering registration and duplicate names, deregistration and missing names, priority ordering, callback failure policy, scope-local inheritance and cleanup, event payload semantics, immutable mark and scope fields, and parity across affected bindings.
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive}/**/*.rs
⚙️ CodeRabbit configuration file
crates/{core,adaptive}/**/*.rs: Review the Rust runtime for async correctness, scope isolation, middleware ordering, and event lifecycle regressions.
Pay close attention to task-local/thread-local scope propagation, callback lifetimes, stream finalization, and root_uuid isolation.
Public API changes should preserve existing behavior unless tests and docs show the intended migration path.
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rs
crates/core/src/{api/**/*.rs,api/runtime/**/*.rs,codec/**/*.rs,json.rs}
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Implement the new or changed public runtime behavior first in the Rust core, especially under
crates/core/src/api/and related core modules such ascrates/core/src/api/runtime/,crates/core/src/codec/, andcrates/core/src/json.rs.
Files:
crates/core/src/codec/oci_genai.rs
{crates/**/src/**/*.rs,python/**/*.py}
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Do not add tests under
src; Rust tests belong in cratetests/trees, and Python SDK tests belong underpython/tests.
Files:
crates/core/src/codec/oci_genai.rs
🔇 Additional comments (4)
crates/core/src/codec/oci_genai.rs (2)
13-18: 📐 Maintainability & Code QualityRecord the required core-runtime validation matrix.
Please attach CI evidence for
cargo fmt --all,cargo clippy --workspace --all-targets -- -D warnings,just test-rust,cargo deny check,validate-change, the Rust/Python/Go/Node matrix, anduv run pre-commit run --all-files.As per coding guidelines, changed
crates/corecode requires these Rust checks,validate-change, dependency validation, and the full language matrix.Source: Coding guidelines
219-224: LGTM!Also applies to: 297-371
crates/core/tests/unit/codec/oci_genai_tests.rs (1)
131-206: LGTM!Also applies to: 305-358, 368-369
crates/core/tests/integration/pipeline_tests.rs (1)
33-33: LGTM!
Relay only interfaces with the wire format, so yes. |
Per review, Relay only interfaces with the wire format, so the codec now accepts the documented camelCase schema only. Removes the kebab-case/snake_case key derivation and the CLI data-envelope unwrapping; converting alternate renderings produced by Oracle tooling is the caller's responsibility. Adds a contract test asserting non-wire renderings are not decoded. Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
|
Done in 7282cdd — the codec now accepts the camelCase wire format only. Dropped the kebab/snake key derivation and the CLI |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@crates/core/tests/unit/codec/oci_genai_tests.rs`:
- Around line 106-124: Extend test_non_wire_renderings_are_not_decoded with a
kebab-case CLI-shaped response wrapped in {"data": {...}}, using the documented
non-REST field names. Decode it with OCIGenAIChatCodec and assert model,
message, and finish_reason are all None, matching the existing snake_case case.
🪄 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: 6bd01613-ee5b-40e4-9587-2f9cfce7b63d
📒 Files selected for processing (2)
crates/core/src/codec/oci_genai.rscrates/core/tests/unit/codec/oci_genai_tests.rs
📜 Review details
🧰 Additional context used
📓 Path-based instructions (15)
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor all FFI work since it is Rust work
Runjust test-rustto validate FFI changes
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting on FFI workWhen Rust files changed as part of Go work, also run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allwhen Rust files are changed as part of Node work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files are changed as part of Node work
Runjust test-rustwhen Rust files are changed as part of Node workWhen changing the core Rust runtime or Rust-facing API surface, format Rust code with
cargo fmt(rustfmt defaults), keepcargo clippy -- -D warningsclean, and satisfycargo deny checkperdeny.toml.
**/*.rs: If any Rust code changed, always runjust test-rust.
If any Rust code changed, also runcargo fmt --all.
If any Rust code changed, also runcargo clippy --workspace --all-targets -- -D warnings.
For Rust changes headed for review, runcargo fmt --allandcargo clippy --workspace --all-targets -- -D warningseven if relying on pre-commit.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/core,crates/adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changes to
crates/coreorcrates/adaptivemust run the full language matrix
Files:
crates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/core/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-go-binding/SKILL.md)
If the change touched
crates/coreor shared runtime semantics, also usevalidate-changefor broader validation
Files:
crates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py}
📄 CodeRabbit inference engine (AGENTS.md)
Follow binding naming conventions in Rust and Python: use
snake_case.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,mjs,cjs,ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
**/*.{rs,py,js,mjs,cjs,ts,tsx}: UseJson = serde_json::Valuein Rust-facing runtime APIs where the existing code expects JSON payloads.
UseResult<T>withFlowErrorin core runtime paths, and keep errors explicit and binding-appropriate at the wrapper layer.
Keep async behavior on the existing tokio-based model; bindings should preserve callback and future lifetimes rather than blocking or hiding async work unexpectedly.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,ts,c,h}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Use language-appropriate naming conventions: Rust
snake_case, C FFI exports prefixednemo_relay_, GoPascalCase, Node.jscamelCase, and Pythonsnake_case.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,go,js,ts}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Add the SPDX license header to all Rust, Go, JavaScript, and TypeScript source files using the corresponding
//comment form.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
**/*: Format changed files with the language-native formatter before the final lint/test pass.
If dynamic plugin behavior changed, usemaintain-dynamic-pluginsand include the native SDK, worker protocol, Python SDK, docs, packaging, and Codecov surfaces in the validation plan.
If code changes alter APIs, bindings, commands, paths, packaging behavior, observability/adaptive semantics, or documented best practices, update any dependent maintainer or consumer skills in the same branch.
During iteration, preferuv run pre-commit run --files <changed files...>.
Before review or handoff, runuv run pre-commit run --all-files.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If
crates/coreorcrates/adaptivechanged, run the full validation matrix across Rust, Python, Go, and Node.js.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,ts}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If a language surface changed, always run that language's test target even when Rust core did not change.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,ts,tsx,go,java,kt,swift}
📄 CodeRabbit inference engine (.agents/skills/add-middleware/SKILL.md)
Add tests covering registration and duplicate names, deregistration and missing names, priority ordering, callback failure policy, scope-local inheritance and cleanup, event payload semantics, immutable mark and scope fields, and parity across affected bindings.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive}/**/*.rs
⚙️ CodeRabbit configuration file
crates/{core,adaptive}/**/*.rs: Review the Rust runtime for async correctness, scope isolation, middleware ordering, and event lifecycle regressions.
Pay close attention to task-local/thread-local scope propagation, callback lifetimes, stream finalization, and root_uuid isolation.
Public API changes should preserve existing behavior unless tests and docs show the intended migration path.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/core/tests/unit/codec/oci_genai_tests.rs
crates/core/src/{api/**/*.rs,api/runtime/**/*.rs,codec/**/*.rs,json.rs}
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Implement the new or changed public runtime behavior first in the Rust core, especially under
crates/core/src/api/and related core modules such ascrates/core/src/api/runtime/,crates/core/src/codec/, andcrates/core/src/json.rs.
Files:
crates/core/src/codec/oci_genai.rs
{crates/**/src/**/*.rs,python/**/*.py}
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Do not add tests under
src; Rust tests belong in cratetests/trees, and Python SDK tests belong underpython/tests.
Files:
crates/core/src/codec/oci_genai.rs
🔇 Additional comments (1)
crates/core/src/codec/oci_genai.rs (1)
168-196: 📐 Maintainability & Code QualityProvide the required core validation evidence.
The summary reports formatting, workspace tests, and Clippy, but not
just test-rust,cargo deny check,validate-change,uv run pre-commit run --all-files, or the required Rust/Python/Go/Node matrix forcrates/corechanges. Attach the corresponding CI or command logs before handoff.As per coding guidelines, “If
crates/coreorcrates/adaptivechanged, run the full validation matrix across Rust, Python, Go, and Node.js,” and core runtime changes must “satisfycargo deny checkperdeny.toml.”Source: Coding guidelines
Extends the non-wire-rendering contract test with a kebab-case data-enveloped CLI-shaped response, guarding the REST-only boundary against regression on both alternate renderings. Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
willkill07
left a comment
There was a problem hiding this comment.
Thanks for splitting this into a focused first step. I found two issues that need addressing before this response codec is ready to merge.
| .unwrap_or("GENERIC") | ||
| .to_uppercase(); | ||
|
|
||
| let (message, tool_calls, finish_reason) = if api_format == "COHERE" { |
There was a problem hiding this comment.
Could we handle COHEREV2 explicitly here? OCI lists it as a supported apiFormat, but this branch sends it through decode_generic_response_body.
V2 responses use message and finishReason rather than choices, so Relay currently records no response text, tool calls, or finish reason—without surfacing an error. Please add a V2 decoder (or return an explicit unsupported-format error) and cover it with a fixture.
If you are introducing OCI support, it seems odd to not also support COHEREV2
There was a problem hiding this comment.
Done in 2ab7e34 — added a dedicated COHEREV2 decoder rather than an error, since the shape is fully specified. Two notes from verifying this:
- The live service doesn't accept the format yet: I probed us-chicago-1 yesterday with
apiFormat: COHEREV2againstcohere.command-a-03-2025andcohere.command-a-reasoning(both v2-messages and v1 shapes) and got HTTP 400 "Please pass in correct format of request" in all cases. It is, however, in the current SDK spec (oci2.182.1 definesCohereChatResponseV2and dispatchesCOHEREV2to it), so the decoder and fixture mirror that published schema exactly: single assistantmessagewith typed content parts, nested-functiontoolCalls({id, type: FUNCTION, function: {name, arguments}}), top-level responseid, and the V2 finish reasonsTOOL_CALL/STOP_SEQUENCE. - TEXT parts flatten like GENERIC; THINKING/IMAGE_URL/DOCUMENT parts are preserved losslessly as provider-native parts.
Covered by test_cohere_v2_chat_result and test_cohere_v2_text_only_flattens, plus the finish-reason mapping cases. I'll re-probe when the service starts accepting the format and adjust if the wire diverges from the spec.
There was a problem hiding this comment.
Update with live-wire evidence: the service accepts apiFormat: COHEREV2 as of today (the same request returned HTTP 400 on 07-28), so I swept every Cohere chat model in the us-chicago-1 catalog with both formats:
| Model | COHERE (v1) | COHEREV2 |
|---|---|---|
cohere.command-a-03-2025 |
✅ accepted | ✅ accepted |
cohere.command-a-vision |
❌ 400 apiFormat COHERE is not supported |
✅ accepted |
cohere.command-latest |
✅ accepted | ❌ 400 not supported |
cohere.command-plus-latest |
✅ accepted | ❌ 400 not supported |
cohere.command-r-08-2024 |
✅ accepted | ❌ 400 not supported |
cohere.command-r-plus-08-2024 |
✅ accepted | ❌ 400 not supported |
cohere.command-a-reasoning, command-r-16k, command-r-plus |
404 (not served on-demand) | 404 |
So the split is generational: the older command/command-r line is V1-only, the current command-a line is V2-first, and command-a-vision is V2-only — without this decoder Relay would record nothing for that model. command-a-03-2025 serves both formats and its wire responses were decoded through the codec for each.
Live V2 responses (text and parallel tool calls) match the CohereChatResponseV2 fixture exactly: nested-function tool calls with provider-supplied ids, JSON-encoded string arguments (parsed like GENERIC), TOOL_CALL finish reason, and message-level toolPlan/citations (now preserved in extra per the other thread). The fixture comment records the live confirmation as of 07ded78.
There was a problem hiding this comment.
| api_format: Some(api_format), | ||
| model_version, | ||
| }), | ||
| extra: serde_json::Map::new(), |
There was a problem hiding this comment.
Could we retain the response fields that are not normalized instead of always returning an empty extra map?
This currently discards OCI data such as timeCreated, service-tier/grounding metadata, and future provider fields that are useful for observability.
Please preserve unknown envelope fields and/or retain the raw chatResponse in the OCI-specific response data, consistent with the other response codecs.
There was a problem hiding this comment.
Done in 2ab7e34 — decode now carries all unmodeled fields in extra, matching the flatten-passthrough behavior of the OpenAI/Anthropic response codecs: unknown envelope fields (anything besides modelId/modelVersion/chatResponse) plus chat-response fields outside the per-format modeled set. Concretely that preserves timeCreated, serviceTier, COHERE chatHistory, grounding metadata, and any future provider fields. Covered by test_unmodeled_response_fields_preserved_in_extra, which also asserts modeled keys aren't duplicated into extra.
There was a problem hiding this comment.
Follow-up in 9cae2fb — auditing the preservation claim field-by-field against the OCI schema (ChatChoice, AssistantMessage, CohereAssistantMessageV2) exposed a second layer of the same gap: fields nested inside the decoded choice and assistant message were still dropped. Per the schema that's logprobs, serviceTier, groundingMetadata, usage (choice) and refusal, annotations, reasoningContent (message) for GENERIC, and toolPlan, citations for COHEREV2 — so the grounding metadata you called out actually lives one level deeper than the chat-response pass I'd added. These are now carried in extra, namespaced under "choice" and "message" so their origin stays unambiguous.
Re-validated against live wire responses (us-chicago-1): a GENERIC reply from an OpenAI-family model carries choice-level logprobs and message-level annotations on the wire, both now preserved (previously silently dropped); COHERE v1 behavior is unchanged. Same pass also mapped GENERIC content_filter finish reasons to the normalized ContentFilter, matching the OpenAI codec.
There was a problem hiding this comment.
Addressed in 9cae2fb (plus the earlier envelope work): unmodeled envelope, chat-response, choice-, and message-level fields (timeCreated, serviceTier, grounding metadata, future provider fields) are now preserved in extra instead of being discarded, with tests asserting the passthrough.
Per review on the OCI codec: - Add a COHEREV2 decoder matching the OCI CohereChatResponseV2 schema: single assistant message with typed content parts (TEXT flattened, THINKING/IMAGE_URL/DOCUMENT preserved as provider-native), nested OpenAI-style function tool calls, response id, and the V2 finish reasons TOOL_CALL and STOP_SEQUENCE. The live service does not accept the format yet (probed us-chicago-1: HTTP 400), so the fixture mirrors the published SDK schema. - Preserve envelope and chat-response fields the normalized shape does not model (timeCreated, serviceTier, chatHistory, grounding metadata, future fields) in extra instead of discarding them, consistent with the other response codecs. Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
|
Status after the branch update merging Validation on the current tip: full workspace suite green (3,485 tests), clippy zero warnings, |
The service now accepts apiFormat COHEREV2 (it rejected it with HTTP 400 the day before); live text and parallel tool-call responses match the spec-mirrored fixture exactly, so the fixture comment no longer claims the format is spec-only. Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
|
@coderabbitai review |
✅ Action performedReview finished.
|
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)
crates/core/src/codec/oci_genai.rs (1)
148-159: 🎯 Functional Correctness | 🟡 Minor | ⚡ Quick winReject non-string
TEXT.textvalues.
{"type":"TEXT","text":1}bypasses text flattening, then becomesText("")here viaunwrap_or_default(). ReturnInvalidArgumentinstead of silently altering provider content, and add a regression fixture.Proposed fix
Some("TEXT") => Ok(ContentPart::Text { - text: obj - .get("text") - .and_then(Json::as_str) - .unwrap_or_default() - .to_string(), + text: match obj.get("text") { + None | Some(Json::Null) => String::new(), + Some(Json::String(text)) => text.clone(), + Some(_) => { + return Err(FlowError::InvalidArgument( + "OCI GenAI TEXT content part text must be a string or null".into(), + )); + } + },🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@crates/core/src/codec/oci_genai.rs` around lines 148 - 159, Update the TEXT branch of the OCI content decoder to distinguish a missing text field from a present non-string value: reject non-string TEXT.text values with InvalidArgument instead of defaulting them to an empty string. Preserve the existing handling for valid strings and absent fields as intended, and add a regression fixture covering {"type":"TEXT","text":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.
Outside diff comments:
In `@crates/core/src/codec/oci_genai.rs`:
- Around line 148-159: Update the TEXT branch of the OCI content decoder to
distinguish a missing text field from a present non-string value: reject
non-string TEXT.text values with InvalidArgument instead of defaulting them to
an empty string. Preserve the existing handling for valid strings and absent
fields as intended, and add a regression fixture covering
{"type":"TEXT","text":1}.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Enterprise
Run ID: dcdc699c-5639-4eb9-bffb-94647cbc0b4f
📒 Files selected for processing (4)
crates/core/src/codec/oci_genai.rscrates/core/src/observability/otel_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rs
📜 Review details
🧰 Additional context used
📓 Path-based instructions (15)
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor all FFI work since it is Rust work
Runjust test-rustto validate FFI changes
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting on FFI workWhen Rust files changed as part of Go work, also run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allwhen Rust files are changed as part of Node work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files are changed as part of Node work
Runjust test-rustwhen Rust files are changed as part of Node workWhen changing the core Rust runtime or Rust-facing API surface, format Rust code with
cargo fmt(rustfmt defaults), keepcargo clippy -- -D warningsclean, and satisfycargo deny checkperdeny.toml.
**/*.rs: If any Rust code changed, always runjust test-rust.
If any Rust code changed, also runcargo fmt --all.
If any Rust code changed, also runcargo clippy --workspace --all-targets -- -D warnings.
For Rust changes headed for review, runcargo fmt --allandcargo clippy --workspace --all-targets -- -D warningseven if relying on pre-commit.
Files:
crates/core/src/observability/otel_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/core,crates/adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changes to
crates/coreorcrates/adaptivemust run the full language matrix
Files:
crates/core/src/observability/otel_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/core/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-go-binding/SKILL.md)
If the change touched
crates/coreor shared runtime semantics, also usevalidate-changefor broader validation
Files:
crates/core/src/observability/otel_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py}
📄 CodeRabbit inference engine (AGENTS.md)
Follow binding naming conventions in Rust and Python: use
snake_case.
Files:
crates/core/src/observability/otel_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,mjs,cjs,ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
**/*.{rs,py,js,mjs,cjs,ts,tsx}: UseJson = serde_json::Valuein Rust-facing runtime APIs where the existing code expects JSON payloads.
UseResult<T>withFlowErrorin core runtime paths, and keep errors explicit and binding-appropriate at the wrapper layer.
Keep async behavior on the existing tokio-based model; bindings should preserve callback and future lifetimes rather than blocking or hiding async work unexpectedly.
Files:
crates/core/src/observability/otel_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,ts,c,h}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Use language-appropriate naming conventions: Rust
snake_case, C FFI exports prefixednemo_relay_, GoPascalCase, Node.jscamelCase, and Pythonsnake_case.
Files:
crates/core/src/observability/otel_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,go,js,ts}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Add the SPDX license header to all Rust, Go, JavaScript, and TypeScript source files using the corresponding
//comment form.
Files:
crates/core/src/observability/otel_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/**/src/**/*.rs,python/**/*.py}
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Do not add tests under
src; Rust tests belong in cratetests/trees, and Python SDK tests belong underpython/tests.
Files:
crates/core/src/observability/otel_genai.rscrates/core/src/codec/oci_genai.rs
**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
**/*: Format changed files with the language-native formatter before the final lint/test pass.
If dynamic plugin behavior changed, usemaintain-dynamic-pluginsand include the native SDK, worker protocol, Python SDK, docs, packaging, and Codecov surfaces in the validation plan.
If code changes alter APIs, bindings, commands, paths, packaging behavior, observability/adaptive semantics, or documented best practices, update any dependent maintainer or consumer skills in the same branch.
During iteration, preferuv run pre-commit run --files <changed files...>.
Before review or handoff, runuv run pre-commit run --all-files.
Files:
crates/core/src/observability/otel_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If
crates/coreorcrates/adaptivechanged, run the full validation matrix across Rust, Python, Go, and Node.js.
Files:
crates/core/src/observability/otel_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,ts}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If a language surface changed, always run that language's test target even when Rust core did not change.
Files:
crates/core/src/observability/otel_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,ts,tsx,go,java,kt,swift}
📄 CodeRabbit inference engine (.agents/skills/add-middleware/SKILL.md)
Add tests covering registration and duplicate names, deregistration and missing names, priority ordering, callback failure policy, scope-local inheritance and cleanup, event payload semantics, immutable mark and scope fields, and parity across affected bindings.
Files:
crates/core/src/observability/otel_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive}/**/*.rs
⚙️ CodeRabbit configuration file
crates/{core,adaptive}/**/*.rs: Review the Rust runtime for async correctness, scope isolation, middleware ordering, and event lifecycle regressions.
Pay close attention to task-local/thread-local scope propagation, callback lifetimes, stream finalization, and root_uuid isolation.
Public API changes should preserve existing behavior unless tests and docs show the intended migration path.
Files:
crates/core/src/observability/otel_genai.rscrates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/core/tests/integration/pipeline_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rs
crates/core/src/{api/**/*.rs,api/runtime/**/*.rs,codec/**/*.rs,json.rs}
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Implement the new or changed public runtime behavior first in the Rust core, especially under
crates/core/src/api/and related core modules such ascrates/core/src/api/runtime/,crates/core/src/codec/, andcrates/core/src/json.rs.
Files:
crates/core/src/codec/oci_genai.rs
🧠 Learnings (1)
📚 Learning: 2026-07-28T20:07:29.880Z
Learnt from: willkill07
Repo: NVIDIA/NeMo-Relay PR: 571
File: crates/core/src/api/runtime/state.rs:996-1020
Timestamp: 2026-07-28T20:07:29.880Z
Learning: In NeMo Relay (RELAY-509), sanitizer callback failures must be treated as intentional fail-open behavior. When an event/tool (request/response) or LLM (request/response) sanitizer callback fails, the sanitizer chain should retain and publish the last valid event/payload snapshot (rather than dropping/invalidating the data) and log the failure including callback context (e.g., which sanitizer/callback failed and relevant identifiers). Apply this consistently across all sanitizer chains mentioned in the RELAY-509 documentation/migration guide.
Applied to files:
crates/core/src/observability/otel_genai.rscrates/core/src/codec/oci_genai.rs
🔇 Additional comments (8)
crates/core/src/codec/oci_genai.rs (2)
11-64: LGTM!Also applies to: 126-139, 189-257, 269-445
176-260: 📐 Maintainability & Code QualityAttach the required core validation evidence.
The supplied summary reports workspace Rust checks, but not the required full core matrix. Please provide results for
just test-rust,cargo fmt --all,cargo clippy --workspace --all-targets -- -D warnings,cargo deny check,uv run pre-commit run --all-files, and the configured Python, Go, and Node test targets.
crates/core/src/codec/oci_genai.rs#L176-L260: validate OCI response decoding through the required core matrix.crates/core/src/observability/otel_genai.rs#L390-L401: validate the OCI provider projection through the same matrix.Source: Coding guidelines
crates/core/src/observability/otel_genai.rs (1)
1-388: LGTM!Also applies to: 404-523
crates/core/tests/unit/codec/oci_genai_tests.rs (2)
106-146: LGTM!
300-507: LGTM!crates/core/tests/integration/pipeline_tests.rs (3)
33-33: LGTM!Also applies to: 1476-1517
1536-1536: LGTM!Also applies to: 1736-1741, 2004-2004
1451-1475: 🗄️ Data Integrity & IntegrationNo issue: GENERIC
toolCallsshape matches the decoder
OCIGenAIChatCodecaccepts directid/name/argumentsentries fortoolCalls, and also falls back to a nestedfunctionobject for CohereV2-style payloads.> Likely an incorrect or invalid review comment.
|
@fede-kamel believe it or not, it will actually be easier for me to review and get merged if all parts were in one PR. |
Implement LlmCodec for OCIGenAIChatCodec so request intercepts (PII
redaction, guardrails, policy) can operate on OCI Generative AI chat
traffic. Requests are accepted as a full ChatDetails envelope
({compartmentId, servingMode, chatRequest}) or as a bare chatRequest,
in both chatRequest.apiFormat variants: GENERIC (UPPERCASE roles,
typed TEXT content-part lists, flat toolCalls {id, type: FUNCTION,
name, arguments}, toolCallId on tool messages) and COHERE
(preambleOverride, chatHistory USER/CHATBOT/SYSTEM turns, current
message string). GENERIC maxTokens/temperature/topP/stop and COHERE
stopSequences normalize into GenerationParams; unmodeled params
(topK, seed, penalties, ...) stay in the raw payload untouched.
encode() uses baseline-compare-and-patch semantics per the LlmCodec
contract: the original request is re-decoded as the baseline and only
fields an intercept actually changed are rewritten, so unchanged
messages pass through from the raw payload verbatim, per-message
provider fields survive edits, and
encode(decode(original), original) == original at the JSON level.
Model identity is read from servingMode.modelId/endpointId and model
edits are rejected as unsupported.
Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
Register ProviderSurface::OCIGenAI as the fourth built-in provider surface, placed first in BUILTIN_PROVIDER_SURFACES: the ChatDetails envelope and apiFormat markers are the strongest request signal and never appear in the other surfaces' shapes. Request detection accepts the envelope, a bare apiFormat chat request, or an oci/oci.genai provider hint; response detection requires the apiFormat marker so bare GENERIC responses stay unambiguous with OpenAI Chat. OCIGenAIStreamingCodec assembles OCI SSE choice deltas (GENERIC) and text fragments (COHERE) back into a non-streaming ChatResult shape that decode_response can consume, matching the streaming strategy of the existing provider codecs and satisfying the mandatory streaming_codec field of the surface descriptor. Extend every surface-exhaustive consumer: nemo_guardrails codec enum, schema, and local stream-text extraction; pii-redaction codec enum and response overlay (GENERIC text parts, tool calls, and finish reasons plus COHERE text); adaptive ACG request-surface resolution (no semantic applier exists for OCI GenAI yet, so it resolves to None). Add detection, non-shadowing, resolver-registry, overlay, and cross-surface parity tests. Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
Bindings for the OCI Generative AI chat codec: OCIGenAIChatCodec pyclass with decode/encode/decode_response, module registration, and the fast-path builtin response-codec downcast in py_api so the native implementation is used without a Python round trip; the matching napi class for Node; type stubs (_native.pyi, pii_redaction.d.ts) and the nemo_relay.codecs re-export; oci_genai added to the pii-redaction config codec literals; Python test coverage for construction, method presence, response decoding, and the LlmResponseCodec protocol. Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
|
Done — the PR now carries all four parts, per your request. The three follow-up layers (request codec, provider surface + streaming, Python/Node bindings) are folded in as the last three commits, so the branch is the complete feature: typed variants, response + request codecs with round-trip identity, Validation on the consolidated tip: full workspace build and test suite green, |
|
@coderabbitai review |
✅ Action performedReview finished.
|
The typed stub python/nemo_relay/codecs.pyi was missed when the class was exposed through codecs.py, so type checkers rejected the import used by the binding tests. Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
There was a problem hiding this comment.
Actionable comments posted: 15
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
crates/adaptive/src/acg/request_surfaces/mod.rs (1)
92-102: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winDistinguish "shape not detected" from "surface not supported by ACG".
OCI GenAI requests now reach this function with a successfully detected provider surface. They still fail with "unable to resolve request surface from request shape". That message misstates the cause and will slow diagnosis of an expected, newly reachable failure path. Report the detected surface when the mapping returns
None.♻️ Proposed refactor
- detect_request_surface(&request.content) - .and_then(RequestSurface::from_provider_surface) - .ok_or_else(|| { - crate::acg::AcgError::Internal( - "unable to resolve request surface from request shape".to_string(), - ) - }) + let Some(provider_surface) = detect_request_surface(&request.content) else { + return Err(crate::acg::AcgError::Internal( + "unable to resolve request surface from request shape".to_string(), + )); + }; + RequestSurface::from_provider_surface(provider_surface).ok_or_else(|| { + crate::acg::AcgError::Internal(format!( + "adaptive request surfaces do not support provider surface {provider_surface:?}" + )) + })🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@crates/adaptive/src/acg/request_surfaces/mod.rs` around lines 92 - 102, Update resolve_request_surface_from_request to separate detection from mapping: retain the detected provider surface, then return the existing success path when RequestSurface::from_provider_surface succeeds and report the detected surface in the AcgError::Internal message when mapping returns None. Use wording that identifies the surface as unsupported by ACG rather than claiming the request shape could not be resolved.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@crates/core/src/codec/oci_genai.rs`:
- Around line 465-484: Update the assistant-message encoding branch in the
Message::Assistant handler so content: None emits an empty JSON array, or omits
the content field, instead of Json::Null. Preserve the existing
encode_generic_content behavior for present content and ensure tool-call-only
messages retain the OCI typed-part-list shape during re-encoding.
- Around line 876-944: Update patch_oci_api_specific to compare the edited and
baseline OCIGenAI api_format values and synchronize the chat request’s apiFormat
whenever the format changes, using the same edited format that encode_api_format
targets. Preserve existing compartmentId and servingMode handling, and ensure
the apiFormat field is patched through the envelope before returning.
- Around line 613-644: Update encode_cohere_messages so it does not default the
required “message” field to an empty string when the remaining messages do not
end with Message::User. Return FlowError::InvalidArgument for any edited message
list lacking a trailing user turn, while preserving the existing extraction and
history encoding for valid requests.
- Around line 355-381: Update encode_oci_tool_call so it omits the "id" field
when tool_call.id is empty, while preserving the existing ID field for non-empty
values. Build the JSON object conditionally rather than always emitting the key,
and leave decode_oci_tool_call unchanged.
- Around line 1632-1649: Update OCIChoiceState::finalize to insert the content
field only when self.text contains accumulated text. For tool-call-only
responses, omit content entirely so decoding yields no assistant text; preserve
the existing TEXT content structure when text is present.
- Around line 646-665: Update encode_cohere_turn and the corresponding Cohere
decoding logic to preserve Message::Tool.tool_call_id using OCI’s required wire
key while retaining the existing role and message fields. Ensure TOOL turns
decode back into Message::Tool with the identifier and content, and add a
round-trip test covering a tool result with a tool-call ID.
- Around line 1616-1630: Update observe_tool_call and its caller
observe_generic_choice to key tool-call state by the stable OCI id rather than
the event-local position, preserving separate state when parallel calls arrive
at position 0. Adjust the tool-call map and lookup flow so identity fields and
argument fragments remain associated with the correct id, and add coverage for
parallel-call fragments.
In `@crates/core/src/plugins/nemo_guardrails/python.rs`:
- Around line 1269-1290: Update the LocalGuardrailsCodec::OCIGenAI branch in
extract_stream_text to inspect a choices array and process each choice’s nested
message content using the existing TEXT-part collection logic. Retain the
current direct message fallback for chunks without choices, and return the first
non-empty extracted text.
In `@crates/core/tests/unit/codec/oci_genai_tests.rs`:
- Around line 353-430: Add a COHERE-specific test alongside
test_cohere_edit_rebuilds_modeled_fields that replaces the final annotated
message content with MessageContent::Parts, calls OCIGenAIChatCodec::encode, and
asserts the result is FlowError::InvalidArgument(_). Reuse the existing
cohere_chat_details and make_request setup.
In `@crates/core/tests/unit/codec/resolve_tests.rs`:
- Line 26: Update the ALL_SURFACES collection to include
ProviderSurface::OCIGenAI and change its declared length to 4, ensuring both
codec_name_round_trips_for_every_surface and
streaming_codec_constructs_a_usable_codec_for_every_surface exercise the OCI
codec.
In `@crates/core/tests/unit/plugins/nemo_guardrails/component_tests.rs`:
- Around line 636-638: Extend the remote-mode rejection coverage in the relevant
codec test to include codec = "oci_genai". Configure the case so input and
output retain their default true values, then assert the existing diagnostic
message alongside the other non-openai_chat codecs.
In `@crates/pii-redaction/src/overlay.rs`:
- Around line 198-223: Update the text-part construction in the block overlay
logic to use splitn with text_part_count instead of split, ensuring the final
TEXT block retains any remaining newline-separated content. Keep the existing
text_part_index mapping and fallback behavior unchanged.
- Around line 242-253: The tool-call overlay currently updates only top-level
fields, leaving OCI’s nested function values unsanitized. In the loop over
raw_calls and sanitized_call, update the existing raw_call.function object’s
name and arguments using the sanitized values, and use the top-level name and
arguments fields only when that nested object is absent.
In `@crates/pii-redaction/tests/coverage/overlay_tests.rs`:
- Around line 137-180: Add a focused test alongside
oci_genai_overlay_rewrites_generic_text_and_tool_calls using multiple
message.content blocks: include two TEXT blocks separated by a non-TEXT block,
provide matching redacted message lines in AnnotatedLlmResponse, and assert both
TEXT blocks are rewritten while the intervening non-TEXT block remains
unchanged.
In `@crates/python/src/py_api/mod.rs`:
- Around line 75-77: Update the PyOCIGenAIChatCodec fallback in py_llm_codec to
return builtin.inner_codec.clone() directly instead of inner_response_codec,
avoiding Python method dispatch. Add an OCI request integration test covering
this codec path.
---
Outside diff comments:
In `@crates/adaptive/src/acg/request_surfaces/mod.rs`:
- Around line 92-102: Update resolve_request_surface_from_request to separate
detection from mapping: retain the detected provider surface, then return the
existing success path when RequestSurface::from_provider_surface succeeds and
report the detected surface in the AcgError::Internal message when mapping
returns None. Use wording that identifies the surface as unsupported by ACG
rather than claiming the request shape could not be resolved.
🪄 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: 5883d735-69f6-46e9-ad4b-0fe5b2ed4382
📒 Files selected for processing (22)
crates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/codec/oci_genai.rscrates/core/src/codec/resolve.rscrates/core/src/plugins/nemo_guardrails/component.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/node/pii_redaction.d.tscrates/node/src/types/mod.rscrates/pii-redaction/src/component.rscrates/pii-redaction/src/overlay.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/python/src/py_types/mod.rspython/nemo_relay/_native.pyipython/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pypython/nemo_relay/pii_redaction.pyipython/tests/test_builtin_codecs.py
📜 Review details
🧰 Additional context used
📓 Path-based instructions (37)
{crates/python/src/py_api/mod.rs,python/nemo_relay/**/*.py,python/nemo_relay/**/*.pyi,go/nemo_relay/**/*.go,crates/node/src/api/**/*.rs}
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Update the language-native bindings for every exposed surface in Python, Go, and Node.js.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pycrates/python/src/py_api/mod.rspython/nemo_relay/pii_redaction.pyipython/nemo_relay/_native.pyi
{python/nemo_relay/**/*.py,python/nemo_relay/**/*.pyi,go/nemo_relay/**/*.go}
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Update language wrapper helpers such as Python wrapper modules, Python type stubs, and Go shorthand packages when the new behavior belongs in those helper layers.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pypython/nemo_relay/pii_redaction.pyipython/nemo_relay/_native.pyi
**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
**/*: Format changed files with the language-native formatter before the final lint/test pass.
If dynamic plugin behavior changed, usemaintain-dynamic-pluginsand include the native SDK, worker protocol, Python SDK, docs, packaging, and Codecov surfaces in the validation plan.
If code changes alter APIs, bindings, commands, paths, packaging behavior, observability/adaptive semantics, or documented best practices, update any dependent maintainer or consumer skills in the same branch.
During iteration, preferuv run pre-commit run --files <changed files...>.
Before review or handoff, runuv run pre-commit run --all-files.
**/*: Use release tags in raw Rust-compatible SemVer without a leadingv; tags such asv0.1.0are prohibited.
Use branch prefixesfeat/,fix/,docs/,test/, orrefactor/according to the change purpose.
Every commit in a pull request must include a DCOSigned-off-by:sign-off.
Before submitting a pull request, ensure pre-commit hooks, relevant tests, target-specific builds, documentation updates, and a rebase on the latestmainare complete.
Use commit messages in the formtype: short description, with a valid type and a first line under 72 characters.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pycrates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/adaptive/src/acg/request_surfaces/mod.rspython/nemo_relay/pii_redaction.pyicrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/pii-redaction/src/component.rscrates/core/tests/unit/codec/resolve_tests.rspython/nemo_relay/_native.pyicrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rspython/tests/test_builtin_codecs.pycrates/core/tests/unit/codec/oci_genai_tests.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rscrates/node/pii_redaction.d.ts
**/*.{rs,py,go,js,ts}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If a language surface changed, always run that language's test target even when Rust core did not change.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pycrates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/pii-redaction/src/component.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rspython/tests/test_builtin_codecs.pycrates/core/tests/unit/codec/oci_genai_tests.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rscrates/node/pii_redaction.d.ts
**/*.{rs,py,js,ts,tsx,go,java,kt,swift}
📄 CodeRabbit inference engine (.agents/skills/add-middleware/SKILL.md)
Add tests covering registration and duplicate names, deregistration and missing names, priority ordering, callback failure policy, scope-local inheritance and cleanup, event payload semantics, immutable mark and scope fields, and parity across affected bindings.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pycrates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/pii-redaction/src/component.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rspython/tests/test_builtin_codecs.pycrates/core/tests/unit/codec/oci_genai_tests.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rscrates/node/pii_redaction.d.ts
**/*.{rs,py,js,jsx,ts,tsx,go,c,h,cc,cpp,md,toml,yml,yaml,sh}
📄 CodeRabbit inference engine (AGENTS.md)
Keep SPDX headers on source, documentation, scripts, and configuration files; the project is Apache-2.0.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pycrates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/pii-redaction/src/component.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rspython/tests/test_builtin_codecs.pycrates/core/tests/unit/codec/oci_genai_tests.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rscrates/node/pii_redaction.d.ts
**/*.{rs,py}
📄 CodeRabbit inference engine (AGENTS.md)
Use
snake_casenaming in Rust and Python.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pycrates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/pii-redaction/src/component.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rspython/tests/test_builtin_codecs.pycrates/core/tests/unit/codec/oci_genai_tests.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,mjs,ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
Preserve the existing Tokio-based asynchronous model and callback/future lifetimes; do not unexpectedly block or hide async work in bindings.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pycrates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/pii-redaction/src/component.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rspython/tests/test_builtin_codecs.pycrates/core/tests/unit/codec/oci_genai_tests.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rscrates/node/pii_redaction.d.ts
python/nemo_relay/**/*.py
📄 CodeRabbit inference engine (AGENTS.md)
Keep Python wrapper modules under
python/nemo_relay/; the native extension is built fromcrates/pythonwithmaturin.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.py
**/*.py
📄 CodeRabbit inference engine (CONTRIBUTING.md)
**/*.py: Lint Python with Ruff using rule setsE,F,W, andI.
Format Python with the Ruff formatter, using a 120-character line length and double quotes.
Runtyfor Python type checking.
Use Pythonsnake_casenaming conventions.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pypython/tests/test_builtin_codecs.py
**/*.{rs,py,go,js,jsx,ts,tsx,c,h}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
**/*.{rs,py,go,js,jsx,ts,tsx,c,h}: Run tests for every language affected by a change; changes to the core Rust crate require tests across all bindings.
UseSONAR_IGNORE_START/SONAR_IGNORE_ENDonly for documented false positives, keep ignored blocks minimal, explain them with a comment, and obtain reviewer sign-off.
Preserve the layered architecture in which Rust provides the core runtime and C FFI, PyO3, and NAPI provide bindings that mirror the full API surface.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pycrates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/pii-redaction/src/component.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rspython/tests/test_builtin_codecs.pycrates/core/tests/unit/codec/oci_genai_tests.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rscrates/node/pii_redaction.d.ts
**/*.{rs,py,go,js,jsx,ts,tsx,c,h,html,md,mdx,toml}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include the appropriate SPDX copyright and Apache-2.0 license header in every source file.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pycrates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/pii-redaction/src/component.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rspython/tests/test_builtin_codecs.pycrates/core/tests/unit/codec/oci_genai_tests.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rscrates/node/pii_redaction.d.ts
**/*.{rs,py,go,js,ts,mdx}
📄 CodeRabbit inference engine (.agents/skills/maintain-observability/SKILL.md)
**/*.{rs,py,go,js,ts,mdx}: When changing observability event fields, exporter behavior, subscriber configuration, or binding parity, keep the core event model, ATIF, typed OpenTelemetry projections, FFI wrappers, language bindings, configuration, and documentation synchronized.
Examples and documentation must use each exporter's documented flush/deregister order before shutdown.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pycrates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/pii-redaction/src/component.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rspython/tests/test_builtin_codecs.pycrates/core/tests/unit/codec/oci_genai_tests.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rscrates/node/pii_redaction.d.ts
**/*.{py,go,js,ts}
📄 CodeRabbit inference engine (.agents/skills/maintain-observability/SKILL.md)
**/*.{py,go,js,ts}: Ensure Python, Go, and Node.js configuration objects and subscriber/exporter methods expose the same logical knobs and semantics as the core implementation.
Runjust test-python,just test-go, andjust test-nodewhen binding-native configuration or lifecycle changes.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pypython/tests/test_builtin_codecs.pycrates/node/pii_redaction.d.ts
python/**/*.py
📄 CodeRabbit inference engine (.agents/skills/test-python-binding/SKILL.md)
python/**/*.py: Format changed Python wrapper and test files withuv run ruff format python python/plugin.
Run the full Python suite withjust test-pythonbefore review.
Usejust build-pythonfor an explicit editable-package and native-extension build pass.
Files:
python/nemo_relay/codecs.pypython/nemo_relay/pii_redaction.pypython/tests/test_builtin_codecs.py
python/nemo_relay/**/*
⚙️ CodeRabbit configuration file
python/nemo_relay/**/*: 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_relay/codecs.pypython/nemo_relay/pii_redaction.pypython/nemo_relay/pii_redaction.pyipython/nemo_relay/_native.pyi
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor all FFI work since it is Rust work
Runjust test-rustto validate FFI changes
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting on FFI workWhen Rust files changed as part of Go work, also run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allwhen Rust files are changed as part of Node work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files are changed as part of Node work
Runjust test-rustwhen Rust files are changed as part of Node work
**/*.rs: If any Rust code changed, always runjust test-rust.
If any Rust code changed, also runcargo fmt --all.
If any Rust code changed, also runcargo clippy --workspace --all-targets -- -D warnings.
For Rust changes headed for review, runcargo fmt --allandcargo clippy --workspace --all-targets -- -D warningseven if relying on pre-commit.
**/*.rs: Format Rust code with rustfmt defaults usingcargo fmt.
Runcargo clippy -- -D warnings; all Rust warnings must be treated as errors.
Use Rustsnake_casenaming conventions.
Files:
crates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/pii-redaction/src/component.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rs
crates/**/*.rs
📄 CodeRabbit inference engine (AGENTS.md)
crates/**/*.rs: UseJson = serde_json::Valuein Rust-facing runtime APIs where existing code expects JSON payloads.
Treat Rust as the source of truth for runtime behavior; binding APIs should mirror Rust semantics unless a language-specific wrapper intentionally improves ergonomics.
Files:
crates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/pii-redaction/src/component.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rs
crates/**/src/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Do not add tests under
src; Rust tests belong in cratetests/trees.
Files:
crates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/src/codec/resolve.rscrates/pii-redaction/src/component.rscrates/core/src/plugins/nemo_guardrails/component.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rs
crates/python/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-python-binding/SKILL.md)
crates/python/**/*.rs: When Rust files change as part of Python work, runcargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings.
When the native Rust bridge changes, add and run the Rust crate tests fornemo-relay-python, includingcargo test -p nemo-relay-python.
Files:
crates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rs
crates/{python,ffi,node}/**/*
⚙️ CodeRabbit configuration file
crates/{python,ffi,node}/**/*: Treat binding changes as public API changes. Check for parity with the other language bindings, FFI ownership/lifetime safety,
callback error propagation, stable type conversion, and consistent async/stream semantics.
Flag changes that update one binding without corresponding tests or documentation for the same surface elsewhere.
Files:
crates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/node/pii_redaction.d.ts
{crates/core,crates/adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changes to
crates/coreorcrates/adaptivemust run the full language matrix
Files:
crates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/adaptive/**
📄 CodeRabbit inference engine (.agents/skills/maintain-optimizer/SKILL.md)
Keep
crates/adaptivealigned with the canonical adaptive config schema, built-in section helpers, plugin lifecycle, and validation/report behavior.
Files:
crates/adaptive/src/acg/request_surfaces/mod.rs
crates/{core,adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If
crates/coreorcrates/adaptivechanged, run the full validation matrix across Rust, Python, Go, and Node.js.
Files:
crates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive,plugin,worker,worker-proto,types}/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-rust-core/SKILL.md)
crates/{core,adaptive,plugin,worker,worker-proto,types}/**/*.rs: For changes in the Rust core, adaptive, plugin, worker, worker-proto, or types crates, runcargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings.
Use narrower crate tests only as a local debugging loop; final Rust validation must use the sharedjust test-rustworkflow.
For changes tocrates/core,crates/adaptive, or shared runtime semantics, expand validation to the full binding matrix withvalidate-changeorjust ci=true test-rust.
When public APIs, event shapes, middleware behavior, plugin semantics, or core/adaptive behavior change, also runvalidate-change.
If a change is isolated to one binding wrapper with unchanged Rust semantics, prefer that binding's build and test skill instead.
Files:
crates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive}/**/*.rs
⚙️ CodeRabbit configuration file
crates/{core,adaptive}/**/*.rs: Review the Rust runtime for async correctness, scope isolation, middleware ordering, and event lifecycle regressions.
Pay close attention to task-local/thread-local scope propagation, callback lifetimes, stream finalization, and root_uuid isolation.
Public API changes should preserve existing behavior unless tests and docs show the intended migration path.
Files:
crates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/core/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-go-binding/SKILL.md)
If the change touched
crates/coreor shared runtime semantics, also usevalidate-changefor broader validationUse
Result<T>withFlowErrorin core runtime paths, keeping wrapper-layer errors explicit and binding-appropriate.Run affected Rust crate tests, and run
just test-rustwhen event fields change.
Files:
crates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/core/src/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
crates/core/src/**/*.rs:plugins list,plugins inspect, andplugins validatemust report lifecycle and compatibility status without leaking secret configuration.
Top-leveldoctormust report resolved dynamic-plugin and host-configuration status.
Files:
crates/core/src/plugins/nemo_guardrails/python.rscrates/core/src/codec/resolve.rscrates/core/src/plugins/nemo_guardrails/component.rscrates/core/src/codec/oci_genai.rs
{crates/plugin/**/*.rs,crates/worker-proto/**/*.rs,crates/worker/**/*.rs,crates/types/**/*.rs,crates/core/**/*.{rs,toml},python/plugin/**/*.py}
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Run the targeted Rust, Python plugin, integration, documentation, and broader validation commands when validating dynamic-plugin changes.
Files:
crates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/{test,tests}/**/*
📄 CodeRabbit inference engine (CONTRIBUTING.md)
When adding functionality, include tests in the appropriate test files for each affected language binding.
Files:
crates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rspython/tests/test_builtin_codecs.pycrates/core/tests/unit/codec/oci_genai_tests.rs
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rspython/tests/test_builtin_codecs.pycrates/core/tests/unit/codec/oci_genai_tests.rs
crates/core/src/{api/**/*.rs,api/runtime/**/*.rs,codec/**/*.rs,json.rs}
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Implement the new or changed public runtime behavior first in the Rust core, especially under
crates/core/src/api/and related core modules such ascrates/core/src/api/runtime/,crates/core/src/codec/, andcrates/core/src/json.rs.
Files:
crates/core/src/codec/resolve.rscrates/core/src/codec/oci_genai.rs
python/tests/**/*.py
📄 CodeRabbit inference engine (AGENTS.md)
Maintain test coverage for Python binding and wrapper changes with the Python test suite.
python/tests/**/*.py: Use pytest to run Python tests.
Do not add@pytest.mark.asyncio; async tests are automatically detected by the async runner.
Do not add-> Nonereturn annotations to test functions.
When mocking a class, useunittest.mock.MagicMockorunittest.mock.AsyncMock, using thespecargument when necessary; do not define a new mock class.
Prefix mocked class names withmock, notfake.
Prefer pytest fixtures over helper methods.
Define fixtures needed by multiple test files inconftest.pyrather than repeating them.
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.
Files:
python/tests/test_builtin_codecs.py
crates/node/**/*.{js,ts,jsx,tsx,json}
📄 CodeRabbit inference engine (.agents/skills/test-node-binding/SKILL.md)
Format changed Node files with
npm run format --workspace=nemo-relay-node
Files:
crates/node/pii_redaction.d.ts
crates/node/**/*.{ts,tsx,d.ts}
📄 CodeRabbit inference engine (.agents/skills/test-node-binding/SKILL.md)
Use
npm run check:docstrings --workspace=nemo-relay-nodeto validate public API docstring checks when surface docs changed
Files:
crates/node/pii_redaction.d.ts
crates/node/**/*.{js,mjs,ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
Use
camelCasenaming for Node.js APIs.
Files:
crates/node/pii_redaction.d.ts
**/*.{js,jsx,ts,tsx}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Use Node.js
camelCasenaming conventions.
Files:
crates/node/pii_redaction.d.ts
🧠 Learnings (6)
📚 Learning: 2026-08-03T19:55:03.931Z
Learnt from: afourniernv
Repo: NVIDIA/NeMo-Relay PR: 558
File: crates/pii-redaction/src/rampart/mod.rs:265-274
Timestamp: 2026-08-03T19:55:03.931Z
Learning: In NeMo Relay first-party plugin registration helpers, treat the documented duplicate-registration `PluginError::RegistrationFailed` result from `register_plugin` as success when registration is intended to be idempotent. Do not locally reclassify this as `PluginError::Conflict`; changing the classification requires a core-wide review of the public API and FFI behavior.
Applied to files:
crates/python/src/py_types/mod.rscrates/python/src/py_api/mod.rscrates/python/src/py_types/codecs.rscrates/node/src/types/mod.rscrates/adaptive/src/acg/request_surfaces/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/codec/resolve.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/pii-redaction/src/component.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/codec/parity_tests.rscrates/core/src/plugins/nemo_guardrails/component.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rs
📚 Learning: 2026-07-28T20:07:29.880Z
Learnt from: willkill07
Repo: NVIDIA/NeMo-Relay PR: 571
File: crates/core/src/api/runtime/state.rs:996-1020
Timestamp: 2026-07-28T20:07:29.880Z
Learning: In NeMo Relay (RELAY-509), sanitizer callback failures must be treated as intentional fail-open behavior. When an event/tool (request/response) or LLM (request/response) sanitizer callback fails, the sanitizer chain should retain and publish the last valid event/payload snapshot (rather than dropping/invalidating the data) and log the failure including callback context (e.g., which sanitizer/callback failed and relevant identifiers). Apply this consistently across all sanitizer chains mentioned in the RELAY-509 documentation/migration guide.
Applied to files:
crates/core/src/plugins/nemo_guardrails/python.rscrates/core/src/codec/resolve.rscrates/core/src/plugins/nemo_guardrails/component.rscrates/core/src/codec/oci_genai.rs
📚 Learning: 2026-08-03T19:54:17.292Z
Learnt from: afourniernv
Repo: NVIDIA/NeMo-Relay PR: 558
File: crates/pii-redaction/src/rampart/mod.rs:486-492
Timestamp: 2026-08-03T19:54:17.292Z
Learning: In the Rust plugin configuration editor, use literal enum values for codec lists because `nemo_relay::editor_config!` generates static editor metadata. Do not replace these literals with a shared source such as `supported_codec_names()` unless the core editor-metadata API is first changed to support dynamic values.
Applied to files:
crates/pii-redaction/src/component.rscrates/pii-redaction/src/overlay.rs
📚 Learning: 2026-08-03T19:54:44.552Z
Learnt from: afourniernv
Repo: NVIDIA/NeMo-Relay PR: 558
File: crates/pii-redaction/src/rampart/mod.rs:670-792
Timestamp: 2026-08-03T19:54:44.552Z
Learning: In the Rust `crates/pii-redaction` crate, treat `pii_rampart` as a first-party built-in component. Preserve private `#[cfg(test)]` unit-test modules under `src`, including Rampart tests, according to the crate’s existing convention. Do not request moving these tests to `tests/` when doing so would require widening implementation visibility solely for test access.
Applied to files:
crates/pii-redaction/src/component.rscrates/pii-redaction/src/overlay.rs
📚 Learning: 2026-07-02T18:33:06.638Z
Learnt from: yczhang-nv
Repo: NVIDIA/NeMo-Relay PR: 355
File: crates/core/tests/unit/codec/parity_tests.rs:500-548
Timestamp: 2026-07-02T18:33:06.638Z
Learning: In Rust codec parity unit tests, when comparing a computed float/cost against a hand-derived literal (typically documented in a nearby comment), use a tolerance-based assertion rather than `assert_eq!` (e.g., `assert!((total - expected).abs() < 1e-9)`) to avoid harmless floating-point/rounding differences. Keep cross-codec parity assertions (e.g., `assert_eq!(chat_cost, anthropic_cost)`) exact with `assert_eq!` when the intention is a strict parity contract across codecs, since they are expected to share the same estimation path and produce bit-identical output across codecs.
Applied to files:
crates/core/tests/unit/codec/parity_tests.rs
📚 Learning: 2026-05-07T18:04:44.387Z
Learnt from: mnajafian-nv
Repo: NVIDIA/NeMo-Flow PR: 67
File: integrations/openclaw/src/modules.ts:1-2
Timestamp: 2026-05-07T18:04:44.387Z
Learning: In NVIDIA/NeMo-Flow, TypeScript source files should use `//` line comments for SPDX headers (e.g., `// SPDX-FileCopyrightText: ...` and `// SPDX-License-Identifier: ...`) rather than C-style block comments (`/* ... */`). The repo’s copyright checker enforces this mapping, so `//` SPDX headers in `.ts` files should not be flagged as a style violation.
Applied to files:
crates/node/pii_redaction.d.ts
🔇 Additional comments (34)
crates/node/src/types/mod.rs (1)
535-593: LGTM!crates/python/src/py_api/mod.rs (1)
46-48: LGTM!crates/python/src/py_types/codecs.rs (1)
1018-1082: LGTM!crates/python/src/py_types/mod.rs (1)
185-190: LGTM!python/nemo_relay/_native.pyi (1)
1151-1170: LGTM!python/nemo_relay/codecs.py (1)
51-51: LGTM!Also applies to: 162-170
crates/core/src/plugins/nemo_guardrails/component.rs (1)
285-285: LGTM!Also applies to: 433-438, 929-930
crates/core/src/plugins/nemo_guardrails/python.rs (1)
894-912: LGTM!crates/pii-redaction/src/overlay.rs (1)
15-37: LGTM!Also applies to: 505-523
crates/node/pii_redaction.d.ts (1)
42-42: LGTM!crates/pii-redaction/src/component.rs (1)
277-277: LGTM!Also applies to: 503-508, 1145-1146
python/nemo_relay/pii_redaction.py (1)
139-139: LGTM!python/nemo_relay/pii_redaction.pyi (1)
61-61: LGTM!crates/core/src/codec/oci_genai.rs (10)
66-91: LGTM!
97-149: LGTM!
181-213: LGTM!
310-338: LGTM!
387-452: LGTM!Also applies to: 509-532
671-749: LGTM!
751-872: LGTM!
950-1109: LGTM!
1390-1456: LGTM!
1586-1612: 🩺 Stability & AvailabilityNo issue: empty choices are handled safely.
decode_generic_response_bodyreturnsOkwhenchoicesis empty, so the close path does not panic or return an error.> Likely an incorrect or invalid review comment.crates/core/src/codec/resolve.rs (3)
17-17: LGTM!Also applies to: 28-29
69-71: LGTM!
160-160: LGTM!crates/adaptive/src/acg/request_surfaces/mod.rs (2)
46-53: LGTM!
46-53: 📐 Maintainability & Code QualityConfirm the Go binding tests ran for this
crates/adaptivechange.The PR report lists Rust, Python, and Node results. It does not list Go. The guidelines require the full Rust, Python, Go, and Node.js matrix when
crates/adaptivechanges. Runjust test-go, or state why it does not apply.As per coding guidelines: "If
crates/coreorcrates/adaptivechanged, run the full validation matrix across Rust, Python, Go, and Node.js."Source: Coding guidelines
crates/core/tests/unit/codec/oci_genai_tests.rs (1)
9-146: LGTM!Also applies to: 152-249, 255-347, 436-540, 1002-1091, 1097-1203
crates/core/tests/unit/codec/parity_tests.rs (1)
832-870: LGTM!Also applies to: 872-921, 923-968, 970-988, 990-1027, 1029-1062
crates/core/tests/unit/codec/resolve_tests.rs (1)
427-427: LGTM!Also applies to: 441-446
crates/core/tests/unit/plugins/nemo_guardrails/component_tests.rs (1)
402-407: LGTM!crates/pii-redaction/tests/coverage/overlay_tests.rs (1)
182-201: LGTM!python/tests/test_builtin_codecs.py (1)
7-8: LGTM!Also applies to: 28-33, 77-88, 295-320, 341-341
…rlays Review-driven fixes across the OCI GenAI surface: - encode omits an empty tool-call id instead of emitting "id": "", and re-encodes a tool-call-only assistant message with content: [] rather than null, matching the OCI typed-part-list wire shape - COHERE encode fails loudly (InvalidArgument) when the edited messages do not end with a user turn instead of silently sending an empty prompt, and rejects normalized tool messages outright since OCI's CohereToolMessage has no field for the normalized tool_call_id - an edited api_format now patches the wire apiFormat so the declared format can no longer contradict the rebuilt body - streamed tool-call fragments are keyed by their stable id (falling back to array position) so parallel calls arriving in separate events no longer merge, and a tool-call-only stream finalizes with an empty content list so it decodes without a synthetic empty message - the guardrails stream-text extractor handles choices-wrapped GENERIC deltas in addition to bare choice deltas - the PII overlay sanitizes nested function tool-call objects (the shape the decoder already accepts) and uses splitn so multi-part TEXT overlays never drop sanitized text containing newlines - the Python binding extracts the native OCI request codec directly, avoiding Python method dispatch on the managed-call path New coverage: parallel streamed tool calls, tool-call-only streams, apiFormat edits, COHERE trailing-user/multimodal/tool-message encode errors, empty-id omission, choices-wrapped and COHERE stream text extraction, remote-mode oci_genai rejection diagnostics, multi-part and nested-function overlays, an OCI request round-trip through the Python binding, and ProviderSurface::OCIGenAI in the every-surface resolver tests. Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
crates/core/tests/fixtures/native_plugin/Cargo.lock is already tracked on main with its own contents; the locally generated copy only added diff noise to the PR. Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
|
@coderabbitai review |
✅ Action performedReview finished.
|
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@crates/core/src/codec/oci_genai.rs`:
- Around line 1072-1077: Make an api_format change trigger the same body rebuild
path as an annotated.messages change, converting between GENERIC, COHERE, and
COHEREV2 request shapes as needed. Before updating apiFormat, validate that the
required format-specific encoder exists and return FlowError::InvalidArgument
when it does not. Preserve the existing COHERE encoder behavior and ensure
COHEREV2 uses the intended GENERIC-path semantics. Add coverage for format-only
transitions in both directions, including COHEREV2.
🪄 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: aa866bd2-4013-4c28-b68b-47151f547c6e
📒 Files selected for processing (11)
crates/core/src/codec/oci_genai.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/pii-redaction/src/overlay.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/python/src/py_api/mod.rspython/nemo_relay/codecs.pyipython/tests/test_builtin_codecs.py
📜 Review details
🧰 Additional context used
📓 Path-based instructions (31)
**/*.rs
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
**/*.rs: Any Rust change must runjust test-rust
Any Rust change must runcargo fmt --all
Any Rust change must runcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allfor all FFI work since it is Rust work
Runjust test-rustto validate FFI changes
Runcargo clippy --workspace --all-targets -- -D warningsto enforce strict linting on FFI workWhen Rust files changed as part of Go work, also run
cargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings
**/*.rs: Runcargo fmt --allwhen Rust files are changed as part of Node work
Runcargo clippy --workspace --all-targets -- -D warningswhen Rust files are changed as part of Node work
Runjust test-rustwhen Rust files are changed as part of Node work
**/*.rs: If any Rust code changed, always runjust test-rust.
If any Rust code changed, also runcargo fmt --all.
If any Rust code changed, also runcargo clippy --workspace --all-targets -- -D warnings.
For Rust changes headed for review, runcargo fmt --allandcargo clippy --workspace --all-targets -- -D warningseven if relying on pre-commit.
**/*.rs: Format Rust code with rustfmt defaults usingcargo fmt.
Runcargo clippy -- -D warnings; all Rust warnings must be treated as errors.
Use Rustsnake_casenaming conventions.
Files:
crates/python/src/py_api/mod.rscrates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/pii-redaction/src/overlay.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/python/src/py_api/mod.rs,python/nemo_relay/**/*.py,python/nemo_relay/**/*.pyi,go/nemo_relay/**/*.go,crates/node/src/api/**/*.rs}
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Update the language-native bindings for every exposed surface in Python, Go, and Node.js.
Files:
crates/python/src/py_api/mod.rspython/nemo_relay/codecs.pyi
**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
**/*: Format changed files with the language-native formatter before the final lint/test pass.
If dynamic plugin behavior changed, usemaintain-dynamic-pluginsand include the native SDK, worker protocol, Python SDK, docs, packaging, and Codecov surfaces in the validation plan.
If code changes alter APIs, bindings, commands, paths, packaging behavior, observability/adaptive semantics, or documented best practices, update any dependent maintainer or consumer skills in the same branch.
During iteration, preferuv run pre-commit run --files <changed files...>.
Before review or handoff, runuv run pre-commit run --all-files.
**/*: Use release tags in raw Rust-compatible SemVer without a leadingv; tags such asv0.1.0are prohibited.
Use branch prefixesfeat/,fix/,docs/,test/, orrefactor/according to the change purpose.
Every commit in a pull request must include a DCOSigned-off-by:sign-off.
Before submitting a pull request, ensure pre-commit hooks, relevant tests, target-specific builds, documentation updates, and a rebase on the latestmainare complete.
Use commit messages in the formtype: short description, with a valid type and a first line under 72 characters.
Files:
crates/python/src/py_api/mod.rscrates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rspython/tests/test_builtin_codecs.pycrates/pii-redaction/tests/coverage/overlay_tests.rspython/nemo_relay/codecs.pyicrates/core/src/plugins/nemo_guardrails/python.rscrates/pii-redaction/src/overlay.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,ts}
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If a language surface changed, always run that language's test target even when Rust core did not change.
Files:
crates/python/src/py_api/mod.rscrates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rspython/tests/test_builtin_codecs.pycrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/pii-redaction/src/overlay.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,ts,tsx,go,java,kt,swift}
📄 CodeRabbit inference engine (.agents/skills/add-middleware/SKILL.md)
Add tests covering registration and duplicate names, deregistration and missing names, priority ordering, callback failure policy, scope-local inheritance and cleanup, event payload semantics, immutable mark and scope fields, and parity across affected bindings.
Files:
crates/python/src/py_api/mod.rscrates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rspython/tests/test_builtin_codecs.pycrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/pii-redaction/src/overlay.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,jsx,ts,tsx,go,c,h,cc,cpp,md,toml,yml,yaml,sh}
📄 CodeRabbit inference engine (AGENTS.md)
Keep SPDX headers on source, documentation, scripts, and configuration files; the project is Apache-2.0.
Files:
crates/python/src/py_api/mod.rscrates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rspython/tests/test_builtin_codecs.pycrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/pii-redaction/src/overlay.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py}
📄 CodeRabbit inference engine (AGENTS.md)
Use
snake_casenaming in Rust and Python.
Files:
crates/python/src/py_api/mod.rscrates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rspython/tests/test_builtin_codecs.pycrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/pii-redaction/src/overlay.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/**/*.rs
📄 CodeRabbit inference engine (AGENTS.md)
crates/**/*.rs: UseJson = serde_json::Valuein Rust-facing runtime APIs where existing code expects JSON payloads.
Treat Rust as the source of truth for runtime behavior; binding APIs should mirror Rust semantics unless a language-specific wrapper intentionally improves ergonomics.
Files:
crates/python/src/py_api/mod.rscrates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/pii-redaction/src/overlay.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,js,mjs,ts,tsx}
📄 CodeRabbit inference engine (AGENTS.md)
Preserve the existing Tokio-based asynchronous model and callback/future lifetimes; do not unexpectedly block or hide async work in bindings.
Files:
crates/python/src/py_api/mod.rscrates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rspython/tests/test_builtin_codecs.pycrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/pii-redaction/src/overlay.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,jsx,ts,tsx,c,h}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
**/*.{rs,py,go,js,jsx,ts,tsx,c,h}: Run tests for every language affected by a change; changes to the core Rust crate require tests across all bindings.
UseSONAR_IGNORE_START/SONAR_IGNORE_ENDonly for documented false positives, keep ignored blocks minimal, explain them with a comment, and obtain reviewer sign-off.
Preserve the layered architecture in which Rust provides the core runtime and C FFI, PyO3, and NAPI provide bindings that mirror the full API surface.
Files:
crates/python/src/py_api/mod.rscrates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rspython/tests/test_builtin_codecs.pycrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/pii-redaction/src/overlay.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,jsx,ts,tsx,c,h,html,md,mdx,toml}
📄 CodeRabbit inference engine (CONTRIBUTING.md)
Include the appropriate SPDX copyright and Apache-2.0 license header in every source file.
Files:
crates/python/src/py_api/mod.rscrates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rspython/tests/test_builtin_codecs.pycrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/pii-redaction/src/overlay.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/**/src/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Do not add tests under
src; Rust tests belong in cratetests/trees.
Files:
crates/python/src/py_api/mod.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/pii-redaction/src/overlay.rscrates/core/src/codec/oci_genai.rs
**/*.{rs,py,go,js,ts,mdx}
📄 CodeRabbit inference engine (.agents/skills/maintain-observability/SKILL.md)
**/*.{rs,py,go,js,ts,mdx}: When changing observability event fields, exporter behavior, subscriber configuration, or binding parity, keep the core event model, ATIF, typed OpenTelemetry projections, FFI wrappers, language bindings, configuration, and documentation synchronized.
Examples and documentation must use each exporter's documented flush/deregister order before shutdown.
Files:
crates/python/src/py_api/mod.rscrates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rspython/tests/test_builtin_codecs.pycrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/pii-redaction/src/overlay.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/python/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-python-binding/SKILL.md)
crates/python/**/*.rs: When Rust files change as part of Python work, runcargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings.
When the native Rust bridge changes, add and run the Rust crate tests fornemo-relay-python, includingcargo test -p nemo-relay-python.
Files:
crates/python/src/py_api/mod.rs
crates/{python,ffi,node}/**/*
⚙️ CodeRabbit configuration file
crates/{python,ffi,node}/**/*: Treat binding changes as public API changes. Check for parity with the other language bindings, FFI ownership/lifetime safety,
callback error propagation, stable type conversion, and consistent async/stream semantics.
Flag changes that update one binding without corresponding tests or documentation for the same surface elsewhere.
Files:
crates/python/src/py_api/mod.rs
{crates/core,crates/adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/prepare-pr/SKILL.md)
Changes to
crates/coreorcrates/adaptivemust run the full language matrix
Files:
crates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/core/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-go-binding/SKILL.md)
If the change touched
crates/coreor shared runtime semantics, also usevalidate-changefor broader validationUse
Result<T>withFlowErrorin core runtime paths, keeping wrapper-layer errors explicit and binding-appropriate.Run affected Rust crate tests, and run
just test-rustwhen event fields change.
Files:
crates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive}/**/*
📄 CodeRabbit inference engine (.agents/skills/validate-change/SKILL.md)
If
crates/coreorcrates/adaptivechanged, run the full validation matrix across Rust, Python, Go, and Node.js.
Files:
crates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
**/{test,tests}/**/*
📄 CodeRabbit inference engine (CONTRIBUTING.md)
When adding functionality, include tests in the appropriate test files for each affected language binding.
Files:
crates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rspython/tests/test_builtin_codecs.pycrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rs
{crates/plugin/**/*.rs,crates/worker-proto/**/*.rs,crates/worker/**/*.rs,crates/types/**/*.rs,crates/core/**/*.{rs,toml},python/plugin/**/*.py}
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
Run the targeted Rust, Python plugin, integration, documentation, and broader validation commands when validating dynamic-plugin changes.
Files:
crates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive,plugin,worker,worker-proto,types}/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/test-rust-core/SKILL.md)
crates/{core,adaptive,plugin,worker,worker-proto,types}/**/*.rs: For changes in the Rust core, adaptive, plugin, worker, worker-proto, or types crates, runcargo fmt --all,just test-rust, andcargo clippy --workspace --all-targets -- -D warnings.
Use narrower crate tests only as a local debugging loop; final Rust validation must use the sharedjust test-rustworkflow.
For changes tocrates/core,crates/adaptive, or shared runtime semantics, expand validation to the full binding matrix withvalidate-changeorjust ci=true test-rust.
When public APIs, event shapes, middleware behavior, plugin semantics, or core/adaptive behavior change, also runvalidate-change.
If a change is isolated to one binding wrapper with unchanged Rust semantics, prefer that binding's build and test skill instead.
Files:
crates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
crates/{core,adaptive}/**/*.rs
⚙️ CodeRabbit configuration file
crates/{core,adaptive}/**/*.rs: Review the Rust runtime for async correctness, scope isolation, middleware ordering, and event lifecycle regressions.
Pay close attention to task-local/thread-local scope propagation, callback lifetimes, stream finalization, and root_uuid isolation.
Public API changes should preserve existing behavior unless tests and docs show the intended migration path.
Files:
crates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}
⚙️ CodeRabbit configuration file
{crates/**/tests/**,python/tests/**,go/nemo_relay/**/*_test.go}: Tests should cover the behavior promised by the changed API surface, including error paths and cross-request isolation where relevant.
Prefer assertions on lifecycle events, scope stacks, middleware ordering, and binding parity over shallow smoke tests.
Files:
crates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rspython/tests/test_builtin_codecs.pycrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/tests/unit/codec/oci_genai_tests.rs
python/tests/**/*.py
📄 CodeRabbit inference engine (AGENTS.md)
Maintain test coverage for Python binding and wrapper changes with the Python test suite.
python/tests/**/*.py: Use pytest to run Python tests.
Do not add@pytest.mark.asyncio; async tests are automatically detected by the async runner.
Do not add-> Nonereturn annotations to test functions.
When mocking a class, useunittest.mock.MagicMockorunittest.mock.AsyncMock, using thespecargument when necessary; do not define a new mock class.
Prefix mocked class names withmock, notfake.
Prefer pytest fixtures over helper methods.
Define fixtures needed by multiple test files inconftest.pyrather than repeating them.
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.
Files:
python/tests/test_builtin_codecs.py
**/*.py
📄 CodeRabbit inference engine (CONTRIBUTING.md)
**/*.py: Lint Python with Ruff using rule setsE,F,W, andI.
Format Python with the Ruff formatter, using a 120-character line length and double quotes.
Runtyfor Python type checking.
Use Pythonsnake_casenaming conventions.
Files:
python/tests/test_builtin_codecs.py
**/*.{py,go,js,ts}
📄 CodeRabbit inference engine (.agents/skills/maintain-observability/SKILL.md)
**/*.{py,go,js,ts}: Ensure Python, Go, and Node.js configuration objects and subscriber/exporter methods expose the same logical knobs and semantics as the core implementation.
Runjust test-python,just test-go, andjust test-nodewhen binding-native configuration or lifecycle changes.
Files:
python/tests/test_builtin_codecs.py
python/**/*.py
📄 CodeRabbit inference engine (.agents/skills/test-python-binding/SKILL.md)
python/**/*.py: Format changed Python wrapper and test files withuv run ruff format python python/plugin.
Run the full Python suite withjust test-pythonbefore review.
Usejust build-pythonfor an explicit editable-package and native-extension build pass.
Files:
python/tests/test_builtin_codecs.py
{python/nemo_relay/**/*.py,python/nemo_relay/**/*.pyi,go/nemo_relay/**/*.go}
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Update language wrapper helpers such as Python wrapper modules, Python type stubs, and Go shorthand packages when the new behavior belongs in those helper layers.
Files:
python/nemo_relay/codecs.pyi
python/nemo_relay/**/*
⚙️ CodeRabbit configuration file
python/nemo_relay/**/*: 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_relay/codecs.pyi
crates/core/src/**/*.rs
📄 CodeRabbit inference engine (.agents/skills/maintain-dynamic-plugins/SKILL.md)
crates/core/src/**/*.rs:plugins list,plugins inspect, andplugins validatemust report lifecycle and compatibility status without leaking secret configuration.
Top-leveldoctormust report resolved dynamic-plugin and host-configuration status.
Files:
crates/core/src/plugins/nemo_guardrails/python.rscrates/core/src/codec/oci_genai.rs
crates/core/src/{api/**/*.rs,api/runtime/**/*.rs,codec/**/*.rs,json.rs}
📄 CodeRabbit inference engine (.agents/skills/add-binding-feature/SKILL.md)
Implement the new or changed public runtime behavior first in the Rust core, especially under
crates/core/src/api/and related core modules such ascrates/core/src/api/runtime/,crates/core/src/codec/, andcrates/core/src/json.rs.
Files:
crates/core/src/codec/oci_genai.rs
🧠 Learnings (4)
📚 Learning: 2026-08-03T19:55:03.931Z
Learnt from: afourniernv
Repo: NVIDIA/NeMo-Relay PR: 558
File: crates/pii-redaction/src/rampart/mod.rs:265-274
Timestamp: 2026-08-03T19:55:03.931Z
Learning: In NeMo Relay first-party plugin registration helpers, treat the documented duplicate-registration `PluginError::RegistrationFailed` result from `register_plugin` as success when registration is intended to be idempotent. Do not locally reclassify this as `PluginError::Conflict`; changing the classification requires a core-wide review of the public API and FFI behavior.
Applied to files:
crates/python/src/py_api/mod.rscrates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rscrates/core/tests/unit/codec/resolve_tests.rscrates/core/tests/unit/plugins/nemo_guardrails/component_tests.rscrates/pii-redaction/tests/coverage/overlay_tests.rscrates/core/src/plugins/nemo_guardrails/python.rscrates/pii-redaction/src/overlay.rscrates/core/tests/unit/codec/oci_genai_tests.rscrates/core/src/codec/oci_genai.rs
📚 Learning: 2026-07-28T20:07:29.880Z
Learnt from: willkill07
Repo: NVIDIA/NeMo-Relay PR: 571
File: crates/core/src/api/runtime/state.rs:996-1020
Timestamp: 2026-07-28T20:07:29.880Z
Learning: In NeMo Relay (RELAY-509), sanitizer callback failures must be treated as intentional fail-open behavior. When an event/tool (request/response) or LLM (request/response) sanitizer callback fails, the sanitizer chain should retain and publish the last valid event/payload snapshot (rather than dropping/invalidating the data) and log the failure including callback context (e.g., which sanitizer/callback failed and relevant identifiers). Apply this consistently across all sanitizer chains mentioned in the RELAY-509 documentation/migration guide.
Applied to files:
crates/core/src/plugins/nemo_guardrails/python.rscrates/core/src/codec/oci_genai.rs
📚 Learning: 2026-08-03T19:54:17.292Z
Learnt from: afourniernv
Repo: NVIDIA/NeMo-Relay PR: 558
File: crates/pii-redaction/src/rampart/mod.rs:486-492
Timestamp: 2026-08-03T19:54:17.292Z
Learning: In the Rust plugin configuration editor, use literal enum values for codec lists because `nemo_relay::editor_config!` generates static editor metadata. Do not replace these literals with a shared source such as `supported_codec_names()` unless the core editor-metadata API is first changed to support dynamic values.
Applied to files:
crates/pii-redaction/src/overlay.rs
📚 Learning: 2026-08-03T19:54:44.552Z
Learnt from: afourniernv
Repo: NVIDIA/NeMo-Relay PR: 558
File: crates/pii-redaction/src/rampart/mod.rs:670-792
Timestamp: 2026-08-03T19:54:44.552Z
Learning: In the Rust `crates/pii-redaction` crate, treat `pii_rampart` as a first-party built-in component. Preserve private `#[cfg(test)]` unit-test modules under `src`, including Rampart tests, according to the crate’s existing convention. Do not request moving these tests to `tests/` when doing so would require widening implementation visibility solely for test access.
Applied to files:
crates/pii-redaction/src/overlay.rs
🔇 Additional comments (11)
crates/core/src/plugins/nemo_guardrails/python.rs (1)
894-894: LGTM!Also applies to: 903-903, 912-912, 1280-1311
crates/pii-redaction/src/overlay.rs (1)
193-229: LGTM!Also applies to: 231-271
crates/core/src/codec/oci_genai.rs (1)
374-388: LGTM!Also applies to: 479-487, 639-678, 1507-1511, 1649-1703
crates/python/src/py_api/mod.rs (1)
99-101: LGTM!python/nemo_relay/codecs.pyi (1)
166-209: LGTM!crates/core/tests/unit/codec/oci_genai_tests.rs (1)
1209-1226: LGTM!Also applies to: 1228-1242, 1244-1261, 1263-1307, 1309-1328, 1330-1372, 1374-1395
crates/core/tests/unit/codec/resolve_tests.rs (1)
399-403: LGTM!crates/core/tests/unit/plugins/nemo_guardrails/component_tests.rs (1)
636-638: LGTM!Also applies to: 674-687
crates/core/tests/unit/plugins/nemo_guardrails/local_python_tests.rs (1)
576-599: LGTM!crates/pii-redaction/tests/coverage/overlay_tests.rs (1)
203-238: LGTM!Also applies to: 240-280
python/tests/test_builtin_codecs.py (1)
295-328: LGTM!Also applies to: 330-354
A format switch can never be encoded soundly with merge-not-replace semantics: rebuilding the body for the new format would still leave the previous format's modeled fields (messages vs message/chatHistory) in the patched request. Treat api_format as read-only — patch_oci_api_specific returns InvalidArgument when an intercept changes it — and drop the partial apiFormat/body rewrite added in the previous commit. Covered for GENERIC->COHERE, GENERIC->COHEREV2, and COHERE->GENERIC transitions. Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
|
@coderabbitai review |
✅ Action performedReview finished.
|
|
please address merge conflicts when you get a chance. I can then start to exhaustively review |
Overview
Adds Oracle Cloud Infrastructure (OCI) Generative AI as a built-in provider across the Rust core and the Python/Node bindings. Originally opened as layer 1 of a four-part stacked series; per reviewer request (comment), the remaining three layers are now folded into this single PR, so it carries the complete feature.
The four capability layers, now all in this PR (one commit each, reviewable in sequence):
ApiSpecificOCI variants andLlmResponseCodecforGENERIC,COHERE, andCOHEREV2ChatResultpayloadsLlmCodecdecode plus merge-not-replace encode withencode(decode(x), x) == xidentity and unmodeled-field preservationProviderSurface::OCIGenAIregistration and detection,OCIGenAIStreamingCodec(SSE for both formats), and OCI awareness in guardrails, the PII-redaction overlay, and adaptive request surfacesOCIGenAIChatCodecexposed to Python (pyo3,.pyi,codecs.py) and Node (napi,.d.ts), with binding testsDetails
What:
ApiSpecificRequest::OCIGenAI { compartment_id, serving_mode, api_format }andApiSpecificResponse::OCIGenAI { api_format, model_version }(serde tag"oci_genai") incrates/types, pluscrates/core/src/codec/oci_genai.rsintroducingOCIGenAIChatCodec:apiFormats —GENERIC(choices-based; Meta Llama, Google, xAI, OpenAI, and imported open-weights models such as NVIDIA Nemotron on dedicated AI clusters),COHERE(text-based), andCOHEREV2(single assistantmessagewith typed content parts and nested-function tool calls) — normalizing model, response id, message content, tool calls, finish reasons, and usage counters (includingpromptTokensDetails.cachedTokens). Envelope and chat-response fields outside the normalized shape (timeCreated,serviceTier,chatHistory, grounding metadata) are preserved inextra.ChatDetailsfor both formats and re-encodes by merging into the original payload rather than replacing it, so unmodeled fields survive intercept round-trips; the encode/decode identity is asserted in tests.ProviderSurface::OCIGenAIwith detection keyed on the strongest-signal envelope fields (placed first in the resolver), so OCI payloads resolve without an explicit codec. Streaming is handled byOCIGenAIStreamingCodec(SSE lifecycle for GENERIC and COHERE). Guardrails, the PII-redaction overlay, and adaptive request surfaces gain OCI-format awareness with parity cases mirroring the existing providers.OCIGenAIChatCodecclasses in Python and Node with the same construction and resolver-integration semantics as the other built-in codecs.The codec accepts the REST wire format only (camelCase, as documented); converting alternate renderings produced by Oracle tooling is the caller's responsibility, per review discussion.
Why: OCI GenAI calls are currently opaque to Relay. This PR provides normalized
LLMEndannotations (model, finish reason, token usage), safe request editing for intercepts (redaction, policy), automatic provider detection including streaming, and access from every primary binding.How: Follows the built-in provider pattern (
anthropic.rsas template): unit-struct codec,FinishReasonmapping for the three formats' vocabularies (stop/length/max_tokens/tool_calls;COMPLETE/MAX_TOKENS;TOOL_CALL/STOP_SEQUENCE), positionalcall_{index}fallback ids for COHERE tool calls (noidon the wire). Binding classes mirrorAnthropicMessagesCodec/OpenAIChatCodecexposure.Testing: Full workspace suite green,
cargo clippy --workspace --all-targetszero warnings,cargo fmt --checkclean,missing_docssatisfied;just test-python(567 passed) andjust test-node(294 passed) green on the built bindings. OCI-specific coverage includes: GENERIC/COHERE fixtures from live OCI wire captures (simple, tool-call, mixed-content, tool-call-only, model-family sweep across Meta, OpenAI, Google, xAI, Cohere), COHEREV2 fixtures per the publishedCohereChatResponseV2schema with the wire shape confirmed against the live service, request round-trip identity and unmodeled-field preservation, wire-format-only contract tests, streaming lifecycle tests for both formats, resolver detection and parity cases, PII-redaction overlay coverage, invalid-content error paths, and binding tests in both languages. The combined content was also validated end-to-end: the codec-encoded request was posted verbatim to the signed OCI REST chat endpoint (dedicated AI cluster serving an imported NVIDIA Nemotron 3 model) and the live reply decoded with correct finish reason and token usage. Known unrelated flake:install_registrations_covers_registry_error_edges(dynamic worker plugin) is parallelism-sensitive onmain; the worker code here is byte-identical tomainand the test passes serially and in isolation.Breaking changes: None — additive enum variants, a new codec module, a new provider surface, and new binding classes.
Where should the reviewer start?
crates/core/src/codec/oci_genai.rstop-to-bottom (module docs explain the three formats and the wire-only contract), then the fixtures and round-trip tests incrates/core/tests/unit/codec/oci_genai_tests.rs, then the resolver registration incrates/core/src/codec/resolve.rs. The four commits after themainmerge apply the layers in order if commit-by-commit review is preferred.Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)
Summary by CodeRabbit
New Features
Bug Fixes