nemo-relay-debug-runti…
Use this skill when NeMo Relay is installed or imported but application-side runtime behavior is missing or incorrect, including…
Use this skill when adding NeMo Relay typed wrappers, domain types, or provider codecs while preserving JSON middleware semantics and caller-visible behavior.
$ npx -y skills add NVIDIA/NeMo-Relay --skill nemo-relay-instrument-typed-wrappers --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/nemo-relay-instrument-typed-wrappersContext preview
The summary Claude sees to decide when to auto-load this skill.
Use this skill when adding NeMo Relay typed wrappers, domain types, or provider codecs while preserving JSON middleware semantics and caller-visible behavior.
name: nemo-relay-instrument-typed-wrappers description: Use this skill when adding NeMo Relay typed wrappers, domain types, or provider codecs while preserving JSON middleware semantics and caller-visible behavior. license: Apache-2.0 metadata: author: NVIDIA Corporation and Affiliates
Use this skill when an application wants stronger domain types than raw JSON for tool or LLM integration. Keep typed boundaries explicit so middleware still sees predictable JSON.
application-facing values to JSON before NeMo Relay emits events or runs middleware, then converts JSON back into the framework callback or caller type.
`BestEffortAnyCodec`. Node.js exposes `JsonPassthrough` plus custom `Codec<T>` implementations.
available. Prefer dataclass, Pydantic, or explicit Node.js codecs when the framework owns a stable schema.
provider-specific LLM requests and responses so middleware and subscribers can inspect messages, tools, model names, generation parameters, and response annotations.
and `AnthropicMessagesCodec` in Python, Node.js, and Rust. Choose the codec that matches the actual provider payload shape.
`message`, `tool_calls`, `finish_reason`, `usage`, provider-specific data, and extra unmodeled fields. They do not rewrite the caller-visible response.
raw `LLMRequest` and optional annotated request; `encode` merges annotated edits back before execution intercepts and the provider callback run.
annotation. They compare edits with a decoded baseline and patch only changed fields, preserving native representation details and unknown fields.
`api_specific` request surface for normalized edits. Provider-only union members use explicit `{ provider, kind, value }` native components. Reserve top-level `extra` for unknown future fields.
Messages, OpenAI Chat Completions, and OpenAI Responses generation routes. On those routes, treat raw `request.content` as read-only and return body edits through the annotated request. Header edits still use the raw request.
uses codec traits directly
conversion
intercept intentionally changes them
NVIDIA NeMo Relay provides visibility into and control over agent runs without requiring changes to the existing agent stack.
Use this skill when NeMo Relay is installed or imported but application-side runtime behavior is missing or incorrect, including…
Use this skill when first-time NeMo Relay users want to try Relay, choose the least-complex supported quick start, or verify…
Use this skill when choosing or running NeMo Relay installation for the CLI, Python, Node.js, Rust, OpenClaw, or maintained…
Use this skill when an application owns tool or LLM/provider call sites and needs to wrap them with NeMo Relay scopes and managed…
Use this skill when concurrent requests, async tasks, threads, workers, goroutines, or agents need independent NeMo Relay scope…
Use this skill when assessing, extending, or implementing NeMo Relay support in an agent harness or agent framework, including…