> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# Known Issues

This page lists current limitations and support notes for the release
documentation set.

## NeMo Relay 0.4

These notes apply to the NeMo Relay 0.4 release. The following known issues
and limitations apply to NeMo Relay 0.4:

* Go, WebAssembly, and the raw C FFI surface are experimental and source-first.
* Generated API pages cover Rust, Python, and Node.js. Experimental bindings do
  not yet have the same generated documentation depth.
* The NeMo Relay CLI is experimental. Coding agent observability support varies
  due to capabilities of hooks. Any encountered problems should be filed as
  bugs.
* Host plugin mode depends on each coding-agent host's plugin, hook, and
  provider-routing behavior. Hooks alone cannot produce complete LLM request
  and response spans.
* Complete first-request capture in Codex plugin mode depends on Codex firing
  an installed hook before the first provider request.
* Node.js 24 or newer is required for Node.js binding and package workflows.
* OpenClaw support uses public hook-backed telemetry with partial security and
  optimization support. Security is limited to pre-tool conditional guardrails,
  and optimization is limited to adaptive telemetry unless the integration owns
  a managed execution path.
* The NeMo Guardrails plugin remote backend depends on the availability,
  latency, and policy behavior of the configured remote service.
* The NeMo Guardrails plugin local backend starts a Python worker subprocess.
  That worker environment must provide Python 3.11 or newer and
  `nemoguardrails==0.22.0`; `SUPPORTED_NEMOGUARDRAILS_VERSION` in
  `crates/core/src/plugins/nemo_guardrails/local_worker.py` is the
  authoritative pin.
* The PII redaction plugin currently provides deterministic local backend
  support. Local-model backend configuration is reserved for future expansion.
* Pricing estimates depend on configured pricing sources and the freshness of
  the source catalog. Unknown model pricing and missing token data leave cost
  absent instead of defaulting to zero.
* ATOF streaming endpoints depend on collector availability. Failed endpoints
  are skipped or retried without blocking file output or other configured
  endpoints.
* S3-compatible ATIF export requires valid storage credentials and endpoint
  configuration in the runtime environment.
* Remote ATIF storage requires valid destination credentials and endpoint
  configuration in the runtime environment.
* `LLMRequest` objects in the Python binding should be treated as immutable.
  Request middleware that changes content should return a new request object.
* Native subscriber callbacks are delivered asynchronously. Flush subscribers
  before relying on callback side effects, captured event lists, files, or
  exporter output. Deregistering a subscriber affects future emissions, but
  callbacks from already-queued event snapshots may still run.

### Fixed in NeMo Relay 0.4

* ATIF shutdown no longer deadlocks queued subscribers.
* Sanitized LLM requests are resolved from annotations for observability output.
* Structured ATIF tool results and Hermes tool-result observations are
  preserved more reliably.
* Hermes routed-provider spans, wrapped ATIF fidelity, subagent lineage, and
  error-path export consistency are covered and corrected.
* OpenClaw observability output is more consistent for nested subagents, model
  timing diagnostics, hook-backed provenance, placeholder replay, and
  hook-only fallback exports.
* LangChain serialization handles wrapped integration payloads more reliably.
* Plugin context-manager teardown avoids the previous deadlock path.
* Node.js `withScope` callbacks receive a real `ScopeHandle`.
* Deep Agents model responses are annotated for downstream observability.

### Fixed in Earlier Releases

* Managed LLM start events are emitted before execution intercepts.
* Coding-agent trace scopes are aligned with NeMo Relay agent scope semantics.
* ATIF tool observations are correlated with their matching tool calls.
* OpenClaw tool call replay visibility is preserved.
* Enabled TLS support for OTLP HTTP export.
* Preserved Go scope stacks across OS threads.