ReferenceAPIsRust Library Referencenemo-relayapillm

Function llm_call

View as Markdown

Generated from cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-pii-redaction -p nemo-relay-ffi -p nemo-relay-types -p nemo-relay-plugin -p nemo-relay-worker-proto -p nemo-relay-worker.

pub fn llm_call(params: LlmCallParams<'_>) -> Result<LlmHandle>

Start a manual LLM lifecycle span.

This emits an LLM-start event after applying sanitize-request guardrails to the payload recorded for observability.

If a sanitizer errors or panics, Relay omits the payload and request annotation and does not run remaining sanitizers.

Parameters

  • name: Logical provider or model family name recorded on the span.
  • request: Raw LlmRequest associated with the span.
  • parent: Optional explicit parent scope.
  • attributes: LLM attribute bitflags applied to the span.
  • data: Optional application payload stored on the returned handle. The emitted start event data is the sanitized request payload.
  • metadata: Optional JSON metadata recorded on the start event.
  • model_name: Optional normalized model name recorded separately from the request payload.
  • annotated_request: Optional normalized request annotation produced by a codec.
  • timestamp: Optional timestamp recorded as the handle start time and on the emitted start event. When None, the current UTC time is used.

Returns

A Result containing the created LlmHandle after its start-event snapshot has been submitted for queued publication.

Errors

Returns an error when the runtime owner check fails or when internal state cannot be read safely. Dispatcher submission failures are logged because observability publication is best effort.

Notes

The runtime removes standard credential headers (authorization, proxy-authorization, cookie, x-api-key, api-key, anthropic-api-key, and x-goog-api-key) from the event-only request copy before sanitize-request guardrails run. This does not change the caller-owned LlmRequest. By default, when the owning agent is not fresh, the emitted request annotation is limited to the current user turn. Managed calls with a request codec also apply that projection to the event input, without changing the request used for provider execution. The observability plugin’s enable_full_payloads option disables this projection.