> 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 full documentation content, see https://docs.nvidia.com/nemo/relay/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# Observability

Use the Observability plugin when you need to inspect NeMo Relay lifecycle events
in process or export agent activity to tracing, trajectory, or analysis
systems from one plugin configuration document.

Observability in NeMo Relay starts with events. Scopes, marks, managed tool
calls, managed LLM calls, middleware, and manual lifecycle APIs emit the
canonical Agent Trajectory Observability Format (ATOF) event stream.
Subscribers consume that stream in process, and exporter-oriented subscribers
write raw ATOF JSONL or translate events into Agent Trajectory Interchange
Format (ATIF), OpenTelemetry, or OpenInference.

The first-party plugin component has kind `observability`. It can install:

* Agent Trajectory Observability Format (ATOF) JSONL export for raw lifecycle events.
* Agent Trajectory Interchange Format (ATIF) trajectory export for each top-level agent scope.
* OpenTelemetry OTLP trace export.
* OpenInference-oriented OTLP trace export.

## Plugin-Managed Versus Manual Export

Use the Observability plugin for process-level exporter setup that should be
activated from config, `plugins.toml`, or a shared plugin document.

Use manual subscriber or exporter APIs when a test, script, or application
needs direct control over registration names, collection windows, explicit
flush timing, or per-run exporter objects. The plugin owns subscriber names and
teardown for the sections it enables.

## Use Observability When

Start here when you need to:

* Verify that instrumentation is attached to the right scope.
* Inspect tool and LLM inputs and outputs after sanitization.
* Correlate concurrent agent runs by root scope.
* Export traces to OTLP-compatible infrastructure.
* Produce trajectory data for analysis, replay, or evaluation workflows.

If you have not instrumented scopes, tools, or LLM calls yet, start with
[Instrument Applications](/instrument-applications/about).

## Exporter Selection

Choose the exporter based on the downstream system:

| Need                                                 | Use                                                                        |
| ---------------------------------------------------- | -------------------------------------------------------------------------- |
| Raw canonical event stream                           | [Agent Trajectory Observability Format (ATOF)](/observability-plugin/atof) |
| Offline analysis, replay, or evaluation trajectories | [Agent Trajectory Interchange Format (ATIF)](/observability-plugin/atif)   |
| Generic OTLP traces                                  | [OpenTelemetry](/observability-plugin/opentelemetry)                       |
| OpenInference-oriented agent and LLM spans           | [OpenInference](/observability-plugin/openinference)                       |

Start with in-process event inspection before exporting externally. Add sanitize
guardrails before exporters receive sensitive payloads.

For trace incidents involving missing traces, wrong scope attachment, export
failures, duplicate events, or sensitive telemetry, use the
[Trace Incident Runbook](/resources/troubleshooting/trace-incident-runbook).

## Correlating Trajectories And Traces

When ATIF and trace exporters observe the same NeMo Relay events, they share
NeMo Relay UUIDs for cross-format joins. Plugin-managed ATIF uses the top-level
agent scope UUID as the trajectory `session_id`. ATIF step lineage stores the
event UUID as `step.extra.ancestry.function_id` and the parent UUID as
`step.extra.ancestry.parent_id`.

OpenTelemetry and OpenInference spans carry the same values as
`nemo_relay.uuid` and `nemo_relay.parent_uuid` span attributes. Mark events use
`nemo_relay.mark.uuid` and `nemo_relay.mark.parent_uuid`. Native backend
`trace_id` and `span_id` values are still generated by the tracing backend and
are not written into ATIF.

## Pages

* [Observability Configuration](/observability-plugin/configuration) documents the whole plugin
  component shape, activation, validation, and teardown.
* [Agent Trajectory Observability Format (ATOF)](/observability-plugin/atof) covers raw JSONL event stream export.
* [Agent Trajectory Interchange Format (ATIF)](/observability-plugin/atif) covers per-agent trajectory export.
* [OpenTelemetry](/observability-plugin/opentelemetry) covers generic OTLP trace export.
* [OpenInference](/observability-plugin/openinference) covers OpenInference-oriented OTLP trace
  export.