Mastra Agent Telemetry

Implementation evidence

Mastra Agent Telemetry: from boundary to verified row

Use Mastra Agent Telemetry at a controlled application boundary, keep the event contract small, and verify a known outcome before building aggregate views.

1
Choose the outcome
Mastra agent observability
2
Define the contract
run_id, workflow, agent_name, model_alias, prompt_version, and release
3
Instrument the boundary
Wrap the public agent.generate, agent.stream, or workflow run boundary and emit one application outcome after completion.
4
Verify the evidence
Exercise a known fixture, then inspect agent_run_completed for one correctly typed terminal row.

Before you start

Prerequisites and boundaries

Mastra and telemetry-sh initialized in a trusted server runtime
Stable agent, workflow, prompt-version, and outcome categories
A reviewed boundary for prompts, responses, memory, tool payloads, traces, and scorer output

Delivery setup

Install and initialize server-side

Import telemetry-sh in server-only code and initialize it once with process.env.TELEMETRY_API_KEY. Keep ingestion credentials out of browser bundles, client-visible environment variables, source control, logs, and exception messages.

mastra-install

npm installation

bash

npm install telemetry-sh

1Prepare one reusable server-side delivery client with bounded network behavior.
2Add the outcome event at the success, failure, retry, or timeout boundary.
3Send controlled fixtures and inspect the stored rows before enabling an alert.

Snippet

Start with one structured event

Add this shape where the workflow completes, fails, or retries. Then build the dashboard from real fields.

mastra

Mastra Agent Telemetry event

javascript

async function runSupportAgent(prompt, runId) {
  const startedAt = performance.now();
  let status = "success";
  let errorType;

  try {
    return await supportAgent.generate(prompt);
  } catch (error) {
    status = "failed";
    errorType = classifyAgentError(error);
    throw error;
  } finally {
    await telemetry.log("agent_run_completed", {
      run_id: runId,
      workflow: "support_resolution",
      agent_name: "support_agent",
      status,
      error_type: errorType,
      duration_ms: Math.round(performance.now() - startedAt),
      release: process.env.APP_RELEASE,
    });
  }
}

Event contract

run_id, workflow, agent_name, model_alias, prompt_version, and release

status, duration_ms, tool_call_count, retry_count, and estimated_cost_usd

accepted, scorer_category, human_handoff, error_type, and environment

Implementation checkpoints

Checkpoint 1

Wrap the public agent.generate, agent.stream, or workflow run boundary and emit one application outcome after completion.

Checkpoint 2

Use Mastra's built-in logs, traces, and eval primitives for detailed execution evidence rather than copying every trace attribute into Telemetry.

Checkpoint 3

Keep model and provider names bounded, and never emit messages, memory contents, retrieved documents, or tool arguments by default.

Verification

Prove the event arrived

Run this after exercising known success and failure cases. Replace the fallback table name if your final event contract differs from the snippet.

mastra-verification

Mastra Agent Telemetry verification query

sql

SELECT *
FROM agent_run_completed
ORDER BY timestamp_utc DESC
LIMIT 20;

Confirm one terminal row per logical outcome, with the expected status, identifiers, units, and UTC time.

Inspect the inferred schema and verify that retries do not change field types or generate a new logical event ID.

Search the stored fields for credentials, raw payloads, prompts, private content, and unbounded error messages.

Exercise a provider timeout, ingestion rejection, and process shutdown before treating the dashboard as complete.

Implementation references

Review the event contract, data-safety guidance, and upstream primary documentation before enabling a new production path.

Tracking LLM costs RAG evaluation SQL Canonical wide events Mastra agents overview Mastra observability overview

Production boundary

Keep the outcome event small and recoverable

This pattern provides

A bounded, SQL-ready outcome beside the upstream workflow.
Stable fields for dashboards, alerts, and cross-event correlation.
A fixture-driven path for validating success, failure, retry, and timeout behavior.

This pattern does not provide

An OTLP exporter, automatic collection pipeline, or replacement for detailed traces and diagnostic logs.
Exactly-once delivery merely because the payload contains an event ID.
Permission to collect raw provider payloads, user content, credentials, or regulated data.

Delivery and idempotency Batching and shutdown Troubleshoot ingestion

Event schema starting points

Review the row grain, emit boundary, required types, privacy classes, example payload, and validation checklist before adapting a query or snippet to production.

AI operations10 fields