Skip to content
Live
Trending storyPast story

Mastra introduced Span Queries feature

2 reports1 outlets14 days agoUpdate

The story so far

AI overview

Mastra introduced Span Queries functionality, allowing users to filter and group individual spans across all traces based on conditions such as time range, span type, span name, status, errors, and duration to find and fix issues. Using this feature requires platform access tokens and project IDs, and the correct Mastra observability base URL must be used based on the project's region. Mastra also launched latency metric tracking functionality, supporting the tracking of latency metrics for each agent and model call, with filtering and sorting of traces and threads via TTFC and TTFT to identify slow components. Latency metrics are applicable to the Mastra platform and self-hosted projects (storage.observability using DuckDB, PostgreSQL, or ClickHouse), and also require platform access tokens and project IDs, with availability through Mastra CLI, platform and Studio, client SDKs, and observability endpoints.

AI-written from the reports · Updated 13 days ago

Developments

2 developments

  1. 5 Nov, 08:00 · 1 reports
    Introducing Latency Metrics
    Mastra Blog:Introducing Latency Metrics for Mastra Observability
  2. 28 Oct, 08:00 · 1 reports
    Introducing Span Queries
    Mastra Blog:Introducing Span Queries

Coverage timeline

Follow the coverage to see every side of the story.

5 Nov
  1. Mastra Blog
    Introducing Latency Metrics for Mastra Observability

    The Mastra platform and Studio now support tracking latency metrics for each agent and model call, with filtering and sorting of tracking, span, and threads via TTFC (First Data Block Time) and TTFT (First Token Time) to identify slow components.

28 Oct
  1. Mastra Blog
    Introducing Span Queries

    Mastra platform and Studio now allow you to filter or group spans by time range, span type, span name, status, error, duration, etc. Your coding agents can also use CLI, Mastra client SDK, and HTTP observability endpoints to build the same queries to find and fix issues.