Mastra Blog·· 1 days agoAI score34
Introducing Latency Metrics for Mastra Observability
Introducing Latency Metrics for Mastra Observability
AI summary
Mastra now records TTFC (time to first chunk) and TTFT (time to first token) on every span, from model calls up to agent runs, so traces, spans, and threads can be filtered and sorted by these metrics on Mastra platform and Studio. The metrics work on self-hosted projects using DuckDB, PostgreSQL, or ClickHouse, and are queryable via the Mastra CLI ([email protected]+), Client SDK (@mastra/[email protected]+), and observability endpoints. Studio support requires [email protected] and @mastra/[email protected] or later.
Source: Mastra Blog · mastra.ai