Mastra Observability adds TTFC and TTFT latency metrics
Understand this story
Mastra adds latency metrics for every agent and model call in the platform and Studio, allowing traces, spans, and threads to be filtered and sorted by time to first chunk (TTFC) and time to first token (TTFT). This feature is available for the Mastra platform and for self-hosted projects where storage.observability uses DuckDB, PostgreSQL, or ClickHouse; each request must carry a platform access token and project ID. Use requires [email protected] or later; in Studio, it requires [email protected] and @mastra/[email protected] or later.
AI overview based on source reports · Updated 12 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Mastra BlogIntroducing Latency Metrics for Mastra Observability
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.
Activity for this story
- Current comparable activity
- 4
- Peak comparable activity
- 6Nov 6 02:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.