Skip to main content
HoneyHive automatically aggregates metrics from child spans to the session level. These fields are reserved on the session event and will be overwritten if you set them there manually.

​
Reserved Session Fields

​
Token and cost tracking

HoneyHive automatically rolls up token counts from every model event in a session, and sums any cost values you attach to events. Token counts are extracted from the LLM provider’s response (e.g. OpenAI’s usage field). If a session contains multiple LLM calls (e.g. a chain or agent loop), all calls are summed at the session level. To track cost, set metadata.cost on each child event, for example with enrich_span(metadata={"cost": 0.0021}) (see Enrich traces). The session-level metadata.cost is the sum of those values, so setting it on the session event itself has no effect. Sessions where no event carries a cost display no cost. You can use these fields to filter, alert, and chart in the HoneyHive dashboard - for example, flagging sessions where cost > 0.10 or total_tokens > 10000.

​
Duration Calculation

Duration is calculated as max(end_time) - min(start_time) across all events in the session. This works for both synchronous and asynchronous execution:
Diagram comparing synchronous execution (events in sequence) vs asynchronous execution (events in parallel branches)
  • Synchronous: Events chain sequentially (Session Start → Event 1 → Event 2)
  • Asynchronous: Events branch in parallel from Session Start
If you manually set duration on the session, that value is preserved.

Alerts

Set up alerts based on session metrics

Charts

Visualize session metrics over time