Understand user behavior and application performance with session-level aggregations.
Root Field | Field | Description |
---|---|---|
metadata | num_events 1 | The total number of events captured during the session. |
num_model_events 1 | The number of model-related events (e.g., LLM requests) within the session. | |
has_feedback 1 | A boolean indicating whether the session contains any events with user feedback. | |
cost 1 | The total cost incurred for LLM usage during the session, based on the pricing model of the LLM provider. | |
total_tokens 1 | The total number of tokens processed by the LLM during the session, including both user input and generated output. | |
prompt_tokens 1 | The number of tokens in the user input or prompts during the session. | |
completion_tokens 1 | The number of tokens in the LLM-generated responses during the session. | |
start_time | The minimum UTC timestamp (in milliseconds) of start_time field of the session and its children. | |
end_time | The maximum UTC timestamp (in milliseconds) of end_time field of the session and its children. | |
duration | The difference of the end_time and start_time aggregates. Measured in milliseconds. However, this field will not be aggregated if manually declared. |
outputs
: The outputs
field from the final event will be inherited on to the session.error
: The session will adopt the error
field from the last child event that encountered a failure.duration
field is manually provided to the session, that value will be used.