Describes properties of a run when loaded from the database. Extends the BaseRun interface.
interface RunJSON body of the response that caused the error
reference_example_id is the dataset example UUID this run was compared
app_path identifies the application code location that produced this run, if
recorded.
attachments maps each attachment file name to a pre-signed HTTPS download URL.
completion_tokens is the completion-side token count.
dotted_order is the hierarchical ordering key for trace trees.
end_time is when the run ended (RFC3339 date-time). JSON null if the run has
not finished yet.
JSON body of the response that caused the error
events is the ordered list of run events (for example streaming tokens).
feedback_stats aggregates feedback scores keyed by feedback key.
first_token_time is when the first output token was produced (RFC3339
date-time), when recorded for streamed runs.
id is the dataset example UUID.
inputs is the example input payload (arbitrary JSON object).
name is the example's optional name.
outputs is the example reference-output payload (arbitrary JSON object).
parent_run_ids lists ancestor run UUIDs from the trace root down to the direct
parent.
prompt_tokens is the prompt-side token count.
reference_example_id is the dataset example UUID this run was compared
against, if any.
run_type identifies what kind of operation this run represents (for example an
LLM call, a tool invocation, or a chain step). See the RunType enum for
allowed values.
start_time is when the run started (RFC3339 date-time).
HTTP status for the response that caused the error
total_tokens is prompt plus completion tokens.
trace_id is the root trace UUID; for a root run it matches id.