LangChain Reference home pageLangChain ReferenceLangChain Reference
  • GitHub
  • Main Docs
Deep Agents
LangChain
LangGraph
Integrations
LangSmith
LangSmith
  • Client
  • Run Trees
  • Traceable
  • Evaluation
  • Schemas
  • Langchain
  • Jest
  • Vitest
  • Wrappers
  • Anonymizer
  • Jestlike
  • Vercel
  • Anthropic
  • Sandbox
⌘I

LangChain Assistant

Ask a question to get started

Enter to send•Shift+Enter new line

Menu

LangSmith
ClientRun TreesTraceableEvaluationSchemasLangchainJestVitestWrappersAnonymizerJestlikeVercelAnthropicSandbox
Language
Theme
JavaScriptlangsmithschemasTracerSessionResult
Interface●Since v0.0

TracerSessionResult

Copy
interface TracerSessionResult

Bases

TracerSession

Properties

Inherited fromTracerSession

Properties

Pdescription: string | nullPend_time: number
—

The epoch time at which the run ended, if applicable.

Pextra: KVMap
—

Additional RunTree configuration to pass through.

Pid
View source on GitHub
: string
—

Optionally, a unique identifier for the run.

Pname: string
—

Custom name for the root span. If not provided, defaults to the

Preference_dataset_id: string
Pstart_time: number
—

The epoch time at which the run started, if available.

Ptenant_id: string
—

The ID of the tenant associated with the annotation queue.

property
completion_tokens: number
property
description: string
property
end_time: number
property
extra: KVMap
property
feedback_stats: Record<string, unknown>
property
id: string
property
last_run_start_time: number
property
latency_p50: number
property
latency_p99: number
property
name: string
property
prompt_tokens: number
property
reference_dataset_id: string
property
run_count: number
property
run_facets: KVMap[]
property
start_time: number
property
tenant_id: string
property
total_tokens: number

Number of tokens generated in the completion.

The epoch time at which the run ended, if applicable.

Additional RunTree configuration to pass through.

Optionally, a unique identifier for the run.

Custom name for the root span. If not provided, defaults to the model display name or "generateText"/"streamText".

Number of tokens used in the prompt.

The epoch time at which the run started, if available.

The ID of the tenant associated with the annotation queue.