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
JavaScriptlangsmithindexRun
Interface●Since v0.1

Run

Describes properties of a run when loaded from the database. Extends the BaseRun interface.

Copy
interface Run

Bases

BaseRun

Used in Docs

  • How to create and manage datasets programmatically
  • How to define a code evaluator
  • How to evaluate agents
  • How to evaluate an application's intermediate steps
  • How to fetch performance metrics for an experiment

Properties

property
app_path: string

app_path identifies the application code location that produced this run, if recorded.

property
attachments: Attachments

attachments maps each attachment file name to a pre-signed HTTPS download URL.

property
child_run_ids: string[]
property
child_runs: Run[]
property
completion_tokens: number

completion_tokens is the completion-side token count.

property
dotted_order: string

dotted_order is the hierarchical ordering key for trace trees.

property
end_time: string | number

end_time is when the run ended (RFC3339 date-time). JSON null if the run has not finished yet.

property
error: string

JSON body of the response that caused the error

property
events: KVMap[]

events is the ordered list of run events (for example streaming tokens).

property
extra: KVMap
property
feedback_stats: KVMap

feedback_stats aggregates feedback scores keyed by feedback key.

property
first_token_time: number

first_token_time is when the first output token was produced (RFC3339 date-time), when recorded for streamed runs.

property
id: string

id is the dataset example UUID.

property
in_dataset: boolean
property
inputs: KVMap

inputs is the example input payload (arbitrary JSON object).

property
inputs_s3_urls: S3URL
property
manifest_id: string
property
name: string

name is the example's optional name.

property
outputs: KVMap

outputs is the example reference-output payload (arbitrary JSON object).

property
outputs_s3_urls: S3URL
property
parent_run_id: string
property
parent_run_ids: string[]

parent_run_ids lists ancestor run UUIDs from the trace root down to the direct parent.

property
prompt_tokens: number

prompt_tokens is the prompt-side token count.

property
reference_example_id: string

reference_example_id is the dataset example UUID this run was compared against, if any.

property
run_type: string

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.

property
serialized: object
property
session_id: string
property
start_time: string | number

start_time is when the run started (RFC3339 date-time).

property
status: string

HTTP status for the response that caused the error

property
tags: string[]
property
total_tokens: number

total_tokens is prompt plus completion tokens.

property
trace_id: string

trace_id is the root trace UUID; for a root run it matches id.

Inherited fromBaseRun

Properties

Pattachments: __type
—

attachments maps each attachment file name to a pre-signed HTTPS download URL.

Pdotted_order: string
—

dotted_order is the hierarchical ordering key for trace trees.

Pend_time: string
—

end_time is when the run ended (RFC3339 date-time). JSON null if the run has

Perror: undefined
—

JSON body of the response that caused the error

Pevents: Event[]
—

events is the ordered list of run events (for example streaming tokens).

Pextra: __type | nullPid: string
—

id is the dataset example UUID.

Pinputs: unknown
—

inputs is the example input payload (arbitrary JSON object).

Pname: string
—

name is the example's optional name.

Poutputs: unknown
—

outputs is the example reference-output payload (arbitrary JSON object).

Pparent_run_id: stringPreference_example_id: string
—

reference_example_id is the dataset example UUID this run was compared

Prun_type: "TOOL" | "CHAIN" | "LLM" | "RETRIEVER" | "EMBEDDING" | "PROMPT" | "PARSER"
—

run_type identifies what kind of operation this run represents (for example an

Pserialized: __typePstart_time: string
—

start_time is when the run started (RFC3339 date-time).

Ptags: string[] | nullPtrace_id: string
—

trace_id is the root trace UUID; for a root run it matches id.

View source on GitHub