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

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

View source on GitHub
P
error
: 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 | null
Pid: 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: string
Preference_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: __type
Pstart_time: string
—

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

Ptags: string[] | null
Ptrace_id: string
—

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

property
app_path: string
property
attachments: Attachments
property
child_run_ids: string[]
property
child_runs: Run[]
property
completion_tokens: number
property
dotted_order: string
property
end_time: string | number
property
error: string
property
events: KVMap[]
property
extra: KVMap
property
feedback_stats: KVMap
property
first_token_time: number
property
id: string
property
in_dataset: boolean
property
inputs: KVMap
property
inputs_s3_urls: S3URL
property
manifest_id: string
property
name: string
property
outputs: KVMap
property
outputs_s3_urls: S3URL
property
parent_run_id: string
property
parent_run_ids: string[]
property
prompt_tokens: number
property
reference_example_id: string
property
run_type: string
property
serialized: object
property
session_id: string
property
start_time: string | number
property
status: string
property
tags: string[]
property
total_tokens: number
property
trace_id: string

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.