Create Run, Wait for Output

Create a run in existing thread. Wait for the final output and then return it.

POST /threads/{thread_id}/runs/wait

Try it

404

"<string>"

Path Parameters

thread_id · string<uuid> · required

The ID of the thread.

Body

application/json

Payload for creating a run.

assistant_id · required

The assistant ID or graph name to run. If using graph name, will default to first assistant created from that graph.

checkpoint · Checkpoint · object

The checkpoint to resume from.

Show child attributes

checkpoint. thread_id · string

Unique identifier for the thread associated with this checkpoint.

checkpoint. checkpoint_ns · string

Namespace for the checkpoint, used for organization and retrieval.

checkpoint. checkpoint_id · string

Optional unique identifier for the checkpoint itself.

checkpoint. checkpoint_map · object

Optional dictionary containing checkpoint-specific data.

input

The input to the graph.

command · Command · object

The input to the graph.

Show child attributes

command. update

An update to the state.

command. resume

A value to pass to an interrupted node.

command. goto

Name of the node(s) to navigate to next or node(s) to be executed with a provided input.

Show child attributes

command.goto. node · string · required

The node to send the message to.

command.goto. input · required

The message to send.

metadata · Metadata · object

Metadata to assign to the run.

config · Config · object

The configuration for the assistant.

Show child attributes

config. tags · string[]

config. recursion_limit · integer

config. configurable · Configurable · object

context · Context · object

Static context added to the assistant.

webhook · string<uri-reference>

Webhook to call after LangGraph API call is done.

Required string length: 1 - 65536

interrupt_before

Nodes to interrupt immediately before they get executed.

Available options: *

interrupt_after

Nodes to interrupt immediately after they get executed.

Available options: *

stream_mode

The stream mode(s) to use.

Available options: values, messages, messages-tuple, tasks, checkpoints, updates, events, debug, custom

stream_subgraphs · boolean · default: false

Whether to stream output from subgraphs.

stream_resumable · boolean · default: false

Whether to persist the stream chunks in order to resume the stream later.

on_disconnect · enum<string> · default: cancel

The disconnect mode to use. Must be one of 'cancel' or 'continue'.

Available options: cancel, continue

feedback_keys · string[]

Feedback keys to assign to run.

multitask_strategy · enum<string> · default: enqueue

Multitask strategy to use. Must be one of 'reject', 'interrupt', 'rollback', or 'enqueue'.

Available options: reject, rollback, interrupt, enqueue

if_not_exists · enum<string> · default: reject

How to handle missing thread. Must be either 'reject' (raise error if missing), or 'create' (create new thread).

Available options: create, reject

after_seconds · number

The number of seconds to wait before starting the run. Use to schedule future runs.

checkpoint_during · boolean · default: false

Whether to checkpoint during the run.

durability · enum<string> · default: async

Durability level for the run. Must be one of 'sync', 'async', or 'exit'.

Available options: sync, async, exit

Response

200

application/json

Success