Skip to main content
POST
/
threads
/
{thread_id}
/
runs
/
stream
Create Run, Stream Output
curl --request POST \
  --url https://api.b-bot.space/api/v2/threads/{thread_id}/runs/stream \
  --header 'Content-Type: application/json' \
  --header 'bbot-api-key: <api-key>' \
  --data '
{
  "channel_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "checkpoint": {
    "thread_id": "<string>",
    "checkpoint_ns": "<string>",
    "checkpoint_id": "<string>",
    "checkpoint_map": {}
  },
  "input": {},
  "command": {
    "update": {},
    "resume": {},
    "goto": {
      "node": "<string>",
      "input": {}
    }
  },
  "metadata": {},
  "config": {
    "tags": [
      "<string>"
    ],
    "recursion_limit": 123,
    "configurable": {}
  },
  "context": {},
  "webhook": "<string>",
  "interrupt_before": "*",
  "interrupt_after": "*",
  "stream_mode": [
    "values"
  ],
  "stream_subgraphs": false,
  "stream_resumable": false,
  "on_disconnect": "cancel",
  "feedback_keys": [
    "<string>"
  ],
  "multitask_strategy": "enqueue",
  "if_not_exists": "reject",
  "after_seconds": 123,
  "checkpoint_during": false,
  "durability": "async"
}
'
"<string>"

Authorizations

​
bbot-api-key
string
header
required

API key for authentication

Path Parameters

​
thread_id
string<uuid>
required

The ID of the thread.

Body

application/json

Payload for creating a run.

​
channel_id
required

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

​
checkpoint
Checkpoint · object

The checkpoint to resume from.

​
input

The input to the graph.

​
command
Command · object

The input to the graph.

​
metadata
Metadata · object

Metadata to assign to the run.

​
config
Config · object

The configuration for the assistant.

​
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

Success

The server will send a stream of events in SSE format.

Example event:

id: 1

event: message

data: {}