Skip to main content
POST
/
threads
/
{thread_id}
/
runs
/
{run_id}
/
cancel
Cancel Run Endpoint
curl --request POST \
  --url https://api.example.com/threads/{thread_id}/runs/{run_id}/cancel
{
  "run_id": "<string>",
  "thread_id": "<string>",
  "assistant_id": "<string>",
  "user_id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "status": "pending",
  "input": {},
  "output": {},
  "error_message": "<string>",
  "config": {},
  "context": {}
}

Documentation Index

Fetch the complete documentation index at: https://docs.aegra.dev/llms.txt

Use this file to discover all available pages before exploring further.

Path Parameters

​
thread_id
string
required
​
run_id
string
required

Query Parameters

​
wait
integer
default:0

Set to 1 to wait for the run task to settle before returning.

Required range: 0 <= x <= 1
​
action
string
default:cancel

Cancellation strategy: 'cancel' for hard cancel, 'interrupt' for cooperative interrupt.

Pattern: ^(cancel|interrupt)$

Response

Successful Response

Run entity model

Status values: pending, running, error, success, timeout, interrupted

​
run_id
string
required

Unique identifier for the run.

​
thread_id
string
required

Thread this run belongs to.

​
assistant_id
string
required

Assistant that is executing this run.

​
user_id
string
required

Identifier of the user who owns this run.

​
created_at
string<date-time>
required

Timestamp when the run was created.

​
updated_at
string<date-time>
required

Timestamp when the run was last updated.

​
status
string
default:pending

Current run status: pending, running, error, success, timeout, or interrupted.

​
input
Input · object

Input data provided to the run. None for checkpoint-only resume.

​
output
Output · object

Final output produced by the run, or null if not yet complete.

​
error_message
string | null

Error message if the run failed.

​
config
Config · object

Configuration passed to the graph at runtime.

​
context
Context · object

Context variables available during execution.