Get Durable Execution Status

GET

/api/v3/organizations/{organisation}/ai/chat/executions/{identifier}

const url = 'https://dashboard.quantcdn.io/api/v3/organizations/example/ai/chat/executions/XkdVWiEfSwMEPrw%3D';
const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}

curl --request GET \
  --url https://dashboard.quantcdn.io/api/v3/organizations/example/ai/chat/executions/XkdVWiEfSwMEPrw%3D \
  --header 'Authorization: Bearer <token>'

Poll the status of an async/durable chat execution. * * When to use: After starting chat inference with async: true, poll this endpoint * to check execution status and retrieve results when complete. * * Identifier: Accepts either: * - requestId (recommended): The short ID returned from the async request * - executionArn: The full AWS Lambda durable execution ARN (must be URL-encoded) * * Statuses: * - pending: Execution is starting (retry shortly) * - running: Execution is in progress * - waiting_callback: Execution paused, waiting for client tool results * - complete: Execution finished successfully * - failed: Execution failed with error * * Client Tool Callback: * When status is waiting_callback, submit tool results via POST /ai/chat/callback. * * Polling Recommendations: * - Start with 1 second delay, exponential backoff up to 30 seconds * - Stop polling after 15 minutes (consider failed)

Authorizations

BearerAuth

Parameters

Path Parameters

organisation

required

string

The organisation ID

identifier

required

string

Either the requestId from async response, or full executionArn (URL-encoded)

Example

XkdVWiEfSwMEPrw=

Responses

200

Execution status retrieved

application/json

object

requestId

string

executionArn

string

status

string

Allowed values: pending running waiting_callback complete failed

awsStatus

Raw AWS Step Functions status

string

callbackId

Present when status is waiting_callback - use with /chat/callback

string

pendingTools

Present when status is waiting_callback - tools waiting for results

Array<object>

object

name

string

toolUseId

string

input

object

result

Present when status is complete

object

response

object

role

string

content

string

usage

Token usage and cost for the final synthesis turn

object

inputTokens

integer

outputTokens

integer

totalTokens

integer

costCents

Cost of the final synthesis turn in US cents

number format: float

toolExecutions

Array<object>

object

error

Present when status is failed

object

ErrorMessage

string

ErrorType

string

Example

{
  "requestId": "XkdVWiEfSwMEPrw=",
  "executionArn": "arn:aws:lambda:ap-southeast-2:...",
  "status": "pending",
  "awsStatus": "SUCCEEDED",
  "callbackId": "Ab9hZXi/YXJuOmF3czpsYW1iZGE...",
  "pendingTools": [
    {
      "name": "get_weather",
      "toolUseId": "toolu_bdrk_012KTC8NCG...",
      "input": {
        "location": "Sydney"
      }
    }
  ],
  "result": {
    "response": {
      "role": "assistant",
      "content": "The weather in Sydney is sunny."
    }
  }
}

403

Access denied

404

Execution not found

500

Failed to retrieve execution status