Events

Assistant stream events

During the execution of Runs with , a series of events occur sequentially, allowing you to track the current step in processing user Messages by the Assistant, as well as the statuses of the previously completed steps.

Every event in a server-sent events stream includes an event and data property:

event: thread.created
data: {"id": "thread_123", "object": "thread", ...}

We emit events whenever a new object is created, transitions to a new state, or is being streamed in parts (deltas). For example, we emit thread.run.created when a new Run is created, thread.run.completed when a Run completes, and so on. When an Assistant chooses to create a Message during a Run, we emit a thread.message.created event, a thread.message.in_progress event, many thread.message.delta events, and finally a thread.message.completed event.

We may add additional events over time, so we recommend handling unknown events gracefully in your code. See the this guide to learn how to integrate the Assistants API with streaming.

Event list

Event name	Content of the 'data' parameter	When occurs
done	[DONE]	Occurs when a stream ends.
error	an error object	Occurs when an error occurs. This can happen due to an internal server error or a timeout.
thread.created	a Thread object	Occurs when a new Thread is created.
thread.message.completed	a Message object	Occurs when a Message is completed.
thread.message.created	a Message object	Occurs when a Message is created.
thread.message.delta	a Message delta	Occurs when parts of a Message are being streamed.
thread.message.in_progress	a Message object	Occurs when a Message moves to an in_progress state.
thread.message.incomplete	a Message object	Occurs when a Message ends before it is completed.
thread.run.cancelled	a Run object	Occurs when a Run is cancelled.
thread.run.cancelling	a Run object	Occurs when a Run moves to a cancelling status.
thread.run.completed	a Run object	Occurs when a Run is completed.
thread.run.created	a Run object	Occurs when a new Run is created.
thread.run.expired	a Run object	Occurs when a Run expires.
thread.run.failed	a Run object	Occurs when a Run fails.
thread.run.in_progress	a Run object	Occurs when a Run moves to an in_progress status.
thread.run.incomplete	a Run object	Occurs when a Run ends with status incomplete.
thread.run.queued	a Run object	Occurs when a Run moves to a queued status.
thread.run.requires_action	a Run object	Occurs when a Run moves to a requires_action status.
thread.run.step.cancelled	a Run step object	Occurs when a Run step is cancelled.
thread.run.step.completed	a Run step object	Occurs when a Run step is completed.
thread.run.step.created	a Run step object	Occurs when a Run step is created.
thread.run.step.delta	a Run step delta object	Occurs when parts of a Run step are being streamed.
thread.run.step.expired	a Run step object	Occurs when a Run step expires.
thread.run.step.failed	a Run step object	Occurs when a Run step fails.
thread.run.step.in_progress	a Run step object	Occurs when a Run step moves to an in_progress state.

Errors that may occur while working with Assistants

Code	Overview
401 - Invalid Authentication	Cause: Invalid Authentication Solution: Ensure the correct AIML API key and requesting organization are being used.
401 - Incorrect API key provided	Cause: The requesting AIML API key is not correct. Solution: Ensure the AIML API key used is correct, clear your browser cache, or generate a new key.
403 - Country, region, or territory not supported	Cause: You are accessing the API from an unsupported country, region, or territory. Solution: Please see the complete list of supported countries by OpenAI for more information.
429 - Rate limit reached for requests	Cause: You are sending requests too quickly. Solution: Pace your requests. Read the OpenAI Rate limit guide.
429 - You exceeded your current quota, please check your plan and billing details	Cause: You have run out of credits or hit your maximum monthly spend. Solution: Buy more credits or learn how to increase your limits on the billing page inside your personal account on the AI/ML API website.
500 - The server had an error while processing your request	Cause: Issue on our servers. Solution: Retry your request after a brief wait and contact us if the issue persists.
503 - The engine is currently overloaded, please try again later	Cause: Our servers are experiencing high traffic. Solution: Please retry your requests after a brief wait.
503 - Slow Down	Cause: A sudden increase in your request rate is impacting service reliability. Solution: Please reduce your request rate to its original level, maintain a consistent rate for at least 15 minutes, and then gradually increase it.