Interface Run

Represents an execution run on a thread.

interface Run {
    assistant_id: string;
    cancelled_at: null | number;
    completed_at: null | number;
    created_at: number;
    expires_at: null | number;
    failed_at: null | number;
    id: string;
    incomplete_details: null | OpenAIClient.Beta.Threads.Runs.Run.IncompleteDetails;
    instructions: string;
    last_error: null | OpenAIClient.Beta.Threads.Runs.Run.LastError;
    max_completion_tokens: null | number;
    max_prompt_tokens: null | number;
    metadata: unknown;
    model: string;
    object: "thread.run";
    parallel_tool_calls: boolean;
    required_action: null | RequiredAction;
    response_format: null | AssistantResponseFormatOption;
    started_at: null | number;
    status: RunStatus;
    temperature?: null | number;
    thread_id: string;
    tool_choice: null | AssistantToolChoiceOption;
    tools: AssistantTool[];
    top_p?: null | number;
    truncation_strategy: null | OpenAIClient.Beta.Threads.Runs.Run.TruncationStrategy;
    usage: null | OpenAIClient.Beta.Threads.Runs.Run.Usage;
}

Properties

assistant_id cancelled_at completed_at created_at expires_at failed_at id incomplete_details instructions last_error max_completion_tokens max_prompt_tokens metadata model object parallel_tool_calls required_action response_format started_at status temperature? thread_id tool_choice tools top_p? truncation_strategy usage

Properties

assistant_id

assistant_id: string

The ID of the assistant used for execution of this run.

cancelled_at

cancelled_at: null | number

The Unix timestamp (in seconds) for when the run was cancelled.

completed_at

completed_at: null | number

The Unix timestamp (in seconds) for when the run was completed.

created_at

created_at: number

The Unix timestamp (in seconds) for when the run was created.

expires_at

expires_at: null | number

The Unix timestamp (in seconds) for when the run will expire.

failed_at

failed_at: null | number

The Unix timestamp (in seconds) for when the run failed.

id

id: string

The identifier, which can be referenced in API endpoints.

incomplete_details

incomplete_details: null | OpenAIClient.Beta.Threads.Runs.Run.IncompleteDetails

Details on why the run is incomplete. Will be null if the run is not incomplete.

instructions

instructions: string

The instructions that the assistant used for this run.

last_error

last_error: null | OpenAIClient.Beta.Threads.Runs.Run.LastError

The last error associated with this run. Will be null if there are no errors.

max_completion_tokens

max_completion_tokens: null | number

The maximum number of completion tokens specified to have been used over the course of the run.

max_prompt_tokens

max_prompt_tokens: null | number

The maximum number of prompt tokens specified to have been used over the course of the run.

metadata

metadata: unknown

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.

model

model: string

The model that the assistant used for this run.

object

object: "thread.run"

The object type, which is always thread.run.

parallel_tool_calls

parallel_tool_calls: boolean

Whether to enable parallel function calling during tool use.

required_action

required_action: null | RequiredAction

Details on the action required to continue the run. Will be null if no action is required.

response_format

response_format: null | AssistantResponseFormatOption

Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

started_at

started_at: null | number

The Unix timestamp (in seconds) for when the run was started.

status

status: RunStatus

The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

Optionaltemperature

temperature?: null | number

The sampling temperature used for this run. If not set, defaults to 1.

thread_id

thread_id: string

The ID of the thread that was executed on as a part of this run.

tool_choice

tool_choice: null | AssistantToolChoiceOption

Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

tools

tools: AssistantTool[]

The list of tools that the assistant used for this run.

Optionaltop_p

top_p?: null | number

The nucleus sampling value used for this run. If not set, defaults to 1.

truncation_strategy

truncation_strategy: null | OpenAIClient.Beta.Threads.Runs.Run.TruncationStrategy

Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run.

usage

usage: null | OpenAIClient.Beta.Threads.Runs.Run.Usage

Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).

Settings

Member Visibility

On This Page

Properties