All Implemented Interfaces:


public final class Run

Represents an execution run on a thread.

Nested Class Summary

Nested Classes
Modifier and Type	Class	Description
`public final class`	`Run.Builder`	A builder for Run.
`public final class`	`Run.IncompleteDetails`	Details on why the run is incomplete. Will be `null` if the run is not incomplete.
`public final class`	`Run.LastError`	The last error associated with this run. Will be `null` if there are no errors.
`public final class`	`Run.RequiredAction`	Details on the action required to continue the run. Will be `null` if no action is required.
`public final class`	`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.
`public final class`	`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.).

Field Summary

Fields
Modifier and Type	Field	Description

Constructor Summary

Constructors
Constructor	Description

Enum Constant Summary

Enum Constants
Enum Constant	Description

Method Summary

Modifier and Type	Method	Description
`final String`	`id()`	The identifier, which can be referenced in API endpoints.
`final String`	`assistantId()`	The ID of the assistant used for execution of this run.
`final Optional<Long>`	`cancelledAt()`	The Unix timestamp (in seconds) for when the run was cancelled.
`final Optional<Long>`	`completedAt()`	The Unix timestamp (in seconds) for when the run was completed.
`final Long`	`createdAt()`	The Unix timestamp (in seconds) for when the run was created.
`final Optional<Long>`	`expiresAt()`	The Unix timestamp (in seconds) for when the run will expire.
`final Optional<Long>`	`failedAt()`	The Unix timestamp (in seconds) for when the run failed.
`final Optional<Run.IncompleteDetails>`	`incompleteDetails()`	Details on why the run is incomplete.
`final String`	`instructions()`	The instructions that the assistant used for this run.
`final Optional<Run.LastError>`	`lastError()`	The last error associated with this run.
`final Optional<Long>`	`maxCompletionTokens()`	The maximum number of completion tokens specified to have been used over the course of the run.
`final Optional<Long>`	`maxPromptTokens()`	The maximum number of prompt tokens specified to have been used over the course of the run.
`final Optional<Metadata>`	`metadata()`	Set of 16 key-value pairs that can be attached to an object.
`final String`	`model()`	The model that the assistant used for this run.
`final JsonValue`	`_object_()`	The object type, which is always `thread.run`.
`final Boolean`	`parallelToolCalls()`	Whether to enable parallel function calling during tool use.
`final Optional<Run.RequiredAction>`	`requiredAction()`	Details on the action required to continue the run.
`final Optional<AssistantResponseFormatOption>`	`responseFormat()`	Specifies the format that the model must output.
`final Optional<Long>`	`startedAt()`	The Unix timestamp (in seconds) for when the run was started.
`final RunStatus`	`status()`	The status of the run, which can be either `queued`, `in_progress`, `requires_action`, `cancelling`, `cancelled`, `failed`, `completed`, `incomplete`, or `expired`.
`final String`	`threadId()`	The ID of the thread that was executed on as a part of this run.
`final Optional<AssistantToolChoiceOption>`	`toolChoice()`	Controls which (if any) tool is called by the model.
`final List<AssistantTool>`	`tools()`	The list of tools that the assistant used for this run.
`final Optional<Run.TruncationStrategy>`	`truncationStrategy()`	Controls for how a thread will be truncated prior to the run.
`final Optional<Run.Usage>`	`usage()`	Usage statistics related to the run.
`final Optional<Double>`	`temperature()`	The sampling temperature used for this run.
`final Optional<Double>`	`topP()`	The nucleus sampling value used for this run.
`final JsonField<String>`	`_id()`	The identifier, which can be referenced in API endpoints.
`final JsonField<String>`	`_assistantId()`	The ID of the assistant used for execution of this run.
`final JsonField<Long>`	`_cancelledAt()`	The Unix timestamp (in seconds) for when the run was cancelled.
`final JsonField<Long>`	`_completedAt()`	The Unix timestamp (in seconds) for when the run was completed.
`final JsonField<Long>`	`_createdAt()`	The Unix timestamp (in seconds) for when the run was created.
`final JsonField<Long>`	`_expiresAt()`	The Unix timestamp (in seconds) for when the run will expire.
`final JsonField<Long>`	`_failedAt()`	The Unix timestamp (in seconds) for when the run failed.
`final JsonField<Run.IncompleteDetails>`	`_incompleteDetails()`	Details on why the run is incomplete.
`final JsonField<String>`	`_instructions()`	The instructions that the assistant used for this run.
`final JsonField<Run.LastError>`	`_lastError()`	The last error associated with this run.
`final JsonField<Long>`	`_maxCompletionTokens()`	The maximum number of completion tokens specified to have been used over the course of the run.
`final JsonField<Long>`	`_maxPromptTokens()`	The maximum number of prompt tokens specified to have been used over the course of the run.
`final JsonField<Metadata>`	`_metadata()`	Set of 16 key-value pairs that can be attached to an object.
`final JsonField<String>`	`_model()`	The model that the assistant used for this run.
`final JsonField<Boolean>`	`_parallelToolCalls()`	Whether to enable parallel function calling during tool use.
`final JsonField<Run.RequiredAction>`	`_requiredAction()`	Details on the action required to continue the run.
`final JsonField<AssistantResponseFormatOption>`	`_responseFormat()`	Specifies the format that the model must output.
`final JsonField<Long>`	`_startedAt()`	The Unix timestamp (in seconds) for when the run was started.
`final JsonField<RunStatus>`	`_status()`	The status of the run, which can be either `queued`, `in_progress`, `requires_action`, `cancelling`, `cancelled`, `failed`, `completed`, `incomplete`, or `expired`.
`final JsonField<String>`	`_threadId()`	The ID of the thread that was executed on as a part of this run.
`final JsonField<AssistantToolChoiceOption>`	`_toolChoice()`	Controls which (if any) tool is called by the model.
`final JsonField<List<AssistantTool>>`	`_tools()`	The list of tools that the assistant used for this run.
`final JsonField<Run.TruncationStrategy>`	`_truncationStrategy()`	Controls for how a thread will be truncated prior to the run.
`final JsonField<Run.Usage>`	`_usage()`	Usage statistics related to the run.
`final JsonField<Double>`	`_temperature()`	The sampling temperature used for this run.
`final JsonField<Double>`	`_topP()`	The nucleus sampling value used for this run.
`final Map<String, JsonValue>`	`_additionalProperties()`
`final Run`	`validate()`
`final Run.Builder`	`toBuilder()`
`Boolean`	`equals(Object other)`
`Integer`	`hashCode()`
`String`	`toString()`
`final static Run.Builder`	`builder()`

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
- Method Detail
  - id
```
 final String id()
```
    The identifier, which can be referenced in API endpoints.
  - assistantId
```
 final String assistantId()
```
    The ID of the assistant used for execution of this run.
  - cancelledAt
```
 final Optional<Long> cancelledAt()
```
    The Unix timestamp (in seconds) for when the run was cancelled.
  - completedAt
```
 final Optional<Long> completedAt()
```
    The Unix timestamp (in seconds) for when the run was completed.
  - createdAt
```
 final Long createdAt()
```
    The Unix timestamp (in seconds) for when the run was created.
  - expiresAt
```
 final Optional<Long> expiresAt()
```
    The Unix timestamp (in seconds) for when the run will expire.
  - failedAt
```
 final Optional<Long> failedAt()
```
    The Unix timestamp (in seconds) for when the run failed.
  - incompleteDetails
```
 final Optional<Run.IncompleteDetails> incompleteDetails()
```
    Details on why the run is incomplete. Will be null if the run is not incomplete.
  - instructions
```
 final String instructions()
```
    The instructions that the assistant used for this run.
  - lastError
```
 final Optional<Run.LastError> lastError()
```
    The last error associated with this run. Will be null if there are no errors.
  - maxCompletionTokens
```
 final Optional<Long> maxCompletionTokens()
```
    The maximum number of completion tokens specified to have been used over the course of the run.
  - maxPromptTokens
```
 final Optional<Long> maxPromptTokens()
```
    The maximum number of prompt tokens specified to have been used over the course of the run.
  - metadata
```
 final Optional<Metadata> metadata()
```
    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, and querying for objects via API or the dashboard.
    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
  - model
```
 final String model()
```
    The model that the assistant used for this run.
  - _object_
```
 final JsonValue _object_()
```
    The object type, which is always thread.run.
  - parallelToolCalls
```
 final Boolean parallelToolCalls()
```
    Whether to enable parallel function calling during tool use.
  - requiredAction
```
 final Optional<Run.RequiredAction> requiredAction()
```
    Details on the action required to continue the run. Will be null if no action is required.
  - responseFormat
```
 final Optional<AssistantResponseFormatOption> responseFormat()
```
    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.
  - startedAt
```
 final Optional<Long> startedAt()
```
    The Unix timestamp (in seconds) for when the run was started.
  - status
```
 final RunStatus status()
```
    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
  - threadId
```
 final String threadId()
```
    The ID of the thread that was executed on as a part of this run.
  - toolChoice
```
 final Optional<AssistantToolChoiceOption> toolChoice()
```
    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
```
 final List<AssistantTool> tools()
```
    The list of tools that the assistant used for this run.
  - truncationStrategy
```
 final Optional<Run.TruncationStrategy> 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
```
 final Optional<Run.Usage> 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.).
  - temperature
```
 final Optional<Double> temperature()
```
    The sampling temperature used for this run. If not set, defaults to 1.
  - topP
```
 final Optional<Double> topP()
```
    The nucleus sampling value used for this run. If not set, defaults to 1.
  - _id
```
 final JsonField<String> _id()
```
    The identifier, which can be referenced in API endpoints.
  - _assistantId
```
 final JsonField<String> _assistantId()
```
    The ID of the assistant used for execution of this run.
  - _cancelledAt
```
 final JsonField<Long> _cancelledAt()
```
    The Unix timestamp (in seconds) for when the run was cancelled.
  - _completedAt
```
 final JsonField<Long> _completedAt()
```
    The Unix timestamp (in seconds) for when the run was completed.
  - _createdAt
```
 final JsonField<Long> _createdAt()
```
    The Unix timestamp (in seconds) for when the run was created.
  - _expiresAt
```
 final JsonField<Long> _expiresAt()
```
    The Unix timestamp (in seconds) for when the run will expire.
  - _failedAt
```
 final JsonField<Long> _failedAt()
```
    The Unix timestamp (in seconds) for when the run failed.
  - _incompleteDetails
```
 final JsonField<Run.IncompleteDetails> _incompleteDetails()
```
    Details on why the run is incomplete. Will be null if the run is not incomplete.
  - _instructions
```
 final JsonField<String> _instructions()
```
    The instructions that the assistant used for this run.
  - _lastError
```
 final JsonField<Run.LastError> _lastError()
```
    The last error associated with this run. Will be null if there are no errors.
  - _maxCompletionTokens
```
 final JsonField<Long> _maxCompletionTokens()
```
    The maximum number of completion tokens specified to have been used over the course of the run.
  - _maxPromptTokens
```
 final JsonField<Long> _maxPromptTokens()
```
    The maximum number of prompt tokens specified to have been used over the course of the run.
  - _metadata
```
 final JsonField<Metadata> _metadata()
```
    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, and querying for objects via API or the dashboard.
    Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
  - _model
```
 final JsonField<String> _model()
```
    The model that the assistant used for this run.
  - _parallelToolCalls
```
 final JsonField<Boolean> _parallelToolCalls()
```
    Whether to enable parallel function calling during tool use.
  - _requiredAction
```
 final JsonField<Run.RequiredAction> _requiredAction()
```
    Details on the action required to continue the run. Will be null if no action is required.
  - _responseFormat
```
 final JsonField<AssistantResponseFormatOption> _responseFormat()
```
    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.
  - _startedAt
```
 final JsonField<Long> _startedAt()
```
    The Unix timestamp (in seconds) for when the run was started.
  - _status
```
 final JsonField<RunStatus> _status()
```
    The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
  - _threadId
```
 final JsonField<String> _threadId()
```
    The ID of the thread that was executed on as a part of this run.
  - _toolChoice
```
 final JsonField<AssistantToolChoiceOption> _toolChoice()
```
    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
```
 final JsonField<List<AssistantTool>> _tools()
```
    The list of tools that the assistant used for this run.
  - _truncationStrategy
```
 final JsonField<Run.TruncationStrategy> _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
```
 final JsonField<Run.Usage> _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.).
  - _temperature
```
 final JsonField<Double> _temperature()
```
    The sampling temperature used for this run. If not set, defaults to 1.
  - _topP
```
 final JsonField<Double> _topP()
```
    The nucleus sampling value used for this run. If not set, defaults to 1.
  - _additionalProperties
```
 final Map<String, JsonValue> _additionalProperties()
```
  - validate
```
 final Run validate()
```
  - toBuilder
```
 final Run.Builder toBuilder()
```
  - equals
```
 Boolean equals(Object other)
```
  - hashCode
```
 Integer hashCode()
```
  - toString
```
 String toString()
```
  - builder
```
 final static Run.Builder builder()
```

Class Run

Nested Class Summary

Field Summary

Constructor Summary

Enum Constant Summary

Method Summary

Methods inherited from class java.lang.Object

Constructor Detail

Method Detail

id

assistantId

cancelledAt

completedAt

createdAt

expiresAt

failedAt

incompleteDetails

instructions

lastError

maxCompletionTokens

maxPromptTokens

metadata

model

_object_

parallelToolCalls

requiredAction

responseFormat

startedAt

status

threadId

toolChoice

tools

truncationStrategy

usage

temperature

topP

_id

_assistantId

_cancelledAt

_completedAt

_createdAt

_expiresAt

_failedAt

_incompleteDetails

_instructions

_lastError

_maxCompletionTokens

_maxPromptTokens

_metadata

_model

_parallelToolCalls

_requiredAction

_responseFormat

_startedAt

_status

_threadId

_toolChoice

_tools

_truncationStrategy

_usage

_temperature

_topP

_additionalProperties

validate

toBuilder

equals

hashCode

toString

builder