AgentTask
A Pulumi Copilot agent task representing a conversation and its associated context.
Properties
idstring requiredUnique identifier for the task.namestring requiredDisplay name for the task, typically auto-generated from the initial user message.taskTypeenum requiredWhether the task was started synchronously by a user or asynchronously by background automation.Values:sync,asyncasyncTriggerTypeenum optionalThe async trigger source for this task. Null for sync tasks.Values:scheduled,external_signalstatusenum requiredCurrent execution status of the task.Values:running,idlecreatedAtstring requiredWhen the task was created, in ISO 8601 format.approvalModeenum requiredApproval mode for this task. Valid values: ‘manual’, ‘auto’, ‘balanced’.Values:manual,auto,balanced- Pulumi entities (stacks, projects, etc.) that provide context for the agent.
- ↳
typestring required planModeboolean requiredWhether the task is in plan mode. Set based on the first user message.isSharedboolean requiredWhether this task is shared with other org members.sharedAtstring optionalWhen the task was first shared. Null if never shared.- Information about the user who created this task.
- ↳
namestring requiredThe user’s display name. - ↳
githubLoginstring requiredThe user’s login name. - ↳
avatarUrlstring requiredThe URL of the user’s avatar image. - ↳
emailstring optionalIMPORTANT: The email address of the user is only included on a few admin-only APIs. For nearly all APIs that return a UserInfo object, this will not be provided. considered sensitive information. permissionModeenum optionalThe permission scope for the task.Values:default,read-onlyruntimePhaseenum optionalThe current runtime phase for this task. Null until the runtime checks in.Values:booting,ready,runninglastHeartbeatstring optionalWhen the task runtime last reported a heartbeat. Null if the runtime has never checked in.contextUsedTokensinteger optionalTotal input tokens consumed across all model invocations for this task. Approximate context window usage.contextWindowTokensinteger optionalMaximum context window size in tokens for the primary model used by this task.contextCompactionThresholdPercentinteger optionalPercentage of the context window (1-100) at which the agent triggers conversation compaction. Populated alongside contextWindowTokens when token usage data is available; omitted otherwise.tokensUsedinteger requiredTotal Neo tokens consumed across all model invocations for this task. Neo tokens are the priced unit used for billing — distinct from the raw model input tokens surfaced in contextUsedTokens / contextWindowTokens.toolExecutionModeenum optionalWhere tools are executed for this task. Valid values: ‘cloud’, ‘cli’.Values:cloud,clisourceAutomationIDstring optionalThe automation that spawned this task, if the task was created by an automation run.sourceenum optionalThe origin that triggered this task. Valid values: ‘console’, ‘cli’, ‘slack’, ‘schedule’, ‘api’, ‘github’.Values:api,console,cli,slack,schedule,github
Thank you for your feedback!
If you have a question about how to use Pulumi, reach out in Community Slack.
Open an issue on GitHub to report a problem or suggest an improvement.