Skip to content
Get started

Agents

Manage AI agents within a workspace. Agents define AI behavior and tool access.

List agents
client.agents.list(stringworkspaceID, AgentListParams { bundleKey, cursor, includeInfo, 6 more } query?, RequestOptionsoptions?): CursorPagination<Agent { metadata, spec, info } >
GET/v1/workspaces/{workspaceId}/agents
Create a new agent
client.agents.create(stringworkspaceID, AgentCreateParams { metadata, spec, defaultVariation } body, RequestOptionsoptions?): Agent { metadata, spec, info }
POST/v1/workspaces/{workspaceId}/agents
Get an agent by ID
client.agents.retrieve(stringid, AgentRetrieveParams { workspaceId } params, RequestOptionsoptions?): Agent { metadata, spec, info }
GET/v1/workspaces/{workspaceId}/agents/{id}
Delete an agent
client.agents.delete(stringid, AgentDeleteParams { workspaceId } params, RequestOptionsoptions?): void
DELETE/v1/workspaces/{workspaceId}/agents/{id}
Update an agent
client.agents.update(stringid, AgentUpdateParams { workspaceId, metadata, spec, updateMask } params, RequestOptionsoptions?): Agent { metadata, spec, info }
PATCH/v1/workspaces/{workspaceId}/agents/{id}
ModelsExpand Collapse
Agent { metadata, spec, info }

Agent resource

metadata: ResourceMetadata { id, accountId, createdAt, 6 more }

Standard metadata for persistent, named resources (e.g., agents, tools, prompts)

id: string

Unique identifier for the resource (prefixed ULID, e.g., “agent_01HXK…”)

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

createdAt: string

Timestamp when this resource was created

formatdate-time
name: string

Human-readable name for the resource (e.g., “Customer Support Agent”, “Email Tool”) Required for resources that users interact with directly

profileId: string

ID of the actor (user or service account) that created this resource

workspaceId: string

Workspace this resource belongs to for organizational grouping (prefixed ULID)

bundleKey?: string

Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply.

externalId?: string

External ID for the resource (e.g., a workflow ID from an external system)

labels?: Record<string, string>

Arbitrary key-value pairs for categorization and filtering Examples: {“environment”: “production”, “team”: “platform”, “version”: “v2”}

spec: AgentSpec { status, variationSelectionMode, description, 3 more }

Agent specification (user-provided configuration)

status: "AGENT_STATUS_UNSPECIFIED" | "AGENT_STATUS_DRAFT" | "AGENT_STATUS_PUBLISHED" | "AGENT_STATUS_ARCHIVED"

Status of the agent

formatenum
One of the following:
"AGENT_STATUS_UNSPECIFIED"
"AGENT_STATUS_DRAFT"
"AGENT_STATUS_PUBLISHED"
"AGENT_STATUS_ARCHIVED"
variationSelectionMode: "VARIATION_SELECTION_MODE_UNSPECIFIED" | "VARIATION_SELECTION_MODE_RANDOM" | "VARIATION_SELECTION_MODE_WEIGHTED"

Controls how variations are automatically selected when creating objectives Defaults to RANDOM when unspecified

formatenum
One of the following:
"VARIATION_SELECTION_MODE_UNSPECIFIED"
"VARIATION_SELECTION_MODE_RANDOM"
"VARIATION_SELECTION_MODE_WEIGHTED"
description?: string

Description of the agent’s purpose

inputDataSchema?: Record<string, unknown>

InputDataSchema is used for enforcing a data input when objectives are created. This is valuable when using liquid formatting in agent variation prompts. Input data schema is also valuable when using an agent as a sub-agent, as the schema is used as the tool’s input parameter schema. If omitted, the sub-agent schema will be loaded with a simple “prompt” free text string as its schema.

outputDefinition?: Record<string, unknown>

Optional output definition for objectives created for this agent. When provided, Cadenya will append a tool to that will be called by the LLM in use by the variant to extract information in the format provided here. Use this option when you want structured data to be created by your objectives.

webhookEventsUrl?: string

The URL that Cadenya will send events for any objective assigned to the agent.

info?: AgentInfo { createdBy, variationCount }

AgentInfo contains simple information about an agent for display or quick reference

createdBy?: Profile { metadata, spec }

A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces.

metadata: AccountResourceMetadata { id, accountId, name, 3 more }

AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.

id: string

Unique identifier for the resource (prefixed ULID, e.g., “apikey_01HXK…”)

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

name: string

Human-readable name for the resource (e.g., “Customer Support Agent”, “Email Tool”) Required for resources that users interact with directly

profileId: string
externalId?: string

External ID for the resource (e.g., a workflow ID from an external system)

labels?: Record<string, string>

Arbitrary key-value pairs for categorization and filtering Examples: {“environment”: “production”, “team”: “platform”, “version”: “v2”}

spec: ProfileSpec { type, email, name }

Configuration for a profile.

type: "PROFILE_TYPE_UNSPECIFIED" | "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"

Whether this profile represents a human user, an API key, or a system principal.

formatenum
One of the following:
"PROFILE_TYPE_UNSPECIFIED"
"PROFILE_TYPE_USER"
"PROFILE_TYPE_API_KEY"
"PROFILE_TYPE_SYSTEM"
email?: string

Email address of the profile. Required and unique within an account for user profiles.

name?: string

Display name (e.g., “Bobby Tables”).

variationCount?: number
AgentInfo { createdBy, variationCount }

AgentInfo contains simple information about an agent for display or quick reference

createdBy?: Profile { metadata, spec }

A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces.

metadata: AccountResourceMetadata { id, accountId, name, 3 more }

AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.

id: string

Unique identifier for the resource (prefixed ULID, e.g., “apikey_01HXK…”)

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

name: string

Human-readable name for the resource (e.g., “Customer Support Agent”, “Email Tool”) Required for resources that users interact with directly

profileId: string
externalId?: string

External ID for the resource (e.g., a workflow ID from an external system)

labels?: Record<string, string>

Arbitrary key-value pairs for categorization and filtering Examples: {“environment”: “production”, “team”: “platform”, “version”: “v2”}

spec: ProfileSpec { type, email, name }

Configuration for a profile.

type: "PROFILE_TYPE_UNSPECIFIED" | "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"

Whether this profile represents a human user, an API key, or a system principal.

formatenum
One of the following:
"PROFILE_TYPE_UNSPECIFIED"
"PROFILE_TYPE_USER"
"PROFILE_TYPE_API_KEY"
"PROFILE_TYPE_SYSTEM"
email?: string

Email address of the profile. Required and unique within an account for user profiles.

name?: string

Display name (e.g., “Bobby Tables”).

variationCount?: number
AgentSpec { status, variationSelectionMode, description, 3 more }

Agent specification (user-provided configuration)

status: "AGENT_STATUS_UNSPECIFIED" | "AGENT_STATUS_DRAFT" | "AGENT_STATUS_PUBLISHED" | "AGENT_STATUS_ARCHIVED"

Status of the agent

formatenum
One of the following:
"AGENT_STATUS_UNSPECIFIED"
"AGENT_STATUS_DRAFT"
"AGENT_STATUS_PUBLISHED"
"AGENT_STATUS_ARCHIVED"
variationSelectionMode: "VARIATION_SELECTION_MODE_UNSPECIFIED" | "VARIATION_SELECTION_MODE_RANDOM" | "VARIATION_SELECTION_MODE_WEIGHTED"

Controls how variations are automatically selected when creating objectives Defaults to RANDOM when unspecified

formatenum
One of the following:
"VARIATION_SELECTION_MODE_UNSPECIFIED"
"VARIATION_SELECTION_MODE_RANDOM"
"VARIATION_SELECTION_MODE_WEIGHTED"
description?: string

Description of the agent’s purpose

inputDataSchema?: Record<string, unknown>

InputDataSchema is used for enforcing a data input when objectives are created. This is valuable when using liquid formatting in agent variation prompts. Input data schema is also valuable when using an agent as a sub-agent, as the schema is used as the tool’s input parameter schema. If omitted, the sub-agent schema will be loaded with a simple “prompt” free text string as its schema.

outputDefinition?: Record<string, unknown>

Optional output definition for objectives created for this agent. When provided, Cadenya will append a tool to that will be called by the LLM in use by the variant to extract information in the format provided here. Use this option when you want structured data to be created by your objectives.

webhookEventsUrl?: string

The URL that Cadenya will send events for any objective assigned to the agent.

Page { nextCursor, total }
nextCursor?: string
total?: number

AgentsFeedback

Manage AI agents within a workspace. Agents define AI behavior and tool access.

List feedback for an agent
client.agents.feedback.list(stringagentID, FeedbackListParams { workspaceId, agentVariationId, createdAfter, 6 more } params, RequestOptionsoptions?): CursorPagination<ObjectiveFeedback { data, metadata, info } >
GET/v1/workspaces/{workspaceId}/agents/{agentId}/feedback

AgentsWebhook Deliveries

Manage AI agents within a workspace. Agents define AI behavior and tool access.

List webhook deliveries
client.agents.webhookDeliveries.list(stringagentID, WebhookDeliveryListParams { workspaceId, cursor, eventType, 2 more } params, RequestOptionsoptions?): CursorPagination<WebhookDelivery { data, metadata } >
GET/v1/workspaces/{workspaceId}/agents/{agentId}/webhook_deliveries
ModelsExpand Collapse
WebhookDelivery { data, metadata }
data: WebhookDeliveryData { agentId, attemptCount, eventType, 11 more }

Webhook delivery details.

agentId: string

Related resources

attemptCount: number
eventType: "OBJECTIVE_EVENT_TYPE_UNSPECIFIED" | "OBJECTIVE_EVENT_TYPE_USER_MESSAGE" | "OBJECTIVE_EVENT_TYPE_TOOL_APPROVAL_REQUESTED" | 13 more

The type of objective event that triggered this webhook delivery

formatenum
One of the following:
"OBJECTIVE_EVENT_TYPE_UNSPECIFIED"
"OBJECTIVE_EVENT_TYPE_USER_MESSAGE"
"OBJECTIVE_EVENT_TYPE_TOOL_APPROVAL_REQUESTED"
"OBJECTIVE_EVENT_TYPE_TOOL_APPROVED"
"OBJECTIVE_EVENT_TYPE_TOOL_DENIED"
"OBJECTIVE_EVENT_TYPE_TOOL_CALLED"
"OBJECTIVE_EVENT_TYPE_ERROR"
"OBJECTIVE_EVENT_TYPE_ASSISTANT_MESSAGE"
"OBJECTIVE_EVENT_TYPE_TOOL_RESULT"
"OBJECTIVE_EVENT_TYPE_TOOL_ERROR"
"OBJECTIVE_EVENT_TYPE_CONTEXT_WINDOW_COMPACTED"
"OBJECTIVE_EVENT_TYPE_MEMORY_READ"
"OBJECTIVE_EVENT_TYPE_CANCELLED"
"OBJECTIVE_EVENT_TYPE_SUB_AGENT_SPAWNED"
"OBJECTIVE_EVENT_TYPE_SUB_AGENT_UPDATED"
"OBJECTIVE_EVENT_TYPE_FINALIZED"
httpStatusCode: number

Response details. The response body is not retained.

formatint32
lastAttemptAt: string
latencyMs: number
objectiveEventId: string
objectiveId: string
responseContentLength: string

Content length of the response body in bytes

status: "WEBHOOK_DELIVERY_STATUS_UNSPECIFIED" | "WEBHOOK_DELIVERY_STATUS_PENDING" | "WEBHOOK_DELIVERY_STATUS_COMPLETED" | 2 more
formatenum
One of the following:
"WEBHOOK_DELIVERY_STATUS_UNSPECIFIED"
"WEBHOOK_DELIVERY_STATUS_PENDING"
"WEBHOOK_DELIVERY_STATUS_COMPLETED"
"WEBHOOK_DELIVERY_STATUS_FAILED"
"WEBHOOK_DELIVERY_STATUS_DISABLED"
webhookId: string
webhookUrl: string

Webhook delivery details

errorMessage?: string
responseHeaders?: Record<string, string>

Response headers received from the webhook endpoint

metadata: OperationMetadata { id, accountId, createdAt, 4 more }

Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)

id: string

Unique identifier for the operation (prefixed ULID, e.g., “obj_01HXK…”)

accountId: string

Account this operation belongs to for multi-tenant isolation (prefixed ULID)

createdAt: string

Timestamp when this operation was created ULID includes timestamp information, but this explicit field enables easier querying

formatdate-time
profileId: string

ID of the actor (user or service account) that created this operation

workspaceId: string

Workspace this operation belongs to for organizational grouping (prefixed ULID)

externalId?: string

External ID for the operation (e.g., a workflow ID from an external system)

labels?: Record<string, string>

Arbitrary key-value pairs for categorization and filtering Examples: {“priority”: “high”, “source”: “api”, “workflow”: “onboarding”}

WebhookDeliveryData { agentId, attemptCount, eventType, 11 more }
agentId: string

Related resources

attemptCount: number
eventType: "OBJECTIVE_EVENT_TYPE_UNSPECIFIED" | "OBJECTIVE_EVENT_TYPE_USER_MESSAGE" | "OBJECTIVE_EVENT_TYPE_TOOL_APPROVAL_REQUESTED" | 13 more

The type of objective event that triggered this webhook delivery

formatenum
One of the following:
"OBJECTIVE_EVENT_TYPE_UNSPECIFIED"
"OBJECTIVE_EVENT_TYPE_USER_MESSAGE"
"OBJECTIVE_EVENT_TYPE_TOOL_APPROVAL_REQUESTED"
"OBJECTIVE_EVENT_TYPE_TOOL_APPROVED"
"OBJECTIVE_EVENT_TYPE_TOOL_DENIED"
"OBJECTIVE_EVENT_TYPE_TOOL_CALLED"
"OBJECTIVE_EVENT_TYPE_ERROR"
"OBJECTIVE_EVENT_TYPE_ASSISTANT_MESSAGE"
"OBJECTIVE_EVENT_TYPE_TOOL_RESULT"
"OBJECTIVE_EVENT_TYPE_TOOL_ERROR"
"OBJECTIVE_EVENT_TYPE_CONTEXT_WINDOW_COMPACTED"
"OBJECTIVE_EVENT_TYPE_MEMORY_READ"
"OBJECTIVE_EVENT_TYPE_CANCELLED"
"OBJECTIVE_EVENT_TYPE_SUB_AGENT_SPAWNED"
"OBJECTIVE_EVENT_TYPE_SUB_AGENT_UPDATED"
"OBJECTIVE_EVENT_TYPE_FINALIZED"
httpStatusCode: number

Response details. The response body is not retained.

formatint32
lastAttemptAt: string
latencyMs: number
objectiveEventId: string
objectiveId: string
responseContentLength: string

Content length of the response body in bytes

status: "WEBHOOK_DELIVERY_STATUS_UNSPECIFIED" | "WEBHOOK_DELIVERY_STATUS_PENDING" | "WEBHOOK_DELIVERY_STATUS_COMPLETED" | 2 more
formatenum
One of the following:
"WEBHOOK_DELIVERY_STATUS_UNSPECIFIED"
"WEBHOOK_DELIVERY_STATUS_PENDING"
"WEBHOOK_DELIVERY_STATUS_COMPLETED"
"WEBHOOK_DELIVERY_STATUS_FAILED"
"WEBHOOK_DELIVERY_STATUS_DISABLED"
webhookId: string
webhookUrl: string

Webhook delivery details

errorMessage?: string
responseHeaders?: Record<string, string>

Response headers received from the webhook endpoint

AgentsVariations

Manage variations of an agent and their tool, sub-agent, and memory layer assignments.

List variations
client.agents.variations.list(stringagentID, VariationListParams { workspaceId, bundleKey, cursor, 3 more } params, RequestOptionsoptions?): CursorPagination<AgentVariation { metadata, spec, info } >
GET/v1/workspaces/{workspaceId}/agents/{agentId}/variations
Create a new variation
client.agents.variations.create(stringagentID, VariationCreateParams { workspaceId, metadata, spec } params, RequestOptionsoptions?): AgentVariation { metadata, spec, info }
POST/v1/workspaces/{workspaceId}/agents/{agentId}/variations
Get a variation by ID
client.agents.variations.retrieve(stringid, VariationRetrieveParams { workspaceId, agentId } params, RequestOptionsoptions?): AgentVariation { metadata, spec, info }
GET/v1/workspaces/{workspaceId}/agents/{agentId}/variations/{id}
Delete a variation
client.agents.variations.delete(stringid, VariationDeleteParams { workspaceId, agentId } params, RequestOptionsoptions?): void
DELETE/v1/workspaces/{workspaceId}/agents/{agentId}/variations/{id}
Update a variation
client.agents.variations.update(stringid, VariationUpdateParams { workspaceId, agentId, metadata, 2 more } params, RequestOptionsoptions?): AgentVariation { metadata, spec, info }
PATCH/v1/workspaces/{workspaceId}/agents/{agentId}/variations/{id}
Add an assignment to a variation
client.agents.variations.addAssignment(stringvariationID, VariationAddAssignmentParams { workspaceId, agentId, subAgentId, 2 more } params, RequestOptionsoptions?): VariationAssignment { id, agent, tool, toolSet }
POST/v1/workspaces/{workspaceId}/agents/{agentId}/variations/{variationId}/assignments
Remove an assignment from a variation
client.agents.variations.removeAssignment(stringid, VariationRemoveAssignmentParams { workspaceId, agentId, variationId } params, RequestOptionsoptions?): void
DELETE/v1/workspaces/{workspaceId}/agents/{agentId}/variations/{variationId}/assignments/{id}
Attach a memory layer to a variation
client.agents.variations.addMemoryLayer(stringvariationID, VariationAddMemoryLayerParams { workspaceId, agentId, memoryLayerId, position } params, RequestOptionsoptions?): VariationMemoryLayerAssignment { id, memoryLayer, position }
POST/v1/workspaces/{workspaceId}/agents/{agentId}/variations/{variationId}/memory_layer_assignments
Update a variation's memory layer assignment
client.agents.variations.updateMemoryLayer(stringid, VariationUpdateMemoryLayerParams { workspaceId, agentId, variationId, position } params, RequestOptionsoptions?): VariationMemoryLayerAssignment { id, memoryLayer, position }
PATCH/v1/workspaces/{workspaceId}/agents/{agentId}/variations/{variationId}/memory_layer_assignments/{id}
Remove a memory layer assignment from a variation
client.agents.variations.removeMemoryLayer(stringid, VariationRemoveMemoryLayerParams { workspaceId, agentId, variationId } params, RequestOptionsoptions?): void
DELETE/v1/workspaces/{workspaceId}/agents/{agentId}/variations/{variationId}/memory_layer_assignments/{id}
ModelsExpand Collapse
AgentVariation { metadata, spec, info }

AgentVariation resource

metadata: ResourceMetadata { id, accountId, createdAt, 6 more }

Standard metadata for persistent, named resources (e.g., agents, tools, prompts)

id: string

Unique identifier for the resource (prefixed ULID, e.g., “agent_01HXK…”)

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

createdAt: string

Timestamp when this resource was created

formatdate-time
name: string

Human-readable name for the resource (e.g., “Customer Support Agent”, “Email Tool”) Required for resources that users interact with directly

profileId: string

ID of the actor (user or service account) that created this resource

workspaceId: string

Workspace this resource belongs to for organizational grouping (prefixed ULID)

bundleKey?: string

Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply.

externalId?: string

External ID for the resource (e.g., a workflow ID from an external system)

labels?: Record<string, string>

Arbitrary key-value pairs for categorization and filtering Examples: {“environment”: “production”, “team”: “platform”, “version”: “v2”}

spec: AgentVariationSpec { compactionConfig, constraints, description, 6 more }

AgentVariationSpec defines the operational configuration for a variation

compactionConfig?: AgentVariationSpecCompactionConfig { summarization, toolResultClearing, triggerThreshold }

CompactionConfig defines how context window compaction behaves for objectives using this variation.

summarization?: CompactionConfigSummarizationStrategy { instructions }

SummarizationStrategy configures LLM-powered summarization of older conversation turns.

instructions?: string

Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: “Preserve all code snippets, variable names, and technical decisions.”

toolResultClearing?: CompactionConfigToolResultClearingStrategy { preserveRecentResults }

ToolResultClearingStrategy configures clearing of older tool result content.

preserveRecentResults?: number

Number of most recent tool call results to keep intact. Older tool results have their content replaced with “[result cleared]” while preserving the assistant tool call message (function name, arguments). Default: 2

formatint32
triggerThreshold?: number

Trigger threshold as a percentage of the model’s context window (0.0 to 1.0). When input tokens reach this percentage of the model’s limit, compaction triggers. Default: 0.75 (75%)

formatfloat
constraints?: AgentVariationSpecConstraints { maxSubObjectives, maxToolCalls }

Execution constraints

maxSubObjectives?: number

The maximum number of sub-objectives that can be created. 0 means no limit.

formatint32
maxToolCalls?: number

The maximum number of tool calls that can be made. 0 means no limit.

formatint32
description?: string

Human-readable description of what this variation does or when it should be used

enableEpisodicMemory?: boolean

Enable episodic memory for objectives using this variation. When true, the system automatically creates a document namespace for each objective using the objective’s episodic_key as the external_id, allowing the agent to store and retrieve documents specific to that episode.

episodicMemoryTtl?: number

How long episodic memories should be retained. After this duration, episodic document namespaces can be automatically cleaned up. If not set, episodic memories are retained indefinitely.

modelConfig?: AgentVariationSpecModelConfig { modelId, temperature }

ModelConfig defines the model configuration for a variation

modelId?: string

The model identifier in family/model format (e.g., “claude/opus-4.6”, “claude/sonnet-4.5”)

temperature?: number

Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness

formatfloat
progressiveDiscovery?: AgentVariationSpecProgressiveDiscovery { hints, maxTools, rerankThreshold }

ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task.

hints?: Array<string>
maxTools?: number
rerankThreshold?: number

Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed.

formatfloat
prompt?: string

The system prompt for this variation

weight?: number

Weight for weighted random selection (>= 0). P(v) = v.weight / sum(all_weights). Only used when the agent’s variation_selection_mode is WEIGHTED. A weight of 0 means never auto-selected, but can still be chosen explicitly via variation_id on CreateObjectiveRequest.

formatint32
info?: AgentVariationInfo { assignments, createdBy, feedbackCount, 7 more }

AgentVariationInfo provides read-only summary information about a variation

assignments?: Array<VariationAssignment { id, agent, tool, toolSet } >

All tools, tool sets, and sub-agents assigned to this variation. Populated on reads so clients can render a variation’s full assignment list without calling the add/remove endpoints just to enumerate.

id?: string
agent?: BareMetadata { id, name }

BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves.

id?: string
name?: string

Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks).

tool?: BareMetadata { id, name }

BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves.

id?: string
name?: string

Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks).

toolSet?: BareMetadata { id, name }

BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves.

id?: string
name?: string

Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks).

createdBy?: Profile { metadata, spec }

A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces.

metadata: AccountResourceMetadata { id, accountId, name, 3 more }

AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.

id: string

Unique identifier for the resource (prefixed ULID, e.g., “apikey_01HXK…”)

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

name: string

Human-readable name for the resource (e.g., “Customer Support Agent”, “Email Tool”) Required for resources that users interact with directly

profileId: string
externalId?: string

External ID for the resource (e.g., a workflow ID from an external system)

labels?: Record<string, string>

Arbitrary key-value pairs for categorization and filtering Examples: {“environment”: “production”, “team”: “platform”, “version”: “v2”}

spec: ProfileSpec { type, email, name }

Configuration for a profile.

type: "PROFILE_TYPE_UNSPECIFIED" | "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"

Whether this profile represents a human user, an API key, or a system principal.

formatenum
One of the following:
"PROFILE_TYPE_UNSPECIFIED"
"PROFILE_TYPE_USER"
"PROFILE_TYPE_API_KEY"
"PROFILE_TYPE_SYSTEM"
email?: string

Email address of the profile. Required and unique within an account for user profiles.

name?: string

Display name (e.g., “Bobby Tables”).

feedbackCount?: number

Total number of objective feedbacks received for this variation

formatint32
memoryLayerAssignments?: Array<VariationMemoryLayerAssignment { id, memoryLayer, position } >

Read-only list of memory layer assignments for this variation, returned in ascending position (bottom → top). Capped at 10 entries.

id?: string

Assignment row id — handle for removing the assignment. Distinct from the referenced memory layer’s id.

memoryLayer?: BareMetadata { id, name }

BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves.

id?: string
name?: string

Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks).

position?: number

Position in the variation’s baseline stack. Lower values sit lower; the highest-position assignment is on top of the variation’s baseline. Gaps are fine — only relative position matters. Positions must be unique within a variation; a request that would collide with an existing assignment’s position is rejected with InvalidArgument.

formatint32
memoryLayerCount?: number

Count of memory layer assignments.

formatint32
model?: ResourceMetadata { id, accountId, createdAt, 6 more }

Standard metadata for persistent, named resources (e.g., agents, tools, prompts)

id: string

Unique identifier for the resource (prefixed ULID, e.g., “agent_01HXK…”)

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

createdAt: string

Timestamp when this resource was created

formatdate-time
name: string

Human-readable name for the resource (e.g., “Customer Support Agent”, “Email Tool”) Required for resources that users interact with directly

profileId: string

ID of the actor (user or service account) that created this resource

workspaceId: string

Workspace this resource belongs to for organizational grouping (prefixed ULID)

bundleKey?: string

Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply.

externalId?: string

External ID for the resource (e.g., a workflow ID from an external system)

labels?: Record<string, string>

Arbitrary key-value pairs for categorization and filtering Examples: {“environment”: “production”, “team”: “platform”, “version”: “v2”}

score?: number

Thompson Sampling score: posterior mean of Beta(ts_alpha, ts_beta). Range [0, 1] where 0.5 = neutral, >0.5 = positive, <0.5 = negative.

formatfloat
subAgentCount?: number

Number of sub-agents assigned to this variation

formatint32
toolCount?: number

Number of individual tools assigned to this variation

formatint32
toolSetCount?: number

Number of tool sets assigned to this variation

formatint32
AgentVariationInfo { assignments, createdBy, feedbackCount, 7 more }

AgentVariationInfo provides read-only summary information about a variation

assignments?: Array<VariationAssignment { id, agent, tool, toolSet } >

All tools, tool sets, and sub-agents assigned to this variation. Populated on reads so clients can render a variation’s full assignment list without calling the add/remove endpoints just to enumerate.

id?: string
agent?: BareMetadata { id, name }

BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves.

id?: string
name?: string

Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks).

tool?: BareMetadata { id, name }

BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves.

id?: string
name?: string

Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks).

toolSet?: BareMetadata { id, name }

BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves.

id?: string
name?: string

Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks).

createdBy?: Profile { metadata, spec }

A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces.

metadata: AccountResourceMetadata { id, accountId, name, 3 more }

AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.

id: string

Unique identifier for the resource (prefixed ULID, e.g., “apikey_01HXK…”)

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

name: string

Human-readable name for the resource (e.g., “Customer Support Agent”, “Email Tool”) Required for resources that users interact with directly

profileId: string
externalId?: string

External ID for the resource (e.g., a workflow ID from an external system)

labels?: Record<string, string>

Arbitrary key-value pairs for categorization and filtering Examples: {“environment”: “production”, “team”: “platform”, “version”: “v2”}

spec: ProfileSpec { type, email, name }

Configuration for a profile.

type: "PROFILE_TYPE_UNSPECIFIED" | "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"

Whether this profile represents a human user, an API key, or a system principal.

formatenum
One of the following:
"PROFILE_TYPE_UNSPECIFIED"
"PROFILE_TYPE_USER"
"PROFILE_TYPE_API_KEY"
"PROFILE_TYPE_SYSTEM"
email?: string

Email address of the profile. Required and unique within an account for user profiles.

name?: string

Display name (e.g., “Bobby Tables”).

feedbackCount?: number

Total number of objective feedbacks received for this variation

formatint32
memoryLayerAssignments?: Array<VariationMemoryLayerAssignment { id, memoryLayer, position } >

Read-only list of memory layer assignments for this variation, returned in ascending position (bottom → top). Capped at 10 entries.

id?: string

Assignment row id — handle for removing the assignment. Distinct from the referenced memory layer’s id.

memoryLayer?: BareMetadata { id, name }

BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves.

id?: string
name?: string

Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks).

position?: number

Position in the variation’s baseline stack. Lower values sit lower; the highest-position assignment is on top of the variation’s baseline. Gaps are fine — only relative position matters. Positions must be unique within a variation; a request that would collide with an existing assignment’s position is rejected with InvalidArgument.

formatint32
memoryLayerCount?: number

Count of memory layer assignments.

formatint32
model?: ResourceMetadata { id, accountId, createdAt, 6 more }

Standard metadata for persistent, named resources (e.g., agents, tools, prompts)

id: string

Unique identifier for the resource (prefixed ULID, e.g., “agent_01HXK…”)

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

createdAt: string

Timestamp when this resource was created

formatdate-time
name: string

Human-readable name for the resource (e.g., “Customer Support Agent”, “Email Tool”) Required for resources that users interact with directly

profileId: string

ID of the actor (user or service account) that created this resource

workspaceId: string

Workspace this resource belongs to for organizational grouping (prefixed ULID)

bundleKey?: string

Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply.

externalId?: string

External ID for the resource (e.g., a workflow ID from an external system)

labels?: Record<string, string>

Arbitrary key-value pairs for categorization and filtering Examples: {“environment”: “production”, “team”: “platform”, “version”: “v2”}

score?: number

Thompson Sampling score: posterior mean of Beta(ts_alpha, ts_beta). Range [0, 1] where 0.5 = neutral, >0.5 = positive, <0.5 = negative.

formatfloat
subAgentCount?: number

Number of sub-agents assigned to this variation

formatint32
toolCount?: number

Number of individual tools assigned to this variation

formatint32
toolSetCount?: number

Number of tool sets assigned to this variation

formatint32
AgentVariationSpec { compactionConfig, constraints, description, 6 more }

AgentVariationSpec defines the operational configuration for a variation

compactionConfig?: AgentVariationSpecCompactionConfig { summarization, toolResultClearing, triggerThreshold }

CompactionConfig defines how context window compaction behaves for objectives using this variation.

summarization?: CompactionConfigSummarizationStrategy { instructions }

SummarizationStrategy configures LLM-powered summarization of older conversation turns.

instructions?: string

Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: “Preserve all code snippets, variable names, and technical decisions.”

toolResultClearing?: CompactionConfigToolResultClearingStrategy { preserveRecentResults }

ToolResultClearingStrategy configures clearing of older tool result content.

preserveRecentResults?: number

Number of most recent tool call results to keep intact. Older tool results have their content replaced with “[result cleared]” while preserving the assistant tool call message (function name, arguments). Default: 2

formatint32
triggerThreshold?: number

Trigger threshold as a percentage of the model’s context window (0.0 to 1.0). When input tokens reach this percentage of the model’s limit, compaction triggers. Default: 0.75 (75%)

formatfloat
constraints?: AgentVariationSpecConstraints { maxSubObjectives, maxToolCalls }

Execution constraints

maxSubObjectives?: number

The maximum number of sub-objectives that can be created. 0 means no limit.

formatint32
maxToolCalls?: number

The maximum number of tool calls that can be made. 0 means no limit.

formatint32
description?: string

Human-readable description of what this variation does or when it should be used

enableEpisodicMemory?: boolean

Enable episodic memory for objectives using this variation. When true, the system automatically creates a document namespace for each objective using the objective’s episodic_key as the external_id, allowing the agent to store and retrieve documents specific to that episode.

episodicMemoryTtl?: number

How long episodic memories should be retained. After this duration, episodic document namespaces can be automatically cleaned up. If not set, episodic memories are retained indefinitely.

modelConfig?: AgentVariationSpecModelConfig { modelId, temperature }

ModelConfig defines the model configuration for a variation

modelId?: string

The model identifier in family/model format (e.g., “claude/opus-4.6”, “claude/sonnet-4.5”)

temperature?: number

Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness

formatfloat
progressiveDiscovery?: AgentVariationSpecProgressiveDiscovery { hints, maxTools, rerankThreshold }

ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task.

hints?: Array<string>
maxTools?: number
rerankThreshold?: number

Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed.

formatfloat
prompt?: string

The system prompt for this variation

weight?: number

Weight for weighted random selection (>= 0). P(v) = v.weight / sum(all_weights). Only used when the agent’s variation_selection_mode is WEIGHTED. A weight of 0 means never auto-selected, but can still be chosen explicitly via variation_id on CreateObjectiveRequest.

formatint32
AgentVariationSpecCompactionConfig { summarization, toolResultClearing, triggerThreshold }

CompactionConfig defines how context window compaction behaves for objectives using this variation.

summarization?: CompactionConfigSummarizationStrategy { instructions }

SummarizationStrategy configures LLM-powered summarization of older conversation turns.

instructions?: string

Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: “Preserve all code snippets, variable names, and technical decisions.”

toolResultClearing?: CompactionConfigToolResultClearingStrategy { preserveRecentResults }

ToolResultClearingStrategy configures clearing of older tool result content.

preserveRecentResults?: number

Number of most recent tool call results to keep intact. Older tool results have their content replaced with “[result cleared]” while preserving the assistant tool call message (function name, arguments). Default: 2

formatint32
triggerThreshold?: number

Trigger threshold as a percentage of the model’s context window (0.0 to 1.0). When input tokens reach this percentage of the model’s limit, compaction triggers. Default: 0.75 (75%)

formatfloat
AgentVariationSpecConstraints { maxSubObjectives, maxToolCalls }
maxSubObjectives?: number

The maximum number of sub-objectives that can be created. 0 means no limit.

formatint32
maxToolCalls?: number

The maximum number of tool calls that can be made. 0 means no limit.

formatint32
AgentVariationSpecModelConfig { modelId, temperature }

ModelConfig defines the model configuration for a variation

modelId?: string

The model identifier in family/model format (e.g., “claude/opus-4.6”, “claude/sonnet-4.5”)

temperature?: number

Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness

formatfloat
AgentVariationSpecProgressiveDiscovery { hints, maxTools, rerankThreshold }

ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task.

hints?: Array<string>
maxTools?: number
rerankThreshold?: number

Rerank Threshold is an optional value that instructs whether or not to run a search result through a embedding/reranker process which can improve performance and reduce context bloat when tools reach the configured threshold. If a tool match must exceed 0.8, for example, the tool very closely match the query the tool search performed.

formatfloat
CompactionConfigSummarizationStrategy { instructions }

SummarizationStrategy configures LLM-powered summarization of older conversation turns.

instructions?: string

Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: “Preserve all code snippets, variable names, and technical decisions.”

CompactionConfigToolResultClearingStrategy { preserveRecentResults }

ToolResultClearingStrategy configures clearing of older tool result content.

preserveRecentResults?: number

Number of most recent tool call results to keep intact. Older tool results have their content replaced with “[result cleared]” while preserving the assistant tool call message (function name, arguments). Default: 2

formatint32
VariationAssignment { id, agent, tool, toolSet }

A read-only reference to a single tool, tool set, or sub-agent attached to a variation. Read the full set of assignments via AgentVariationInfo.assignments; mutations go through the dedicated add/remove assignment endpoints.

The id identifies the assignment itself (not the referenced resource) and is the handle used to remove the assignment. It is returned by the add endpoint and present on every entry in AgentVariationInfo.assignments.

id?: string
agent?: BareMetadata { id, name }

BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves.

id?: string
name?: string

Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks).

tool?: BareMetadata { id, name }

BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves.

id?: string
name?: string

Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks).

toolSet?: BareMetadata { id, name }

BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves.

id?: string
name?: string

Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks).

VariationMemoryLayerAssignment { id, memoryLayer, position }

VariationMemoryLayerAssignment attaches a single MemoryLayer to a variation at a given position in the variation’s baseline memory stack. A variation has at most one assignment per memory_layer_id.

Variations only support whole-layer attachments — entry pinning is an objective-level capability.

id?: string

Assignment row id — handle for removing the assignment. Distinct from the referenced memory layer’s id.

memoryLayer?: BareMetadata { id, name }

BareMetadata contains the minimal metadata for a resource: the ID and an optional human-readable name. These are used for reference fields where the full metadata (account scoping, timestamps, labels, external IDs) is not needed — e.g., the tool references inside an agent variation spec or the tools assigned to an objective. Both fields are server-populated; clients provide IDs through sibling fields rather than by constructing a BareMetadata themselves.

id?: string
name?: string

Human-readable name of the referenced resource, populated by the server on reads for convenience. Absent on references to resources that do not have a name (e.g., objective tasks).

position?: number

Position in the variation’s baseline stack. Lower values sit lower; the highest-position assignment is on top of the variation’s baseline. Gaps are fine — only relative position matters. Positions must be unique within a variation; a request that would collide with an existing assignment’s position is rejected with InvalidArgument.

formatint32

AgentsSchedules

Manage recurring schedules attached to agents. Schedules trigger objectives on a cadence defined by AgentScheduleSpec.Schedule.

List schedules
client.agents.schedules.list(stringagentID, ScheduleListParams { workspaceId, bundleKey, cursor, 5 more } params, RequestOptionsoptions?): CursorPagination<AgentSchedule { metadata, spec, info } >
GET/v1/workspaces/{workspaceId}/agents/{agentId}/schedules
Create a new schedule
client.agents.schedules.create(stringagentID, ScheduleCreateParams { workspaceId, metadata, spec } params, RequestOptionsoptions?): AgentSchedule { metadata, spec, info }
POST/v1/workspaces/{workspaceId}/agents/{agentId}/schedules
Get a schedule by ID
client.agents.schedules.retrieve(stringid, ScheduleRetrieveParams { workspaceId, agentId } params, RequestOptionsoptions?): AgentSchedule { metadata, spec, info }
GET/v1/workspaces/{workspaceId}/agents/{agentId}/schedules/{id}
Delete a schedule
client.agents.schedules.delete(stringid, ScheduleDeleteParams { workspaceId, agentId } params, RequestOptionsoptions?): void
DELETE/v1/workspaces/{workspaceId}/agents/{agentId}/schedules/{id}
Update a schedule
client.agents.schedules.update(stringid, ScheduleUpdateParams { workspaceId, agentId, metadata, 2 more } params, RequestOptionsoptions?): AgentSchedule { metadata, spec, info }
PATCH/v1/workspaces/{workspaceId}/agents/{agentId}/schedules/{id}
ModelsExpand Collapse
AgentSchedule { metadata, spec, info }

AgentSchedule resource — a recurring trigger attached to an agent that creates objectives on its cadence.

metadata: ResourceMetadata { id, accountId, createdAt, 6 more }

Standard metadata for persistent, named resources (e.g., agents, tools, prompts)

id: string

Unique identifier for the resource (prefixed ULID, e.g., “agent_01HXK…”)

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

createdAt: string

Timestamp when this resource was created

formatdate-time
name: string

Human-readable name for the resource (e.g., “Customer Support Agent”, “Email Tool”) Required for resources that users interact with directly

profileId: string

ID of the actor (user or service account) that created this resource

workspaceId: string

Workspace this resource belongs to for organizational grouping (prefixed ULID)

bundleKey?: string

Optional bundle ownership key. When set, indicates the resource is managed by a configuration bundle identified by this key. Used by BulkWorkspaceResources.Apply to track which resources belong to which bundle for reconciliation / soft-delete on re-apply.

externalId?: string

External ID for the resource (e.g., a workflow ID from an external system)

labels?: Record<string, string>

Arbitrary key-value pairs for categorization and filtering Examples: {“environment”: “production”, “team”: “platform”, “version”: “v2”}

spec: AgentScheduleSpec { initialMessage, schedule, data, 3 more }

AgentScheduleSpec is the user-provided configuration for a schedule.

initialMessage: string

The initial message passed to CreateObjective on each fire. Becomes the first user message in the objective’s chat history.

schedule: AgentScheduleSpecSchedule { calendars, intervals, timezone }

Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR’d together. At least one rule is required.

calendars?: Array<ScheduleCalendar { comment, dayOfMonth, dayOfWeek, 4 more } >

Wall-clock rules. May be empty if intervals is non-empty.

comment?: string
dayOfMonth?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
dayOfWeek?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
hour?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
minute?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
month?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
second?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
intervals?: Array<ScheduleInterval { every, offset } >

Duration-based rules. May be empty if calendars is non-empty.

every?: string
offset?: string

Phase shift within every. Must be < every (enforced at runtime).

timezone?: string

IANA tz name (e.g. “America/New_York”). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone.

data?: unknown

Optional input data passed to the objective. If the agent has an input_data_schema, this must satisfy it.

overlapPolicy?: "OVERLAP_POLICY_UNSPECIFIED" | "OVERLAP_POLICY_ALLOW" | "OVERLAP_POLICY_SKIP"

What to do when the previous run is still in flight. Defaults to SKIP.

formatenum
One of the following:
"OVERLAP_POLICY_UNSPECIFIED"
"OVERLAP_POLICY_ALLOW"
"OVERLAP_POLICY_SKIP"
status?: "AGENT_SCHEDULE_STATUS_UNSPECIFIED" | "AGENT_SCHEDULE_STATUS_ACTIVE" | "AGENT_SCHEDULE_STATUS_PAUSED" | "AGENT_SCHEDULE_STATUS_ARCHIVED"

Lifecycle. Defaults to ACTIVE on create when unspecified.

formatenum
One of the following:
"AGENT_SCHEDULE_STATUS_UNSPECIFIED"
"AGENT_SCHEDULE_STATUS_ACTIVE"
"AGENT_SCHEDULE_STATUS_PAUSED"
"AGENT_SCHEDULE_STATUS_ARCHIVED"
variationId?: string

Optional explicit variation. When unset, the agent’s variation_selection_mode chooses per fire.

info?: AgentScheduleInfo { createdBy, lastFireAt, lastObjectiveId, 4 more }

AgentScheduleInfo provides read-only runtime data about a schedule.

createdBy?: Profile { metadata, spec }

A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces.

metadata: AccountResourceMetadata { id, accountId, name, 3 more }

AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.

id: string

Unique identifier for the resource (prefixed ULID, e.g., “apikey_01HXK…”)

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

name: string

Human-readable name for the resource (e.g., “Customer Support Agent”, “Email Tool”) Required for resources that users interact with directly

profileId: string
externalId?: string

External ID for the resource (e.g., a workflow ID from an external system)

labels?: Record<string, string>

Arbitrary key-value pairs for categorization and filtering Examples: {“environment”: “production”, “team”: “platform”, “version”: “v2”}

spec: ProfileSpec { type, email, name }

Configuration for a profile.

type: "PROFILE_TYPE_UNSPECIFIED" | "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"

Whether this profile represents a human user, an API key, or a system principal.

formatenum
One of the following:
"PROFILE_TYPE_UNSPECIFIED"
"PROFILE_TYPE_USER"
"PROFILE_TYPE_API_KEY"
"PROFILE_TYPE_SYSTEM"
email?: string

Email address of the profile. Required and unique within an account for user profiles.

name?: string

Display name (e.g., “Bobby Tables”).

lastFireAt?: string

When the schedule last fired (regardless of objective outcome).

formatdate-time
lastObjectiveId?: string

ID of the most recent objective the schedule created.

lastSkippedAt?: string

When the schedule most recently skipped a fire (SKIP policy + prior in flight).

formatdate-time
lastSkipReason?: string

Reason for the most recent skip (e.g. “previous objective still running”).

nextFireAt?: string

When the schedule will next fire. Computed from the spec; absent when the schedule is PAUSED/ARCHIVED or has no future fire times.

formatdate-time
totalFires?: number

Lifetime count of objectives created by this schedule.

formatint32
AgentScheduleInfo { createdBy, lastFireAt, lastObjectiveId, 4 more }

AgentScheduleInfo provides read-only runtime data about a schedule.

createdBy?: Profile { metadata, spec }

A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces.

metadata: AccountResourceMetadata { id, accountId, name, 3 more }

AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.

id: string

Unique identifier for the resource (prefixed ULID, e.g., “apikey_01HXK…”)

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

name: string

Human-readable name for the resource (e.g., “Customer Support Agent”, “Email Tool”) Required for resources that users interact with directly

profileId: string
externalId?: string

External ID for the resource (e.g., a workflow ID from an external system)

labels?: Record<string, string>

Arbitrary key-value pairs for categorization and filtering Examples: {“environment”: “production”, “team”: “platform”, “version”: “v2”}

spec: ProfileSpec { type, email, name }

Configuration for a profile.

type: "PROFILE_TYPE_UNSPECIFIED" | "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"

Whether this profile represents a human user, an API key, or a system principal.

formatenum
One of the following:
"PROFILE_TYPE_UNSPECIFIED"
"PROFILE_TYPE_USER"
"PROFILE_TYPE_API_KEY"
"PROFILE_TYPE_SYSTEM"
email?: string

Email address of the profile. Required and unique within an account for user profiles.

name?: string

Display name (e.g., “Bobby Tables”).

lastFireAt?: string

When the schedule last fired (regardless of objective outcome).

formatdate-time
lastObjectiveId?: string

ID of the most recent objective the schedule created.

lastSkippedAt?: string

When the schedule most recently skipped a fire (SKIP policy + prior in flight).

formatdate-time
lastSkipReason?: string

Reason for the most recent skip (e.g. “previous objective still running”).

nextFireAt?: string

When the schedule will next fire. Computed from the spec; absent when the schedule is PAUSED/ARCHIVED or has no future fire times.

formatdate-time
totalFires?: number

Lifetime count of objectives created by this schedule.

formatint32
AgentScheduleSpec { initialMessage, schedule, data, 3 more }

AgentScheduleSpec is the user-provided configuration for a schedule.

initialMessage: string

The initial message passed to CreateObjective on each fire. Becomes the first user message in the objective’s chat history.

schedule: AgentScheduleSpecSchedule { calendars, intervals, timezone }

Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR’d together. At least one rule is required.

calendars?: Array<ScheduleCalendar { comment, dayOfMonth, dayOfWeek, 4 more } >

Wall-clock rules. May be empty if intervals is non-empty.

comment?: string
dayOfMonth?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
dayOfWeek?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
hour?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
minute?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
month?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
second?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
intervals?: Array<ScheduleInterval { every, offset } >

Duration-based rules. May be empty if calendars is non-empty.

every?: string
offset?: string

Phase shift within every. Must be < every (enforced at runtime).

timezone?: string

IANA tz name (e.g. “America/New_York”). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone.

data?: unknown

Optional input data passed to the objective. If the agent has an input_data_schema, this must satisfy it.

overlapPolicy?: "OVERLAP_POLICY_UNSPECIFIED" | "OVERLAP_POLICY_ALLOW" | "OVERLAP_POLICY_SKIP"

What to do when the previous run is still in flight. Defaults to SKIP.

formatenum
One of the following:
"OVERLAP_POLICY_UNSPECIFIED"
"OVERLAP_POLICY_ALLOW"
"OVERLAP_POLICY_SKIP"
status?: "AGENT_SCHEDULE_STATUS_UNSPECIFIED" | "AGENT_SCHEDULE_STATUS_ACTIVE" | "AGENT_SCHEDULE_STATUS_PAUSED" | "AGENT_SCHEDULE_STATUS_ARCHIVED"

Lifecycle. Defaults to ACTIVE on create when unspecified.

formatenum
One of the following:
"AGENT_SCHEDULE_STATUS_UNSPECIFIED"
"AGENT_SCHEDULE_STATUS_ACTIVE"
"AGENT_SCHEDULE_STATUS_PAUSED"
"AGENT_SCHEDULE_STATUS_ARCHIVED"
variationId?: string

Optional explicit variation. When unset, the agent’s variation_selection_mode chooses per fire.

AgentScheduleSpecSchedule { calendars, intervals, timezone }

Schedule defines WHEN the schedule fires. Temporal-style structured form: a list of calendar rules (wall-clock) and/or interval rules (duration), OR’d together. At least one rule is required.

calendars?: Array<ScheduleCalendar { comment, dayOfMonth, dayOfWeek, 4 more } >

Wall-clock rules. May be empty if intervals is non-empty.

comment?: string
dayOfMonth?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
dayOfWeek?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
hour?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
minute?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
month?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
second?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
intervals?: Array<ScheduleInterval { every, offset } >

Duration-based rules. May be empty if calendars is non-empty.

every?: string
offset?: string

Phase shift within every. Must be < every (enforced at runtime).

timezone?: string

IANA tz name (e.g. “America/New_York”). Required. Applies to calendars; intervals fire on wall-clock cadence anchored in this zone.

ScheduleCalendar { comment, dayOfMonth, dayOfWeek, 4 more }

Calendar is a wall-clock rule. Empty field-list semantics:

  • second/minute/hour: empty means [{start: 0}] (top of the unit)
  • day_of_month/month/day_of_week: empty means “any value” Fire times = cartesian product across all fields.
comment?: string
dayOfMonth?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
dayOfWeek?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
hour?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
minute?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
month?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
second?: Array<ScheduleRange { end, start, step } >
end?: number
start?: number
step?: number
ScheduleInterval { every, offset }

Interval is a duration-based rule. Fires every every from a stable anchor (workspace epoch), optionally phase-shifted by offset.

every?: string
offset?: string

Phase shift within every. Must be < every (enforced at runtime).

ScheduleRange { end, start, step }

Inclusive numeric range with optional step. {start: 9} → 9 {start: 9, end: 17} → 9..17 {start: 0, end: 59, step: 15} → 0,15,30,45 end defaults to start; step defaults to 1.

end?: number
start?: number
step?: number