Objectives
List objective context windows
ModelsExpand Collapse
assistant_message: object { content, toolCalls }
tool: optional object { agent, cadenyaProvidedTool, tool }
CallableTool is a union that represents a tool that can be called by an agent. In Cadenya, a tool that is used within an agent objective might be a user-defined tool (IE: MCP, HTTP), another Agent (useful to separate context), or a Cadenya Tool (one Cadenya provides).
agent: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
cadenyaProvidedTool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
tool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
assistant_tool_call: object { arguments, functionName, tool }
tool: optional object { agent, cadenyaProvidedTool, tool }
CallableTool is a union that represents a tool that can be called by an agent. In Cadenya, a tool that is used within an agent objective might be a user-defined tool (IE: MCP, HTTP), another Agent (useful to separate context), or a Cadenya Tool (one Cadenya provides).
agent: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
cadenyaProvidedTool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
tool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
callable_tool: object { agent, cadenyaProvidedTool, tool }
CallableTool is a union that represents a tool that can be called by an agent. In Cadenya, a tool that is used within an agent objective might be a user-defined tool (IE: MCP, HTTP), another Agent (useful to separate context), or a Cadenya Tool (one Cadenya provides).
agent: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
cadenyaProvidedTool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
tool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
context_window_compacted: object { messagesCompacted, newContextWindow, strategies, summary }
newContextWindow: optional object { completionTokens, objectiveId, previousWindowContinueInstructions, 2 more }
The new context window created by this compaction
completionTokens: optional number
A calculated value for how many completion tokens (output tokens) have been used in this context window
previousWindowContinueInstructions: optional string
The instructions for this window to continue from a previous window's chat history.
objective: object { data, metadata, status, 2 more }
data: object { agent, data, initialMessage, 4 more }
agent: optional object { metadata, spec, info }
Agent resource
metadata: object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
spec: object { status, variationSelectionMode, description, webhookEventsUrl }
Agent specification (user-provided configuration)
info: optional object { createdBy, variationCount }
AgentInfo contains simple information about an agent for display or quick reference
createdBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
data: optional unknown
Represents a dynamically typed value which can be either null, a number, a string, a boolean, a recursive struct value, or a list of values.
initialMessage: optional string
The initial message sent to the agent. This becomes the first user message in the LLM chat history.
parentObjectiveId: optional string
A parent objective means the objective was spawned off using a separate agent to complete an objective
systemPrompt: optional string
system_prompt is read-only, derived from the selected variation's prompt
variation: optional object { metadata, spec, info }
AgentVariation resource
metadata: object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
spec: object { compactionConfig, constraints, description, 6 more }
AgentVariationSpec defines the operational configuration for a variation
compactionConfig: optional object { summarization, toolResultClearing, triggerThreshold }
CompactionConfig defines how context window compaction behaves for objectives using this variation.
description: optional string
Human-readable description of what this variation does or when it should be used
enableEpisodicMemory: optional 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: optional 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: optional object { modelId, temperature }
ModelConfig defines the model configuration for a variation
toolSelection: optional object { assignedTools, autoDiscovery }
Tool selection strategy
autoDiscovery: optional object { hints, maxTools }
AutoDiscovery 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. 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.
info: optional object { assignments, createdBy, feedbackCount, 5 more }
AgentVariationInfo provides read-only summary information about a variation
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.
agent: optional object { 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.
tool: optional object { 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.
toolSet: optional object { 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.
createdBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
model: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
metadata: object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
info: optional object { callableTools, createdBy, totalContextWindows, 4 more }
ObjectiveInfo provides read-only aggregated statistics about an objective's execution
List of callable tools assigned to the agent for this objective Includes tools, agents, and cadenya-provided tools from the agent's configuration
agent: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
cadenyaProvidedTool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
tool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
createdBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
totalContextWindows: optional number
Total number of context windows that this objective has generated
totalInputTokens: optional number
Total input tokens consumed across all LLM completions across all context windows
Read-only list of the last five windows of execution for this objective, ordered by most recent first. Is only included in singular RPC calls (GetObjective, for example).
data: object { completionTokens, objectiveId, previousWindowContinueInstructions, 2 more }
completionTokens: optional number
A calculated value for how many completion tokens (output tokens) have been used in this context window
previousWindowContinueInstructions: optional string
The instructions for this window to continue from a previous window's chat history.
metadata: object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
info: optional object { createdBy, objective }
createdBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
objective: optional object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
objective_context_window: object { data, metadata, info }
ObjectiveContextWindow is a window of chat completions that is grouped together to prevent context-window overflows. Context windows also allow agents to compact their windows and carry on into a new one.
data: object { completionTokens, objectiveId, previousWindowContinueInstructions, 2 more }
completionTokens: optional number
A calculated value for how many completion tokens (output tokens) have been used in this context window
previousWindowContinueInstructions: optional string
The instructions for this window to continue from a previous window's chat history.
metadata: object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
info: optional object { createdBy, objective }
createdBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
objective: optional object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
objective_context_window_data: object { completionTokens, objectiveId, previousWindowContinueInstructions, 2 more }
completionTokens: optional number
A calculated value for how many completion tokens (output tokens) have been used in this context window
previousWindowContinueInstructions: optional string
The instructions for this window to continue from a previous window's chat history.
objective_data: object { agent, data, initialMessage, 4 more }
agent: optional object { metadata, spec, info }
Agent resource
metadata: object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
spec: object { status, variationSelectionMode, description, webhookEventsUrl }
Agent specification (user-provided configuration)
info: optional object { createdBy, variationCount }
AgentInfo contains simple information about an agent for display or quick reference
createdBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
data: optional unknown
Represents a dynamically typed value which can be either null, a number, a string, a boolean, a recursive struct value, or a list of values.
initialMessage: optional string
The initial message sent to the agent. This becomes the first user message in the LLM chat history.
parentObjectiveId: optional string
A parent objective means the objective was spawned off using a separate agent to complete an objective
systemPrompt: optional string
system_prompt is read-only, derived from the selected variation's prompt
variation: optional object { metadata, spec, info }
AgentVariation resource
metadata: object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
spec: object { compactionConfig, constraints, description, 6 more }
AgentVariationSpec defines the operational configuration for a variation
compactionConfig: optional object { summarization, toolResultClearing, triggerThreshold }
CompactionConfig defines how context window compaction behaves for objectives using this variation.
description: optional string
Human-readable description of what this variation does or when it should be used
enableEpisodicMemory: optional 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: optional 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: optional object { modelId, temperature }
ModelConfig defines the model configuration for a variation
toolSelection: optional object { assignedTools, autoDiscovery }
Tool selection strategy
autoDiscovery: optional object { hints, maxTools }
AutoDiscovery 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. 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.
info: optional object { assignments, createdBy, feedbackCount, 5 more }
AgentVariationInfo provides read-only summary information about a variation
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.
agent: optional object { 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.
tool: optional object { 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.
toolSet: optional object { 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.
createdBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
model: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
objective_event_data: object { assistantMessage, contextWindowCompacted, error, 9 more }
assistantMessage: optional object { content, toolCalls }
tool: optional object { agent, cadenyaProvidedTool, tool }
CallableTool is a union that represents a tool that can be called by an agent. In Cadenya, a tool that is used within an agent objective might be a user-defined tool (IE: MCP, HTTP), another Agent (useful to separate context), or a Cadenya Tool (one Cadenya provides).
agent: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
cadenyaProvidedTool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
tool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
contextWindowCompacted: optional object { messagesCompacted, newContextWindow, strategies, summary }
newContextWindow: optional object { completionTokens, objectiveId, previousWindowContinueInstructions, 2 more }
The new context window created by this compaction
completionTokens: optional number
A calculated value for how many completion tokens (output tokens) have been used in this context window
previousWindowContinueInstructions: optional string
The instructions for this window to continue from a previous window's chat history.
subObjectiveCreated: optional object { metadata }
metadata: optional object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
objective_event_info: object { createdBy, objective }
createdBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
objective: optional object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
objective_event_webhook_data: object { data, timestamp, type }
The envelope for an objective event webhook delivery. Contains timestamp, event type, and the webhook data payload.
data: object { agent, agentVariation, objective, objectiveEvent }
The webhook data payload with flat top-level keys for agent, variation, objective, and event.
agent: object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
agentVariation: object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
objective: object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
objectiveEvent: object { data, metadata, contextWindowId, info }
data: object { assistantMessage, contextWindowCompacted, error, 9 more }
assistantMessage: optional object { content, toolCalls }
tool: optional object { agent, cadenyaProvidedTool, tool }
CallableTool is a union that represents a tool that can be called by an agent. In Cadenya, a tool that is used within an agent objective might be a user-defined tool (IE: MCP, HTTP), another Agent (useful to separate context), or a Cadenya Tool (one Cadenya provides).
agent: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
cadenyaProvidedTool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
tool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
contextWindowCompacted: optional object { messagesCompacted, newContextWindow, strategies, summary }
newContextWindow: optional object { completionTokens, objectiveId, previousWindowContinueInstructions, 2 more }
The new context window created by this compaction
completionTokens: optional number
A calculated value for how many completion tokens (output tokens) have been used in this context window
previousWindowContinueInstructions: optional string
The instructions for this window to continue from a previous window's chat history.
subObjectiveCreated: optional object { metadata }
metadata: optional object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
metadata: object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
info: optional object { createdBy, objective }
createdBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
objective: optional object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
objective_info: object { callableTools, createdBy, totalContextWindows, 4 more }
ObjectiveInfo provides read-only aggregated statistics about an objective's execution
List of callable tools assigned to the agent for this objective Includes tools, agents, and cadenya-provided tools from the agent's configuration
agent: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
cadenyaProvidedTool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
tool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
createdBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
totalContextWindows: optional number
Total number of context windows that this objective has generated
totalInputTokens: optional number
Total input tokens consumed across all LLM completions across all context windows
sub_objective_created: object { metadata }
metadata: optional object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
ObjectivesTools
ModelsExpand Collapse
objective_tool: object { metadata, snapshot }
ObjectiveTool represents a tool that was assigned to an objective.
metadata: object { 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.
snapshot: optional object { metadata, spec, info }
Snapshot of the tool at the time it was assigned to the objective. Because tools can change over time, snapshots are used to ensure tools don't change unexpectedly during an objective's lifecycle.
metadata: object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
spec: object { config, description, parameters, 2 more }
config: object { http, mcp }
Config defines the adapter to use for the tool. This is used to determine how the tool is called. For example, if the tool is an HTTP tool, the adapter will be Http. If the tool is an inline tool, the adapter will be Inline.
info: optional object { createdBy, toolSet }
createdBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
toolSet: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
ObjectivesTool Calls
List objective tool calls
Approve a tool call
Deny a tool call
ModelsExpand Collapse
objective_tool_call: object { data, metadata, status, 2 more }
ObjectiveToolCall is a record of a tool call made during an objective's execution. Tool calls are mutable — their status changes as they are approved, denied, or executed.
data: object { callable, arguments, memo, 2 more }
callable: object { agent, cadenyaProvidedTool, tool }
CallableTool is a union that represents a tool that can be called by an agent. In Cadenya, a tool that is used within an agent objective might be a user-defined tool (IE: MCP, HTTP), another Agent (useful to separate context), or a Cadenya Tool (one Cadenya provides).
agent: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
cadenyaProvidedTool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
tool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
statusChangedBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
metadata: object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
status: "TOOL_CALL_STATUS_UNSPECIFIED" or "TOOL_CALL_STATUS_AUTO_APPROVED" or "TOOL_CALL_STATUS_WAITING_FOR_APPROVAL" or 2 more
executionStatus: optional "TOOL_CALL_EXECUTION_STATUS_UNSPECIFIED" or "TOOL_CALL_EXECUTION_STATUS_PENDING" or "TOOL_CALL_EXECUTION_STATUS_RUNNING" or 2 more
info: optional object { createdBy, objective }
createdBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
objective: optional object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
objective_tool_call_data: object { callable, arguments, memo, 2 more }
callable: object { agent, cadenyaProvidedTool, tool }
CallableTool is a union that represents a tool that can be called by an agent. In Cadenya, a tool that is used within an agent objective might be a user-defined tool (IE: MCP, HTTP), another Agent (useful to separate context), or a Cadenya Tool (one Cadenya provides).
agent: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
cadenyaProvidedTool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
tool: optional object { id, accountId, createdAt, 5 more }
Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
statusChangedBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
objective_tool_call_info: object { createdBy, objective }
createdBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
objective: optional object { id, accountId, createdAt, 4 more }
Metadata for ephemeral operations and activities (e.g., objectives, executions, runs)
ObjectivesTasks
Get an objective task by ID
ModelsExpand Collapse
objective_task: object { data, metadata }
ObjectiveTask represents a task within an objective, typically created and managed by an AI agent to track progress toward completing the objective.
metadata: object { 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.
ObjectivesFeedback
Submit feedback for an objective
List feedback for an objective
ModelsExpand Collapse
objective_feedback: object { data, metadata, info }
ObjectiveFeedback represents feedback submitted for an objective's execution. Feedback is used to score agent variations and improve agent performance over time.
data: object { attributes, comment, score }
metadata: object { 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.
info: optional object { submittedBy }
submittedBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.
objective_feedback_data: object { attributes, comment, score }
objective_feedback_info: object { submittedBy }
submittedBy: optional object { metadata, spec }
Profile represents a human user at the account level. Profiles are account-scoped resources that can be associated with multiple workspaces through the Actor model. Authentication for profiles is handled via SSO/OAuth (WorkOS).
metadata: object { id, accountId, name, 3 more }
AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace.