# Objectives ## List objectives `client.objectives.list(ObjectiveListParamsquery?, RequestOptionsoptions?): CursorPagination` **get** `/v1/objectives` Lists all objectives in the workspace ### Parameters - `query: ObjectiveListParams` - `agentId?: string` Agent ID for filtering - `cursor?: string` Pagination cursor from previous response - `includeInfo?: boolean` When set to true you may use more of your alloted API rate-limit - `limit?: number` Maximum number of results to return - `parentObjectiveId?: string` Optional filters - `profileId?: string` - `sortOrder?: string` Sort order for results (asc or desc by creation time) - `state?: "STATE_UNSPECIFIED" | "STATE_PENDING" | "STATE_RUNNING" | 3 more` Filter by state - `"STATE_UNSPECIFIED"` - `"STATE_PENDING"` - `"STATE_RUNNING"` - `"STATE_COMPLETED"` - `"STATE_FAILED"` - `"STATE_CANCELLED"` ### Returns - `Objective` - `data: ObjectiveData` - `agent?: Agent` Agent resource - `metadata: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: AgentSpec` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" | "AGENT_STATUS_DRAFT" | "AGENT_STATUS_PUBLISHED" | "AGENT_STATUS_ARCHIVED"` Status of the agent - `"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 - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description?: string` Description of the agent's purpose - `webhookEventsUrl?: string` The URL that Cadenya will send events for any objective assigned to the agent. - `info?: AgentInfo` AgentInfo contains simple information about an agent for display or quick reference - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `variationCount?: number` - `data?: 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?: string` The initial message sent to the agent. This becomes the first user message in the LLM chat history. - `parentObjectiveId?: string` A parent objective means the objective was spawned off using a separate agent to complete an objective - `secrets?: Array` Secrets that can be used in the headers for tool calls using the secret interpolation format. - `name?: string` - `value?: string` - `systemPrompt?: string` system_prompt is read-only, derived from the selected variation's prompt - `variation?: AgentVariation` AgentVariation resource - `metadata: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `spec: AgentVariationSpec` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig?: AgentVariationSpecCompactionConfig` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization?: CompactionConfigSummarizationStrategy` 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` 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 - `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%) - `constraints?: AgentVariationSpecConstraints` Execution constraints - `maxSubObjectives?: number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls?: number` The maximum number of tool calls that can be made. 0 means no limit. - `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` 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 - `prompt?: string` The system prompt for this variation - `toolSelection?: AgentVariationSpecToolSelection` Tool selection strategy - `assignedTools?: ToolSelectionAssignedTools` AssignedTools is used to indicate that the agent should only use the tools/tool sets that are explicitly assigned to it. Allow discovery is used when the agent thinks it needs to discover more tools. - `allowDiscovery?: boolean` - `autoDiscovery?: ToolSelectionAutoDiscovery` 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. - `hints?: Array` - `maxTools?: number` - `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. - `info?: AgentVariationInfo` AgentVariationInfo provides read-only summary information about a variation - `assignments?: Array` 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` 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` 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?: BareMetadata` 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?: Profile` 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). - `feedbackCount?: number` Total number of objective feedbacks received for this variation - `model?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `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. - `subAgentCount?: number` Number of sub-agents assigned to this variation - `toolCount?: number` Number of individual tools assigned to this variation - `toolSetCount?: number` Number of tool sets assigned to this variation - `metadata: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `status: ObjectiveStatus` - `state: "STATE_UNSPECIFIED" | "STATE_PENDING" | "STATE_RUNNING" | 3 more` - `"STATE_UNSPECIFIED"` - `"STATE_PENDING"` - `"STATE_RUNNING"` - `"STATE_COMPLETED"` - `"STATE_FAILED"` - `"STATE_CANCELLED"` - `message?: string` - `info?: ObjectiveInfo` ObjectiveInfo provides read-only aggregated statistics about an objective's execution - `callableTools?: Array` List of callable tools assigned to the agent for this objective Includes tools, agents, and cadenya-provided tools from the agent's configuration - `agent?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `createdBy?: Profile` 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). - `totalContextWindows?: number` Total number of context windows that this objective has generated - `totalEvents?: number` Total number of events generated during this objective's execution - `totalInputTokens?: number` Total input tokens consumed across all LLM completions across all context windows - `totalOutputTokens?: number` Total output tokens generated across all LLM completions across all context windows - `totalToolCalls?: number` Total number of tool calls made during execution - `lastFiveWindows?: Array` 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: ObjectiveContextWindowData` - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `metadata: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `info?: Info` - `createdBy?: Profile` 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). - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); // Automatically fetches more pages as needed. for await (const objective of client.objectives.list()) { console.log(objective.data); } ``` #### Response ```json { "items": [ { "data": { "agent": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "status": "AGENT_STATUS_UNSPECIFIED", "variationSelectionMode": "VARIATION_SELECTION_MODE_UNSPECIFIED", "description": "description", "webhookEventsUrl": "webhookEventsUrl" }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "variationCount": 0 } }, "data": {}, "initialMessage": "initialMessage", "parentObjectiveId": "parentObjectiveId", "secrets": [ { "name": "name", "value": "value" } ], "systemPrompt": "systemPrompt", "variation": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "compactionConfig": { "summarization": { "instructions": "instructions" }, "toolResultClearing": { "preserveRecentResults": 0 }, "triggerThreshold": 0 }, "constraints": { "maxSubObjectives": 0, "maxToolCalls": 0 }, "description": "description", "enableEpisodicMemory": true, "episodicMemoryTtl": 0, "modelConfig": { "modelId": "modelId", "temperature": 0 }, "prompt": "prompt", "toolSelection": { "assignedTools": { "allowDiscovery": true }, "autoDiscovery": { "hints": [ "string" ], "maxTools": 0 } }, "weight": 0 }, "info": { "assignments": [ { "id": "id", "agent": { "id": "id", "name": "name" }, "tool": { "id": "id", "name": "name" }, "toolSet": { "id": "id", "name": "name" } } ], "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "feedbackCount": 0, "model": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "score": 0, "subAgentCount": 0, "toolCount": 0, "toolSetCount": 0 } } }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "status": { "state": "STATE_UNSPECIFIED", "message": "message" }, "info": { "callableTools": [ { "agent": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "cadenyaProvidedTool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "tool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } ], "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "totalContextWindows": 0, "totalEvents": 0, "totalInputTokens": 0, "totalOutputTokens": 0, "totalToolCalls": 0 }, "lastFiveWindows": [ { "data": { "completionTokens": 0, "objectiveId": "objectiveId", "previousWindowContinueInstructions": "previousWindowContinueInstructions", "promptTokens": 0, "sequence": 0 }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "objective": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } } ] } ], "pagination": { "nextCursor": "nextCursor", "total": 0 } } ``` ## Create a new objective `client.objectives.create(ObjectiveCreateParamsbody, RequestOptionsoptions?): Objective` **post** `/v1/objectives` Creates a new objective in the workspace ### Parameters - `body: ObjectiveCreateParams` - `agentId: string` - `data: ObjectiveData` - `agent?: Agent` Agent resource - `metadata: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: AgentSpec` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" | "AGENT_STATUS_DRAFT" | "AGENT_STATUS_PUBLISHED" | "AGENT_STATUS_ARCHIVED"` Status of the agent - `"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 - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description?: string` Description of the agent's purpose - `webhookEventsUrl?: string` The URL that Cadenya will send events for any objective assigned to the agent. - `info?: AgentInfo` AgentInfo contains simple information about an agent for display or quick reference - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `variationCount?: number` - `data?: 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?: string` The initial message sent to the agent. This becomes the first user message in the LLM chat history. - `parentObjectiveId?: string` A parent objective means the objective was spawned off using a separate agent to complete an objective - `secrets?: Array` Secrets that can be used in the headers for tool calls using the secret interpolation format. - `name?: string` - `value?: string` - `systemPrompt?: string` system_prompt is read-only, derived from the selected variation's prompt - `variation?: AgentVariation` AgentVariation resource - `metadata: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `spec: AgentVariationSpec` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig?: AgentVariationSpecCompactionConfig` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization?: CompactionConfigSummarizationStrategy` 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` 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 - `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%) - `constraints?: AgentVariationSpecConstraints` Execution constraints - `maxSubObjectives?: number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls?: number` The maximum number of tool calls that can be made. 0 means no limit. - `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` 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 - `prompt?: string` The system prompt for this variation - `toolSelection?: AgentVariationSpecToolSelection` Tool selection strategy - `assignedTools?: ToolSelectionAssignedTools` AssignedTools is used to indicate that the agent should only use the tools/tool sets that are explicitly assigned to it. Allow discovery is used when the agent thinks it needs to discover more tools. - `allowDiscovery?: boolean` - `autoDiscovery?: ToolSelectionAutoDiscovery` 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. - `hints?: Array` - `maxTools?: number` - `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. - `info?: AgentVariationInfo` AgentVariationInfo provides read-only summary information about a variation - `assignments?: Array` 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` 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` 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?: BareMetadata` 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?: Profile` 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). - `feedbackCount?: number` Total number of objective feedbacks received for this variation - `model?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `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. - `subAgentCount?: number` Number of sub-agents assigned to this variation - `toolCount?: number` Number of individual tools assigned to this variation - `toolSetCount?: number` Number of tool sets assigned to this variation - `metadata: CreateOperationMetadata` CreateOperationMetadata contains the user-provided fields for creating an operation. Read-only fields (id, account_id, workspace_id, created_at, profile_id) are excluded since they are set by the server. - `externalId?: string` External ID for the operation (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `variationId?: string` Optional explicit variation selection. Overrides the agent's variation_selection_mode. ### Returns - `Objective` - `data: ObjectiveData` - `agent?: Agent` Agent resource - `metadata: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: AgentSpec` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" | "AGENT_STATUS_DRAFT" | "AGENT_STATUS_PUBLISHED" | "AGENT_STATUS_ARCHIVED"` Status of the agent - `"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 - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description?: string` Description of the agent's purpose - `webhookEventsUrl?: string` The URL that Cadenya will send events for any objective assigned to the agent. - `info?: AgentInfo` AgentInfo contains simple information about an agent for display or quick reference - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `variationCount?: number` - `data?: 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?: string` The initial message sent to the agent. This becomes the first user message in the LLM chat history. - `parentObjectiveId?: string` A parent objective means the objective was spawned off using a separate agent to complete an objective - `secrets?: Array` Secrets that can be used in the headers for tool calls using the secret interpolation format. - `name?: string` - `value?: string` - `systemPrompt?: string` system_prompt is read-only, derived from the selected variation's prompt - `variation?: AgentVariation` AgentVariation resource - `metadata: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `spec: AgentVariationSpec` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig?: AgentVariationSpecCompactionConfig` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization?: CompactionConfigSummarizationStrategy` 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` 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 - `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%) - `constraints?: AgentVariationSpecConstraints` Execution constraints - `maxSubObjectives?: number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls?: number` The maximum number of tool calls that can be made. 0 means no limit. - `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` 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 - `prompt?: string` The system prompt for this variation - `toolSelection?: AgentVariationSpecToolSelection` Tool selection strategy - `assignedTools?: ToolSelectionAssignedTools` AssignedTools is used to indicate that the agent should only use the tools/tool sets that are explicitly assigned to it. Allow discovery is used when the agent thinks it needs to discover more tools. - `allowDiscovery?: boolean` - `autoDiscovery?: ToolSelectionAutoDiscovery` 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. - `hints?: Array` - `maxTools?: number` - `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. - `info?: AgentVariationInfo` AgentVariationInfo provides read-only summary information about a variation - `assignments?: Array` 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` 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` 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?: BareMetadata` 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?: Profile` 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). - `feedbackCount?: number` Total number of objective feedbacks received for this variation - `model?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `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. - `subAgentCount?: number` Number of sub-agents assigned to this variation - `toolCount?: number` Number of individual tools assigned to this variation - `toolSetCount?: number` Number of tool sets assigned to this variation - `metadata: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `status: ObjectiveStatus` - `state: "STATE_UNSPECIFIED" | "STATE_PENDING" | "STATE_RUNNING" | 3 more` - `"STATE_UNSPECIFIED"` - `"STATE_PENDING"` - `"STATE_RUNNING"` - `"STATE_COMPLETED"` - `"STATE_FAILED"` - `"STATE_CANCELLED"` - `message?: string` - `info?: ObjectiveInfo` ObjectiveInfo provides read-only aggregated statistics about an objective's execution - `callableTools?: Array` List of callable tools assigned to the agent for this objective Includes tools, agents, and cadenya-provided tools from the agent's configuration - `agent?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `createdBy?: Profile` 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). - `totalContextWindows?: number` Total number of context windows that this objective has generated - `totalEvents?: number` Total number of events generated during this objective's execution - `totalInputTokens?: number` Total input tokens consumed across all LLM completions across all context windows - `totalOutputTokens?: number` Total output tokens generated across all LLM completions across all context windows - `totalToolCalls?: number` Total number of tool calls made during execution - `lastFiveWindows?: Array` 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: ObjectiveContextWindowData` - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `metadata: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `info?: Info` - `createdBy?: Profile` 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). - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); const objective = await client.objectives.create({ agentId: 'agentId', data: {}, metadata: {}, }); console.log(objective.data); ``` #### Response ```json { "data": { "agent": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "status": "AGENT_STATUS_UNSPECIFIED", "variationSelectionMode": "VARIATION_SELECTION_MODE_UNSPECIFIED", "description": "description", "webhookEventsUrl": "webhookEventsUrl" }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "variationCount": 0 } }, "data": {}, "initialMessage": "initialMessage", "parentObjectiveId": "parentObjectiveId", "secrets": [ { "name": "name", "value": "value" } ], "systemPrompt": "systemPrompt", "variation": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "compactionConfig": { "summarization": { "instructions": "instructions" }, "toolResultClearing": { "preserveRecentResults": 0 }, "triggerThreshold": 0 }, "constraints": { "maxSubObjectives": 0, "maxToolCalls": 0 }, "description": "description", "enableEpisodicMemory": true, "episodicMemoryTtl": 0, "modelConfig": { "modelId": "modelId", "temperature": 0 }, "prompt": "prompt", "toolSelection": { "assignedTools": { "allowDiscovery": true }, "autoDiscovery": { "hints": [ "string" ], "maxTools": 0 } }, "weight": 0 }, "info": { "assignments": [ { "id": "id", "agent": { "id": "id", "name": "name" }, "tool": { "id": "id", "name": "name" }, "toolSet": { "id": "id", "name": "name" } } ], "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "feedbackCount": 0, "model": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "score": 0, "subAgentCount": 0, "toolCount": 0, "toolSetCount": 0 } } }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "status": { "state": "STATE_UNSPECIFIED", "message": "message" }, "info": { "callableTools": [ { "agent": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "cadenyaProvidedTool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "tool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } ], "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "totalContextWindows": 0, "totalEvents": 0, "totalInputTokens": 0, "totalOutputTokens": 0, "totalToolCalls": 0 }, "lastFiveWindows": [ { "data": { "completionTokens": 0, "objectiveId": "objectiveId", "previousWindowContinueInstructions": "previousWindowContinueInstructions", "promptTokens": 0, "sequence": 0 }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "objective": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } } ] } ``` ## Get an objective by ID `client.objectives.retrieve(stringid, RequestOptionsoptions?): Objective` **get** `/v1/objectives/{id}` Retrieves an objective by ID from the workspace ### Parameters - `id: string` ### Returns - `Objective` - `data: ObjectiveData` - `agent?: Agent` Agent resource - `metadata: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: AgentSpec` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" | "AGENT_STATUS_DRAFT" | "AGENT_STATUS_PUBLISHED" | "AGENT_STATUS_ARCHIVED"` Status of the agent - `"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 - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description?: string` Description of the agent's purpose - `webhookEventsUrl?: string` The URL that Cadenya will send events for any objective assigned to the agent. - `info?: AgentInfo` AgentInfo contains simple information about an agent for display or quick reference - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `variationCount?: number` - `data?: 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?: string` The initial message sent to the agent. This becomes the first user message in the LLM chat history. - `parentObjectiveId?: string` A parent objective means the objective was spawned off using a separate agent to complete an objective - `secrets?: Array` Secrets that can be used in the headers for tool calls using the secret interpolation format. - `name?: string` - `value?: string` - `systemPrompt?: string` system_prompt is read-only, derived from the selected variation's prompt - `variation?: AgentVariation` AgentVariation resource - `metadata: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `spec: AgentVariationSpec` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig?: AgentVariationSpecCompactionConfig` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization?: CompactionConfigSummarizationStrategy` 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` 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 - `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%) - `constraints?: AgentVariationSpecConstraints` Execution constraints - `maxSubObjectives?: number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls?: number` The maximum number of tool calls that can be made. 0 means no limit. - `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` 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 - `prompt?: string` The system prompt for this variation - `toolSelection?: AgentVariationSpecToolSelection` Tool selection strategy - `assignedTools?: ToolSelectionAssignedTools` AssignedTools is used to indicate that the agent should only use the tools/tool sets that are explicitly assigned to it. Allow discovery is used when the agent thinks it needs to discover more tools. - `allowDiscovery?: boolean` - `autoDiscovery?: ToolSelectionAutoDiscovery` 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. - `hints?: Array` - `maxTools?: number` - `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. - `info?: AgentVariationInfo` AgentVariationInfo provides read-only summary information about a variation - `assignments?: Array` 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` 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` 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?: BareMetadata` 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?: Profile` 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). - `feedbackCount?: number` Total number of objective feedbacks received for this variation - `model?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `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. - `subAgentCount?: number` Number of sub-agents assigned to this variation - `toolCount?: number` Number of individual tools assigned to this variation - `toolSetCount?: number` Number of tool sets assigned to this variation - `metadata: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `status: ObjectiveStatus` - `state: "STATE_UNSPECIFIED" | "STATE_PENDING" | "STATE_RUNNING" | 3 more` - `"STATE_UNSPECIFIED"` - `"STATE_PENDING"` - `"STATE_RUNNING"` - `"STATE_COMPLETED"` - `"STATE_FAILED"` - `"STATE_CANCELLED"` - `message?: string` - `info?: ObjectiveInfo` ObjectiveInfo provides read-only aggregated statistics about an objective's execution - `callableTools?: Array` List of callable tools assigned to the agent for this objective Includes tools, agents, and cadenya-provided tools from the agent's configuration - `agent?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `createdBy?: Profile` 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). - `totalContextWindows?: number` Total number of context windows that this objective has generated - `totalEvents?: number` Total number of events generated during this objective's execution - `totalInputTokens?: number` Total input tokens consumed across all LLM completions across all context windows - `totalOutputTokens?: number` Total output tokens generated across all LLM completions across all context windows - `totalToolCalls?: number` Total number of tool calls made during execution - `lastFiveWindows?: Array` 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: ObjectiveContextWindowData` - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `metadata: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `info?: Info` - `createdBy?: Profile` 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). - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); const objective = await client.objectives.retrieve('id'); console.log(objective.data); ``` #### Response ```json { "data": { "agent": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "status": "AGENT_STATUS_UNSPECIFIED", "variationSelectionMode": "VARIATION_SELECTION_MODE_UNSPECIFIED", "description": "description", "webhookEventsUrl": "webhookEventsUrl" }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "variationCount": 0 } }, "data": {}, "initialMessage": "initialMessage", "parentObjectiveId": "parentObjectiveId", "secrets": [ { "name": "name", "value": "value" } ], "systemPrompt": "systemPrompt", "variation": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "compactionConfig": { "summarization": { "instructions": "instructions" }, "toolResultClearing": { "preserveRecentResults": 0 }, "triggerThreshold": 0 }, "constraints": { "maxSubObjectives": 0, "maxToolCalls": 0 }, "description": "description", "enableEpisodicMemory": true, "episodicMemoryTtl": 0, "modelConfig": { "modelId": "modelId", "temperature": 0 }, "prompt": "prompt", "toolSelection": { "assignedTools": { "allowDiscovery": true }, "autoDiscovery": { "hints": [ "string" ], "maxTools": 0 } }, "weight": 0 }, "info": { "assignments": [ { "id": "id", "agent": { "id": "id", "name": "name" }, "tool": { "id": "id", "name": "name" }, "toolSet": { "id": "id", "name": "name" } } ], "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "feedbackCount": 0, "model": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "score": 0, "subAgentCount": 0, "toolCount": 0, "toolSetCount": 0 } } }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "status": { "state": "STATE_UNSPECIFIED", "message": "message" }, "info": { "callableTools": [ { "agent": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "cadenyaProvidedTool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "tool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } ], "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "totalContextWindows": 0, "totalEvents": 0, "totalInputTokens": 0, "totalOutputTokens": 0, "totalToolCalls": 0 }, "lastFiveWindows": [ { "data": { "completionTokens": 0, "objectiveId": "objectiveId", "previousWindowContinueInstructions": "previousWindowContinueInstructions", "promptTokens": 0, "sequence": 0 }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "objective": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } } ] } ``` ## List objective events `client.objectives.listEvents(stringobjectiveID, ObjectiveListEventsParamsquery?, RequestOptionsoptions?): CursorPagination` **get** `/v1/objectives/{objectiveId}/events` Lists all events for an objective ### Parameters - `objectiveID: string` - `query: ObjectiveListEventsParams` - `cursor?: string` Pagination cursor from previous response - `includeInfo?: boolean` When set to true you may use more of your alloted API rate-limit - `limit?: number` Maximum number of results to return - `sortOrder?: string` Sort order for results (asc or desc by creation time) - `windowId?: string` Optional context window ID to filter events by ### Returns - `ObjectiveListEventsResponse` - `data: ObjectiveEventData` - `assistantMessage?: AssistantMessage` - `content?: string` - `toolCalls?: Array` - `arguments?: string` - `functionName?: string` - `tool?: CallableTool` 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?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `contextWindowCompacted?: ContextWindowCompacted` - `messagesCompacted?: number` Number of messages that were compacted - `newContextWindow?: ObjectiveContextWindowData` The new context window created by this compaction - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `strategies?: Array` The strategies that were applied during this compaction - `summary?: string` The summary generated by the summarization strategy, if used. - `error?: ObjectiveError` - `message?: string` - `type?: string` - `subObjectiveCreated?: SubObjectiveCreated` - `metadata?: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `toolApprovalRequested?: ToolApprovalRequested` - `toolCallId?: string` The ID of the objective tool call record. Use this ID with the ApproveToolCall or DenyToolCall RPCs to approve or deny the tool call. - `toolApproved?: ToolApproved` - `toolCallId?: string` The ID of the objective tool call record that was approved via the ApproveToolCall RPC. - `toolCalled?: ToolCalled` - `toolCallId?: string` The ID of the objective tool call record that was executed. - `toolDenied?: ToolDenied` - `memo?: string` The memo provided by the reviewer when denying the tool call. This is passed to the agent to provide further instructions. - `toolCallId?: string` The ID of the objective tool call record that was denied via the DenyToolCall RPC. - `toolError?: ToolError` - `message?: string` - `toolCallId?: string` The ID of the objective tool call record that encountered an error during execution. - `toolResult?: ToolResult` - `content?: string` - `toolCallId?: string` - `type?: string` - `userMessage?: UserMessage` - `content?: string` - `metadata: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `contextWindowId?: string` - `info?: ObjectiveEventInfo` - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); // Automatically fetches more pages as needed. for await (const objectiveListEventsResponse of client.objectives.listEvents('objectiveId')) { console.log(objectiveListEventsResponse.data); } ``` #### Response ```json { "items": [ { "data": { "assistantMessage": { "content": "content", "toolCalls": [ { "arguments": "arguments", "functionName": "functionName", "tool": { "agent": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "cadenyaProvidedTool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "tool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } } ] }, "contextWindowCompacted": { "messagesCompacted": 0, "newContextWindow": { "completionTokens": 0, "objectiveId": "objectiveId", "previousWindowContinueInstructions": "previousWindowContinueInstructions", "promptTokens": 0, "sequence": 0 }, "strategies": [ "string" ], "summary": "summary" }, "error": { "message": "message", "type": "type" }, "subObjectiveCreated": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } }, "toolApprovalRequested": { "toolCallId": "toolCallId" }, "toolApproved": { "toolCallId": "toolCallId" }, "toolCalled": { "toolCallId": "toolCallId" }, "toolDenied": { "memo": "memo", "toolCallId": "toolCallId" }, "toolError": { "message": "message", "toolCallId": "toolCallId" }, "toolResult": { "content": "content", "toolCallId": "toolCallId" }, "type": "type", "userMessage": { "content": "content" } }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "contextWindowId": "contextWindowId", "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "objective": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } } ], "pagination": { "nextCursor": "nextCursor", "total": 0 } } ``` ## Continue an objective `client.objectives.continue(stringobjectiveID, ObjectiveContinueParamsbody, RequestOptionsoptions?): ObjectiveContinueResponse` **post** `/v1/objectives/{objectiveId}/continue` Continues an objective that has completed ### Parameters - `objectiveID: string` - `body: ObjectiveContinueParams` - `enqueue?: boolean` When set to true, the message will be enqueued for when the agent loop is available to process it. - `message?: string` The message to continue an objective that has completed (or you are enqueing) - `secrets?: Array` Secrets that should be included with the message. Helpful for when you need to update secrets on the objective (IE: A secret expires and needs to be refreshed) - `name?: string` - `value?: string` ### Returns - `ObjectiveContinueResponse` - `data: ObjectiveEventData` - `assistantMessage?: AssistantMessage` - `content?: string` - `toolCalls?: Array` - `arguments?: string` - `functionName?: string` - `tool?: CallableTool` 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?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `contextWindowCompacted?: ContextWindowCompacted` - `messagesCompacted?: number` Number of messages that were compacted - `newContextWindow?: ObjectiveContextWindowData` The new context window created by this compaction - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `strategies?: Array` The strategies that were applied during this compaction - `summary?: string` The summary generated by the summarization strategy, if used. - `error?: ObjectiveError` - `message?: string` - `type?: string` - `subObjectiveCreated?: SubObjectiveCreated` - `metadata?: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `toolApprovalRequested?: ToolApprovalRequested` - `toolCallId?: string` The ID of the objective tool call record. Use this ID with the ApproveToolCall or DenyToolCall RPCs to approve or deny the tool call. - `toolApproved?: ToolApproved` - `toolCallId?: string` The ID of the objective tool call record that was approved via the ApproveToolCall RPC. - `toolCalled?: ToolCalled` - `toolCallId?: string` The ID of the objective tool call record that was executed. - `toolDenied?: ToolDenied` - `memo?: string` The memo provided by the reviewer when denying the tool call. This is passed to the agent to provide further instructions. - `toolCallId?: string` The ID of the objective tool call record that was denied via the DenyToolCall RPC. - `toolError?: ToolError` - `message?: string` - `toolCallId?: string` The ID of the objective tool call record that encountered an error during execution. - `toolResult?: ToolResult` - `content?: string` - `toolCallId?: string` - `type?: string` - `userMessage?: UserMessage` - `content?: string` - `metadata: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `contextWindowId?: string` - `info?: ObjectiveEventInfo` - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); const response = await client.objectives.continue('objectiveId'); console.log(response.data); ``` #### Response ```json { "data": { "assistantMessage": { "content": "content", "toolCalls": [ { "arguments": "arguments", "functionName": "functionName", "tool": { "agent": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "cadenyaProvidedTool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "tool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } } ] }, "contextWindowCompacted": { "messagesCompacted": 0, "newContextWindow": { "completionTokens": 0, "objectiveId": "objectiveId", "previousWindowContinueInstructions": "previousWindowContinueInstructions", "promptTokens": 0, "sequence": 0 }, "strategies": [ "string" ], "summary": "summary" }, "error": { "message": "message", "type": "type" }, "subObjectiveCreated": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } }, "toolApprovalRequested": { "toolCallId": "toolCallId" }, "toolApproved": { "toolCallId": "toolCallId" }, "toolCalled": { "toolCallId": "toolCallId" }, "toolDenied": { "memo": "memo", "toolCallId": "toolCallId" }, "toolError": { "message": "message", "toolCallId": "toolCallId" }, "toolResult": { "content": "content", "toolCallId": "toolCallId" }, "type": "type", "userMessage": { "content": "content" } }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "contextWindowId": "contextWindowId", "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "objective": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } } ``` ## Cancel an objective `client.objectives.cancel(stringobjectiveID, ObjectiveCancelParamsbody, RequestOptionsoptions?): Objective` **post** `/v1/objectives/{objectiveId}/cancel` Cancels a running or pending objective. The objective's state will be set to STATE_CANCELLED. ### Parameters - `objectiveID: string` - `body: ObjectiveCancelParams` - `reason?: string` Optional reason for cancellation ### Returns - `Objective` - `data: ObjectiveData` - `agent?: Agent` Agent resource - `metadata: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: AgentSpec` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" | "AGENT_STATUS_DRAFT" | "AGENT_STATUS_PUBLISHED" | "AGENT_STATUS_ARCHIVED"` Status of the agent - `"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 - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description?: string` Description of the agent's purpose - `webhookEventsUrl?: string` The URL that Cadenya will send events for any objective assigned to the agent. - `info?: AgentInfo` AgentInfo contains simple information about an agent for display or quick reference - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `variationCount?: number` - `data?: 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?: string` The initial message sent to the agent. This becomes the first user message in the LLM chat history. - `parentObjectiveId?: string` A parent objective means the objective was spawned off using a separate agent to complete an objective - `secrets?: Array` Secrets that can be used in the headers for tool calls using the secret interpolation format. - `name?: string` - `value?: string` - `systemPrompt?: string` system_prompt is read-only, derived from the selected variation's prompt - `variation?: AgentVariation` AgentVariation resource - `metadata: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `spec: AgentVariationSpec` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig?: AgentVariationSpecCompactionConfig` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization?: CompactionConfigSummarizationStrategy` 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` 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 - `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%) - `constraints?: AgentVariationSpecConstraints` Execution constraints - `maxSubObjectives?: number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls?: number` The maximum number of tool calls that can be made. 0 means no limit. - `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` 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 - `prompt?: string` The system prompt for this variation - `toolSelection?: AgentVariationSpecToolSelection` Tool selection strategy - `assignedTools?: ToolSelectionAssignedTools` AssignedTools is used to indicate that the agent should only use the tools/tool sets that are explicitly assigned to it. Allow discovery is used when the agent thinks it needs to discover more tools. - `allowDiscovery?: boolean` - `autoDiscovery?: ToolSelectionAutoDiscovery` 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. - `hints?: Array` - `maxTools?: number` - `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. - `info?: AgentVariationInfo` AgentVariationInfo provides read-only summary information about a variation - `assignments?: Array` 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` 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` 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?: BareMetadata` 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?: Profile` 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). - `feedbackCount?: number` Total number of objective feedbacks received for this variation - `model?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `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. - `subAgentCount?: number` Number of sub-agents assigned to this variation - `toolCount?: number` Number of individual tools assigned to this variation - `toolSetCount?: number` Number of tool sets assigned to this variation - `metadata: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `status: ObjectiveStatus` - `state: "STATE_UNSPECIFIED" | "STATE_PENDING" | "STATE_RUNNING" | 3 more` - `"STATE_UNSPECIFIED"` - `"STATE_PENDING"` - `"STATE_RUNNING"` - `"STATE_COMPLETED"` - `"STATE_FAILED"` - `"STATE_CANCELLED"` - `message?: string` - `info?: ObjectiveInfo` ObjectiveInfo provides read-only aggregated statistics about an objective's execution - `callableTools?: Array` List of callable tools assigned to the agent for this objective Includes tools, agents, and cadenya-provided tools from the agent's configuration - `agent?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `createdBy?: Profile` 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). - `totalContextWindows?: number` Total number of context windows that this objective has generated - `totalEvents?: number` Total number of events generated during this objective's execution - `totalInputTokens?: number` Total input tokens consumed across all LLM completions across all context windows - `totalOutputTokens?: number` Total output tokens generated across all LLM completions across all context windows - `totalToolCalls?: number` Total number of tool calls made during execution - `lastFiveWindows?: Array` 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: ObjectiveContextWindowData` - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `metadata: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `info?: Info` - `createdBy?: Profile` 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). - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); const objective = await client.objectives.cancel('objectiveId'); console.log(objective.data); ``` #### Response ```json { "data": { "agent": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "status": "AGENT_STATUS_UNSPECIFIED", "variationSelectionMode": "VARIATION_SELECTION_MODE_UNSPECIFIED", "description": "description", "webhookEventsUrl": "webhookEventsUrl" }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "variationCount": 0 } }, "data": {}, "initialMessage": "initialMessage", "parentObjectiveId": "parentObjectiveId", "secrets": [ { "name": "name", "value": "value" } ], "systemPrompt": "systemPrompt", "variation": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "compactionConfig": { "summarization": { "instructions": "instructions" }, "toolResultClearing": { "preserveRecentResults": 0 }, "triggerThreshold": 0 }, "constraints": { "maxSubObjectives": 0, "maxToolCalls": 0 }, "description": "description", "enableEpisodicMemory": true, "episodicMemoryTtl": 0, "modelConfig": { "modelId": "modelId", "temperature": 0 }, "prompt": "prompt", "toolSelection": { "assignedTools": { "allowDiscovery": true }, "autoDiscovery": { "hints": [ "string" ], "maxTools": 0 } }, "weight": 0 }, "info": { "assignments": [ { "id": "id", "agent": { "id": "id", "name": "name" }, "tool": { "id": "id", "name": "name" }, "toolSet": { "id": "id", "name": "name" } } ], "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "feedbackCount": 0, "model": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "score": 0, "subAgentCount": 0, "toolCount": 0, "toolSetCount": 0 } } }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "status": { "state": "STATE_UNSPECIFIED", "message": "message" }, "info": { "callableTools": [ { "agent": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "cadenyaProvidedTool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "tool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } ], "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "totalContextWindows": 0, "totalEvents": 0, "totalInputTokens": 0, "totalOutputTokens": 0, "totalToolCalls": 0 }, "lastFiveWindows": [ { "data": { "completionTokens": 0, "objectiveId": "objectiveId", "previousWindowContinueInstructions": "previousWindowContinueInstructions", "promptTokens": 0, "sequence": 0 }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "objective": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } } ] } ``` ## Compact an objective `client.objectives.compact(stringobjectiveID, ObjectiveCompactParamsbody, RequestOptionsoptions?): ObjectiveCompactResponse` **post** `/v1/objectives/{objectiveId}/compact` Triggers compaction on a running objective. Optionally override the variation's compaction config. ### Parameters - `objectiveID: string` - `body: ObjectiveCompactParams` - `compactionConfig?: AgentVariationSpecCompactionConfig` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization?: CompactionConfigSummarizationStrategy` 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` 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 - `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%) ### Returns - `ObjectiveCompactResponse` Compact objective response - `contextWindow?: ObjectiveContextWindowData` The new context window created by the compaction - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); const response = await client.objectives.compact('objectiveId'); console.log(response.contextWindow); ``` #### Response ```json { "contextWindow": { "completionTokens": 0, "objectiveId": "objectiveId", "previousWindowContinueInstructions": "previousWindowContinueInstructions", "promptTokens": 0, "sequence": 0 } } ``` ## List objective context windows `client.objectives.listContextWindows(stringobjectiveID, ObjectiveListContextWindowsParamsquery?, RequestOptionsoptions?): CursorPagination` **get** `/v1/objectives/{objectiveId}/context_windows` Read-only list of the last five windows of execution for this objective, ordered by most recent first ### Parameters - `objectiveID: string` - `query: ObjectiveListContextWindowsParams` - `cursor?: string` Pagination cursor from previous response - `includeInfo?: boolean` When set to true you may use more of your alloted API rate-limit - `limit?: number` Maximum number of results to return ### Returns - `ObjectiveContextWindow` 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: ObjectiveContextWindowData` - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `metadata: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `info?: Info` - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); // Automatically fetches more pages as needed. for await (const objectiveContextWindow of client.objectives.listContextWindows('objectiveId')) { console.log(objectiveContextWindow.data); } ``` #### Response ```json { "items": [ { "data": { "completionTokens": 0, "objectiveId": "objectiveId", "previousWindowContinueInstructions": "previousWindowContinueInstructions", "promptTokens": 0, "sequence": 0 }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "objective": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } } ], "pagination": { "nextCursor": "nextCursor", "total": 0 } } ``` ## Domain Types ### Assistant Message - `AssistantMessage` - `content?: string` - `toolCalls?: Array` - `arguments?: string` - `functionName?: string` - `tool?: CallableTool` 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?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) ### Assistant Tool Call - `AssistantToolCall` - `arguments?: string` - `functionName?: string` - `tool?: CallableTool` 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?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) ### Callable Tool - `CallableTool` 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?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) ### Context Window Compacted - `ContextWindowCompacted` - `messagesCompacted?: number` Number of messages that were compacted - `newContextWindow?: ObjectiveContextWindowData` The new context window created by this compaction - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `strategies?: Array` The strategies that were applied during this compaction - `summary?: string` The summary generated by the summarization strategy, if used. ### Objective - `Objective` - `data: ObjectiveData` - `agent?: Agent` Agent resource - `metadata: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: AgentSpec` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" | "AGENT_STATUS_DRAFT" | "AGENT_STATUS_PUBLISHED" | "AGENT_STATUS_ARCHIVED"` Status of the agent - `"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 - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description?: string` Description of the agent's purpose - `webhookEventsUrl?: string` The URL that Cadenya will send events for any objective assigned to the agent. - `info?: AgentInfo` AgentInfo contains simple information about an agent for display or quick reference - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `variationCount?: number` - `data?: 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?: string` The initial message sent to the agent. This becomes the first user message in the LLM chat history. - `parentObjectiveId?: string` A parent objective means the objective was spawned off using a separate agent to complete an objective - `secrets?: Array` Secrets that can be used in the headers for tool calls using the secret interpolation format. - `name?: string` - `value?: string` - `systemPrompt?: string` system_prompt is read-only, derived from the selected variation's prompt - `variation?: AgentVariation` AgentVariation resource - `metadata: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `spec: AgentVariationSpec` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig?: AgentVariationSpecCompactionConfig` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization?: CompactionConfigSummarizationStrategy` 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` 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 - `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%) - `constraints?: AgentVariationSpecConstraints` Execution constraints - `maxSubObjectives?: number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls?: number` The maximum number of tool calls that can be made. 0 means no limit. - `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` 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 - `prompt?: string` The system prompt for this variation - `toolSelection?: AgentVariationSpecToolSelection` Tool selection strategy - `assignedTools?: ToolSelectionAssignedTools` AssignedTools is used to indicate that the agent should only use the tools/tool sets that are explicitly assigned to it. Allow discovery is used when the agent thinks it needs to discover more tools. - `allowDiscovery?: boolean` - `autoDiscovery?: ToolSelectionAutoDiscovery` 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. - `hints?: Array` - `maxTools?: number` - `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. - `info?: AgentVariationInfo` AgentVariationInfo provides read-only summary information about a variation - `assignments?: Array` 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` 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` 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?: BareMetadata` 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?: Profile` 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). - `feedbackCount?: number` Total number of objective feedbacks received for this variation - `model?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `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. - `subAgentCount?: number` Number of sub-agents assigned to this variation - `toolCount?: number` Number of individual tools assigned to this variation - `toolSetCount?: number` Number of tool sets assigned to this variation - `metadata: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `status: ObjectiveStatus` - `state: "STATE_UNSPECIFIED" | "STATE_PENDING" | "STATE_RUNNING" | 3 more` - `"STATE_UNSPECIFIED"` - `"STATE_PENDING"` - `"STATE_RUNNING"` - `"STATE_COMPLETED"` - `"STATE_FAILED"` - `"STATE_CANCELLED"` - `message?: string` - `info?: ObjectiveInfo` ObjectiveInfo provides read-only aggregated statistics about an objective's execution - `callableTools?: Array` List of callable tools assigned to the agent for this objective Includes tools, agents, and cadenya-provided tools from the agent's configuration - `agent?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `createdBy?: Profile` 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). - `totalContextWindows?: number` Total number of context windows that this objective has generated - `totalEvents?: number` Total number of events generated during this objective's execution - `totalInputTokens?: number` Total input tokens consumed across all LLM completions across all context windows - `totalOutputTokens?: number` Total output tokens generated across all LLM completions across all context windows - `totalToolCalls?: number` Total number of tool calls made during execution - `lastFiveWindows?: Array` 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: ObjectiveContextWindowData` - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `metadata: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `info?: Info` - `createdBy?: Profile` 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). - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Objective Context Window - `ObjectiveContextWindow` 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: ObjectiveContextWindowData` - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `metadata: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `info?: Info` - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Objective Context Window Data - `ObjectiveContextWindowData` - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. ### Objective Data - `ObjectiveData` - `agent?: Agent` Agent resource - `metadata: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: AgentSpec` Agent specification (user-provided configuration) - `status: "AGENT_STATUS_UNSPECIFIED" | "AGENT_STATUS_DRAFT" | "AGENT_STATUS_PUBLISHED" | "AGENT_STATUS_ARCHIVED"` Status of the agent - `"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 - `"VARIATION_SELECTION_MODE_UNSPECIFIED"` - `"VARIATION_SELECTION_MODE_RANDOM"` - `"VARIATION_SELECTION_MODE_WEIGHTED"` - `description?: string` Description of the agent's purpose - `webhookEventsUrl?: string` The URL that Cadenya will send events for any objective assigned to the agent. - `info?: AgentInfo` AgentInfo contains simple information about an agent for display or quick reference - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `variationCount?: number` - `data?: 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?: string` The initial message sent to the agent. This becomes the first user message in the LLM chat history. - `parentObjectiveId?: string` A parent objective means the objective was spawned off using a separate agent to complete an objective - `secrets?: Array` Secrets that can be used in the headers for tool calls using the secret interpolation format. - `name?: string` - `value?: string` - `systemPrompt?: string` system_prompt is read-only, derived from the selected variation's prompt - `variation?: AgentVariation` AgentVariation resource - `metadata: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `spec: AgentVariationSpec` AgentVariationSpec defines the operational configuration for a variation - `compactionConfig?: AgentVariationSpecCompactionConfig` CompactionConfig defines how context window compaction behaves for objectives using this variation. - `summarization?: CompactionConfigSummarizationStrategy` 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` 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 - `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%) - `constraints?: AgentVariationSpecConstraints` Execution constraints - `maxSubObjectives?: number` The maximum number of sub-objectives that can be created. 0 means no limit. - `maxToolCalls?: number` The maximum number of tool calls that can be made. 0 means no limit. - `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` 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 - `prompt?: string` The system prompt for this variation - `toolSelection?: AgentVariationSpecToolSelection` Tool selection strategy - `assignedTools?: ToolSelectionAssignedTools` AssignedTools is used to indicate that the agent should only use the tools/tool sets that are explicitly assigned to it. Allow discovery is used when the agent thinks it needs to discover more tools. - `allowDiscovery?: boolean` - `autoDiscovery?: ToolSelectionAutoDiscovery` 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. - `hints?: Array` - `maxTools?: number` - `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. - `info?: AgentVariationInfo` AgentVariationInfo provides read-only summary information about a variation - `assignments?: Array` 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` 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` 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?: BareMetadata` 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?: Profile` 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). - `feedbackCount?: number` Total number of objective feedbacks received for this variation - `model?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `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. - `subAgentCount?: number` Number of sub-agents assigned to this variation - `toolCount?: number` Number of individual tools assigned to this variation - `toolSetCount?: number` Number of tool sets assigned to this variation ### Objective Data Secret - `ObjectiveDataSecret` - `name?: string` - `value?: string` ### Objective Error - `ObjectiveError` - `message?: string` - `type?: string` ### Objective Event Data - `ObjectiveEventData` - `assistantMessage?: AssistantMessage` - `content?: string` - `toolCalls?: Array` - `arguments?: string` - `functionName?: string` - `tool?: CallableTool` 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?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `contextWindowCompacted?: ContextWindowCompacted` - `messagesCompacted?: number` Number of messages that were compacted - `newContextWindow?: ObjectiveContextWindowData` The new context window created by this compaction - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `strategies?: Array` The strategies that were applied during this compaction - `summary?: string` The summary generated by the summarization strategy, if used. - `error?: ObjectiveError` - `message?: string` - `type?: string` - `subObjectiveCreated?: SubObjectiveCreated` - `metadata?: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `toolApprovalRequested?: ToolApprovalRequested` - `toolCallId?: string` The ID of the objective tool call record. Use this ID with the ApproveToolCall or DenyToolCall RPCs to approve or deny the tool call. - `toolApproved?: ToolApproved` - `toolCallId?: string` The ID of the objective tool call record that was approved via the ApproveToolCall RPC. - `toolCalled?: ToolCalled` - `toolCallId?: string` The ID of the objective tool call record that was executed. - `toolDenied?: ToolDenied` - `memo?: string` The memo provided by the reviewer when denying the tool call. This is passed to the agent to provide further instructions. - `toolCallId?: string` The ID of the objective tool call record that was denied via the DenyToolCall RPC. - `toolError?: ToolError` - `message?: string` - `toolCallId?: string` The ID of the objective tool call record that encountered an error during execution. - `toolResult?: ToolResult` - `content?: string` - `toolCallId?: string` - `type?: string` - `userMessage?: UserMessage` - `content?: string` ### Objective Event Info - `ObjectiveEventInfo` - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `objective?: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} ### Objective Event Webhook Data - `ObjectiveEventWebhookData` The envelope for an objective event webhook delivery. Contains timestamp, event type, and the webhook data payload. - `data: Data` The webhook data payload with flat top-level keys for agent, variation, objective, and event. - `agent: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `agentVariation: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `objective: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `objectiveEvent: ObjectiveEvent` - `data: ObjectiveEventData` - `assistantMessage?: AssistantMessage` - `content?: string` - `toolCalls?: Array` - `arguments?: string` - `functionName?: string` - `tool?: CallableTool` 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?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `contextWindowCompacted?: ContextWindowCompacted` - `messagesCompacted?: number` Number of messages that were compacted - `newContextWindow?: ObjectiveContextWindowData` The new context window created by this compaction - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `strategies?: Array` The strategies that were applied during this compaction - `summary?: string` The summary generated by the summarization strategy, if used. - `error?: ObjectiveError` - `message?: string` - `type?: string` - `subObjectiveCreated?: SubObjectiveCreated` - `metadata?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `toolApprovalRequested?: ToolApprovalRequested` - `toolCallId?: string` The ID of the objective tool call record. Use this ID with the ApproveToolCall or DenyToolCall RPCs to approve or deny the tool call. - `toolApproved?: ToolApproved` - `toolCallId?: string` The ID of the objective tool call record that was approved via the ApproveToolCall RPC. - `toolCalled?: ToolCalled` - `toolCallId?: string` The ID of the objective tool call record that was executed. - `toolDenied?: ToolDenied` - `memo?: string` The memo provided by the reviewer when denying the tool call. This is passed to the agent to provide further instructions. - `toolCallId?: string` The ID of the objective tool call record that was denied via the DenyToolCall RPC. - `toolError?: ToolError` - `message?: string` - `toolCallId?: string` The ID of the objective tool call record that encountered an error during execution. - `toolResult?: ToolResult` - `content?: string` - `toolCallId?: string` - `type?: string` - `userMessage?: UserMessage` - `content?: string` - `metadata: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `contextWindowId?: string` - `info?: ObjectiveEventInfo` - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `timestamp: string` - `type: string` The event type, prefixed with objective_event. (e.g., objective_event.tool_result) ### Objective Info - `ObjectiveInfo` ObjectiveInfo provides read-only aggregated statistics about an objective's execution - `callableTools?: Array` List of callable tools assigned to the agent for this objective Includes tools, agents, and cadenya-provided tools from the agent's configuration - `agent?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `totalContextWindows?: number` Total number of context windows that this objective has generated - `totalEvents?: number` Total number of events generated during this objective's execution - `totalInputTokens?: number` Total input tokens consumed across all LLM completions across all context windows - `totalOutputTokens?: number` Total output tokens generated across all LLM completions across all context windows - `totalToolCalls?: number` Total number of tool calls made during execution ### Objective Status - `ObjectiveStatus` - `state: "STATE_UNSPECIFIED" | "STATE_PENDING" | "STATE_RUNNING" | 3 more` - `"STATE_UNSPECIFIED"` - `"STATE_PENDING"` - `"STATE_RUNNING"` - `"STATE_COMPLETED"` - `"STATE_FAILED"` - `"STATE_CANCELLED"` - `message?: string` ### Sub Objective Created - `SubObjectiveCreated` - `metadata?: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} ### Tool Approval Requested - `ToolApprovalRequested` - `toolCallId?: string` The ID of the objective tool call record. Use this ID with the ApproveToolCall or DenyToolCall RPCs to approve or deny the tool call. ### Tool Approved - `ToolApproved` - `toolCallId?: string` The ID of the objective tool call record that was approved via the ApproveToolCall RPC. ### Tool Called - `ToolCalled` - `toolCallId?: string` The ID of the objective tool call record that was executed. ### Tool Denied - `ToolDenied` - `memo?: string` The memo provided by the reviewer when denying the tool call. This is passed to the agent to provide further instructions. - `toolCallId?: string` The ID of the objective tool call record that was denied via the DenyToolCall RPC. ### Tool Error - `ToolError` - `message?: string` - `toolCallId?: string` The ID of the objective tool call record that encountered an error during execution. ### Tool Result - `ToolResult` - `content?: string` - `toolCallId?: string` ### User Message - `UserMessage` - `content?: string` ### Objective List Events Response - `ObjectiveListEventsResponse` - `data: ObjectiveEventData` - `assistantMessage?: AssistantMessage` - `content?: string` - `toolCalls?: Array` - `arguments?: string` - `functionName?: string` - `tool?: CallableTool` 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?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `contextWindowCompacted?: ContextWindowCompacted` - `messagesCompacted?: number` Number of messages that were compacted - `newContextWindow?: ObjectiveContextWindowData` The new context window created by this compaction - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `strategies?: Array` The strategies that were applied during this compaction - `summary?: string` The summary generated by the summarization strategy, if used. - `error?: ObjectiveError` - `message?: string` - `type?: string` - `subObjectiveCreated?: SubObjectiveCreated` - `metadata?: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `toolApprovalRequested?: ToolApprovalRequested` - `toolCallId?: string` The ID of the objective tool call record. Use this ID with the ApproveToolCall or DenyToolCall RPCs to approve or deny the tool call. - `toolApproved?: ToolApproved` - `toolCallId?: string` The ID of the objective tool call record that was approved via the ApproveToolCall RPC. - `toolCalled?: ToolCalled` - `toolCallId?: string` The ID of the objective tool call record that was executed. - `toolDenied?: ToolDenied` - `memo?: string` The memo provided by the reviewer when denying the tool call. This is passed to the agent to provide further instructions. - `toolCallId?: string` The ID of the objective tool call record that was denied via the DenyToolCall RPC. - `toolError?: ToolError` - `message?: string` - `toolCallId?: string` The ID of the objective tool call record that encountered an error during execution. - `toolResult?: ToolResult` - `content?: string` - `toolCallId?: string` - `type?: string` - `userMessage?: UserMessage` - `content?: string` - `metadata: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `contextWindowId?: string` - `info?: ObjectiveEventInfo` - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Objective Continue Response - `ObjectiveContinueResponse` - `data: ObjectiveEventData` - `assistantMessage?: AssistantMessage` - `content?: string` - `toolCalls?: Array` - `arguments?: string` - `functionName?: string` - `tool?: CallableTool` 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?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `contextWindowCompacted?: ContextWindowCompacted` - `messagesCompacted?: number` Number of messages that were compacted - `newContextWindow?: ObjectiveContextWindowData` The new context window created by this compaction - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. - `strategies?: Array` The strategies that were applied during this compaction - `summary?: string` The summary generated by the summarization strategy, if used. - `error?: ObjectiveError` - `message?: string` - `type?: string` - `subObjectiveCreated?: SubObjectiveCreated` - `metadata?: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `toolApprovalRequested?: ToolApprovalRequested` - `toolCallId?: string` The ID of the objective tool call record. Use this ID with the ApproveToolCall or DenyToolCall RPCs to approve or deny the tool call. - `toolApproved?: ToolApproved` - `toolCallId?: string` The ID of the objective tool call record that was approved via the ApproveToolCall RPC. - `toolCalled?: ToolCalled` - `toolCallId?: string` The ID of the objective tool call record that was executed. - `toolDenied?: ToolDenied` - `memo?: string` The memo provided by the reviewer when denying the tool call. This is passed to the agent to provide further instructions. - `toolCallId?: string` The ID of the objective tool call record that was denied via the DenyToolCall RPC. - `toolError?: ToolError` - `message?: string` - `toolCallId?: string` The ID of the objective tool call record that encountered an error during execution. - `toolResult?: ToolResult` - `content?: string` - `toolCallId?: string` - `type?: string` - `userMessage?: UserMessage` - `content?: string` - `metadata: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) - `contextWindowId?: string` - `info?: ObjectiveEventInfo` - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Objective Compact Response - `ObjectiveCompactResponse` Compact objective response - `contextWindow?: ObjectiveContextWindowData` The new context window created by the compaction - `completionTokens?: number` A calculated value for how many completion tokens (output tokens) have been used in this context window - `objectiveId?: string` The objective's ID that this window belongs to - `previousWindowContinueInstructions?: string` The instructions for this window to continue from a previous window's chat history. - `promptTokens?: number` A calculated value for how many prompt tokens (input tokens) have been used in this context window - `sequence?: number` sequence is a numeric representation of which context window this is. Sequences are useful to perform a max(sequence) on in order to calculate how many context windows an objective has. # Tools ## List objective tools `client.objectives.tools.list(stringobjectiveID, ToolListParamsquery?, RequestOptionsoptions?): CursorPagination` **get** `/v1/objectives/{objectiveId}/tools` Lists all tools that were assigned to an objective ### Parameters - `objectiveID: string` - `query: ToolListParams` - `cursor?: string` Pagination cursor from previous response - `limit?: number` Maximum number of results to return ### Returns - `ObjectiveTool` ObjectiveTool represents a tool that was assigned to an objective. - `metadata: BareMetadata` 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). - `snapshot?: Tool` 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: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ToolSpec` - `config: ToolSpecConfig` 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. - `http?: ConfigHTTP` - `requestMethod: "GET" | "POST" | "PUT" | 2 more` - `"GET"` - `"POST"` - `"PUT"` - `"PATCH"` - `"DELETE"` - `headers?: Record` - `path?: string` - `query?: string` - `requestBodyContentType?: string` - `requestBodyTemplate?: string` These are only used when the request method is a POST, PUT, or PATCH - `toolName?: string` The tool name (commonly an "operation id" in OpenAPI specs) to call on the HTTP adapter. This is used to match the tool spec to the correct endpoint on the HTTP adapter. it will be derived from the name of the tool if not provided. - `mcp?: ConfigMcp` - `toolDescription?: string` - `toolName?: string` - `toolTitle?: string` - `description: string` - `parameters: Record` - `status: "TOOL_STATUS_UNSPECIFIED" | "TOOL_STATUS_AVAILABLE" | "TOOL_STATUS_FILTERED" | "TOOL_STATUS_ARCHIVED"` - `"TOOL_STATUS_UNSPECIFIED"` - `"TOOL_STATUS_AVAILABLE"` - `"TOOL_STATUS_FILTERED"` - `"TOOL_STATUS_ARCHIVED"` - `requiresApproval?: boolean` - `info?: ToolInfo` - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `toolSet?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); // Automatically fetches more pages as needed. for await (const objectiveTool of client.objectives.tools.list('objectiveId')) { console.log(objectiveTool.metadata); } ``` #### Response ```json { "items": [ { "metadata": { "id": "id", "name": "name" }, "snapshot": { "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "config": { "http": { "requestMethod": "GET", "headers": { "foo": "string" }, "path": "path", "query": "query", "requestBodyContentType": "requestBodyContentType", "requestBodyTemplate": "requestBodyTemplate", "toolName": "toolName" }, "mcp": { "toolDescription": "toolDescription", "toolName": "toolName", "toolTitle": "toolTitle" } }, "description": "description", "parameters": { "foo": "bar" }, "status": "TOOL_STATUS_UNSPECIFIED", "requiresApproval": true }, "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "toolSet": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } } } ], "pagination": { "nextCursor": "nextCursor", "total": 0 } } ``` ## Domain Types ### Objective Tool - `ObjectiveTool` ObjectiveTool represents a tool that was assigned to an objective. - `metadata: BareMetadata` 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). - `snapshot?: Tool` 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: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ToolSpec` - `config: ToolSpecConfig` 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. - `http?: ConfigHTTP` - `requestMethod: "GET" | "POST" | "PUT" | 2 more` - `"GET"` - `"POST"` - `"PUT"` - `"PATCH"` - `"DELETE"` - `headers?: Record` - `path?: string` - `query?: string` - `requestBodyContentType?: string` - `requestBodyTemplate?: string` These are only used when the request method is a POST, PUT, or PATCH - `toolName?: string` The tool name (commonly an "operation id" in OpenAPI specs) to call on the HTTP adapter. This is used to match the tool spec to the correct endpoint on the HTTP adapter. it will be derived from the name of the tool if not provided. - `mcp?: ConfigMcp` - `toolDescription?: string` - `toolName?: string` - `toolTitle?: string` - `description: string` - `parameters: Record` - `status: "TOOL_STATUS_UNSPECIFIED" | "TOOL_STATUS_AVAILABLE" | "TOOL_STATUS_FILTERED" | "TOOL_STATUS_ARCHIVED"` - `"TOOL_STATUS_UNSPECIFIED"` - `"TOOL_STATUS_AVAILABLE"` - `"TOOL_STATUS_FILTERED"` - `"TOOL_STATUS_ARCHIVED"` - `requiresApproval?: boolean` - `info?: ToolInfo` - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `toolSet?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) # Tool Calls ## List objective tool calls `client.objectives.toolCalls.list(stringobjectiveID, ToolCallListParamsquery?, RequestOptionsoptions?): CursorPagination` **get** `/v1/objectives/{objectiveId}/tool_calls` Lists all tool calls for an objective ### Parameters - `objectiveID: string` - `query: ToolCallListParams` - `cursor?: string` Pagination cursor from previous response - `includeInfo?: boolean` When set to true you may use more of your alloted API rate-limit - `limit?: number` Maximum number of results to return - `status?: "TOOL_CALL_STATUS_UNSPECIFIED" | "TOOL_CALL_STATUS_AUTO_APPROVED" | "TOOL_CALL_STATUS_WAITING_FOR_APPROVAL" | 2 more` Filter by tool call status - `"TOOL_CALL_STATUS_UNSPECIFIED"` - `"TOOL_CALL_STATUS_AUTO_APPROVED"` - `"TOOL_CALL_STATUS_WAITING_FOR_APPROVAL"` - `"TOOL_CALL_STATUS_APPROVED"` - `"TOOL_CALL_STATUS_DENIED"` ### Returns - `ObjectiveToolCall` 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: ObjectiveToolCallData` - `callable: CallableTool` 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?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `arguments?: Record` The arguments passed to the tool - `memo?: string` A memo supplied by the reviewer when denying the tool call - `result?: string` The result content returned by the tool after execution - `statusChangedBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `metadata: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `status: "TOOL_CALL_STATUS_UNSPECIFIED" | "TOOL_CALL_STATUS_AUTO_APPROVED" | "TOOL_CALL_STATUS_WAITING_FOR_APPROVAL" | 2 more` Current status of the tool call - `"TOOL_CALL_STATUS_UNSPECIFIED"` - `"TOOL_CALL_STATUS_AUTO_APPROVED"` - `"TOOL_CALL_STATUS_WAITING_FOR_APPROVAL"` - `"TOOL_CALL_STATUS_APPROVED"` - `"TOOL_CALL_STATUS_DENIED"` - `executionStatus?: "TOOL_CALL_EXECUTION_STATUS_UNSPECIFIED" | "TOOL_CALL_EXECUTION_STATUS_PENDING" | "TOOL_CALL_EXECUTION_STATUS_RUNNING" | 2 more` - `"TOOL_CALL_EXECUTION_STATUS_UNSPECIFIED"` - `"TOOL_CALL_EXECUTION_STATUS_PENDING"` - `"TOOL_CALL_EXECUTION_STATUS_RUNNING"` - `"TOOL_CALL_EXECUTION_STATUS_COMPLETED"` - `"TOOL_CALL_EXECUTION_STATUS_ERRORED"` - `info?: ObjectiveToolCallInfo` - `createdBy?: Profile` 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). - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); // Automatically fetches more pages as needed. for await (const objectiveToolCall of client.objectives.toolCalls.list('objectiveId')) { console.log(objectiveToolCall.data); } ``` #### Response ```json { "items": [ { "data": { "callable": { "agent": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "cadenyaProvidedTool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "tool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } }, "arguments": { "foo": "bar" }, "memo": "memo", "result": "result", "statusChangedBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } } }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "status": "TOOL_CALL_STATUS_UNSPECIFIED", "executionStatus": "TOOL_CALL_EXECUTION_STATUS_UNSPECIFIED", "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "objective": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } } ], "pagination": { "nextCursor": "nextCursor", "total": 0 } } ``` ## Approve a tool call `client.objectives.toolCalls.approve(stringtoolCallID, ToolCallApproveParamsparams, RequestOptionsoptions?): ObjectiveToolCall` **put** `/v1/objectives/{objectiveId}/tool_calls/{toolCallId}/approve` When an agent attempts to use a tool that requires approval, use this endpoint to mark it as approved. ### Parameters - `toolCallID: string` - `params: ToolCallApproveParams` - `objectiveId: string` The ID of the objective. Supports "external_id:" prefix for external IDs. ### Returns - `ObjectiveToolCall` 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: ObjectiveToolCallData` - `callable: CallableTool` 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?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `arguments?: Record` The arguments passed to the tool - `memo?: string` A memo supplied by the reviewer when denying the tool call - `result?: string` The result content returned by the tool after execution - `statusChangedBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `metadata: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `status: "TOOL_CALL_STATUS_UNSPECIFIED" | "TOOL_CALL_STATUS_AUTO_APPROVED" | "TOOL_CALL_STATUS_WAITING_FOR_APPROVAL" | 2 more` Current status of the tool call - `"TOOL_CALL_STATUS_UNSPECIFIED"` - `"TOOL_CALL_STATUS_AUTO_APPROVED"` - `"TOOL_CALL_STATUS_WAITING_FOR_APPROVAL"` - `"TOOL_CALL_STATUS_APPROVED"` - `"TOOL_CALL_STATUS_DENIED"` - `executionStatus?: "TOOL_CALL_EXECUTION_STATUS_UNSPECIFIED" | "TOOL_CALL_EXECUTION_STATUS_PENDING" | "TOOL_CALL_EXECUTION_STATUS_RUNNING" | 2 more` - `"TOOL_CALL_EXECUTION_STATUS_UNSPECIFIED"` - `"TOOL_CALL_EXECUTION_STATUS_PENDING"` - `"TOOL_CALL_EXECUTION_STATUS_RUNNING"` - `"TOOL_CALL_EXECUTION_STATUS_COMPLETED"` - `"TOOL_CALL_EXECUTION_STATUS_ERRORED"` - `info?: ObjectiveToolCallInfo` - `createdBy?: Profile` 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). - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); const objectiveToolCall = await client.objectives.toolCalls.approve('toolCallId', { objectiveId: 'objectiveId', }); console.log(objectiveToolCall.data); ``` #### Response ```json { "data": { "callable": { "agent": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "cadenyaProvidedTool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "tool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } }, "arguments": { "foo": "bar" }, "memo": "memo", "result": "result", "statusChangedBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } } }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "status": "TOOL_CALL_STATUS_UNSPECIFIED", "executionStatus": "TOOL_CALL_EXECUTION_STATUS_UNSPECIFIED", "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "objective": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } } ``` ## Deny a tool call `client.objectives.toolCalls.deny(stringtoolCallID, ToolCallDenyParamsparams, RequestOptionsoptions?): ObjectiveToolCall` **put** `/v1/objectives/{objectiveId}/tool_calls/{toolCallId}/deny` When an agent attempts to use a tool that requires approval, use this endpoint to mark it as denied. Use a memo to steer the LLM to a different decision or usage of the tool. ### Parameters - `toolCallID: string` - `params: ToolCallDenyParams` - `objectiveId: string` Path param: The ID of the objective. Supports "external_id:" prefix for external IDs. - `memo?: string` Body param: A memo to associate to the tool call denial. Use a memo to steer the LLM to a different decision or usage of the tool. ### Returns - `ObjectiveToolCall` 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: ObjectiveToolCallData` - `callable: CallableTool` 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?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `arguments?: Record` The arguments passed to the tool - `memo?: string` A memo supplied by the reviewer when denying the tool call - `result?: string` The result content returned by the tool after execution - `statusChangedBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `metadata: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `status: "TOOL_CALL_STATUS_UNSPECIFIED" | "TOOL_CALL_STATUS_AUTO_APPROVED" | "TOOL_CALL_STATUS_WAITING_FOR_APPROVAL" | 2 more` Current status of the tool call - `"TOOL_CALL_STATUS_UNSPECIFIED"` - `"TOOL_CALL_STATUS_AUTO_APPROVED"` - `"TOOL_CALL_STATUS_WAITING_FOR_APPROVAL"` - `"TOOL_CALL_STATUS_APPROVED"` - `"TOOL_CALL_STATUS_DENIED"` - `executionStatus?: "TOOL_CALL_EXECUTION_STATUS_UNSPECIFIED" | "TOOL_CALL_EXECUTION_STATUS_PENDING" | "TOOL_CALL_EXECUTION_STATUS_RUNNING" | 2 more` - `"TOOL_CALL_EXECUTION_STATUS_UNSPECIFIED"` - `"TOOL_CALL_EXECUTION_STATUS_PENDING"` - `"TOOL_CALL_EXECUTION_STATUS_RUNNING"` - `"TOOL_CALL_EXECUTION_STATUS_COMPLETED"` - `"TOOL_CALL_EXECUTION_STATUS_ERRORED"` - `info?: ObjectiveToolCallInfo` - `createdBy?: Profile` 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). - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); const objectiveToolCall = await client.objectives.toolCalls.deny('toolCallId', { objectiveId: 'objectiveId', }); console.log(objectiveToolCall.data); ``` #### Response ```json { "data": { "callable": { "agent": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "cadenyaProvidedTool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "tool": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "name": "name", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } }, "arguments": { "foo": "bar" }, "memo": "memo", "result": "result", "statusChangedBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } } }, "metadata": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } }, "status": "TOOL_CALL_STATUS_UNSPECIFIED", "executionStatus": "TOOL_CALL_EXECUTION_STATUS_UNSPECIFIED", "info": { "createdBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } }, "objective": { "id": "id", "accountId": "accountId", "createdAt": "2019-12-27T18:11:19.117Z", "profileId": "profileId", "workspaceId": "workspaceId", "externalId": "externalId", "labels": { "foo": "string" } } } } ``` ## Domain Types ### Objective Tool Call - `ObjectiveToolCall` 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: ObjectiveToolCallData` - `callable: CallableTool` 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?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `arguments?: Record` The arguments passed to the tool - `memo?: string` A memo supplied by the reviewer when denying the tool call - `result?: string` The result content returned by the tool after execution - `statusChangedBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `metadata: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} - `status: "TOOL_CALL_STATUS_UNSPECIFIED" | "TOOL_CALL_STATUS_AUTO_APPROVED" | "TOOL_CALL_STATUS_WAITING_FOR_APPROVAL" | 2 more` Current status of the tool call - `"TOOL_CALL_STATUS_UNSPECIFIED"` - `"TOOL_CALL_STATUS_AUTO_APPROVED"` - `"TOOL_CALL_STATUS_WAITING_FOR_APPROVAL"` - `"TOOL_CALL_STATUS_APPROVED"` - `"TOOL_CALL_STATUS_DENIED"` - `executionStatus?: "TOOL_CALL_EXECUTION_STATUS_UNSPECIFIED" | "TOOL_CALL_EXECUTION_STATUS_PENDING" | "TOOL_CALL_EXECUTION_STATUS_RUNNING" | 2 more` - `"TOOL_CALL_EXECUTION_STATUS_UNSPECIFIED"` - `"TOOL_CALL_EXECUTION_STATUS_PENDING"` - `"TOOL_CALL_EXECUTION_STATUS_RUNNING"` - `"TOOL_CALL_EXECUTION_STATUS_COMPLETED"` - `"TOOL_CALL_EXECUTION_STATUS_ERRORED"` - `info?: ObjectiveToolCallInfo` - `createdBy?: Profile` 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). - `objective?: OperationMetadata` Metadata for ephemeral operations and activities (e.g., objectives, executions, runs) ### Objective Tool Call Data - `ObjectiveToolCallData` - `callable: CallableTool` 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?: ResourceMetadata` 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 - `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) - `externalId?: string` External ID for the resource (e.g., a workflow ID from an external system) - `labels?: Record` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `cadenyaProvidedTool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `tool?: ResourceMetadata` Standard metadata for persistent, named resources (e.g., agents, tools, prompts) - `arguments?: Record` The arguments passed to the tool - `memo?: string` A memo supplied by the reviewer when denying the tool call - `result?: string` The result content returned by the tool after execution - `statusChangedBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") ### Objective Tool Call Info - `ObjectiveToolCallInfo` - `createdBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") - `objective?: OperationMetadata` 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 - `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` Arbitrary key-value pairs for categorization and filtering Examples: {"priority": "high", "source": "api", "workflow": "onboarding"} # Tasks ## List objective tasks `client.objectives.tasks.list(stringobjectiveID, TaskListParamsquery?, RequestOptionsoptions?): CursorPagination` **get** `/v1/objectives/{objectiveId}/tasks` Lists all tasks for an objective ### Parameters - `objectiveID: string` - `query: TaskListParams` - `cursor?: string` Pagination cursor from previous response - `limit?: number` Maximum number of results to return - `sortOrder?: string` Sort order for results ### Returns - `ObjectiveTask` ObjectiveTask represents a task within an objective, typically created and managed by an AI agent to track progress toward completing the objective. - `data: ObjectiveTaskData` - `completed: boolean` Whether the task has been completed - `number: number` The sequential number of this task within the objective (auto-assigned, 1-based) - `task: string` Description of the task to be completed - `completedAt?: string` Timestamp when the task was marked as completed - `metadata: BareMetadata` 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). ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); // Automatically fetches more pages as needed. for await (const objectiveTask of client.objectives.tasks.list('objectiveId')) { console.log(objectiveTask.data); } ``` #### Response ```json { "items": [ { "data": { "completed": true, "number": 0, "task": "task", "completedAt": "2019-12-27T18:11:19.117Z" }, "metadata": { "id": "id", "name": "name" } } ], "pagination": { "nextCursor": "nextCursor", "total": 0 } } ``` ## Get an objective task by ID `client.objectives.tasks.retrieve(stringid, TaskRetrieveParamsparams, RequestOptionsoptions?): ObjectiveTask` **get** `/v1/objectives/{objectiveId}/tasks/{id}` Retrieves a task by ID from an objective ### Parameters - `id: string` - `params: TaskRetrieveParams` - `objectiveId: string` The ID of the objective. Supports "external_id:" prefix for external IDs. ### Returns - `ObjectiveTask` ObjectiveTask represents a task within an objective, typically created and managed by an AI agent to track progress toward completing the objective. - `data: ObjectiveTaskData` - `completed: boolean` Whether the task has been completed - `number: number` The sequential number of this task within the objective (auto-assigned, 1-based) - `task: string` Description of the task to be completed - `completedAt?: string` Timestamp when the task was marked as completed - `metadata: BareMetadata` 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). ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); const objectiveTask = await client.objectives.tasks.retrieve('id', { objectiveId: 'objectiveId' }); console.log(objectiveTask.data); ``` #### Response ```json { "data": { "completed": true, "number": 0, "task": "task", "completedAt": "2019-12-27T18:11:19.117Z" }, "metadata": { "id": "id", "name": "name" } } ``` ## Domain Types ### Objective Task - `ObjectiveTask` ObjectiveTask represents a task within an objective, typically created and managed by an AI agent to track progress toward completing the objective. - `data: ObjectiveTaskData` - `completed: boolean` Whether the task has been completed - `number: number` The sequential number of this task within the objective (auto-assigned, 1-based) - `task: string` Description of the task to be completed - `completedAt?: string` Timestamp when the task was marked as completed - `metadata: BareMetadata` 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). ### Objective Task Data - `ObjectiveTaskData` - `completed: boolean` Whether the task has been completed - `number: number` The sequential number of this task within the objective (auto-assigned, 1-based) - `task: string` Description of the task to be completed - `completedAt?: string` Timestamp when the task was marked as completed # Feedback ## Submit feedback for an objective `client.objectives.feedback.create(stringobjectiveID, FeedbackCreateParamsbody, RequestOptionsoptions?): ObjectiveFeedback` **post** `/v1/objectives/{objectiveId}/feedback` Submits feedback for an objective's execution. Feedback scores are used by the agent variation scoring system to evaluate and rank variation performance. ### Parameters - `objectiveID: string` - `body: FeedbackCreateParams` - `data: ObjectiveFeedbackData` - `attributes?: Record` Arbitrary key-value pairs to identify the source of the feedback. Since the submitting profile is typically an API key, use this to pass through application-specific identifiers (e.g., {"user_id": "usr_123", "session_id": "abc"}). - `comment?: string` Optional human-readable comment explaining the feedback - `score?: number` A score between -1.0 and 1.0 representing the quality of the objective's execution. -1.0 is the worst possible score, 0.0 is neutral, and 1.0 is the best. ### Returns - `ObjectiveFeedback` ObjectiveFeedback represents feedback submitted for an objective's execution. Feedback is used to score agent variations and improve agent performance over time. - `data: ObjectiveFeedbackData` - `attributes?: Record` Arbitrary key-value pairs to identify the source of the feedback. Since the submitting profile is typically an API key, use this to pass through application-specific identifiers (e.g., {"user_id": "usr_123", "session_id": "abc"}). - `comment?: string` Optional human-readable comment explaining the feedback - `score?: number` A score between -1.0 and 1.0 representing the quality of the objective's execution. -1.0 is the worst possible score, 0.0 is neutral, and 1.0 is the best. - `metadata: BareMetadata` 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). - `info?: ObjectiveFeedbackInfo` - `submittedBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); const objectiveFeedback = await client.objectives.feedback.create('objectiveId', { data: {} }); console.log(objectiveFeedback.data); ``` #### Response ```json { "data": { "attributes": { "foo": "string" }, "comment": "comment", "score": 0 }, "metadata": { "id": "id", "name": "name" }, "info": { "submittedBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } } } } ``` ## List feedback for an objective `client.objectives.feedback.list(stringobjectiveID, FeedbackListParamsquery?, RequestOptionsoptions?): CursorPagination` **get** `/v1/objectives/{objectiveId}/feedback` Lists all feedback submitted for an objective ### Parameters - `objectiveID: string` - `query: FeedbackListParams` - `cursor?: string` Pagination cursor from previous response - `limit?: number` Maximum number of results to return ### Returns - `ObjectiveFeedback` ObjectiveFeedback represents feedback submitted for an objective's execution. Feedback is used to score agent variations and improve agent performance over time. - `data: ObjectiveFeedbackData` - `attributes?: Record` Arbitrary key-value pairs to identify the source of the feedback. Since the submitting profile is typically an API key, use this to pass through application-specific identifiers (e.g., {"user_id": "usr_123", "session_id": "abc"}). - `comment?: string` Optional human-readable comment explaining the feedback - `score?: number` A score between -1.0 and 1.0 representing the quality of the objective's execution. -1.0 is the worst possible score, 0.0 is neutral, and 1.0 is the best. - `metadata: BareMetadata` 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). - `info?: ObjectiveFeedbackInfo` - `submittedBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") ### Example ```typescript import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); // Automatically fetches more pages as needed. for await (const objectiveFeedback of client.objectives.feedback.list('objectiveId')) { console.log(objectiveFeedback.data); } ``` #### Response ```json { "items": [ { "data": { "attributes": { "foo": "string" }, "comment": "comment", "score": 0 }, "metadata": { "id": "id", "name": "name" }, "info": { "submittedBy": { "metadata": { "id": "id", "accountId": "accountId", "name": "name", "profileId": "profileId", "externalId": "externalId", "labels": { "foo": "string" } }, "spec": { "type": "PROFILE_TYPE_USER", "email": "email", "name": "name" } } } } ], "pagination": { "nextCursor": "nextCursor", "total": 0 } } ``` ## Domain Types ### Objective Feedback - `ObjectiveFeedback` ObjectiveFeedback represents feedback submitted for an objective's execution. Feedback is used to score agent variations and improve agent performance over time. - `data: ObjectiveFeedbackData` - `attributes?: Record` Arbitrary key-value pairs to identify the source of the feedback. Since the submitting profile is typically an API key, use this to pass through application-specific identifiers (e.g., {"user_id": "usr_123", "session_id": "abc"}). - `comment?: string` Optional human-readable comment explaining the feedback - `score?: number` A score between -1.0 and 1.0 representing the quality of the objective's execution. -1.0 is the worst possible score, 0.0 is neutral, and 1.0 is the best. - `metadata: BareMetadata` 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). - `info?: ObjectiveFeedbackInfo` - `submittedBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables") ### Objective Feedback Data - `ObjectiveFeedbackData` - `attributes?: Record` Arbitrary key-value pairs to identify the source of the feedback. Since the submitting profile is typically an API key, use this to pass through application-specific identifiers (e.g., {"user_id": "usr_123", "session_id": "abc"}). - `comment?: string` Optional human-readable comment explaining the feedback - `score?: number` A score between -1.0 and 1.0 representing the quality of the objective's execution. -1.0 is the worst possible score, 0.0 is neutral, and 1.0 is the best. ### Objective Feedback Info - `ObjectiveFeedbackInfo` - `submittedBy?: Profile` 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: AccountResourceMetadata` 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` Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"} - `spec: ProfileSpec` ProfileSpec contains the profile-specific fields - `type: "PROFILE_TYPE_USER" | "PROFILE_TYPE_API_KEY" | "PROFILE_TYPE_SYSTEM"` Type is the type of profile. User's are humans, API keys are computers. You know the deal. - `"PROFILE_TYPE_USER"` - `"PROFILE_TYPE_API_KEY"` - `"PROFILE_TYPE_SYSTEM"` - `email?: string` Email address of the user (required, unique per account) - `name?: string` Display name for the user (e.g., "Bobby Tables")