Skip to content
Get started

Create a new agent

client.Agents.New(ctx, body) (*Agent, error)
POST/v1/agents

Creates a new agent in the workspace

ParametersExpand Collapse
body AgentNewParams
Metadata param.Field[CreateResourceMetadata]

CreateResourceMetadata contains the user-provided fields for creating a workspace-scoped resource. Read-only fields (id, account_id, workspace_id, profile_id, created_at) are excluded since they are set by the server.

Spec param.Field[AgentSpec]

Agent specification (user-provided configuration)

DefaultVariation param.Field[AgentNewParamsDefaultVariation]optional

Create agent variation request

CreateResourceMetadata contains the user-provided fields for creating a workspace-scoped resource. Read-only fields (id, account_id, workspace_id, profile_id, created_at) are excluded since they are set by the server.

Name string

Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool")

ExternalID stringoptional

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

Labels map[string, string]optional

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

AgentVariationSpec defines the operational configuration for a variation

CompactionConfig AgentVariationSpecCompactionConfigoptional

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

SummarizationStrategy configures LLM-powered summarization of older conversation turns.

Instructions stringoptional

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

ToolResultClearingStrategy configures clearing of older tool result content.

PreserveRecentResults int64optional

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

formatint32
TriggerThreshold float64optional

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

formatfloat
Constraints AgentVariationSpecConstraintsoptional

Execution constraints

MaxSubObjectives int64optional

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

formatint32
MaxToolCalls int64optional

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

formatint32
Description stringoptional

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

EnableEpisodicMemory booloptional

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 int64optional

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 AgentVariationSpecModelConfigoptional

ModelConfig defines the model configuration for a variation

ModelID stringoptional

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

Temperature float64optional

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

formatfloat
Prompt stringoptional

The system prompt for this variation

ToolSelection AgentVariationSpecToolSelectionoptional

Tool selection strategy

AssignedTools ToolSelectionAssignedToolsoptional

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 booloptional
AutoDiscovery ToolSelectionAutoDiscoveryoptional

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 []stringoptional
MaxTools int64optional
Weight int64optional

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

formatint32
AgentID stringoptional

Agent ID (from path)

ReturnsExpand Collapse
type Agent struct{…}

Agent resource

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 Time

Timestamp when this resource was created

formatdate-time
Name string

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

ProfileID string

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

WorkspaceID string

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

ExternalID stringoptional

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

Labels map[string, string]optional

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

Agent specification (user-provided configuration)

Status AgentSpecStatus

Status of the agent

formatenum
One of the following:
const AgentSpecStatusAgentStatusUnspecified AgentSpecStatus = "AGENT_STATUS_UNSPECIFIED"
const AgentSpecStatusAgentStatusDraft AgentSpecStatus = "AGENT_STATUS_DRAFT"
const AgentSpecStatusAgentStatusPublished AgentSpecStatus = "AGENT_STATUS_PUBLISHED"
const AgentSpecStatusAgentStatusArchived AgentSpecStatus = "AGENT_STATUS_ARCHIVED"
VariationSelectionMode AgentSpecVariationSelectionMode

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

formatenum
One of the following:
const AgentSpecVariationSelectionModeVariationSelectionModeUnspecified AgentSpecVariationSelectionMode = "VARIATION_SELECTION_MODE_UNSPECIFIED"
const AgentSpecVariationSelectionModeVariationSelectionModeRandom AgentSpecVariationSelectionMode = "VARIATION_SELECTION_MODE_RANDOM"
const AgentSpecVariationSelectionModeVariationSelectionModeWeighted AgentSpecVariationSelectionMode = "VARIATION_SELECTION_MODE_WEIGHTED"
Description stringoptional

Description of the agent's purpose

WebhookEventsURL stringoptional

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

Info AgentInfooptional

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

CreatedBy Profileoptional

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).

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 stringoptional

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

Labels map[string, string]optional

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

ProfileSpec contains the profile-specific fields

Type ProfileSpecType

Type is the type of profile. User's are humans, API keys are computers. You know the deal.

formatenum
One of the following:
const ProfileSpecTypeProfileTypeUser ProfileSpecType = "PROFILE_TYPE_USER"
const ProfileSpecTypeProfileTypeAPIKey ProfileSpecType = "PROFILE_TYPE_API_KEY"
const ProfileSpecTypeProfileTypeSystem ProfileSpecType = "PROFILE_TYPE_SYSTEM"
Email stringoptional

Email address of the user (required, unique per account)

Name stringoptional

Display name for the user (e.g., "Bobby Tables")

VariationCount int64optional

Create a new agent

package main

import (
  "context"
  "fmt"

  "github.com/cadenya/cadenya-go"
  "github.com/cadenya/cadenya-go/option"
  "github.com/cadenya/cadenya-go/shared"
)

func main() {
  client := cadenya.NewClient(
    option.WithAPIKey("My API Key"),
  )
  agent, err := client.Agents.New(context.TODO(), cadenya.AgentNewParams{
    Metadata: cadenya.F(shared.CreateResourceMetadataParam{
      Name: cadenya.F("name"),
    }),
    Spec: cadenya.F(cadenya.AgentSpecParam{
      Status: cadenya.F(cadenya.AgentSpecStatusAgentStatusUnspecified),
      VariationSelectionMode: cadenya.F(cadenya.AgentSpecVariationSelectionModeVariationSelectionModeUnspecified),
    }),
  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", agent.Metadata)
}
{
  "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
  }
}
Returns Examples
{
  "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
  }
}