> ## Documentation Index > Fetch the complete documentation index at: https://cadenya.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Create an agent > The role, not the resume. An agent holds the contract its objectives obey: input schema, output schema, memory, and how variations compete. An agent is the stable thing your application names. Its [variations](/docs/api-reference/agentvariationservice/create-a-new-variation) carry the prompt and the model, and they come and go. The agent carries the contract. Only `metadata.name` and `spec.variationSelectionMode` are required. ## Create the agent and its first variation in one call An agent cannot publish without a variation, so the API lets you supply one inline. This is the shortest path from nothing to a running agent. ```typescript TypeScript theme={null} const agent = await client.agents.create({ workspaceId, metadata: { name: 'Refund Decider', externalId: 'refund-decider' }, spec: { variationSelectionMode: 'VARIATION_SELECTION_MODE_RANDOM', systemPromptDataSchema: { type: 'object', properties: { company: { type: 'string' } }, required: ['company'], }, outputDefinition: { type: 'object', properties: { resolved: { type: 'boolean' } }, required: ['resolved'], }, }, defaultVariation: { metadata: { name: 'Baseline' }, spec: { systemPromptTemplate: 'Serve {{ system_prompt_data.company }}.', modelConfig: { modelId: 'external_id:claude-haiku-4-5' }, }, }, }); console.log(agent.state); // STATE_DRAFT console.log(agent.info?.variationCount); // 1 await client.agents.publish(agent.metadata.id, { workspaceId }); ``` ```go Go theme={null} agent, err := client.Agents.New(ctx, cadenya.AgentNewParams{ WorkspaceID: cadenya.String(workspaceID), Metadata: shared.CreateResourceMetadataParam{ Name: "Refund Decider", ExternalID: cadenya.String("refund-decider"), }, Spec: cadenya.AgentSpecParam{ VariationSelectionMode: cadenya.AgentSpecVariationSelectionModeVariationSelectionModeRandom, SystemPromptDataSchema: map[string]any{ "type": "object", "properties": map[string]any{"company": map[string]any{"type": "string"}}, "required": []string{"company"}, }, OutputDefinition: map[string]any{ "type": "object", "properties": map[string]any{"resolved": map[string]any{"type": "boolean"}}, "required": []string{"resolved"}, }, }, DefaultVariation: cadenya.AgentNewParamsDefaultVariation{ Metadata: shared.CreateResourceMetadataParam{Name: "Baseline"}, Spec: cadenya.AgentVariationSpecParam{ SystemPromptTemplate: cadenya.String("Serve {{ system_prompt_data.company }}."), ModelConfig: cadenya.AgentVariationSpecModelConfigParam{ ModelID: cadenya.String("external_id:claude-haiku-4-5"), }, }, }, }) if err != nil { log.Fatal(err) } log.Println(agent.State, agent.Info.VariationCount) // STATE_DRAFT 1 _, err = client.Agents.Publish(ctx, agent.Metadata.ID, cadenya.AgentPublishParams{ WorkspaceID: cadenya.String(workspaceID), }) ``` ```ruby Ruby theme={null} agent = cadenya.agents.create( workspace_id: workspace_id, metadata: {name: "Refund Decider", externalId: "refund-decider"}, spec: { variationSelectionMode: :VARIATION_SELECTION_MODE_RANDOM, systemPromptDataSchema: { type: "object", properties: {company: {type: "string"}}, required: ["company"] }, outputDefinition: { type: "object", properties: {resolved: {type: "boolean"}}, required: ["resolved"] } }, default_variation: { metadata: {name: "Baseline"}, spec: { systemPromptTemplate: "Serve {{ system_prompt_data.company }}.", modelConfig: {modelId: "external_id:claude-haiku-4-5"} } } ) puts agent.state # STATE_DRAFT puts agent.info.variation_count # 1 cadenya.agents.publish(agent.metadata.id, workspace_id: workspace_id) ``` ```bash cURL theme={null} curl -X POST "https://api.cadenya.com/v1/workspaces/${WORKSPACE_ID}/agents" \ -H "Authorization: Bearer ${CADENYA_API_KEY}" \ -H "Content-Type: application/json" \ -d '{ "metadata": { "name": "Refund Decider", "externalId": "refund-decider" }, "spec": { "variationSelectionMode": "VARIATION_SELECTION_MODE_RANDOM", "systemPromptDataSchema": { "type": "object", "properties": { "company": { "type": "string" } }, "required": ["company"] }, "outputDefinition": { "type": "object", "properties": { "resolved": { "type": "boolean" } }, "required": ["resolved"] } }, "defaultVariation": { "metadata": { "name": "Baseline" }, "spec": { "systemPromptTemplate": "Serve {{ system_prompt_data.company }}.", "modelConfig": { "modelId": "external_id:claude-haiku-4-5" } } } }' curl -X POST "https://api.cadenya.com/v1/workspaces/${WORKSPACE_ID}/agents/${AGENT_ID}:publish" \ -H "Authorization: Bearer ${CADENYA_API_KEY}" \ -H "Content-Type: application/json" \ -d '{}' ``` Agents are born `STATE_DRAFT` and refuse objectives until published. `publish`, `unpublish`, `archive`, and `unarchive` are dedicated actions; `state` is read-only and a `PATCH` cannot set it. ## `outputDefinition` decides whether an objective ever ends This is the most consequential field on the spec, and the least obvious. **Without an `outputDefinition`,** an objective answers and parks in `STATE_WAITING`, holding its context window open for your next turn. It never finalizes on its own. That is right for a chat agent and surprising for everything else. **With an `outputDefinition`,** Cadenya runs an extraction pass once the agent stops working, validates the result against your schema, and moves the objective to `STATE_FINALIZED` with the result on `output`. ```typescript theme={null} const objective = await client.objectives.create({ workspaceId, agentId: agent.metadata.id, systemPromptData: { company: 'Acme' }, firstUserMessage: 'Refund order A-1007, the package arrived broken.', }); // A few seconds later: const done = await client.objectives.retrieve(objective.metadata.id, { workspaceId }); console.log(done.state); // STATE_FINALIZED console.log(done.output); // { resolved: true } ``` The same value rides on the `finalized` event, at `finalized.output`, so a webhook or [stream](/docs/api-reference/objectiveeventstreamsservice/stream-objective-events) consumer never has to fetch the objective. If you are polling for a terminal state and your agent has no `outputDefinition`, you are waiting for something that never arrives. Either add the schema, or treat `STATE_WAITING` as done. ## `systemPromptDataSchema` catches bad data at the door Declare a JSON Schema and every objective's `systemPromptData` is validated against it before the run starts. ``` systemPromptData: {} -> 400 the data provided does not conform to the system prompt data schema defined on the agent systemPromptData: { company: 123 } -> 400 (wrong type) systemPromptData: { company: 'Acme' } -> 200 ``` Reach for this. Prompt data flows into a Liquid template, and a missing key renders as an empty string rather than an error, so the agent runs with a hole in its prompt and answers anyway. A schema is what turns that silent failure into a `400` on the call that caused it. It validates the data, not the template. A typo in `{{ system_prompt_data.compnay }}` still renders empty. ## Memory and webhooks `enableEpisodicMemory` turns the agent into one that remembers across runs. Once set, **every objective must carry an `episodicMemory.key`**, and omitting it is a `400`. Objectives sharing a key share one system-managed [memory layer](/docs/api-reference/memoryservice/create-a-new-memory-layer). `episodicMemoryTtl` slides that layer's expiry forward on each new objective; leave it unset and memories persist indefinitely. Memory is agent-level, so every variation reads and writes the same memories, and a learning survives a variation swap. `webhookEventsUrl` sends every objective event for this agent to your endpoint. It must be `https`, and deliveries are recorded in [webhook deliveries](/docs/api-reference/agentservice/list-webhook-deliveries). ## `variationSelectionMode` * `VARIATION_SELECTION_MODE_RANDOM` picks uniformly at random, forever. The default. * `VARIATION_SELECTION_MODE_WEIGHTED` learns. Cadenya runs Thompson Sampling over each variation's [feedback](/docs/api-reference/objectiveservice/submit-feedback-for-an-objective), so variations that score well get picked more often while every variation keeps a shrinking chance to prove itself. With one variation the mode is moot. Set `WEIGHTED` anyway, since the second variation is the reason the field exists. ## The lifecycle ```typescript theme={null} await client.agents.publish(agent.metadata.id, { workspaceId }); // draft -> published await client.agents.unpublish(agent.metadata.id, { workspaceId }); // stop taking objectives await client.agents.archive(agent.metadata.id, { workspaceId }); // retire, keep history await client.agents.delete(agent.metadata.id, { workspaceId }); // gone ``` Published agents take objectives and fire [schedules](/docs/api-reference/agentscheduleservice/create-a-new-schedule). Draft agents take edits. Archived agents take neither, but their objectives and feedback stay queryable. Deleting an agent clears its variations' assignments, so the tool sets and memory layers it referenced stay deletable. Delete discards the variations' feedback history; [archive](/docs/api-reference/agentservice/archive-an-agent) keeps it. ## Related The lifecycle in code, in four languages. Prompt, model, compaction, and the constraints that bound a run. The hands-on lesson for `outputDefinition`. What `enableEpisodicMemory` switches on. ## OpenAPI ````yaml post /v1/workspaces/{workspaceId}/agents openapi: 3.1.0 info: title: Cadenya API description: API for the Cadenya Agent Runtime platform. version: '1.0' servers: - url: https://api.cadenya.com description: Production server security: - bearerAuth: [] tags: - name: AIProviderKeyService - name: APIKeyService description: |- Issue, rotate, disable, and revoke a workspace's API keys. Every key belongs to exactly one workspace; the system-managed global account key is managed via GlobalAPIKeyService instead. - name: AccountService description: >- Manage the authenticated account. Accounts are the top-level organizational unit and contain one or more workspaces. - name: AgentScheduleService description: >- Manage recurring schedules attached to agents. Schedules trigger objectives on a cadence defined by AgentScheduleSpec.Schedule. - name: AgentService description: >- Manage AI agents within a workspace. Agents define AI behavior and tool access. - name: AgentVariationService description: >- Manage variations of an agent and their tool, sub-agent, and memory layer assignments. - name: GlobalAPIKeyService description: |- Manage the account's system-provisioned global API key. The global key is the only key that spans every workspace; it is created by the system and cannot be deleted, so the surface is retrieve, rotate, and the disable/enable kill switch. - name: MemoryService description: >- Manage memory layers and their entries. Layers are named containers that can be composed into an objective's memory cascade; entries are the keyed values within a layer. System-managed layers (e.g., episodic layers created by the runtime) cannot be mutated through this API. - name: ModelService description: |- Manage LLM models available to a workspace. Models represent provider and family pairs (e.g., "anthropic/claude-sonnet-4.6"). Workspaces are seeded with the supported models and you can enable or disable each one. - name: ObjectiveEventStreamsService - name: ObjectiveService - name: ProfilesService description: |- Operations on profiles, the account-level principals (users, API keys, system) that authenticate against the API. - name: SearchService - name: TenantService description: >- Read and erase tenants and the subjects under them. Tenants and subjects are created by assertion — on objective creation or widget session mint — never directly, so this service has no create or update: it exists to enumerate what assertions have produced, and to destroy it on request. - name: ToolService description: >- Manage tool sets and the tools they contain. Tool sets group related tools, and tools define specific capabilities available to agents. When a tool set is managed, only API key actors can modify its tools; human (profile) actors cannot. - name: UploadService description: |- Issue short-lived presigned URLs for direct client-to-object-storage uploads. Created uploads can be referenced by id when creating or updating resources that accept binary content (e.g., MemoryEntry). - name: WidgetService description: |- Manage embeddable chat widgets. A widget binds an agent to a globally unique hostname with a per-widget origin allowlist; browsers reach it with session tokens minted via WidgetSessionService. - name: WidgetSessionService description: >- Mint and manage widget sessions. Session creation is server-to-server only: the customer's backend authenticates its visitor, asserts tenant/subject context, attaches any per-visitor secrets, and receives a short-lived bearer token the browser uses against the widget host. - name: WorkspaceAdminService description: >- Administer workspaces across the account: create and archive workspaces and manage their membership. These operations are account-scoped and require the admin role (a token whose profile holds the WorkOS admin role); they live under /v1/account/workspaces rather than the workspace-scoped /v1/workspaces tree so an admin can manage any workspace in the account, including ones they are not themselves a member of. - name: WorkspaceSecretService - name: WorkspaceService description: |- Manage workspaces within an account. Workspaces provide organizational grouping and isolation for resources such as agents, tools, and API keys. This is the workspace-scoped, end-user surface. Administrative operations (create / archive workspaces, manage members) live in WorkspaceAdminService under /v1/account/workspaces and require the admin role. paths: /v1/workspaces/{workspaceId}/agents: post: tags: - AgentService - Agents summary: Create a new agent description: Creates a new agent in the workspace operationId: AgentService_CreateAgent parameters: - name: workspaceId in: path description: Workspace ID. required: true schema: type: string example: workspace_01HXKD2E5NQM3T9AYWCF133E3Q requestBody: content: application/json: schema: $ref: '#/components/schemas/CreateAgentRequest' required: true responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/Agent' default: description: Default error response content: application/json: schema: $ref: '#/components/schemas/Status' x-codeSamples: - lang: JavaScript source: |- import Cadenya from '@cadenya/cadenya'; const client = new Cadenya({ apiKey: process.env['CADENYA_API_KEY'], // This is the default and can be omitted }); const agent = await client.agents.create({ workspaceId: 'workspace_01HXKD2E5NQM3T9AYWCF133E3Q', metadata: { name: 'name' }, spec: { variationSelectionMode: 'VARIATION_SELECTION_MODE_UNSPECIFIED' }, }); console.log(agent.metadata); - lang: Python source: |- import os from cadenya import Cadenya client = Cadenya( api_key=os.environ.get("CADENYA_API_KEY"), # This is the default and can be omitted ) agent = client.agents.create( workspace_id="workspace_01HXKD2E5NQM3T9AYWCF133E3Q", metadata={ "name": "name" }, spec={ "variation_selection_mode": "VARIATION_SELECTION_MODE_UNSPECIFIED" }, ) print(agent.metadata) - lang: Go source: "package main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\t\"go.cadenya.com/cadenya-go\"\n\t\"go.cadenya.com/cadenya-go/option\"\n\t\"go.cadenya.com/cadenya-go/shared\"\n)\n\nfunc main() {\n\tclient := cadenya.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\tagent, err := client.Agents.New(context.TODO(), cadenya.AgentNewParams{\n\t\tWorkspaceID: cadenya.String(\"workspace_01HXKD2E5NQM3T9AYWCF133E3Q\"),\n\t\tMetadata: shared.CreateResourceMetadataParam{\n\t\t\tName: \"name\",\n\t\t},\n\t\tSpec: cadenya.AgentSpecParam{\n\t\t\tVariationSelectionMode: cadenya.AgentSpecVariationSelectionModeVariationSelectionModeUnspecified,\n\t\t},\n\t})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf(\"%+v\\n\", agent.Metadata)\n}\n" - lang: Ruby source: |- require "cadenya" cadenya = Cadenya::Client.new(api_key: "My API Key") agent = cadenya.agents.create( workspace_id: "workspace_01HXKD2E5NQM3T9AYWCF133E3Q", metadata: {name: "name"}, spec: {variationSelectionMode: :VARIATION_SELECTION_MODE_UNSPECIFIED} ) puts(agent) - lang: CLI source: |- cadenya agents create \ --api-key 'My API Key' \ --workspace-id workspace_01HXKD2E5NQM3T9AYWCF133E3Q \ --metadata '{name: name}' \ --spec '{variationSelectionMode: VARIATION_SELECTION_MODE_UNSPECIFIED}' components: schemas: CreateAgentRequest: required: - metadata - spec type: object properties: workspaceId: readOnly: true example: workspace_01HXKD2E5NQM3T9AYWCF133E3Q type: string description: Workspace ID. metadata: $ref: '#/components/schemas/CreateResourceMetadata' spec: $ref: '#/components/schemas/AgentSpec' defaultVariation: allOf: - $ref: '#/components/schemas/CreateAgentVariationRequest' description: Optional default variation to add to the agent on create description: Create agent request Agent: required: - metadata - spec - state type: object properties: metadata: allOf: - $ref: '#/components/schemas/ResourceMetadata' description: Resource metadata spec: allOf: - $ref: '#/components/schemas/AgentSpec' description: Agent specification info: readOnly: true allOf: - $ref: '#/components/schemas/AgentInfo' description: Agent information state: readOnly: true enum: - STATE_UNSPECIFIED - STATE_DRAFT - STATE_PUBLISHED - STATE_ARCHIVED type: string description: >- The current lifecycle state of the agent. Output only. Agents are created in STATE_DRAFT; use the :publish, :unpublish, :archive, and :unarchive actions to transition between states. format: enum description: Agent resource Status: type: object properties: code: type: integer description: >- The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code]. format: int32 message: type: string description: >- A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client. details: type: array items: $ref: '#/components/schemas/GoogleProtobufAny' description: >- A list of messages that carry the error details. There is a common set of message types for APIs to use. description: >- The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). CreateResourceMetadata: required: - name type: object properties: name: type: string description: >- Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") externalId: type: string description: >- External ID for the resource (e.g., a workflow ID from an external system) labels: type: object additionalProperties: type: string description: |- Key-value pairs for categorization and filtering. Values are 0-63 alphanumeric characters with "-", "_", or "." allowed between; keys follow the same shape and additionally accept an optional DNS-subdomain prefix (e.g. "cadenya.com/") of at most 253 characters. Examples: {"environment": "production", "team": "platform", "version": "v2"} description: |- 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. AgentSpec: required: - variationSelectionMode type: object properties: description: type: string description: Description of the agent's purpose webhookEventsUrl: type: string description: >- The URL that Cadenya will send events for any objective assigned to the agent. variationSelectionMode: enum: - VARIATION_SELECTION_MODE_UNSPECIFIED - VARIATION_SELECTION_MODE_RANDOM - VARIATION_SELECTION_MODE_WEIGHTED type: string description: >- Controls how variations are automatically selected when creating objectives Defaults to RANDOM when unspecified format: enum systemPromptDataSchema: type: object additionalProperties: true description: >- SystemPromptDataSchema enforces the shape of system_prompt_data when objectives are created. This is valuable when using liquid formatting in agent variation system prompt templates. The schema is also used when the agent is attached as a sub-agent, as it becomes the tool's input parameter schema. If omitted, the sub-agent schema will be loaded with a simple "prompt" free text string as its schema. outputDefinition: type: object additionalProperties: true description: |- Optional output definition for objectives created for this agent. When provided, Cadenya will append a tool to that will be called by the LLM in use by the variant to extract information in the format provided here. Use this option when you want structured data to be created by your objectives. enableEpisodicMemory: type: boolean description: |- Enable episodic memory for objectives created for this agent. When true, objective creation requires an episodic_memory key and the system finds or creates a memory layer for that (agent, key) pair, letting the agent store and retrieve memories across objectives that share the key. Memory is agent-level so all variations of the agent share the same layers. episodicMemoryTtl: pattern: ^-?(?:0|[1-9][0-9]{0,11})(?:\.[0-9]{1,9})?s$ type: integer description: |- How long episodic memories should be retained. Each new objective slides the layer's expiry forward by this duration, and stored entries expire this long after they are written. If not set, episodic memories are retained indefinitely. description: Agent specification (user-provided configuration) CreateAgentVariationRequest: required: - metadata - spec type: object properties: workspaceId: readOnly: true example: workspace_01HXKD2E5NQM3T9AYWCF133E3Q type: string description: Workspace ID. agentId: readOnly: true example: agent_01HXKD2E5NQM3T9AYWCFMGWT9Y type: string description: >- Agent ID. Accepts the canonical `agent_…` form or the `external_id:` form. metadata: $ref: '#/components/schemas/CreateResourceMetadata' spec: $ref: '#/components/schemas/AgentVariationSpec' description: Create agent variation request ResourceMetadata: required: - id - accountId - workspaceId - name - profileId - createdAt type: object properties: id: readOnly: true type: string description: >- Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...") accountId: readOnly: true example: account_01HXKD2E5NQM3T9AYWCFTJHJVF type: string description: >- Account this resource belongs to for multi-tenant isolation (prefixed ULID) workspaceId: readOnly: true example: workspace_01HXKD2E5NQM3T9AYWCF133E3Q type: string description: >- Workspace this resource belongs to for organizational grouping (prefixed ULID) name: type: string description: >- Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly externalId: type: string description: >- External ID for the resource (e.g., a workflow ID from an external system) labels: type: object additionalProperties: type: string description: |- Key-value pairs for categorization and filtering. Values are 0-63 alphanumeric characters with "-", "_", or "." allowed between; keys follow the same shape and additionally accept an optional DNS-subdomain prefix (e.g. "cadenya.com/") of at most 253 characters. Examples: {"environment": "production", "team": "platform", "version": "v2"} profileId: readOnly: true example: profile_01HXKD2E5NQM3T9AYWCFS0AP08 type: string description: ID of the actor (user or service account) that created this resource createdAt: readOnly: true type: string description: Timestamp when this resource was created format: date-time updatedAt: readOnly: true type: string description: Timestamp when this resource was last updated format: date-time description: >- Standard metadata for persistent, named resources (e.g., agents, tools, prompts) AgentInfo: type: object properties: variationCount: readOnly: true type: integer format: int32 createdBy: $ref: '#/components/schemas/Profile' description: >- AgentInfo contains simple information about an agent for display or quick reference GoogleProtobufAny: type: object properties: '@type': type: string description: The type of the serialized message. additionalProperties: true description: >- Contains an arbitrary serialized message along with a @type that describes the type of the serialized message. AgentVariationSpec: type: object properties: systemPromptTemplate: type: string description: >- Liquid template for the system prompt of objectives using this variation. Rendered with CreateObjectiveRequest.system_prompt_data into Objective.system_prompt. progressiveDiscovery: allOf: - $ref: '#/components/schemas/AgentVariationSpec_ProgressiveDiscovery' description: >- ProgressiveDiscovery is an optional config that, when set, will load a Cadenya provided tool that can search for tools in the assigned tool sets or tools. Note: Sub-agents are always loaded as a tool regardless of this value. constraints: allOf: - $ref: '#/components/schemas/AgentVariationSpec_Constraints' description: Execution constraints description: type: string description: >- Human-readable description of what this variation does or when it should be used modelConfig: allOf: - $ref: '#/components/schemas/AgentVariationSpec_ModelConfig' description: Model configuration for this variation compactionConfig: allOf: - $ref: '#/components/schemas/AgentVariationSpec_CompactionConfig' description: >- Compaction configuration for managing context window limits during long-running objectives. When not set, the system uses a default summarization strategy at 75% context window usage. firstUserMessageTemplate: type: string description: >- Liquid template for the first user message of objectives using this variation. Rendered with CreateObjectiveRequest.first_user_message_data into Objective.first_user_message, the first user message in the LLM chat history. CreateObjectiveRequest.first_user_message, when set, overrides the rendered result. If neither this template nor first_user_message is present, objective creation is rejected with InvalidArgument. description: AgentVariationSpec defines the operational configuration for a variation Profile: required: - metadata - spec type: object properties: metadata: $ref: '#/components/schemas/AccountResourceMetadata' spec: $ref: '#/components/schemas/ProfileSpec' description: |- A profile identifies a user or non-human principal (such as an API key) at the account level. Profiles are account-scoped and can be granted access to multiple workspaces. AgentVariationSpec_ProgressiveDiscovery: type: object properties: maxTools: type: integer description: >- The most tool names tool_search will load in a single call. Requesting more than this returns an error telling the model to retry in smaller batches -- it is a per-call batch limit, not a ceiling on how many tools an objective may end up with. format: int32 hints: type: array items: type: string description: >- Free-text guidance appended to the discoverable-tools appendix in the system prompt. Hints steer the model's choice of tool names; they do not filter or rank anything, because tool_search matches names exactly rather than searching. description: >- ProgressiveDiscovery is used to indicate that the agent should automatically discover tools that are not explicitly assigned to it. Max tools is the maximum number of tools that can be discovered per search. Hints are optional hints for tool search. These are used in conjunction with the context-aware tool search and can help select the best tools for the task. AgentVariationSpec_Constraints: type: object properties: maxToolCalls: type: integer description: The maximum number of tool calls that can be made. 0 means no limit. format: int32 maxSubObjectives: type: integer description: >- The maximum number of sub-objectives that can be created. 0 means no limit. format: int32 inactivityTimeout: pattern: ^-?(?:0|[1-9][0-9]{0,11})(?:\.[0-9]{1,9})?s$ type: string description: |- How long an objective may sit with no activity (no user messages, no LLM calls) before it is finalized as timed out. Between 1 minute and 24 hours, expressed as a duration string in seconds (e.g. "7200s"). When not set, objectives are still swept at the system-wide 24 hour maximum — every objective eventually reaches a terminal state. Note: no gnostic integer hint here on purpose. The Envoy gRPC-JSON transcoder only accepts the canonical protobuf JSON form for Durations — a "s" string — so the SDKs must type this as a string (like AgentScheduleSpec.every), not an integer. AgentVariationSpec_ModelConfig: type: object properties: modelId: example: claude/opus-4.6 type: string description: >- The model identifier in family/model format (e.g., "claude/opus-4.6", "claude/sonnet-4.5") temperature: type: number description: |- Sampling temperature for model inference (0.0 to 1.0) Lower values produce more deterministic outputs, higher values increase randomness format: float description: ModelConfig defines the model configuration for a variation AgentVariationSpec_CompactionConfig: type: object properties: triggerThreshold: type: number description: >- 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%) format: float summarization: allOf: - $ref: '#/components/schemas/CompactionConfig_SummarizationStrategy' description: >- Strategies — set one or more. When multiple are set, they execute in order: tool_result_clearing → summarization. When none are set, defaults to summarization with the system default prompt. toolResultClearing: $ref: '#/components/schemas/CompactionConfig_ToolResultClearingStrategy' description: >- CompactionConfig defines how context window compaction behaves for objectives using this variation. AccountResourceMetadata: required: - id - accountId - name - profileId type: object properties: id: readOnly: true type: string description: >- Unique identifier for the resource (prefixed ULID, e.g., "apikey_01HXK...") accountId: readOnly: true example: account_01HXKD2E5NQM3T9AYWCFTJHJVF type: string description: >- Account this resource belongs to for multi-tenant isolation (prefixed ULID) name: type: string description: >- Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly externalId: type: string description: >- External ID for the resource (e.g., a workflow ID from an external system) labels: type: object additionalProperties: type: string description: |- Key-value pairs for categorization and filtering. Values are 0-63 alphanumeric characters with "-", "_", or "." allowed between; keys follow the same shape and additionally accept an optional DNS-subdomain prefix (e.g. "cadenya.com/") of at most 253 characters. Examples: {"environment": "production", "team": "platform", "version": "v2"} profileId: readOnly: true example: profile_01HXKD2E5NQM3T9AYWCFS0AP08 type: string createdAt: readOnly: true type: string format: date-time description: >- AccountResourceMetadata is used to represent a resource that is associated to an account but not to a workspace. ProfileSpec: required: - type type: object properties: email: type: string description: >- Email address of the profile. Required and unique within an account for user profiles. name: type: string description: Display name (e.g., "Bobby Tables"). type: enum: - PROFILE_TYPE_UNSPECIFIED - PROFILE_TYPE_USER - PROFILE_TYPE_API_KEY - PROFILE_TYPE_SYSTEM type: string description: >- Whether this profile represents a human user, an API key, or a system principal. format: enum description: Configuration for a profile. CompactionConfig_SummarizationStrategy: type: object properties: instructions: type: string description: |- Custom instructions that guide what the summarizer preserves. Replaces the default summarization prompt entirely. Example: "Preserve all code snippets, variable names, and technical decisions." description: >- SummarizationStrategy configures LLM-powered summarization of older conversation turns. CompactionConfig_ToolResultClearingStrategy: type: object properties: preserveRecentResults: type: integer description: |- 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 format: int32 description: >- ToolResultClearingStrategy configures clearing of older tool result content. securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT ````