Skip to main content
POST
Create Ai Agent
Create a new AI agent with custom configuration. The agent is ACTIVE as soon as the call returns and can be invoked right away. Only name is required. A create that names no model_provider, model_name or CLI model follows your organization’s default LLM (Settings, LLM); when the organization has none, the platform default applies: framework: external-harness, harness_settings.default_cli: claude-code, model_provider: anthropic, model_name: claude-sonnet-5, harness_settings.runtime: fleet.

Request Body

string
required
Display name for the agent
string
Description of the agent’s purpose and capabilities
string
Deployment infrastructure: serverless (default; also the value for an agent on the runtime fleet) or container (one always-on pod per agent, only with harness_settings.runtime: legacy).
string
LLM provider, one of the values from List LLM Providers: anthropic (default), openai, gemini, and others. Omit it together with model_name to follow the organization’s default LLM.
string
Model identifier within the chosen provider, from GET /llm_providers/{provider}/models (default claude-sonnet-5; for example gpt-4o, gemini-2.0-flash).
string
Icon shown next to the agent name. Defaults to the platform icon xpi:workflow:dusk; a single emoji character is also accepted.
object
System instructions configuration
string
Access control scope for the agent. Determines who can see and use the agent.Possible values: personal (visible only to the creator) or organizational (visible to the entire organization). Defaults to organizational if not specified.
string
Target environment ID (optional)
boolean
Use Nvidia NeMo (default: false)
string
Custom API base URL for the LLM provider, for when your model calls go through your own LLM proxy
object
Custom HTTP headers to include in LLM requests (for example the headers your LLM proxy expects)
string
Reasoning effort level for the LLM (e.g., low, medium, high)
string
Agent type: manager (default), regular, a2a, curl, orchestration. orchestration marks a workflow; create those through the Workflows API rather than setting it here.
string
Output format: markdown (default), text, json (pair with output_schema), or voice
object
JSON schema for structured output when output_format is json
string
Natural-language description of the desired output
string
How the agent runs. external-harness (default): the agent runs on a coding CLI (claude-code, codex or opencode, chosen by harness_settings.default_cli). agno: the built-in xpander loop. The legacy values claude-code and codex are read as external-harness with that CLI as the default.
object
Runtime settings for an external-harness agent; ignored for agno. Every field is optional.
array
Simplified skill attachment: the same shape as Add Agent Tool, so the API resolves catalog IDs and builds attached_tools and graph for you. Each item is discriminated on type: action, custom_function, mcp, agent, workflow or skill (skill_name from the skills catalog). When tools and attached_tools/graph are both sent, tools is resolved and merged on top. Prefer this over hand-built attached_tools and graph.
array
Operations of connected services to attach, each with its connection ID and selected operation IDs
array
Agent workflow graph configuration defining skill execution order
array
Array of knowledge base IDs to attach to the agent
object
Settings for framework: agno only, including memory, session storage, call limits, and safety features
object
Task-level strategies for retry, stop conditions, and iteration
object
Notification configuration (Slack, email, webhook) for agent events
object
Deep planning configuration for complex multi-step tasks
string
Voice ID for text-to-speech output
array
Source node configurations (e.g., Slack, web UI triggers)
boolean
Whether the agent requires human approval before it acts

Response

Returns the full AIAgent object (about 80 fields). The ones you will read most:
string
Unique identifier for the created agent (UUID)
string
Display name of the agent
string
Agent description
string
Icon shown next to the agent name (default xpi:workflow:dusk)
string
Avatar identifier (default male-avatar)
string
Current status: DRAFT, ACTIVE or INACTIVE. A created agent is ACTIVE.
string
Agent type: manager, regular, a2a, curl or orchestration
string
UUID of the organization that owns this agent
string | null
UUID of the user who created the agent
string
ISO 8601 creation timestamp
string
Deployment infrastructure: serverless or container
string | null
Environment the agent runs in
string | null
Runtime environment (image and environment spec) assigned to the agent, if any
object
System instructions configuration (role, goal, general, plus the dynamic-prompt fields dynamic_prompt_enabled, dynamic_prompt_code, dynamic_prompt_position)
string
Access control scope: personal or organizational
string
LLM provider (default anthropic)
string
Model identifier (default claude-sonnet-5)
string
Reasoning effort (default medium)
string
text, markdown (default), json or voice
string
How the agent runs: external-harness (default) or agno
object | null
Runtime settings of an external-harness agent; null for agno.
object
Settings used when framework is agno; present with defaults on every agent
array
Skills enabled for the agent (name, description, version), resolved at read time
array
Resolved skill definitions; empty on a new agent
array
Attached operations of connected services (id, operation_ids) as sent on create or added with Add Agent Tool
array
Attached knowledge bases (id, name, description, strategy, rw, documents)
array
Ways the agent can be triggered. Each item has id, type (assistant, sdk, webhook, email, and so on), targets and metadata. A new agent gets the default set.
array
Agent workflow graph configuration
array | null
Workspace commands that need approval before they run: {match, unless?, note?, approvers?, channels?} items, where match is literal text. null means no gates.
array | null
Vault secrets bound to the agent, as resolved for its runtime. null means none.
boolean
Whether the agent may schedule its own future runs (default true)
integer
Cap on pending self-scheduled runs per task (default 3)
string | null
Organization user the agent runs as when a non-UI invocation has no resolved user
boolean
Whether the agent may share the live surfaces it builds (default true)
boolean
Whether the agent needs human approval before it acts
string
Auto-generated human-friendly slug identifier (e.g., “lavender-peacock”)
integer
Agent version number
boolean
Whether there are unpublished configuration changes
string
Auto-generated webhook URL for agent invocations

Example Request

Minimal create request (required fields only). The agent follows your organization’s default LLM, or the platform default when there is none:
With an explicit model and instructions:

Example Response

Recorded from the live API on 2026-09-18 for a minimal create; ids replaced with placeholders, two default blocks shortened (agno_settings, source_nodes) and two internal flags (use_agent_gateway, connectivity_details) left out.

Notes

  • Only name is required. Every other field falls back to your organization’s default LLM and then to the platform defaults shown above.
  • A new agent runs as framework: external-harness on claude-code (harness_settings.default_cli) on the runtime fleet (harness_settings.runtime: fleet), with permission_mode: full and approval_hold_hours: 4. Set framework: agno for the built-in loop.
  • harness_settings.models holds one model per CLI; model_provider and model_name mirror the default CLI’s entry.
  • The unique_name is auto-generated as a human-friendly slug (e.g., “lavender-peacock”)
  • The webhook_url is auto-generated for agent invocations
  • The agent is ACTIVE immediately upon creation and ready for invocation
  • version starts at 2 and increments with each deployment
  • has_pending_changes indicates whether there are unpublished configuration changes
  • skills, tools and attached_tools are empty on a new agent. Capabilities the runtime provides on its own (web search, email, file sharing, scheduling, live surfaces) never appear in these arrays.

Next Steps

After creating an agent:
  1. Update instructions using Update Agent
  2. Attach skills with Add Agent Tool and knowledge bases
  3. Deploy the agent using Deploy Agent
  4. Invoke the agent using the task execution endpoints

Authorizations

x-api-key
string
header
required

API Key for authentication

Body

application/json

Request model for creating a new AI agent on the xpander.ai platform.

Only name is required. All other fields have sensible defaults matching the platform's standard agent configuration. The agent will be created with type 'manager' by default, which supports tool use, sub-agent delegation, and multi-step task execution.

Fields like organization_id, id, status, version, and other system-managed properties are set automatically by the platform and should not be provided.

name
string
required

Human-readable name for the agent. Must be unique within the organization. Examples: 'Customer Support Agent', 'Research Assistant'.

description
string | null
default:""

A brief description of what the agent does. Shown in agent listings and used by other agents when deciding delegation. Keep it concise and action-oriented.

icon
string | null
default:xpi:workflow:dusk

Icon shown next to the agent name: the platform icon id (default 'xpi:workflow:dusk') or a single emoji character.

avatar
string | null
default:male-avatar

Avatar identifier for the agent's visual representation in chat interfaces.

type
enum<string> | null
default:manager

The agent type. 'manager' is the standard type that supports tools, sub-agents, and multi-step execution. 'regular' is a simpler agent without orchestration capabilities. 'a2a' and 'curl' are for external agent integrations. 'orchestration' marks a workflow: create those through the Workflows API instead of setting it here.

Available options:
manager,
regular,
a2a,
curl,
orchestration
created_by
string | null

User ID of the creator. Auto-populated from the API key if not provided.

model_provider
enum<string> | null
default:anthropic

The LLM provider for this agent's reasoning. Must match an available provider from GET /llm_providers. Common values: 'anthropic' (default), 'openai', 'gemini'. Omit it together with model_name to follow the organization's default LLM.

Available options:
openai,
nim,
amazon_bedrock,
azure_ai_foundary,
huggingFace,
friendlyAI,
anthropic,
gemini,
fireworks,
google_ai_studio,
helicone,
bytedance,
tzafon_lightcone,
cerebras,
open_router,
nebius,
cloudflare_ai_gw,
z_ai
model_name
string | null
default:claude-sonnet-5

The specific model identifier within the chosen provider. Must match a model from GET /llm_providers/{provider}/models. Examples: 'claude-sonnet-5', 'gpt-4o', 'gemini-2.0-flash'.

llm_reasoning_effort
enum<string> | null
default:medium

Controls the depth of reasoning the LLM applies. 'low' for simple tasks, 'medium' for balanced performance, 'high' for complex reasoning, 'xhigh' for maximum reasoning depth (slower, more expensive).

Available options:
low,
medium,
high,
xhigh
llm_api_base
string | null

Custom API base URL for the LLM provider. Use this when connecting to a self-hosted or proxied LLM endpoint instead of the provider's default URL. Leave None to use the provider's standard endpoint.

llm_credentials_key
string | null

Reference key to stored LLM API credentials in the xpander.ai vault. When set, the agent uses these credentials instead of the organization's default. Create credentials via the platform settings.

llm_credentials_key_type
enum<string> | null
default:xpander

Type of credential storage. 'xpander' uses xpander.ai's built-in credential vault. 'custom' indicates externally managed credentials.

Available options:
xpander,
custom
llm_credentials
LLMCredentials · object | null

Direct LLM credentials object. Prefer using llm_credentials_key for secure credential management. Only use this for testing or when vault access is unavailable.

llm_extra_headers
Llm Extra Headers · object | null

Additional HTTP headers to include in every LLM API request. Useful for custom authentication, routing through gateways (e.g., Helicone, Cloudflare AI Gateway), or passing metadata.

instructions
AIAgentInstructions · object | null

Structured instructions that define the agent's behavior. Contains 'role' (list of role descriptions), 'goal' (list of objectives), and 'general' (free-form instructions text). These are injected into the agent's system prompt.

expected_output
string | null
default:""

Description of the expected output format and content. Guides the agent on what the final response should look like. Used in the system prompt to set output expectations.

output_format
enum<string> | null
default:markdown

The format for the agent's final response. 'markdown' for rich text, 'text' for plain text, 'json' for structured JSON output (pair with output_schema), 'voice' for speech synthesis.

Available options:
text,
markdown,
json,
voice
output_schema
Output Schema · object | null

JSON Schema defining the structure of the agent's output when output_format is 'json'. The agent will conform its response to match this schema. Must be a valid JSON Schema object.

framework
string | null
default:external-harness

How the agent runs. 'external-harness' (default): a coding CLI (claude-code, codex or opencode, chosen by harness_settings.default_cli). 'agno': the built-in xpander loop. Legacy 'claude-code' / 'codex' values read as 'external-harness' with that CLI.

deep_planning
boolean | null
default:false

Enable deep planning mode where the agent creates a detailed execution plan before taking actions. Useful for complex multi-step tasks. Increases latency but improves accuracy on complex workflows.

enforce_deep_planning
boolean | null
default:false

When True, forces the agent to always use deep planning regardless of task complexity. When False (default), the agent decides when to plan based on the task.

tools
(AddActionTool · object | AddCustomFunctionTool · object | AddMcpTool · object | AddSubAgentTool · object | AddWorkflowTool · object | AddSkillTool · object)[] | null

Tools to attach to the agent, in the unified simplified shape (the same payload as POST /v1/agents/{agent_id}/tools). This is the preferred way to attach tools — the API resolves catalog ids and wires the graph for you.

Each entry is one of (discriminated on type):

  • {"type": "action", "connection_id": "<connection_id>", "operation_ids": ["<catalog_op_id>", ...]}
  • {"type": "custom_function", "custom_function_id": ""}
  • {"type": "mcp", "mcp_id": "<registry_id>"} OR {"type": "mcp", "url": "https://...", "name": "...", "transport": "...", "auth_type": "...", "allowed_tools": [...]}
  • {"type": "agent", "agent_id": ""}
  • {"type": "workflow", "workflow_id": ""}
  • {"type": "skill", "skill_name": ""}

Resolves into attached_tools + graph server-side, so you don't need to construct those by hand. For advanced control you may still pass attached_tools/graph directly; when both are provided, tools are resolved and merged on top.

Attach connector operations as agent tools.

attached_tools
Connector · object[] | null

Advanced/low-level: list of connector connections with their operation IDs that this agent can use as tools. Prefer tools for the simplified shape. Each entry binds a connection (connector_organization) to specific operations the agent is allowed to invoke.

Structure: [{"id": "<connection_id>", "operation_ids": ["<catalog_operation_id_1>", "<catalog_operation_id_2>"]}]

  • 'id' is the connection ID (connector_organization.id) from POST /connectors/{connector_id}/connect
  • 'operation_ids' are the catalog operation _id values from GET /connectors/{connector_id}/{connection_id}/operations

If you provide attached_tools without corresponding graph entries, the API will automatically create graph items of type 'tool' for each operation, resolving catalog _id to operationId.

Special cases:

  • Custom functions: use id="xpander-custom-functions" and operation_ids=["<custom_function_id>", ...] Custom function IDs are the function UUIDs, not catalog operation IDs.
  • Sub-agents: do NOT use attached_tools. Add sub-agents directly to the 'graph' field with type='agent'.
  • MCP servers: do NOT use attached_tools. Add MCP servers directly to the 'graph' field with type='mcp'.

Example (connector operations): [{"id": "770832b8-c32b-4e4c-9ca2-232fec8099a7", "operation_ids": ["694bddfcd72d937c39875cf7"]}]

Example (custom functions): [{"id": "xpander-custom-functions", "operation_ids": ["my-function-uuid-1", "my-function-uuid-2"]}]

graph
AIAgentGraphItem · object[] | null

The agent's tool graph — defines which tools are available to the LLM and their execution flow. Each graph item represents a tool the agent can call during task execution.

For connector operations (type='tool'):

  • item_id: the operationId string (e.g., 'XpanderEmailServiceSendEmailWithHtmlOrTextContent')
  • name: human-readable name shown to the LLM (e.g., 'Send Email')
  • type: 'tool'
  • targets: list of graph item IDs that should execute after this tool (empty [] for no chaining)
  • NOTE: auto-created from attached_tools if not provided

For sub-agents (type='agent'):

  • item_id: the agent ID (UUID) to delegate work to
  • name: display name of the sub-agent
  • type: 'agent'
  • NO attached_tools entry needed — sub-agents are graph-only

For custom functions (type='tool', sub_type='custom_function'):

  • item_id: the custom function UUID
  • name: function name
  • type: 'tool'
  • Requires attached_tools entry with id='xpander-custom-functions'

For MCP servers (type='mcp'):

  • item_id: a unique ID for this MCP server instance
  • name: display name of the MCP server
  • type: 'mcp'
  • settings.mcp_settings: {url, transport, auth_type, name, allowed_tools, ...}
  • NO attached_tools entry needed — MCP servers are graph-only

NOTE: If you provide attached_tools with operation_ids but no corresponding graph items, the API will auto-create graph items with resolved operationId and pretty_name from catalog.

Examples: Connector tool: {"item_id": "SlackPostMessage", "name": "Send Slack Message", "type": "tool", "targets": []} Sub-agent: {"item_id": "agent-uuid-here", "name": "Research Agent", "type": "agent", "targets": []} MCP server: {"item_id": "mcp-uuid", "name": "Notion", "type": "mcp", "targets": [], "settings": {"mcp_settings": {"url": "https://mcp.notion.com/sse", "transport": "sse", "name": "Notion"}}}

knowledge_bases
AgentKnowledgeBase · object[] | null

Knowledge bases attached to this agent for RAG (Retrieval-Augmented Generation). Each entry references a knowledge base by ID and specifies the retrieval strategy ('vanilla' for simple retrieval, 'agentic_rag' for agent-driven retrieval).

source_nodes
AIAgentSourceNode · object[] | null

Entry points that can trigger this agent. Defines how the agent can be invoked — via SDK, scheduled tasks, webhooks, assistant UI, MCP, A2A protocol, Telegram, or Slack.

deployment_type
enum<string> | null
default:serverless

Where the agent runs. 'serverless' runs on xpander.ai's managed infrastructure (recommended). 'container' runs on your own infrastructure as a Docker container.

Available options:
serverless,
container
access_scope
enum<string> | null
default:personal

Who can access this agent. 'personal' restricts access to the creating user. 'organizational' makes it available to all organization members.

Available options:
personal,
organizational
environment_id
string | null

Target deployment environment ID. Leave None for the organization's default environment. Use this to deploy agents to specific on-premise or regional environments.

connectivity_details
AIAgentConnectivityDetailsA2A · object

Connection details for external agent integrations (A2A protocol or CURL-based). Only relevant when type is 'a2a' or 'curl'. For standard agents, leave as empty dict.

agno_settings
AgnoSettings · object | null

Configuration specific to the Agno framework. Controls session storage, coordinate mode (multi-agent), learning, memory strategies, guardrails (PII detection, prompt injection), tool call limits, and plan retry strategies. Only applies when framework is 'agno'.

harness_settings
HarnessSettings · object | null

Runtime settings for an 'external-harness' agent: default CLI, per-CLI models, permission mode, parallel task limit, working-directory retention, approval hold, image tag and per-turn sandbox ceilings (resources). Ignored for 'agno'.

task_level_strategies
TaskLevelStrategies · object | null

Execution strategies applied at the task level. Configure retry behavior (max retries), iterative execution (max iterations with stop conditions), stop strategies, daily run limits, and agentic context (persistent memory across runs).

notification_settings
NotificationSettings · object | null

Notification configuration for task completion events. Define notifications to send on success or error via email, Slack, or webhook. Each channel supports custom subject, body, and branding.

voice_id
string | null

Voice ID for text-to-speech output when output_format is 'voice'. References a voice profile in the platform's TTS service.

using_nemo
boolean | null
default:false

Enable NVIDIA NeMo guardrails integration for this agent. Provides additional safety and content filtering capabilities.

is_supervised
boolean | null
default:false

Enable supervised mode where the agent requires human approval before executing mutating operations (write/update/delete). Non-mutating operations (read/search) execute automatically.

is_autonomous
boolean | null
default:false

Run the agent in autonomous mode.

discoverable
boolean | null
default:true

When True, the agent is exposed to agent-discovery surfaces (e.g. omni). When False, it is hidden from discovery and can only be invoked directly.

with_auto_context_management
boolean | null
default:true

When True, the SDK runs its automatic context optimizer (compaction). When False, context management is skipped.

developer_access
boolean | null
default:true

When True, the agent is reachable from the developer API and webhook entry points. When False, external API/webhook invocation is rejected.

should_stage_before_publish
boolean | null
default:true

When True, edits are staged as a draft version before being published. When False, edits publish directly.

on_prem_event_streaming
boolean | null
default:true

Enable real-time event streaming for on-premise deployments. When True, task progress events are streamed to connected clients.

use_oidc_pre_auth
boolean | null
default:false

Enable OIDC pre-authentication for this agent. When enabled, the agent requires a valid OIDC token from the invoking user before execution. Used for user-context-aware operations.

pre_auth_audiences
string[] | null

List of allowed OIDC token audiences for pre-authentication validation. Only tokens with matching audience claims are accepted.

use_oidc_pre_auth_token_for_llm
boolean | null
default:false

When True, the user's OIDC token is forwarded to the LLM provider for authenticated LLM calls. Requires use_oidc_pre_auth to be enabled.

oidc_pre_auth_token_llm_audience
string | null

The audience claim to request when exchanging the user's OIDC token for LLM provider access. Only used when use_oidc_pre_auth_token_for_llm is True.

oidc_pre_auth_token_mcp_audience
string | null

The audience claim to request when exchanging the user's OIDC token for MCP server access. Enables user-context-aware MCP tool execution.

Response

Successful Response

name
string
required
organization_id
string
required
webhook_url
string
required
read-only
id
string | null
unique_name
string | null
origin_template
string | null
environment_id
string | null
runtime_environment_id
string | null

Runtime environment (image and environment spec) assigned to the agent, if any.

deployment_type
enum<string> | null
default:serverless
Available options:
serverless,
container
prompts
string[] | null
is_latest
boolean | null
default:false
has_pending_changes
boolean | null
default:false
deep_planning
boolean | null
default:true
enforce_deep_planning
boolean | null
default:true
use_agent_gateway
boolean | null
default:false
connectivity_details
AIAgentConnectivityDetailsA2A · object
framework
string | null
default:external-harness

How the agent runs: 'external-harness' (default; a coding CLI chosen by harness_settings.default_cli) or 'agno' (the built-in loop). Legacy 'claude-code' / 'codex' values read as 'external-harness' with that CLI.

description
string | null
default:""
tools
any[] | null
icon
string | null
default:xpi:workflow:dusk

Icon shown next to the agent name: the platform icon id (default 'xpi:workflow:dusk') or a single emoji.

avatar
string | null
default:male-avatar
source_nodes
AIAgentSourceNode · object[] | null
attached_tools
Connector · object[] | null
access_scope
enum<string> | null
default:organizational
Available options:
personal,
organizational
instructions
AIAgentInstructions · object | null
oas
Oas · object | null
graph
AIAgentGraphItem · object[] | null
is_omni
boolean | null
default:false
skills
Skills · object[] | null

Skills enabled for the agent (name, description, version), resolved at read time. Attached skills only; built-in runtime capabilities are not listed.

runtime_environment
Runtime Environment · object | null

Flattened environment spec resolved at read time; not persisted.

secret_bindings
Secret Bindings · object[] | null

Vault secrets bound to the agent as resolved for its runtime; null means none.

gated_commands
Gated Commands · object[] | null

Workspace commands that need approval before they run: {match, unless?, note?, approvers?, channels?} items where match is literal text. null means no gates; empty approvers asks the agent owner.

status
enum<string> | null
default:ACTIVE

Enumeration of possible agent statuses.

Attributes: DRAFT: Agent is in a draft state. ACTIVE: Agent is active and operational. INACTIVE: Agent is inactive and not operational.

Available options:
DRAFT,
ACTIVE,
INACTIVE
knowledge_bases
AgentKnowledgeBase · object[] | null
version
integer | null
default:1
created_by
string | null
default_user_id
string | null

Organization user to run as when a non-UI invocation has no resolved user.

background_user_overrides
Background User Overrides · object
created_at
string<date-time> | null
type
enum<string> | null

Enumeration of the agent types.

Attributes: Manager: marks the agent as a Managing agent. Regular: marks the agent as a regular agent. A2A: marks the agent as an external agent used via A2A protocol. Curl: marks the agent as an external agent used via a CURL. Orchestration: marks the agent as an Orchestration object.

Available options:
manager,
regular,
a2a,
curl,
orchestration
using_nemo
boolean | null
default:false
deletable
boolean | null
default:true
model_provider
enum<string> | null
default:amazon_bedrock
Available options:
openai,
nim,
amazon_bedrock,
azure_ai_foundary,
huggingFace,
friendlyAI,
anthropic,
gemini,
fireworks,
google_ai_studio,
helicone,
bytedance,
tzafon_lightcone,
cerebras,
open_router,
nebius,
cloudflare_ai_gw,
z_ai
model_name
string | null
default:global.anthropic.claude-sonnet-5
llm_reasoning_effort
enum<string> | null
default:medium
Available options:
low,
medium,
high,
xhigh
llm_api_base
string | null
output_format
enum<string> | null
default:markdown
Available options:
text,
markdown,
json,
voice
voice_id
string | null
output_schema
Output Schema · object | null
llm_credentials_key
string | null
llm_credentials_key_type
enum<string> | null
default:xpander
Available options:
xpander,
custom
llm_credentials
LLMCredentials · object | null
llm_extra_headers
Llm Extra Headers · object | null
expected_output
string | null
default:""
agno_settings
AgnoSettings · object | null
harness_settings
HarnessSettings · object | null

Runtime settings for an agent whose framework is 'external-harness'; null for 'agno' agents.

on_prem_event_streaming
boolean | null
default:true
is_supervised
boolean | null
default:false
orchestration_nodes
OrchestrationNode · object[] | null
notification_settings
NotificationSettings · object | null

Configuration for event-based notifications.

Attributes: on_success: Notifications to send when an operation succeeds. Maps notification types to a list of notification configurations. on_error: Notifications to send when an operation fails. Maps notification types to a list of notification configurations. on_budget: Notifications to send on budget threshold crossings. A dedicated category — budget alerts are not errors.

task_level_strategies
TaskLevelStrategies · object | null

Configuration object for task-level execution strategies.

This model groups optional strategy configurations that control how a task is executed and managed over time, including retries, iterative execution, stopping conditions, and daily run limits.

Attributes: retry_strategy: Optional retry policy configuration that defines how the task should behave when execution fails (e.g., max attempts, backoff rules).

use_oidc_pre_auth
boolean | null
default:false
pre_auth_audiences
string[] | null
use_oidc_pre_auth_token_for_llm
boolean | null
default:false
oidc_pre_auth_token_llm_audience
string | null
oidc_pre_auth_token_mcp_audience
string | null
can_self_schedule
boolean | null
default:true
max_self_schedules
integer | null
default:3
Required range: 1 <= x <= 1000
use_dynamic_tools
boolean | null
default:false
workspace_tools_enabled
boolean | null
default:true
live_surface_sharing_enabled
boolean | null
default:true

Whether the agent may share the live surfaces it builds.

is_autonomous
boolean | null
default:false
discoverable
boolean | null
default:true
with_auto_context_management
boolean | null
default:true
developer_access
boolean | null
default:true
should_stage_before_publish
boolean | null
default:true