> ## Documentation Index
> Fetch the complete documentation index at: https://docs.xpander.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Deploy Workflow
> Deploy a workflow to make it active and available for execution
Deploy a workflow to activate it for task execution. Validates the node graph, provisions necessary resources, and increments the version number. After deployment, the workflow is ready to receive triggers (webhook, API, chat, or schedule).
## Path Parameters
Unique identifier of the workflow (UUID)
## Response
Returns the deployed `WorkflowResponse` object with updated status.
## Example Request
```bash theme={"dark"}
curl -X PUT -H "x-api-key: " \
"https://api.xpander.ai/v1/workflows/"
```
## Notes
* Validates the node graph before deploying
* Increments the workflow version number
* The workflow must have a valid canvas with properly connected nodes to deploy successfully
* After deployment, all four trigger types become available (webhook, API, chat, schedule)
## OpenAPI
````yaml PUT /v1/workflows/{workflow_id}
openapi: 3.1.0
info:
title: xpander.ai API Service
description: |2-
The xpander.ai API Service provides a unified REST API for managing AI agents,
executing tasks, managing knowledge bases, and integrating with external systems.
Features:
- Agent Management: Create, update, deploy, and delete AI agents
- Task Execution: Invoke agents with support for sync, async, and streaming modes
- Knowledge Bases: Manage knowledge bases and documents for RAG workflows
- Tools: Discover, connect, and attach tools (connectors, custom functions, MCP servers, sub-agents, workflows) to agents and workflows
- MCP Integration: Model Context Protocol support for standardized AI interactions
Authentication: All endpoints require authentication via either an API key (`x-api-key`) or an OAuth2 JWT (`Authorization: Bearer `).
version: '0.001'
servers:
- url: https://api.xpander.ai
security: []
paths:
/v1/workflows/{workflow_id}:
put:
tags:
- API v1
- Workflows
- Workflows CRUD
summary: Deploy Workflow
description: >-
Deploy a workflow to make it active and available for execution.
Validates the workflow configuration and provisions necessary resources.
operationId: Deploy_Workflow_v1_workflows__workflow_id__put
parameters:
- name: workflow_id
in: path
required: true
schema:
type: string
title: Workflow Id
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/WorkflowResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- APIKeyHeader: []
components:
schemas:
WorkflowResponse:
properties:
id:
anyOf:
- type: string
- type: 'null'
title: Id
unique_name:
anyOf:
- type: string
- type: 'null'
title: Unique Name
origin_template:
anyOf:
- type: string
- type: 'null'
title: Origin Template
environment_id:
anyOf:
- type: string
- type: 'null'
title: Environment Id
deployment_type:
anyOf:
- $ref: '#/components/schemas/AIAgentDeploymentType'
- type: 'null'
default: serverless
prompts:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Prompts
default: []
is_latest:
anyOf:
- type: boolean
- type: 'null'
title: Is Latest
default: false
has_pending_changes:
anyOf:
- type: boolean
- type: 'null'
title: Has Pending Changes
default: false
deep_planning:
anyOf:
- type: boolean
- type: 'null'
title: Deep Planning
default: true
enforce_deep_planning:
anyOf:
- type: boolean
- type: 'null'
title: Enforce Deep Planning
default: true
use_agent_gateway:
anyOf:
- type: boolean
- type: 'null'
title: Use Agent Gateway
default: false
name:
type: string
title: Name
connectivity_details:
anyOf:
- $ref: '#/components/schemas/AIAgentConnectivityDetailsA2A'
- $ref: '#/components/schemas/AIAgentConnectivityDetailsCurl'
- additionalProperties: true
type: object
- type: 'null'
title: Connectivity Details
default: {}
framework:
anyOf:
- type: string
- type: 'null'
title: Framework
default: agno
description:
anyOf:
- type: string
- type: 'null'
title: Description
default: ''
tools:
anyOf:
- items: {}
type: array
- type: 'null'
title: Tools
default: []
icon:
anyOf:
- type: string
- type: 'null'
title: Icon
default: 🚀
avatar:
anyOf:
- type: string
- type: 'null'
title: Avatar
default: male-avatar
source_nodes:
anyOf:
- items:
$ref: '#/components/schemas/AIAgentSourceNode'
type: array
- type: 'null'
title: Source Nodes
default: []
attached_tools:
anyOf:
- items:
$ref: '#/components/schemas/Connector'
type: array
- type: 'null'
title: Attached Tools
default: []
access_scope:
anyOf:
- $ref: '#/components/schemas/AIAgentAccessScope'
- type: 'null'
default: personal
instructions:
anyOf:
- $ref: '#/components/schemas/AIAgentInstructions'
- type: 'null'
default:
role: []
goal: []
general: ''
oas:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Oas
default: {}
graph:
anyOf:
- items:
$ref: '#/components/schemas/AIAgentGraphItem-Output'
type: array
- type: 'null'
title: Graph
default: []
is_omni:
anyOf:
- type: boolean
- type: 'null'
title: Is Omni
default: false
skills:
anyOf:
- items:
additionalProperties: true
type: object
type: array
- type: 'null'
title: Skills
default: []
status:
anyOf:
- $ref: '#/components/schemas/AgentStatus'
- type: 'null'
default: ACTIVE
knowledge_bases:
anyOf:
- items:
$ref: '#/components/schemas/AgentKnowledgeBase'
type: array
- type: 'null'
title: Knowledge Bases
default: []
version:
anyOf:
- type: integer
- type: 'null'
title: Version
default: 1
organization_id:
type: string
title: Organization Id
created_by:
anyOf:
- type: string
- type: 'null'
title: Created By
created_at:
anyOf:
- type: string
format: date-time
- type: 'null'
title: Created At
type:
anyOf:
- $ref: '#/components/schemas/AgentType'
- type: 'null'
using_nemo:
anyOf:
- type: boolean
- type: 'null'
title: Using Nemo
default: false
deletable:
anyOf:
- type: boolean
- type: 'null'
title: Deletable
default: true
model_provider:
anyOf:
- $ref: '#/components/schemas/LLMModelProvider'
- type: 'null'
default: anthropic
model_name:
anyOf:
- type: string
- type: 'null'
title: Model Name
default: claude-sonnet-4-6
llm_reasoning_effort:
anyOf:
- $ref: '#/components/schemas/LLMReasoningEffort'
- type: 'null'
default: medium
llm_api_base:
anyOf:
- type: string
- type: 'null'
title: Llm Api Base
output_format:
anyOf:
- $ref: '#/components/schemas/OutputFormat'
- type: 'null'
default: markdown
voice_id:
anyOf:
- type: string
- type: 'null'
title: Voice Id
output_schema:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Output Schema
llm_credentials_key:
anyOf:
- type: string
- type: 'null'
title: Llm Credentials Key
llm_credentials_key_type:
anyOf:
- $ref: '#/components/schemas/LLMCredentialsKeyType'
- type: 'null'
default: xpander
llm_credentials:
anyOf:
- $ref: '#/components/schemas/LLMCredentials'
- type: 'null'
llm_extra_headers:
anyOf:
- additionalProperties:
type: string
type: object
- type: 'null'
title: Llm Extra Headers
default: {}
expected_output:
anyOf:
- type: string
- type: 'null'
title: Expected Output
default: ''
agno_settings:
anyOf:
- $ref: '#/components/schemas/AgnoSettings'
- type: 'null'
default:
session_storage: true
learning: false
agent_memories: false
agentic_culture: false
user_memories: false
agentic_memory: false
session_summaries: false
num_history_runs: 50
max_tool_calls_from_history: 0
tool_call_limit: 0
coordinate_mode: true
pii_detection_enabled: false
pii_detection_mask: true
prompt_injection_detection_enabled: false
openai_moderation_enabled: false
reasoning_tools_enabled: true
max_plan_retries: 15
on_prem_event_streaming:
anyOf:
- type: boolean
- type: 'null'
title: On Prem Event Streaming
default: true
is_supervised:
anyOf:
- type: boolean
- type: 'null'
title: Is Supervised
default: false
orchestration_nodes:
anyOf:
- items:
$ref: '#/components/schemas/OrchestrationNode-Output'
type: array
- type: 'null'
title: Orchestration Nodes
default: []
notification_settings:
anyOf:
- $ref: '#/components/schemas/NotificationSettings-Output'
- type: 'null'
default: {}
task_level_strategies:
anyOf:
- $ref: '#/components/schemas/TaskLevelStrategies-Output'
- type: 'null'
use_oidc_pre_auth:
anyOf:
- type: boolean
- type: 'null'
title: Use Oidc Pre Auth
default: false
pre_auth_audiences:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Pre Auth Audiences
default: []
use_oidc_pre_auth_token_for_llm:
anyOf:
- type: boolean
- type: 'null'
title: Use Oidc Pre Auth Token For Llm
default: false
oidc_pre_auth_token_llm_audience:
anyOf:
- type: string
- type: 'null'
title: Oidc Pre Auth Token Llm Audience
oidc_pre_auth_token_mcp_audience:
anyOf:
- type: string
- type: 'null'
title: Oidc Pre Auth Token Mcp Audience
can_self_schedule:
anyOf:
- type: boolean
- type: 'null'
title: Can Self Schedule
default: false
max_self_schedules:
anyOf:
- type: integer
maximum: 1000
minimum: 1
- type: 'null'
title: Max Self Schedules
default: 3
use_dynamic_tools:
anyOf:
- type: boolean
- type: 'null'
title: Use Dynamic Tools
default: false
workspace_tools_enabled:
anyOf:
- type: boolean
- type: 'null'
title: Workspace Tools Enabled
default: true
webhook_url:
type: string
title: Webhook Url
readOnly: true
type: object
required:
- name
- organization_id
- webhook_url
title: WorkflowResponse
description: >-
Response model for workflow endpoints.
Inherits from AIAgent but excludes agent-specific fields that are not
relevant to workflows (orchestrations). This provides a clean API
surface
for workflow consumers without exposing confusing agent-only concepts.
The workflow's execution logic is defined in `orchestration_nodes` — a
DAG
of typed nodes. Agent-specific fields like `graph`, `attached_tools`,
`delegation_*`, `framework`, and `agno_settings` are hidden.
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
AIAgentDeploymentType:
type: string
enum:
- serverless
- container
title: AIAgentDeploymentType
AIAgentConnectivityDetailsA2A:
properties:
custom_headers:
anyOf:
- additionalProperties:
type: string
type: object
- type: 'null'
title: Custom Headers
default: {}
auth_type:
anyOf:
- $ref: '#/components/schemas/AIAgentConnectivityDetailsA2AAuthType'
- type: 'null'
default: none
api_key_header_name:
anyOf:
- type: string
- type: 'null'
title: Api Key Header Name
default: X-API-Key
auth_value:
anyOf:
- type: string
- type: 'null'
title: Auth Value
agent_url:
type: string
title: Agent Url
type: object
required:
- agent_url
title: AIAgentConnectivityDetailsA2A
AIAgentConnectivityDetailsCurl:
properties:
custom_headers:
anyOf:
- additionalProperties:
type: string
type: object
- type: 'null'
title: Custom Headers
default: {}
auth_type:
anyOf:
- $ref: '#/components/schemas/AIAgentConnectivityDetailsA2AAuthType'
- type: 'null'
default: none
api_key_header_name:
anyOf:
- type: string
- type: 'null'
title: Api Key Header Name
default: X-API-Key
auth_value:
anyOf:
- type: string
- type: 'null'
title: Auth Value
curl_command:
type: string
title: Curl Command
invoke_url:
anyOf:
- type: string
- type: 'null'
title: Invoke Url
method:
anyOf:
- type: string
- type: 'null'
title: Method
default: POST
prompt_field_name:
anyOf:
- type: string
- type: 'null'
title: Prompt Field Name
default: ''
files_field_name:
anyOf:
- type: string
- type: 'null'
title: Files Field Name
default: ''
task_id_field_name:
anyOf:
- type: string
- type: 'null'
title: Task Id Field Name
default: ''
type: object
required:
- curl_command
title: AIAgentConnectivityDetailsCurl
AIAgentSourceNode:
properties:
id:
anyOf:
- type: string
- type: 'null'
title: Id
type:
$ref: '#/components/schemas/SourceNodeType'
targets:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Targets
metadata:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Metadata
default: {}
type: object
required:
- type
title: AIAgentSourceNode
Connector:
properties:
id:
type: string
title: Id
operation_ids:
items:
type: string
type: array
title: Operation Ids
type: object
required:
- id
- operation_ids
title: Connector
description: >-
Connector model representing the structure of a connector with an ID and
associated operation IDs.
Attributes:
id (str): The unique identifier for the connector.
operation_ids (list[str]): A list of operation IDs associated with the connector.
AIAgentAccessScope:
type: string
enum:
- personal
- organizational
title: AIAgentAccessScope
AIAgentInstructions:
properties:
role:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Role
default: []
goal:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Goal
default: []
general:
anyOf:
- type: string
- type: 'null'
title: General
default: ''
type: object
title: AIAgentInstructions
AIAgentGraphItem-Output:
properties:
id:
anyOf:
- type: string
- type: 'null'
title: Id
item_id:
type: string
title: Item Id
name:
anyOf:
- type: string
- type: 'null'
title: Name
type:
$ref: '#/components/schemas/AIAgentGraphItemType'
sub_type:
anyOf:
- $ref: '#/components/schemas/AIAgentGraphItemSubType'
- type: 'null'
targets:
items:
type: string
type: array
title: Targets
settings:
anyOf:
- $ref: '#/components/schemas/AIAgentGraphItemSettings-Output'
- type: 'null'
is_first:
anyOf:
- type: boolean
- type: 'null'
title: Is First
default: false
type: object
required:
- item_id
- type
- targets
title: AIAgentGraphItem
AgentStatus:
type: string
enum:
- DRAFT
- ACTIVE
- INACTIVE
title: AgentStatus
description: |-
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.
AgentKnowledgeBase:
properties:
id:
type: string
title: Id
name:
anyOf:
- type: string
- type: 'null'
title: Name
description:
anyOf:
- type: string
- type: 'null'
title: Description
strategy:
$ref: '#/components/schemas/KnowledgeBaseStrategy'
rw:
anyOf:
- type: boolean
- type: 'null'
title: Rw
default: false
documents:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Documents
default: []
type: object
required:
- id
- strategy
title: AgentKnowledgeBase
AgentType:
type: string
enum:
- manager
- regular
- a2a
- curl
- orchestration
title: AgentType
description: |-
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.
LLMModelProvider:
type: string
enum:
- openai
- nim
- amazon_bedrock
- azure_ai_foundary
- huggingFace
- friendlyAI
- anthropic
- gemini
- fireworks
- google_ai_studio
- helicone
- bytedance
- tzafon_lightcone
- open_router
- nebius
- cloudflare_ai_gw
title: LLMModelProvider
LLMReasoningEffort:
type: string
enum:
- low
- medium
- high
- xhigh
title: LLMReasoningEffort
OutputFormat:
type: string
enum:
- text
- markdown
- json
- voice
title: OutputFormat
LLMCredentialsKeyType:
type: string
enum:
- xpander
- custom
title: LLMCredentialsKeyType
LLMCredentials:
properties:
name:
type: string
title: Name
description:
anyOf:
- type: string
- type: 'null'
title: Description
value:
type: string
title: Value
type: object
required:
- name
- value
title: LLMCredentials
AgnoSettings:
properties:
session_storage:
anyOf:
- type: boolean
- type: 'null'
title: Session Storage
default: true
learning:
anyOf:
- type: boolean
- type: 'null'
title: Learning
default: false
agent_memories:
anyOf:
- type: boolean
- type: 'null'
title: Agent Memories
default: false
agentic_culture:
anyOf:
- type: boolean
- type: 'null'
title: Agentic Culture
default: false
user_memories:
anyOf:
- type: boolean
- type: 'null'
title: User Memories
default: false
agentic_memory:
anyOf:
- type: boolean
- type: 'null'
title: Agentic Memory
default: false
session_summaries:
anyOf:
- type: boolean
- type: 'null'
title: Session Summaries
default: false
num_history_runs:
anyOf:
- type: integer
- type: 'null'
title: Num History Runs
default: 50
max_tool_calls_from_history:
anyOf:
- type: integer
- type: 'null'
title: Max Tool Calls From History
default: 0
tool_call_limit:
anyOf:
- type: integer
- type: 'null'
title: Tool Call Limit
default: 0
coordinate_mode:
anyOf:
- type: boolean
- type: 'null'
title: Coordinate Mode
default: true
pii_detection_enabled:
anyOf:
- type: boolean
- type: 'null'
title: Pii Detection Enabled
default: false
pii_detection_mask:
anyOf:
- type: boolean
- type: 'null'
title: Pii Detection Mask
default: true
prompt_injection_detection_enabled:
anyOf:
- type: boolean
- type: 'null'
title: Prompt Injection Detection Enabled
default: false
openai_moderation_enabled:
anyOf:
- type: boolean
- type: 'null'
title: Openai Moderation Enabled
default: false
openai_moderation_categories:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Openai Moderation Categories
reasoning_tools_enabled:
anyOf:
- type: boolean
- type: 'null'
title: Reasoning Tools Enabled
default: true
max_plan_retries:
anyOf:
- type: integer
- type: 'null'
title: Max Plan Retries
default: 15
type: object
title: AgnoSettings
OrchestrationNode-Output:
properties:
type:
$ref: '#/components/schemas/OrchestrationNodeType'
id:
type: string
title: Id
next_node_ids:
items:
type: string
type: array
title: Next Node Ids
name:
anyOf:
- type: string
- type: 'null'
title: Name
description:
anyOf:
- type: string
- type: 'null'
title: Description
condition:
anyOf:
- $ref: '#/components/schemas/OrchestrationCondition'
- type: 'null'
retry_strategy:
anyOf:
- $ref: '#/components/schemas/OrchestrationRetryStrategy'
- type: 'null'
iterative_strategy:
anyOf:
- $ref: '#/components/schemas/OrchestrationIterativeStrategy-Output'
- type: 'null'
stop_strategy:
anyOf:
- $ref: '#/components/schemas/OrchestrationStopStrategy-Output'
- type: 'null'
definition:
anyOf:
- $ref: '#/components/schemas/OrchestrationCodeNode'
- $ref: '#/components/schemas/OrchestrationClassifierNode-Output'
- $ref: '#/components/schemas/OrchestrationPointerNode'
- $ref: '#/components/schemas/OrchestrationWaitNode-Output'
- $ref: '#/components/schemas/OrchestrationGuardrailNode-Output'
- $ref: '#/components/schemas/OrchestrationSummarizerNode-Output'
- $ref: '#/components/schemas/OrchestrationSendToEndNode'
- $ref: '#/components/schemas/OrchestrationSelfScheduleNode'
- $ref: '#/components/schemas/OrchestrationNodePointerDefinition'
- $ref: '#/components/schemas/OrchestrationParallelNode-Output'
title: Definition
input_type:
anyOf:
- $ref: '#/components/schemas/OutputFormat'
- type: 'null'
default: text
input_schema:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Input Schema
input_instructions:
anyOf:
- type: string
- type: 'null'
title: Input Instructions
agentic_context_input_instructions:
anyOf:
- type: string
- type: 'null'
title: Agentic Context Input Instructions
agentic_context_output_instructions:
anyOf:
- type: string
- type: 'null'
title: Agentic Context Output Instructions
return_this:
anyOf:
- type: boolean
- type: 'null'
title: Return This
default: false
type: object
required:
- type
- definition
title: OrchestrationNode
description: >-
A node in an orchestration workflow.
Represents a single execution unit in an orchestration with control
flow,
execution strategies, and a specific node type definition.
Attributes:
type: Type of the node (must match the definition type).
id: Unique identifier for the node. Auto-generated if not provided.
next_node_ids: List of IDs of the next nodes to execute.
name: Human-readable name for the node.
description: Detailed description of the node's purpose.
condition: Conditional logic for executing this node.
retry_strategy: Strategy for retrying failed executions.
iterative_strategy: Strategy for iterative execution.
stop_strategy: Strategy for stopping the workflow.
definition: The actual node implementation (code, classifier, pointer, or wait).
input_type: Expected input format. Defaults to Text.
input_schema: JSON schema for structured input validation.
input_instructions: Instructions to use for structured input.
agentic_context_input_instructions: Instructions to use for agentic context injection.
agentic_context_output_instructions: Instructions to use for agentic context update.
NotificationSettings-Output:
properties:
on_success:
anyOf:
- additionalProperties:
items:
anyOf:
- $ref: '#/components/schemas/EmailNotificationSettings'
- $ref: '#/components/schemas/SlackNotificationSettings'
- $ref: '#/components/schemas/WebhookNotificationSettings'
type: array
propertyNames:
enum:
- email
- slack
- webhook
type: object
- type: 'null'
title: On Success
default: {}
on_error:
anyOf:
- additionalProperties:
items:
anyOf:
- $ref: '#/components/schemas/EmailNotificationSettings'
- $ref: '#/components/schemas/SlackNotificationSettings'
- $ref: '#/components/schemas/WebhookNotificationSettings'
type: array
propertyNames:
enum:
- email
- slack
- webhook
type: object
- type: 'null'
title: On Error
default: {}
type: object
title: NotificationSettings
description: |-
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.
TaskLevelStrategies-Output:
properties:
retry_strategy:
anyOf:
- $ref: '#/components/schemas/OrchestrationRetryStrategy'
- type: 'null'
iterative_strategy:
anyOf:
- $ref: '#/components/schemas/OrchestrationIterativeStrategy-Output'
- type: 'null'
stop_strategy:
anyOf:
- $ref: '#/components/schemas/OrchestrationStopStrategy-Output'
- type: 'null'
max_runs_per_day:
anyOf:
- type: integer
- type: 'null'
title: Max Runs Per Day
agentic_context_enabled:
anyOf:
- type: boolean
- type: 'null'
title: Agentic Context Enabled
default: false
duplication_prevention:
anyOf:
- $ref: '#/components/schemas/DuplicationPreventionSettings'
- type: 'null'
slackbot_formatting_instructions:
anyOf:
- type: string
- type: 'null'
title: Slackbot Formatting Instructions
type: object
title: TaskLevelStrategies
description: >-
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).
iterative_strategy:
Optional iterative execution configuration for tasks that may run in
repeated cycles/steps until completion or a stop condition is met.
stop_strategy:
Optional stopping policy configuration that defines when the task
should stop running (e.g., timeout, max iterations, success criteria).
max_runs_per_day:
Optional limit on how many times the task is allowed to run within a
24-hour period. If not set, no explicit daily limit is enforced.
agentic_context_enabled:
if agentic memory is enabled and accesible to the executor.
slackbot_formatting_instructions:
Optional SlackBot formatting instructions
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
type: object
required:
- loc
- msg
- type
title: ValidationError
AIAgentConnectivityDetailsA2AAuthType:
type: string
enum:
- none
- api_key
- basic
- bearer
title: AIAgentConnectivityDetailsA2AAuthType
SourceNodeType:
type: string
enum:
- workbench
- sdk
- task
- assistant
- webhook
- mcp
- a2a
- telegram
- slack
title: SourceNodeType
AIAgentGraphItemType:
type: string
enum:
- source_node
- agent
- workflow
- tool
- human_in_the_loop
- xpsleep-agent-delay
- custom_agent
- storage
- local_db
- coding_agent
- mcp
- skills
title: AIAgentGraphItemType
AIAgentGraphItemSubType:
type: string
enum:
- sdk
- task
- assistant
- webhook
- operation
- custom_function
- local_tool
title: AIAgentGraphItemSubType
AIAgentGraphItemSettings-Output:
properties:
instructions:
anyOf:
- type: string
- type: 'null'
title: Instructions
description:
anyOf:
- type: string
- type: 'null'
title: Description
schemas:
anyOf:
- $ref: '#/components/schemas/AIAgentGraphItemSchema'
- type: 'null'
advanced_filtering_options:
anyOf:
- $ref: '#/components/schemas/AIAgentGraphItemAdvancedFilteringOption'
- type: 'null'
hitl_options:
anyOf:
- $ref: '#/components/schemas/AIAgentGraphItemHITLSettings'
- type: 'null'
a2a_options:
anyOf:
- $ref: '#/components/schemas/AIAgentGraphItemA2ASettings'
- type: 'null'
coding_agent_settings:
anyOf:
- $ref: '#/components/schemas/AIAgentGraphItemCodingAgentSettings'
- type: 'null'
mcp_settings:
anyOf:
- $ref: '#/components/schemas/AIAgentGraphItemMCPSettings'
- type: 'null'
skills_settings:
anyOf:
- $ref: '#/components/schemas/AIAgentGraphItemSkillsSettings'
- type: 'null'
use_cache:
anyOf:
- type: boolean
- type: 'null'
title: Use Cache
default: false
type: object
title: AIAgentGraphItemSettings
KnowledgeBaseStrategy:
type: string
enum:
- vanilla
- agentic_rag
title: KnowledgeBaseStrategy
OrchestrationNodeType:
type: string
enum:
- custom_function
- code
- agent
- orchestration
- classifier
- wait
- action
- guardrail
- summarizer
- send_to_end
- node_pointer
- parallel
- self_schedule
title: OrchestrationNodeType
description: |-
Types of nodes available in an orchestration workflow.
Attributes:
CustomFunction: Node that executes a custom function.
Code: Node that executes arbitrary code.
Agent: Node that invokes an AI agent.
Orchestration: Node that references another orchestration.
Classifier: Node that classifies inputs using LLM.
Wait: Node that pauses execution until a condition is met.
Action: Node that triggers an action (api).
Guardrail: Node that enforces guardrails on inputs using LLM.
Summarizer: Node that summarizes or extracts information from inputs using LLM.
OrchestrationCondition:
properties:
type:
$ref: '#/components/schemas/OrchestrationConditionType'
term:
anyOf:
- type: string
- type: 'null'
title: Term
group_id:
anyOf:
- type: string
- type: 'null'
title: Group Id
path:
anyOf:
- type: string
- type: 'null'
title: Path
value:
anyOf:
- {}
- type: 'null'
title: Value
type: object
required:
- type
title: OrchestrationCondition
description: |-
Condition for controlling orchestration flow.
Attributes:
type: Type of condition (regex, contains, else, or comparison operators).
term: The pattern or string to match against. Used for 'regex' and 'contains' types.
group_id: Optional group ID for group-based classifier routing.
When set, routing matches by group ID instead of term matching.
path: Path to extract value from input data (e.g., "input.client_id" or "client_id").
Used for comparison operators (equal, not_equal, gt, lt, gte, lte, not_empty).
value: Value to compare against. Used with comparison operators.
Not required for 'not_empty' type.
OrchestrationRetryStrategy:
properties:
enabled:
anyOf:
- type: boolean
- type: 'null'
title: Enabled
default: false
max_retries:
anyOf:
- type: integer
- type: 'null'
title: Max Retries
default: 3
type: object
title: OrchestrationRetryStrategy
description: |-
Strategy for retrying failed orchestration nodes.
Attributes:
enabled: Whether retry is enabled for this node.
max_retries: Maximum number of retry attempts. Defaults to 3.
OrchestrationIterativeStrategy-Output:
properties:
enabled:
anyOf:
- type: boolean
- type: 'null'
title: Enabled
default: false
max_iterations:
anyOf:
- type: integer
- type: 'null'
title: Max Iterations
default: 3
end_condition:
anyOf:
- $ref: '#/components/schemas/OrchestrationCondition'
- type: 'null'
type: object
title: OrchestrationIterativeStrategy
description: |-
Strategy for iteratively executing orchestration nodes.
Attributes:
enabled: Whether iterative execution is enabled.
max_iterations: Maximum number of iterations. Defaults to 3.
end_condition: Optional condition to stop iteration early.
OrchestrationStopStrategy-Output:
properties:
enabled:
anyOf:
- type: boolean
- type: 'null'
title: Enabled
default: false
stop_on_failure:
anyOf:
- type: boolean
- type: 'null'
title: Stop On Failure
default: true
stop_on_condition:
anyOf:
- $ref: '#/components/schemas/OrchestrationCondition'
- type: 'null'
type: object
title: OrchestrationStopStrategy
description: |-
Strategy for stopping orchestration execution.
Attributes:
enabled: Whether the stop strategy is enabled.
stop_on_failure: Whether to stop the entire orchestration on node failure.
stop_on_condition: Optional condition that will stop execution if met.
OrchestrationCodeNode:
properties:
code:
type: string
title: Code
type: object
required:
- code
title: OrchestrationCodeNode
description: |-
Node that executes arbitrary code.
Attributes:
code: The code string to execute.
OrchestrationClassifierNode-Output:
properties:
groups:
items:
$ref: '#/components/schemas/ClassificationGroup'
type: array
title: Groups
output_type:
anyOf:
- $ref: '#/components/schemas/OutputFormat'
- type: 'null'
default: text
output_schema:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Output Schema
instructions:
anyOf:
- type: string
- type: 'null'
title: Instructions
examples:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Examples
default: []
settings:
$ref: '#/components/schemas/OrchestrationClassifierNodeLLMSettings'
type: object
required:
- groups
- settings
title: OrchestrationClassifierNode
description: |-
Node that uses LLM to classify inputs into groups.
Attributes:
groups: List of classification groups to evaluate against.
output_type: Expected output format. Defaults to Text.
output_schema: JSON schema for structured output validation.
instructions: Classification or transformation instructions for the LLM.
examples: Example inputs/outputs to guide the LLM behavior.
settings: LLM configuration settings.
OrchestrationPointerNode:
properties:
asset_id:
type: string
title: Asset Id
type:
type: string
enum:
- agent
- custom_function
- orchestration
- action
title: Type
output_type:
anyOf:
- $ref: '#/components/schemas/OutputFormat'
- type: 'null'
default: text
output_schema:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Output Schema
instructions:
anyOf:
- type: string
- type: 'null'
title: Instructions
instructions_mode:
anyOf:
- $ref: '#/components/schemas/OrchestrationPointerNodeInstructionsMode'
- type: 'null'
default: append
ignore_response:
anyOf:
- type: boolean
- type: 'null'
title: Ignore Response
default: false
persist_thread_id:
anyOf:
- type: boolean
- type: 'null'
title: Persist Thread Id
default: true
schema_override:
anyOf:
- $ref: '#/components/schemas/SchemaOverride'
- type: 'null'
type: object
required:
- asset_id
- type
title: OrchestrationPointerNode
description: >-
Node that references an external asset (agent, function, or
orchestration).
Attributes:
asset_id: Unique identifier of the asset to execute.
type: Type of asset being referenced.
output_type: Expected output format. Defaults to Text.
output_schema: JSON schema for structured output validation.
instructions: Optional instructions for the pointer node (Action only).
instructions_mode: Mode to use for pointer node, specifically for agent nodes.
ignore_response: Should ignore the node result and proceed with previous result?.
persist_thread_id: Should persist the thread in agent nodes? default (True).
schema_override: Optional schema override with permanentValue fields for fixed values.
OrchestrationWaitNode-Output:
properties:
type:
type: string
enum:
- webhook
- hitl
title: Type
definition:
anyOf:
- $ref: '#/components/schemas/EmailNotificationSettings'
- $ref: '#/components/schemas/SlackNotificationSettings'
- $ref: '#/components/schemas/WebhookNotificationSettings'
title: Definition
type: object
required:
- type
- definition
title: OrchestrationWaitNode
description: |-
Node that pauses execution until an external event occurs.
Attributes:
type: Type of wait event (webhook or human-in-the-loop).
definition: Notification configuration for triggering continuation.
OrchestrationGuardrailNode-Output:
properties:
groups:
items:
$ref: '#/components/schemas/ClassificationGroup'
type: array
title: Groups
examples:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Examples
default: []
settings:
$ref: '#/components/schemas/OrchestrationClassifierNodeLLMSettings'
type: object
required:
- groups
- settings
title: OrchestrationGuardrailNode
description: >-
Node that uses LLM to evaluate input against pass/fail criteria.
This node works like a classifier with exactly 2 groups: "pass" and
"fail".
The user defines evaluation_criteria for each group.
Routing behavior:
- If guardrail passes: routes to downstream node with condition
group_id="pass"
- If guardrail fails: routes to downstream node with condition
group_id="fail"
- If no fail route exists: falls back to end nodes (end-summarizer or
end-classifier)
- A pass route is REQUIRED; fail route is optional.
Attributes:
groups: List of 2 ClassificationGroup objects with IDs "pass" and "fail".
Each group has evaluation_criteria defined by the user.
examples: Example inputs/outputs to guide the LLM behavior.
settings: LLM configuration settings.
OrchestrationSummarizerNode-Output:
properties:
instructions:
type: string
title: Instructions
examples:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Examples
default: []
settings:
$ref: '#/components/schemas/OrchestrationClassifierNodeLLMSettings'
type: object
required:
- instructions
- settings
title: OrchestrationSummarizerNode
description: >-
Node that processes large payloads and answers specific questions.
This node uses an LLM to summarize or extract information from large
inputs.
Attributes:
instructions: Summarization or question-answering instructions for the LLM.
examples: Example inputs/outputs to guide the LLM behavior.
settings: LLM configuration settings.
OrchestrationSendToEndNode:
properties:
message:
anyOf:
- type: string
- type: 'null'
title: Message
type: object
title: OrchestrationSendToEndNode
description: |-
Node that routes execution to end nodes or finishes the workflow.
When triggered, this node will:
1. Route to end nodes (end-summarizer, end-classifier) if they exist
2. Finish workflow execution immediately if no end nodes exist
Attributes:
message: Optional message or reason for finishing the workflow.
OrchestrationSelfScheduleNode:
properties:
when:
type: string
title: When
target_node_id:
type: string
title: Target Node Id
prompt:
anyOf:
- type: string
- type: 'null'
title: Prompt
max_reschedules:
type: integer
maximum: 100
minimum: 1
title: Max Reschedules
default: 1
type: object
required:
- when
- target_node_id
title: OrchestrationSelfScheduleNode
description: >-
Node that pauses the workflow and schedules itself to resume at a later
time.
At runtime the worker's self-schedule executor:
1. LLM-parses ``when`` (free-text like "in 1 hour", "next Monday 9am") into an
absolute ISO-8601 ``run_at`` using the current datetime / user timezone.
2. Creates a row in ``ai_agents_self_schedules`` with the current ``task_id``
and ``workflow_next_node = target_node_id``.
3. Pauses the task.
When APScheduler fires the row, the same task is re-invoked with
``payload_extension={"workflow_next_node": target_node_id}`` and the
worker
resumes execution starting from the target node, re-running target + its
forward cone and skipping everything outside that cone.
``target_node_id`` may point to ANY node in the orchestration (forward,
backward, or sibling). Backward jumps are bounded by ``max_reschedules``
so
loops cannot run away.
Attributes:
when: Free-text schedule expression, parsed by the worker via an LLM.
target_node_id: The id of the node to resume at. Must exist in the
orchestration; no topological constraint.
prompt: Optional instruction appended to the upstream node's result
before being sent as the scheduled run's prompt. If both the upstream
result and this prompt are empty, the node fails rather than creating
an empty row.
max_reschedules: Maximum number of times this node may fire during a
single task lifecycle. Once reached, the executor falls through and
the graph proceeds via ``next_node_ids``. Defaults to 1.
OrchestrationNodePointerDefinition:
properties:
source_node_id:
type: string
title: Source Node Id
type: object
required:
- source_node_id
title: OrchestrationNodePointerDefinition
description: >-
Definition for a NodePointer node that acts as a graph-position jump.
A NodePointer jumps execution to another node's position in the graph.
At resolution time, the pointer adopts the source node's definition,
type,
AND next_node_ids — so after executing the source's logic, the flow
continues to the source's original downstream targets.
The pointer keeps its own id, name, condition, and strategies.
Attributes:
source_node_id: ID of the node to jump to.
OrchestrationParallelNode-Output:
properties:
nodes:
items:
$ref: '#/components/schemas/OrchestrationNode-Output'
type: array
title: Nodes
output_type:
anyOf:
- $ref: '#/components/schemas/OutputFormat'
- type: 'null'
default: text
output_schema:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Output Schema
output_instructions:
anyOf:
- type: string
- type: 'null'
title: Output Instructions
type: object
required:
- nodes
title: OrchestrationParallelNode
description: >-
Node that executes multiple child nodes in parallel.
All child nodes receive the same input (the output of the preceding
node).
When all child nodes complete, their results are combined:
- JSON outputs are merged into a single JSON object keyed by node name.
- String outputs are concatenated with node name headers.
Attributes:
nodes: List of child OrchestrationNode objects to execute in parallel.
output_type: Expected output format for the combined result. Defaults to Text.
output_schema: JSON schema for structured output validation of the combined result.
output_instructions: Instructions for transforming the combined output into the schema.
EmailNotificationSettings:
properties:
subject:
anyOf:
- type: string
- type: 'null'
title: Subject
body:
anyOf:
- type: string
- type: 'null'
title: Body
approve_button_text:
anyOf:
- type: string
- type: 'null'
title: Approve Button Text
default: Approve
deny_button_text:
anyOf:
- type: string
- type: 'null'
title: Deny Button Text
default: Deny
logo_url:
anyOf:
- type: string
- type: 'null'
title: Logo Url
default: https://assets.xpanderai.io/xpander-logo.png
to:
items:
type: string
type: array
title: To
type: object
required:
- to
title: EmailNotificationSettings
description: |-
Configuration for email notifications.
Attributes:
to: List of recipient email addresses.
SlackNotificationSettings:
properties:
subject:
anyOf:
- type: string
- type: 'null'
title: Subject
body:
anyOf:
- type: string
- type: 'null'
title: Body
approve_button_text:
anyOf:
- type: string
- type: 'null'
title: Approve Button Text
default: Approve
deny_button_text:
anyOf:
- type: string
- type: 'null'
title: Deny Button Text
default: Deny
logo_url:
anyOf:
- type: string
- type: 'null'
title: Logo Url
default: https://assets.xpanderai.io/xpander-logo.png
channels:
items:
type: string
type: array
title: Channels
credentials:
$ref: '#/components/schemas/SlackCredentials'
type: object
required:
- channels
- credentials
title: SlackNotificationSettings
description: |-
Configuration for Slack notifications.
Attributes:
channels: List of Slack channel IDs or names to post to.
credentials: Slack API authentication credentials.
WebhookNotificationSettings:
properties:
subject:
anyOf:
- type: string
- type: 'null'
title: Subject
body:
anyOf:
- type: string
- type: 'null'
title: Body
approve_button_text:
anyOf:
- type: string
- type: 'null'
title: Approve Button Text
default: Approve
deny_button_text:
anyOf:
- type: string
- type: 'null'
title: Deny Button Text
default: Deny
logo_url:
anyOf:
- type: string
- type: 'null'
title: Logo Url
default: https://assets.xpanderai.io/xpander-logo.png
url:
type: string
title: Url
headers:
anyOf:
- additionalProperties:
type: string
type: object
- type: 'null'
title: Headers
default: {}
type: object
required:
- url
title: WebhookNotificationSettings
description: |-
Configuration for webhook notifications.
Attributes:
url: Target webhook URL to POST notification data.
headers: Optional HTTP headers to include in the webhook request.
DuplicationPreventionSettings:
properties:
enabled:
anyOf:
- type: boolean
- type: 'null'
title: Enabled
default: false
ttl_minutes:
anyOf:
- type: integer
- type: 'null'
title: Ttl Minutes
default: 10
selectors:
items:
type: string
type: array
title: Selectors
type: object
required:
- selectors
title: DuplicationPreventionSettings
description: >-
Settings for preventing duplicate event processing in workflows.
When enabled, this prevents the same event from triggering a workflow
multiple times
within a configured time window. Useful for webhooks from services like
Stigg or Cal.com
that may fire the same event multiple times.
Attributes:
enabled: Whether duplication prevention is active.
ttl_minutes: Time window to consider events as duplicates (default: 10 minutes).
selectors: List of dot-notation paths to extract unique ID components from input.
Multiple selectors are combined to form a composite key.
Examples:
- ["messageId"] - single field
- ["input.event_id", "input.user_id"] - composite key
- ["triggerEvent", "payload.uid"] - Cal.com style
AIAgentGraphItemSchema:
properties:
input:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Input
output:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Output
type: object
title: AIAgentGraphItemSchema
AIAgentGraphItemAdvancedFilteringOption:
properties:
returnables:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Returnables
searchables:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Searchables
globally_enabled:
anyOf:
- type: boolean
- type: 'null'
title: Globally Enabled
default: false
type: object
title: AIAgentGraphItemAdvancedFilteringOption
AIAgentGraphItemHITLSettings:
properties:
title:
anyOf:
- type: string
- type: 'null'
title: Title
description:
anyOf:
- type: string
- type: 'null'
title: Description
recipients:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Recipients
hitl_type:
anyOf:
- $ref: '#/components/schemas/AIAgentHITLType'
- type: 'null'
slack_app:
anyOf:
- type: string
- type: 'null'
title: Slack App
should_approve_with_current_user:
anyOf:
- type: boolean
- type: 'null'
title: Should Approve With Current User
default: true
type: object
title: AIAgentGraphItemHITLSettings
AIAgentGraphItemA2ASettings:
properties:
url:
anyOf:
- type: string
- type: 'null'
title: Url
type: object
title: AIAgentGraphItemA2ASettings
AIAgentGraphItemCodingAgentSettings:
properties:
type:
anyOf:
- type: string
const: codex
- type: 'null'
title: Type
default: codex
type: object
title: AIAgentGraphItemCodingAgentSettings
AIAgentGraphItemMCPSettings:
properties:
type:
anyOf:
- $ref: '#/components/schemas/MCPServerType'
- type: 'null'
default: remote
name:
anyOf:
- type: string
- type: 'null'
title: Name
command:
anyOf:
- type: string
- type: 'null'
title: Command
url:
anyOf:
- type: string
- type: 'null'
title: Url
transport:
anyOf:
- $ref: '#/components/schemas/MCPServerTransport'
- type: 'null'
default: streamable-http
auth_type:
anyOf:
- $ref: '#/components/schemas/MCPServerAuthType'
- type: 'null'
default: none
api_key:
anyOf:
- type: string
- type: 'null'
title: Api Key
use_secrets_manager:
anyOf:
- type: boolean
- type: 'null'
title: Use Secrets Manager
default: false
client_id:
anyOf:
- type: string
- type: 'null'
title: Client Id
client_secret:
anyOf:
- type: string
- type: 'null'
title: Client Secret
additional_scopes:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Additional Scopes
default: []
headers:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Headers
default: {}
env_vars:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Env Vars
default: {}
allowed_tools:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Allowed Tools
default: []
share_user_token_across_other_agents:
anyOf:
- type: boolean
- type: 'null'
title: Share User Token Across Other Agents
default: true
type: object
title: AIAgentGraphItemMCPSettings
AIAgentGraphItemSkillsSettings:
properties:
enabled_skills:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Enabled Skills
default: []
type: object
title: AIAgentGraphItemSkillsSettings
OrchestrationConditionType:
type: string
enum:
- regex
- contains
- else
- equal
- not_equal
- gt
- lt
- gte
- lte
- not_empty
title: OrchestrationConditionType
description: |-
Types of conditions for orchestration control flow.
Attributes:
Regex: Condition based on regular expression matching.
Contains: Condition based on substring containment.
Else: Fallback condition that always matches (executed when no other conditions match).
Equal: Condition based on equality comparison (path == value).
NotEqual: Condition based on inequality comparison (path != value).
GreaterThan: Condition based on greater than comparison (path > value).
LessThan: Condition based on less than comparison (path < value).
GreaterThanOrEqual: Condition based on greater than or equal comparison (path >= value).
LessThanOrEqual: Condition based on less than or equal comparison (path <= value).
NotEmpty: Condition that checks if a path value is not empty/null.
ClassificationGroup:
properties:
id:
type: string
title: Id
name:
type: string
title: Name
evaluation_criteria:
type: string
title: Evaluation Criteria
auto_extract_relevant_data:
anyOf:
- type: boolean
- type: 'null'
title: Auto Extract Relevant Data
default: false
data_extraction_keys:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Data Extraction Keys
type: object
required:
- name
- evaluation_criteria
title: ClassificationGroup
description: >-
A classification group with evaluation criteria and data extraction
settings.
Attributes:
id: Unique identifier for the group (UUID).
name: Human-readable name for the group.
evaluation_criteria: Instructions for when this group should match.
auto_extract_relevant_data: Whether to automatically extract relevant data for this group.
data_extraction_keys: Specific JSON paths/keys to extract from input (alternative to auto_extract).
OrchestrationClassifierNodeLLMSettings:
properties:
model_provider:
anyOf:
- $ref: '#/components/schemas/LLMModelProvider'
- type: 'null'
default: anthropic
model_name:
anyOf:
- type: string
- type: 'null'
title: Model Name
default: claude-sonnet-4-6
llm_credentials_key:
anyOf:
- type: string
- type: 'null'
title: Llm Credentials Key
llm_credentials_key_type:
anyOf:
- $ref: '#/components/schemas/LLMCredentialsKeyType'
- type: 'null'
default: xpander
llm_credentials:
anyOf:
- $ref: '#/components/schemas/LLMCredentials'
- type: 'null'
llm_api_base:
anyOf:
- type: string
- type: 'null'
title: Llm Api Base
llm_extra_headers:
anyOf:
- additionalProperties:
type: string
type: object
- type: 'null'
title: Llm Extra Headers
default: {}
type: object
title: OrchestrationClassifierNodeLLMSettings
description: |-
LLM configuration for classifier nodes.
Attributes:
model_provider: The LLM provider to use. Defaults to Anthropic.
model_name: Specific model identifier. Defaults to "claude-sonnet-4-6".
llm_credentials_key: Key identifier for stored credentials.
llm_credentials_key_type: Type of credential key storage. Defaults to XPander.
llm_credentials: Direct credential object if not using stored credentials.
llm_api_base: Alternative API Base for the LLM.
llm_extra_headers: Extra headers to be set to LLM Requests.
OrchestrationPointerNodeInstructionsMode:
type: string
enum:
- replace
- append
title: OrchestrationPointerNodeInstructionsMode
description: |-
Modes for instruction usage in pointer node.
Attributes:
Replace: Replaces the traget asset instructions.
Append: Appends to the traget asset instructions.
SchemaOverride:
properties:
input:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Input
type: object
title: SchemaOverride
description: >-
Schema override for workflow action nodes.
Allows setting permanent (fixed) values for tool input properties.
Fields with permanentValue will be removed from the schema sent to the
LLM
and the permanent values will be applied to the payload before
execution.
Attributes:
input: Input schema with permanentValue fields to override LLM-generated values.
SlackCredentials:
properties:
authed_user_id:
anyOf:
- type: string
- type: 'null'
title: Authed User Id
access_token:
anyOf:
- type: string
- type: 'null'
title: Access Token
client_id:
anyOf:
- type: string
- type: 'null'
title: Client Id
client_secret:
anyOf:
- type: string
- type: 'null'
title: Client Secret
verification_token:
anyOf:
- type: string
- type: 'null'
title: Verification Token
signing_secret:
anyOf:
- type: string
- type: 'null'
title: Signing Secret
app_configuration_token:
anyOf:
- type: string
- type: 'null'
title: App Configuration Token
app_configuration_refresh_token:
anyOf:
- type: string
- type: 'null'
title: App Configuration Refresh Token
type: object
title: SlackCredentials
description: |-
Slack API authentication credentials.
Attributes:
authed_user_id: Authenticated user's Slack ID.
access_token: OAuth access token for API calls.
client_id: Slack app client ID.
client_secret: Slack app client secret.
verification_token: Token for verifying requests from Slack.
signing_secret: Secret for validating webhook signatures.
app_configuration_token: Token for app configuration.
app_configuration_refresh_token: Refresh token for app configuration.
AIAgentHITLType:
type: string
enum:
- slack
title: AIAgentHITLType
MCPServerType:
type: string
enum:
- local
- remote
title: MCPServerType
MCPServerTransport:
type: string
enum:
- stdio
- sse
- streamable-http
title: MCPServerTransport
MCPServerAuthType:
type: string
enum:
- api_key
- oauth2
- custom_headers
- none
title: MCPServerAuthType
securitySchemes:
APIKeyHeader:
type: apiKey
description: API Key for authentication
in: header
name: x-api-key
````