AgentCreate
Payload used to create Agent. Required fields are name, description.
- Option 1
- Option 2
- Option 1
- Option 2
chatreactPossible values: non-empty and <= 50 characters, Value must match regular expression ^[a-z0-9]([-_a-z0-9]*[a-z0-9])?(?![\s\S])
alias object
- string
- null
Agent description
Input mode (chat or event)
Possible values: [chat, event]
chatExecution mode (react or workflow)
Possible values: [react, workflow]
reactagent object
ReAct mode agent node configuration
- AgentNodeConfig
- null
Agent system instructions
prompts object[]
Reusable Prompt references. Rendered in list order and joined with '\n\n' as the system prefix; inline instructions is appended as a suffix. Empty = inline instructions only.
variables object
{{var}} bindings for the referenced Prompt
- object
- null
LLM provider name
LLM model name
tools object[]
Available tools
- string
- AgentResourceRef
- AgentToolConfig
- object
actors object[]
- string
- AgentResourceRef
- AgentActorConfig
- object
roles object[]
- string
- AgentResourceRef
- object
outputs object
- object
- null
Maximum iteration count
50max_input_tokens object
Maximum input-token budget for the system prompt and conversation history before each model call. The effective limit cannot exceed the selected model's context_window; null uses the D.Hub default.
- integer
- null
Possible values: >= 1
compaction object
Optional per-agent conversation compaction settings. Omit this field to use D.Hub defaults.
- AgentCompaction
- null
enabled object
Whether conversation compaction is enabled for the agent.
- boolean
- null
trigger_ratio object
Fraction of the input-token budget that triggers compaction.
- number
- null
Possible values: > 0 and < 1
target_ratio object
Fraction of the input-token budget targeted after compaction. It must be lower than trigger_ratio.
- number
- null
Possible values: > 0 and < 1
summary_max_tokens object
Maximum number of tokens allowed in the generated compaction summary.
- integer
- null
Possible values: >= 128 and <= 8192
options object
- object
- null
reasoning_effort object
Default reasoning effort for this agent. A value supplied with an individual request takes precedence; null uses the selected model's default.
- string
- null
Possible values: [none, minimal, low, medium, high, xhigh, max]
nodes object[]
Workflow mode node list
- StartWorkflowNode
- EndWorkflowNode
- LLMWorkflowNode
- ToolCallWorkflowNode
- ActorCallWorkflowNode
- IfElseWorkflowNode
- LoopWorkflowNode
- ParallelWorkflowNode
- HumanInputWorkflowNode
- ErrorHandlerWorkflowNode
- CodeWorkflowNode
- TemplateWorkflowNode
- VariableWorkflowNode
Unique node ID
Node type
startconfig object필수
Type-specific node configuration
variables object[]
Possible values: [string, number, boolean, object, array]
truemetadata object
{}edges object[]
Workflow mode edge list
Source node ID
Target node ID
condition object
Condition expression (unconditional if omitted)
- string
- null
Registered semantic table IDs
[]Registered semantic template (group) IDs
[]Registered semantic ontology IDs
[]conversations object[]
Conversation variables
Possible values: [string, number, boolean, array, object]
collection_id object
Identifier of the containing collection.
- string
- null
Possible values: non-empty
folder_id object
- string
- null
tags object
- string[]
- null
options object
- object
- null
{
"name": "string",
"alias": "string",
"description": "string",
"input_mode": "chat",
"mode": "react",
"agent": {
"instructions": "string",
"prompts": [
{
"prompt_id": "string",
"variables": {}
}
],
"model_provider": "string",
"model": "string",
"tools": [
"string",
{
"id": "string",
"name": "string"
},
{
"name": "string",
"description": "",
"type": "python",
"function": {
"source": "string",
"inputs": {},
"outputs": {},
"dependencies": [
"string"
],
"decorators": [
{
"decorator": "string",
"name": "string",
"arguments": {}
}
]
},
"require_browser": false,
"options": {}
},
{}
],
"actors": [
"string",
{
"id": "string",
"name": "string"
},
{
"name": "string",
"description": "",
"function": {
"source": "string",
"inputs": {},
"outputs": {},
"dependencies": [
"string"
],
"decorators": [
{
"decorator": "string",
"name": "string",
"arguments": {}
}
]
},
"confirmation_policy": "confirm",
"options": {}
},
{}
],
"roles": [
"string",
{
"id": "string",
"name": "string"
},
{}
],
"outputs": {},
"max_iterations": 50,
"max_input_tokens": 0,
"compaction": {
"enabled": true,
"trigger_ratio": 0,
"target_ratio": 0,
"summary_max_tokens": 0
},
"options": {},
"reasoning_effort": "none"
},
"nodes": [
{
"id": "string",
"type": "start",
"config": {
"variables": [
{
"name": "string",
"type": "string",
"required": true,
"description": ""
}
]
},
"metadata": {}
},
{
"id": "string",
"type": "end",
"config": {
"outputs": [
{
"name": "string",
"type": "string",
"value": "string"
}
]
},
"metadata": {}
},
{
"id": "string",
"type": "llm",
"config": {
"model_provider": "string",
"model": "string",
"prompt": "string",
"system_prompt": "",
"reasoning_effort": "none",
"output": "llm_output",
"response": {}
},
"metadata": {}
},
{
"id": "string",
"type": "tool_call",
"config": {
"tool": {
"name": "string",
"description": "",
"type": "python",
"function": {
"source": "string",
"inputs": {},
"outputs": {},
"dependencies": [
"string"
],
"decorators": [
{
"decorator": "string",
"name": "string",
"arguments": {}
}
]
},
"require_browser": false,
"options": {}
},
"input_mappings": {},
"outputs": {},
"timeout": 30
},
"metadata": {}
},
{
"id": "string",
"type": "actor_call",
"config": {
"actor": {
"name": "string",
"description": "",
"function": {
"source": "string",
"inputs": {},
"outputs": {},
"dependencies": [
"string"
],
"decorators": [
{
"decorator": "string",
"name": "string",
"arguments": {}
}
]
},
"confirmation_policy": "confirm",
"options": {}
},
"input_mappings": {},
"outputs": {},
"timeout": 30
},
"metadata": {}
},
{
"id": "string",
"type": "if_else",
"config": {
"condition": "string"
},
"metadata": {}
},
{
"id": "string",
"type": "loop",
"config": {
"mode": "list",
"source": "string",
"iterator": "item",
"count": 0,
"counter": "index",
"max_iterations": 100,
"body_node_ids": [
"string"
]
},
"metadata": {}
},
{
"id": "string",
"type": "parallel",
"config": {
"branches": [
{
"id": "string",
"node_ids": [
"string"
]
}
],
"join_strategy": "all",
"timeout": 300
},
"metadata": {}
},
{
"id": "string",
"type": "human_input",
"config": {
"prompt": "string",
"input_fields": [
{
"name": "string",
"type": "string",
"description": "",
"required": true,
"options": [
"string"
]
}
],
"timeout": 86400,
"assignees": [
"string"
],
"on_timeout": "error"
},
"metadata": {}
},
{
"id": "string",
"type": "error_handler",
"config": {
"target_node_id": "string",
"retry_count": 0,
"retry_delay_seconds": 5,
"retry_backoff": "fixed",
"on_error": "fallback",
"fallback_node_id": "string"
},
"metadata": {}
},
{
"id": "string",
"type": "code",
"config": {
"language": "python",
"source": "string",
"input_mappings": {},
"outputs": {},
"timeout": 30,
"dependencies": [
"string"
]
},
"metadata": {}
},
{
"id": "string",
"type": "template",
"config": {
"template": "string",
"output": "text"
},
"metadata": {}
},
{
"id": "string",
"type": "variable",
"config": {
"operations": [
{
"action": "set",
"variable": "string"
}
]
},
"metadata": {}
}
],
"edges": [
{
"source": "string",
"target": "string",
"condition": "string"
}
],
"tables": [
"string"
],
"templates": [
"string"
],
"ontologies": [
"string"
],
"conversations": [
{
"name": "string",
"type": "string",
"description": "string"
}
],
"collection_id": "string",
"folder_id": "string",
"tags": [
"string"
],
"options": {}
}