dgi.ai_chat

AI-powered chat for DGI conversations

AI-powered chat for DGI conversations.

Uses the AI plugin to provide conversational responses about infrastructure automation.

Inputs:

• messages: List of {role, content} message objects (required). Roles: user, assistant, system.
• system_prompt: Optional system instruction override.
• model: Optional model ID override (default: plugin.default_model).
• temperature: Optional temperature 0.0-2.0 (default: 0.7).
• max_tokens: Optional max tokens (default: 1024).

Outputs (terminal state_data):

• response: str — assistant reply text
• role: str — always "assistant"
• finish_reason: str — stop | length | tool_calls
• model: str — model ID used
• usage: dict — token usage

Plugin required: context.get_plugin("ai")

Overview

Property	Value
Workflow type	Atomic
Library	App-dgi
Version	1.0

Input Schema

Field	Type	Required	Default	Description
messages	json	Yes	—	List of {role, content} message objects
system_prompt	string	No	—	System instruction override
model	string	No	—	Model ID override
temperature	json	No	—	Temperature 0.0-2.0
max_tokens	integer	No	—	Max tokens to generate

Output Schema

Field	Type	Required	Default	Description
messages	json	No	—	—
system_prompt	string	No	—	—
model	string	No	—	—
temperature	json	No	—	—
max_tokens	integer	No	—	—
finish_reason	string	No	—	—
response	string	No	—	—
role	string	No	—	—
usage	dict	No	—	—
failure_reason	string	No	—	—
failure_type	string	No	—	—
failed_action	string	No	—	—
failed_at_state	string	No	—	—
failed_step	string	No	—	—
failed_layer	string	No	—	—
error	string	No	—	—
error_type	string	No	—	—

States

State	Initial	Terminal	Success	Auto-advance	Description
pending	Yes	No	—	execute	—
completed	No	Yes	Yes	—	—
failed	No	Yes	No	—	—

State Diagram

Transitions

From	Action	To	Description
pending	execute	completed	—
* (any state)	fail	failed	—

API Usage

POST /api/workflows/start
Content-Type: application/json

{
  "workflow_type": "dgi.ai_chat",
  "initial_data": {
    "messages": "value"
  }
}