Appearance
dgi.action.think ​
Call the org's LLM for a one-shot reasoning turn (via ai.chat)
Call the org's LLM for a one-shot reasoning turn (dispatches ai.chat)
Overview ​
| Property | Value |
|---|---|
| Workflow type | Linear |
| Library | App-dgi |
| Version | 1.0 |
Input Schema ​
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
message | string | Yes | — | Message to reason about |
context | json | No | — | Free-form context for reasoning (history etc.) |
llm_config | json | Yes | — | LLM config: {connection_uuid |
Output Schema ​
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
message | string | No | — | — |
context | json | No | — | — |
llm_config | json | No | — | — |
result | json | 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 | — |
executing | No | No | — | complete | — |
completed | No | Yes | Yes | — | — |
failed | No | Yes | No | — | — |
State Diagram ​
Transitions ​
| From | Action | To | Description |
|---|---|---|---|
pending | execute | executing | — |
executing | complete | completed | — |
* (any state) | fail | failed | — |
API Usage ​
bash
POST /api/workflows/start
Content-Type: application/json
{
"workflow_type": "dgi.action.think",
"initial_data": {
"message": "value",
"llm_config": "value"
}
}