Send a chat message

Send a natural language message to the LLM chat backend for a specific workflow. The request includes the current workflow state and optional conversation history so the LLM can generate contextually relevant responses.

The LLM response may contain plain text explanations and/or DSL commands in ```flowdrop fenced code blocks. The frontend extracts and previews these commands before execution.

POST /workflows/{id}/chat/messages

cURL

simpleMessage

curl --request POST \
  --url http://localhost:5173/api/flowdrop/workflows/{id}/chat/messages \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "message": "Add a processing node called \"transform\"",
  "workflowState": {
    "nodes": [],
    "edges": []
  }
}
'

200

{
  "success": true,
  "data": {
    "content": "I'll add a processing node and connect it to your start node.\n\n```flowdrop\nadd transform processing\nconnect start:output transform:input\n```\n",
    "conversationId": "conv-abc123"
  }
}

Authorizations

BearerAuthSessionAuth

Authorization · string · header · required

JWT token for authentication

Path Parameters

id · string · required

Workflow ID

Body

application/json

Request payload for sending a chat message

message · string · required

The user's natural language message

Example:

"Add a node called \"transform\" and connect it to the start node"

workflowState · object · required

Serialized current workflow state including nodes and edges. This gives the LLM context about the current workflow being edited.

history · object[]

Optional conversation history for multi-turn context

Show child attributes

Response

200

application/json

Chat response with LLM-generated content

Wrapped response for chat message send

success · boolean

Example:

true

data · object

Response from the chat endpoint containing the LLM's reply. The content may include markdown formatting and fenced code blocks with DSL commands (```flowdrop blocks).

Show child attributes