POST /v1/ai/workflow/chat/stream

Stream AI chat for workflow generation and updates via SSE

POST /v1/ai/workflow/chat/stream
Stream AI chat for workflow generation and updates via SSE

Request Body required

Chat request parameters

application/json
One of:
Option 1
Option 2
agentVersion string
Optional - agent version toggle (defaults to v1)
Enum: v1, v2, both
apiKeyOverride string
Optional - override the LLM API key for this request (eval/testing use only)
conversationId string
Stable conversation identifier (generated client-side, persists across session→workflow transition)
definition object
Definition is the full workflow graph to execute. Must contain a "root" node with type "manual". All action nodes referenced in children arrays must be present.
blockExpansions object
Set on run snapshots only (not workflow DB)
inputSchema object[]
Array of:
description string
key string
required boolean
type string
"string", "number", "boolean", "object", "array"
nodes object REQUIRED
sensitivePropKeys string[]
Legacy: kept for old runs; no longer populated for new workflows
Array of:
description string
Optional - for generating new workflow
images object[]
Optional - images attached to the message (base64 for LLM, IPFS for storage)
Array of:
base64 string
ipfsUrl string
lastEventIndex integer
Last received event index for replay (reconnection)
message string
Optional on reconnect, required for new sessions
modelOverride string
Optional - override the LLM model for this request (eval/testing use only)
name string
Optional - for generating new workflow
preferredMode string
Optional - user's preferred mode hint; overrides auto-classifier when set
Enum: planning, building, repair, conversation
requestId string
Client-generated UUID4 for persistent session tracking (optional for legacy/inline mode)
sessionId string
Optional - metadata: which create-page session started this conversation
temperatureOverride number
Optional - override the LLM temperature for this request (eval/testing use only)
templateSearchMode string
Optional - template search mode toggle (defaults to lightweight)
Enum: lightweight, hybrid
timezone string
Optional - user's IANA timezone (e.g. "America/New_York") for time-aware responses
workflowId string
Optional - metadata: which workflow this conversation is about

Responses

200 SSE stream with events: chunk, node, done, error
text/event-stream
400 Bad Request 
curl -X POST 'https://api.example.com/v1/ai/workflow/chat/stream' \  -H 'Authorization: Bearer YOUR_API_TOKEN' \  -H 'Content-Type: application/json' \  -d '{}'
const response = await fetch('https://api.example.com/v1/ai/workflow/chat/stream', {  method: 'POST',  headers: {      "Authorization": "Bearer YOUR_API_TOKEN",      "Content-Type": "application/json"  },  body: JSON.stringify({})});const data = await response.json();console.log(data);
import requestsheaders = {    'Authorization': 'Bearer YOUR_API_TOKEN'}response = requests.post('https://api.example.com/v1/ai/workflow/chat/stream', headers=headers, json={})print(response.json())
package mainimport (	"fmt"	"io"	"net/http"	"strings")func main() {	body := strings.NewReader(`{}`)	req, _ := http.NewRequest("POST", "https://api.example.com/v1/ai/workflow/chat/stream", body)	req.Header.Set("Authorization", "Bearer YOUR_API_TOKEN")	req.Header.Set("Content-Type", "application/json")	resp, _ := http.DefaultClient.Do(req)	defer resp.Body.Close()	result, _ := io.ReadAll(resp.Body)	fmt.Println(string(result))}
200 Response 
"<string>"
Previous GET /v1/ai/workflow/chat/sessions
Next GET /v1/api-keys