Stream Chat

Start a streaming chat session with the Greenflash AI agent.

Requires a Growth or Enterprise plan.

The response is a Server-Sent Events (SSE) stream (Content-Type: text/event-stream). Each event follows the format:

event: <type>
data: <json>

Event types:

tool_call — The agent is invoking a tool. Data: {"step": 1, "toolName": "...", "displayName": "..."}
tool_result — A tool returned its result. Data: {"step": 1, "toolName": "...", "displayName": "..."}. For draftTicket and createTicket, the event also includes an output field with the tool’s payload (see Ticket creation below).
text_delta — A chunk of the agent’s text response. Concatenate all deltas to build the full message. Data: {"text": "..."}
done — The stream completed successfully. Data: {"conversationId": "...", "status": "complete", "usage": {"toolCalls": N, "tools": ["..."]}}
error — An error occurred during processing. Data: {"error": "...", "code": "..."}

Multi-turn conversations: Pass previous messages in the messages array and reuse the conversationId returned in the done event.

Rate limits: This endpoint is rate-limited per tenant (requests/hour) and subject to token usage limits.

Ticket creation (two-step draft → confirm)

When the tenant has an active ticket-provider connection (e.g. Linear), the agent may emit a draftTicket tool call. The tool_result event includes an output field shaped like:

{
  "step": 2,
  "toolName": "draftTicket",
  "displayName": "Drafting ticket",
  "output": {
    "draft": {
      "provider": "linear",
      "title": "Billing page 500 for enterprise users",
      "description": "...",
      "target": { "teamId": "t_123", "teamName": "Core", "teamKey": "CORE" },
      "labelIds": ["lbl_bug"],
      "source": { "type": "conversation", "conversationId": "conv-abc-123" }
    },
    "availableLabels": [
      { "id": "lbl_bug", "name": "bug", "color": "#f00" }
    ],
    "dedupWarning": null
  }
}

API consumers should render this draft to the end user. To confirm (optionally with edits), send a follow-up user message asking the agent to call createTicket with the final payload. The createTicket tool_result event contains:

{
  "step": 3,
  "toolName": "createTicket",
  "displayName": "Creating ticket",
  "output": {
    "status": "created",
    "providerIdentifier": "LIN-99",
    "providerTicketUrl": "https://linear.app/acme/issue/LIN-99"
  }
}

status is "created" on success, "already_exists" when deduplication matched an existing ticket (the existing providerIdentifier / providerTicketUrl are returned), or the event may carry an error field (e.g. "provider_needs_setup").

POST

chat

cURL

curl --request POST \
  --url https://www.greenflash.ai/api/v1/chat \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "question": "What are the top complaints from enterprise customers this week?",
  "messages": [
    {
      "role": "user",
      "content": "Show me sentiment trends for the support bot."
    },
    {
      "role": "assistant",
      "content": "Based on the last 30 days, sentiment is trending slightly negative (-0.08). The main driver is billing-related frustration, which accounts for 34% of negative conversations."
    }
  ],
  "conversationId": "conv-abc-123",
  "context": "Focus on the Customer Support Bot product.",
  "productId": "123e4567-e89b-12d3-a456-426614174000"
}
'

{
  "success": false,
  "error": "Validation error: question must be between 1 and 4000 characters"
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

question

string

required

The current user question to send to the AI agent.

Required string length: 1 - 4000

messages

object[]

Prior conversation history (NOT including the current question). Used for multi-turn context.

Maximum array length: 50

Show child attributes

conversationId

string

Stable identifier for multi-turn conversations. If omitted, a new ID is generated.

Maximum string length: 128

context

string

Free-form hint injected into the system prompt for this turn only.

Maximum string length: 2000

productId

string<uuid>

Scope the chat to a specific product. If omitted, the agent can access all products.

Response

SSE stream of chat events (text/event-stream). See endpoint description for event format.

Example SSE stream:

event: tool_call
data: {"step":1,"toolName":"getConversations","displayName":"Searching conversations"}

event: tool_call
data: {"step":2,"toolName":"getUserRanking","displayName":"Ranking users by metrics"}

event: tool_result
data: {"step":1,"toolName":"getConversations","displayName":"Searching conversations"}

event: tool_result
data: {"step":2,"toolName":"getUserRanking","displayName":"Ranking users by metrics"}

event: text_delta
data: {"text":"Based on your"}

event: text_delta
data: {"text":" conversation data, the top complaints"}

event: text_delta
data: {"text":" from enterprise customers this week are..."}

event: done
data: {"conversationId":"conv-abc-123","status":"complete","usage":{"toolCalls":2,"tools":["getConversations","getUserRanking"]}}

Create an eventTrack timestamped events representing user or organization actions. Events are used to track important business outcomes (signups, conversions, upgrades, cancellations, etc.) and integrate them into Greenflash's quality metrics. Each event can be optionally linked to a conversation, user, and organization.

cURL

curl --request POST \
  --url https://www.greenflash.ai/api/v1/chat \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "question": "What are the top complaints from enterprise customers this week?",
  "messages": [
    {
      "role": "user",
      "content": "Show me sentiment trends for the support bot."
    },
    {
      "role": "assistant",
      "content": "Based on the last 30 days, sentiment is trending slightly negative (-0.08). The main driver is billing-related frustration, which accounts for 34% of negative conversations."
    }
  ],
  "conversationId": "conv-abc-123",
  "context": "Focus on the Customer Support Bot product.",
  "productId": "123e4567-e89b-12d3-a456-426614174000"
}
'

{
  "success": false,
  "error": "Validation error: question must be between 1 and 4000 characters"
}