Streaming

Stream chat responses token-by-token using Server-Sent Events (SSE) for real-time UX. Enable streaming by setting stream: true in your chat request.

Enabling Streaming

Add stream: true to the request body:

bash

curl -X POST https://chatspark.io/api/v1/agents/{id}/chat \
  -H "Authorization: Bearer cs_live_..." \
  -H "Content-Type: application/json" \
  -d '{"message":"Hello!","stream":true}'

Event Format

The response is a stream of SSE events. Each data line contains a JSON object:

json

data: {"delta":"Hi","conversationId":"conv_abc123"}
data: {"delta":"! ","conversationId":"conv_abc123"}
data: {"delta":"How","conversationId":"conv_abc123"}
data: {"delta":" can","conversationId":"conv_abc123"}
...
data: [DONE]

Each event has a delta (the next token) and conversationId. The stream ends with data: [DONE].

Reading the Stream

const res = await fetch(`https://chatspark.io/api/v1/agents/${agentId}/chat`, {
  method: "POST",
  headers: {
    "Authorization": "Bearer cs_live_...",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ message: "Hello!", stream: true }),
});

if (!res.ok) throw new Error(`Request failed: ${res.status}`);

const reader = res.body.getReader();
const decoder = new TextDecoder();
let fullText = "";

while (true) {
  const { done, value } = await reader.read();
  if (done) break;

  const chunk = decoder.decode(value, { stream: true });
  const lines = chunk.split("\n").filter((l) => l.startsWith("data: "));

  for (const line of lines) {
    const data = line.slice(6);
    if (data === "[DONE]") break;

    try {
      const parsed = JSON.parse(data);
      if (parsed.delta) {
        fullText += parsed.delta;
        process.stdout.write(parsed.delta);
      }
    } catch {}
  }
}

console.log("\n--- Full response ---\n", fullText);

Pagination

Embed Guide