Streaming

{"timestamp": 1759406400810, "data": "Unit tests", "error": null}{"timestamp": 1759406400834, "data": " catch", "error": null}{"timestamp": 1759406400851, "data": " regressions", "error": null}

{"timestamp": 1759406402117, "data": null, "error": {"status": 422, "text": "Validation error", "detail": "not enough user credit"}}

{"timestamp": 1759406400120, "data": "", "error": null}{"timestamp": 1759406400810, "data": "Let me check", "error": null}{"timestamp": 1759406400833, "data": " that.", "error": null}{"timestamp": 1759406401002, "data": "\n\n### calling AI tool ...\n", "error": null}{"timestamp": 1759406401004, "data": "### Scraping URL: https://example.com/rates\n", "error": null}{"timestamp": 1759406402950, "data": "\n***\n", "error": null}{"timestamp": 1759406403410, "data": "The current rate is 24.35 CZK per euro.", "error": null}

{"timestamp": 1759406400810, "data": {"type": "text", "delta": "Unit tests", "phase": null, "call_id": null, "tool_name": null, "tool_display_name": null, "tool_icon": null, "tool_status": null, "data": {}, "chunk": null}, "error": null}

{"type": "status", "phase": "context_building", ...}
{"type": "status", "phase": "model_selected", "data": {"model": "gpt-5-mini", "model_name": "GPT-5 mini"}, ...}
{"type": "status", "phase": "model_call", ...}
{"type": "text", "delta": "Let me check", ...}
{"type": "text", "delta": " that.", ...}
{"type": "status", "phase": "tool_call_pending", "call_id": "call_9f2c", "tool_name": "WebScraperFunctionTool", ...}
{"type": "tool_call_start", "call_id": "call_9f2c", "tool_name": "WebScraperFunctionTool", "tool_display_name": "Web Scraper", "tool_icon": "ayeto", ...}
{"type": "tool_call_output", "call_id": "call_9f2c", "delta": "### Scraping URL: https://example.com/rates\n", ...}
{"type": "tool_call_end", "call_id": "call_9f2c", "tool_status": "ok", ...}
{"type": "status", "phase": "model_call", ...}
{"type": "text", "delta": "The current rate is 24.35 CZK per euro.", ...}
{"type": "done", "data": {"stop_reason": "stop"}, ...}

import codecs
import json
import os
import uuid

import requests


def iter_chunks(response):
    """Yield the JSON chunks of a streamed response."""
    decoder = json.JSONDecoder()
    text = codecs.getincrementaldecoder("utf-8")()
    buffer = ""
    for raw in response.iter_content(chunk_size=None):
        buffer += text.decode(raw)
        while True:
            buffer = buffer.lstrip()
            if not buffer:
                break
            try:
                chunk, end = decoder.raw_decode(buffer)
            except json.JSONDecodeError:
                break  # incomplete object, wait for more data
            buffer = buffer[end:]
            yield chunk


response = requests.post(
    "https://ayeto.ai/api/v3/chat",
    headers={"uni-api-key": os.environ["AYETO_API_KEY"]},
    json={
        "conversation_id": str(uuid.uuid4()),
        "model": "gpt-5-mini",
        "message": "Explain recursion with a short example.",
        "stream": True,
        "runner_version": "2",
    },
    stream=True,
    timeout=(10, 600),
)
if response.status_code != 200:  # failed before the stream started
    raise RuntimeError(f"{response.status_code}: {response.json()['detail']}")

for chunk in iter_chunks(response):
    if chunk["error"]:
        error = chunk["error"]
        raise RuntimeError(f"{error['status']}: {error['detail']}")
    event = chunk["data"]
    if not isinstance(event, dict):
        continue  # keepalive
    if event["type"] == "text":
        print(event["delta"], end="", flush=True)
    elif event["type"] == "tool_call_start":
        print(f"\n[{event['tool_display_name']}]", flush=True)
    elif event["type"] == "status" and event["phase"] == "model_selected":
        print(f"[answering: {event['data']['model']}]", flush=True)
print()

// Yields the JSON chunks of a streamed response.
async function* readChunks(response) {
  const reader = response.body.getReader();
  const decoder = new TextDecoder();
  let buffer = "";
  let pos = 0;
  let depth = 0;
  let inString = false;
  let escaped = false;
  while (true) {
    const { value, done } = await reader.read();
    if (done) break;
    buffer += decoder.decode(value, { stream: true });
    for (; pos < buffer.length; pos++) {
      const c = buffer[pos];
      if (inString) {
        if (escaped) escaped = false;
        else if (c === "\\") escaped = true;
        else if (c === '"') inString = false;
      } else if (c === '"') {
        inString = true;
      } else if (c === "{") {
        depth++;
      } else if (c === "}" && --depth === 0) {
        yield JSON.parse(buffer.slice(0, pos + 1));
        buffer = buffer.slice(pos + 1);
        pos = -1; // continue at the start of the remaining buffer
      }
    }
  }
}

const response = await fetch("https://ayeto.ai/api/v3/chat", {
  method: "POST",
  headers: {
    "uni-api-key": process.env.AYETO_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    conversation_id: crypto.randomUUID(),
    model: "gpt-5-mini",
    message: "Explain recursion with a short example.",
    stream: true,
    runner_version: "2",
  }),
});
if (!response.ok) {
  // failed before the stream started
  const body = await response.json();
  throw new Error(`${response.status}: ${JSON.stringify(body.detail)}`);
}

let answer = "";
for await (const chunk of readChunks(response)) {
  if (chunk.error) {
    throw new Error(`${chunk.error.status}: ${chunk.error.detail}`);
  }
  const event = chunk.data;
  if (typeof event !== "object" || event === null) continue; // keepalive
  if (event.type === "text") {
    answer += event.delta;
    process.stdout.write(event.delta);
  }
}