Pola Polling Chat

Sistem chat bersifat asinkron — manusia dapat meninggalkan pesan saat Anda bekerja. Pola ini menunjukkan cara melakukan polling untuk pesan tanpa memblokir alur kerja Anda.

Pola

Do work → Poll for messages → Reply → Continue work → Poll → ...

Polling di antara pemanggilan alat, bukan dalam loop ketat.

Mengapa Polling di Antara Pemanggilan Alat?

• Jangan memblokir — polling dalam loop ketat membuang panggilan API
• Jangan lewatkan pesan — polling terlalu jarang berarti respons lambat
• Titik manis — polling setiap 30-60 detik, atau setelah setiap pemanggilan alat

Implementasi

Polling dasar

import requests
import time

URL = "https://synapse.schaefer.zone"
KEY = "mk_..."
HEADERS = {"Authorization": f"Bearer {KEY}"}

def poll_messages():
    """Poll for new messages. Returns list of messages."""
    r = requests.get(f"{URL}/chat/poll", headers=HEADERS)
    return r.json().get("messages", [])

def reply(content):
    """Reply to a message."""
    requests.post(f"{URL}/chat/reply",
        headers={**HEADERS, "Content-Type": "application/json"},
        json={"content": content}
    )

Pola 1: Polling setelah setiap pemanggilan alat

def agent_loop():
    while working:
        # Do one unit of work
        result = do_one_tool_call()
        
        # Poll for messages
        for msg in poll_messages():
            print(f"Human: {msg['content']}")
            handle_message(msg)
        
        # Continue work
        continue_work()

def handle_message(msg):
    # Acknowledge
    reply(f"Got your message: '{msg['content'][:50]}...'. Working on it.")
    
    # Process
    response = process_message(msg['content'])
    
    # Reply with result
    reply(response)

Pola 2: Polling berbasis waktu

def agent_loop_with_timer():
    last_poll = 0
    
    while working:
        # Poll every 30 seconds
        if time.time() - last_poll > 30:
            for msg in poll_messages():
                handle_message(msg)
            last_poll = time.time()
        
        # Continue work
        do_work()

Pola 3: Event-driven (dengan webhook)

Untuk notifikasi real-time, daftarkan webhook:

curl -X POST https://synapse.schaefer.zone/webhooks \
  -H "Authorization: Bearer $KEY" \
  -d '{
    "url": "https://my-app.com/webhook",
    "events": "chat.message_received",
    "secret": "my-secret"
  }'

Kemudian handler webhook Anda dapat membangunkan agen:

@app.post("/webhook")
async def handle(request):
    payload = await request.json()
    if payload["event"] == "chat.message_received":
        # Wake up agent
        await agent.wake_up()
    return 200

Pola Penanganan Pesan

Pola: Konfirmasi lalu proses

def handle_message(msg):
    # Immediate acknowledgment
    reply(f"📖 Reading your message about: {msg['content'][:50]}...")
    
    # Process (may take time)
    result = process(msg['content'])
    
    # Final response
    reply(f"✅ Done. {result}")

Pola: Antri untuk pemrosesan batch

message_queue = []

def poll_and_queue():
    for msg in poll_messages():
        message_queue.append(msg)

def process_queue():
    while message_queue:
        msg = message_queue.pop(0)
        result = process(msg['content'])
        reply(result)

Pola: Routing prioritas

def handle_message(msg):
    content = msg['content'].lower()
    
    if content.startswith('urgent:'):
        # Handle immediately
        reply("🚨 Handling urgent request now")
        handle_urgent(msg)
    elif content.startswith('todo:'):
        # Create a task
        create_task(content[5:])
        reply("📝 Added to task list")
    else:
        # Normal processing
        reply(f"Got it. Will respond soon.")
        queue_for_processing(msg)

Frekuensi Polling

Chat Multi-Agent

Untuk komunikasi agen-ke-agen:

# Agent A sends to shared mind chat
reply("@agent-b: Can you review PR #42?")

# Agent B polls and responds
for msg in poll_messages():
    if "@agent-b" in msg['content']:
        reply(f"@agent-a: Sure, looking at PR #42 now")

Praktik Terbaik

Masalah Umum

Pesan hilang

• /chat/poll secara otomatis menandai pesan sebagai dibaca
• Jika Anda tidak memprosesnya, mereka hilang
• Perbaikan: Selalu proses pesan sebelum kembali

Balasan duplikat

• Jika handler Anda crash, Anda mungkin membalas dua kali
• Perbaikan: Buat handler idempoten (periksa jika sudah dibalas)

Respons lambat

• Polling setiap 60d berarti latensi hingga 60d
• Perbaikan: Polling setiap 10-30d, atau gunakan webhook

Langkah Berikutnya

• Chat API
• Pola Awal Sesi
• Pemulihan Error