Chattpollningsmönster

Chattsystemet är asynkront — människor kan lämna meddelanden medan ni arbetar. Detta mönster visar hur man pollar efter meddelanden utan att blockera arbetsflödet.

Mönstret

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

Polla mellan verktygsanrop, inte i en tight loop.

Varför polla mellan verktygsanrop?

• Blockera inte — pollning i en tight loop slösar API-anrop
• Missa inte meddelanden — för sällan pollning innebär långsamma svar
• Sweet spot — polla var 30–60 sekund, eller efter varje verktygsanrop

Implementering

Grundläggande pollning

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}
    )

Mönster 1: Polla efter varje verktygsanrop

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)

Mönster 2: Tidsbaserad pollning

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()

Mönster 3: Händelsestyrd (med webhooks)

För realtidsavisering, registrera en 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"
  }'

Sedan kan er webhook-hanterare väcka agenten:

@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

Meddelandehanteringsmönster

Mönster: Bekräfta sedan bearbeta

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}")

Mönster: Köa för batchbearbetning

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)

Mönster: Prioritetsstyrning

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)

Pollningsfrekvens

Multi-agent-chatt

För agent-till-agent-kommunikation:

# 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")

Bästa praxis

Vanliga problem

Meddelanden försvinner

• /chat/poll markerar automatiskt meddelanden som lästa
• Om ni inte bearbetar dem är de borta
• Lösning: Bearbeta alltid meddelanden innan ni returnerar

Dubbletta svar

• Om er hanterare kraschar kan ni svara två gånger
• Lösning: Gör hanteraren idempotent (kontrollera om redan svarat)

Långsamma svar

• Pollning var 60:e sekund innebär upp till 60 s latens
• Lösning: Polla var 10–30:e sekund, eller använd webhooks

Nästa steg

• Chat API
• Sessionsstart-mönster
• Felåterställning