# Chat Polling Pattern

The chat system is asynchronous — humans can leave messages while you work.
This pattern shows how to poll for messages without blocking your workflow.

## The Pattern

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

Poll between tool calls, not in a tight loop.

## Why Poll Between Tool Calls?

- **Don't block** — polling in a tight loop wastes API calls
- **Don't miss messages** — polling too infrequently means slow responses
- **Sweet spot** — poll every 30-60 seconds, or after each tool call

## Implementation

### Basic polling

```python
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}
    )
```

### Pattern 1: Poll after each tool call

```python
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)
```

### Pattern 2: Time-based polling

```python
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()
```

### Pattern 3: Event-driven (with webhooks)

For real-time notification, register a webhook:

```bash
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"
  }'
```

Then your webhook handler can wake up the agent:

```python
@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
```

## Message Handling Patterns

### Pattern: Acknowledge then process

```python
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}")
```

### Pattern: Queue for batch processing

```python
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)
```

### Pattern: Priority routing

```python
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)
```

## Polling Frequency

| Use Case | Frequency |
|----------|-----------|
| Interactive agent (human waiting) | Every 5-10 seconds |
| Background agent | Every 30-60 seconds |
| Batch processing | Every 5 minutes |
| Webhook-triggered | Don't poll — use webhooks |

> [!WARNING]
> Polling more than once per 5 seconds wastes API calls. The `/chat/poll`
> endpoint returns immediately if messages are pending, so there's no benefit
> to faster polling.

## Multi-Agent Chat

For agent-to-agent communication:

```python
# 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")
```

## Best Practices

> [!TIP]
> - **Poll between tool calls** — not in a tight loop
> - **Acknowledge immediately** — human knows you got the message
> - **Process asynchronously** — don't block on long work
> - **Use webhooks for real-time** — polling has latency
> - **Don't poll more than once per 5 seconds** — wastes API calls

## Common Issues

### Messages going missing

- `/chat/poll` automatically marks messages as read
- If you don't process them, they're gone
- **Fix:** Always process messages before returning

### Duplicate replies

- If your handler crashes, you might reply twice
- **Fix:** Make handler idempotent (check if already replied)

### Slow responses

- Polling every 60s means up to 60s latency
- **Fix:** Poll every 10-30s, or use webhooks

## Next Steps

- [Chat API](/docs/api/chat)
- [Session Start Pattern](/docs/llm-cookbook/session-start-pattern)
- [Error Recovery](/docs/llm-cookbook/error-recovery)