{"title":"Chat-polling-patroon","slug":"chat-polling-pattern","category":"llm-cookbook","summary":"Hoe u pollt voor menselijke berichten tussen tool-aanroepen zonder uw workflow te blokkeren.","audience":["llm"],"tags":["cookbook","chat","polling","async"],"difficulty":"beginner","updated":"2026-06-27","word_count":346,"read_minutes":2,"lang":"nl","translated":true,"requested_lang":"nl","content_markdown":"\n# Chat-polling-patroon\n\nHet chat-systeem is asynchroon — mensen kunnen berichten achterlaten terwijl u werkt.\nDit patroon laat zien hoe u pollt voor berichten zonder uw workflow te blokkeren.\n\n## Het patroon\n\n```\nDo work → Poll for messages → Reply → Continue work → Poll → ...\n```\n\nPoll tussen tool-aanroepen, niet in een strakke lus.\n\n## Waarom pollen tussen tool-aanroepen?\n\n- **Niet blokkeren** — polling in een strakke lus verspilt API-aanroepen\n- **Geen berichten missen** — te infrequent pollen betekent trage reacties\n- **Sweet spot** — poll elke 30-60 seconden, of na elke tool-aanroep\n\n## Implementatie\n\n### Basis polling\n\n```python\nimport requests\nimport time\n\nURL = \"https://synapse.schaefer.zone\"\nKEY = \"mk_...\"\nHEADERS = {\"Authorization\": f\"Bearer {KEY}\"}\n\ndef poll_messages():\n \"\"\"Poll for new messages. Returns list of messages.\"\"\"\n r = requests.get(f\"{URL}/chat/poll\", headers=HEADERS)\n return r.json().get(\"messages\", [])\n\ndef reply(content):\n \"\"\"Reply to a message.\"\"\"\n requests.post(f\"{URL}/chat/reply\",\n headers={**HEADERS, \"Content-Type\": \"application/json\"},\n json={\"content\": content}\n )\n```\n\n### Patroon 1: Poll na elke tool-aanroep\n\n```python\ndef agent_loop():\n while working:\n # Do one unit of work\n result = do_one_tool_call()\n \n # Poll for messages\n for msg in poll_messages():\n print(f\"Human: {msg['content']}\")\n handle_message(msg)\n \n # Continue work\n continue_work()\n\ndef handle_message(msg):\n # Acknowledge\n reply(f\"Got your message: '{msg['content'][:50]}...'. Working on it.\")\n \n # Process\n response = process_message(msg['content'])\n \n # Reply with result\n reply(response)\n```\n\n### Patroon 2: Tijdgebaseerde polling\n\n```python\ndef agent_loop_with_timer():\n last_poll = 0\n \n while working:\n # Poll every 30 seconds\n if time.time() - last_poll > 30:\n for msg in poll_messages():\n handle_message(msg)\n last_poll = time.time()\n \n # Continue work\n do_work()\n```\n\n### Patroon 3: Event-gedreven (met webhooks)\n\nVoor realtime melding, registreer een webhook:\n\n```bash\ncurl -X POST https://synapse.schaefer.zone/webhooks \\\n -H \"Authorization: Bearer $KEY\" \\\n -d '{\n \"url\": \"https://my-app.com/webhook\",\n \"events\": \"chat.message_received\",\n \"secret\": \"my-secret\"\n }'\n```\n\nDan kan uw webhook-handler de agent wakker maken:\n\n```python\n@app.post(\"/webhook\")\nasync def handle(request):\n payload = await request.json()\n if payload[\"event\"] == \"chat.message_received\":\n # Wake up agent\n await agent.wake_up()\n return 200\n```\n\n## Berichtafhandelingspatronen\n\n### Patroon: Bevestig dan verwerk\n\n```python\ndef handle_message(msg):\n # Immediate acknowledgment\n reply(f\"📖 Reading your message about: {msg['content'][:50]}...\")\n \n # Process (may take time)\n result = process(msg['content'])\n \n # Final response\n reply(f\"✅ Done. {result}\")\n```\n\n### Patroon: Wachtrij voor batch-verwerking\n\n```python\nmessage_queue = []\n\ndef poll_and_queue():\n for msg in poll_messages():\n message_queue.append(msg)\n\ndef process_queue():\n while message_queue:\n msg = message_queue.pop(0)\n result = process(msg['content'])\n reply(result)\n```\n\n### Patroon: Prioriteitsroutering\n\n```python\ndef handle_message(msg):\n content = msg['content'].lower()\n \n if content.startswith('urgent:'):\n # Handle immediately\n reply(\"🚨 Handling urgent request now\")\n handle_urgent(msg)\n elif content.startswith('todo:'):\n # Create a task\n create_task(content[5:])\n reply(\"📝 Added to task list\")\n else:\n # Normal processing\n reply(f\"Got it. Will respond soon.\")\n queue_for_processing(msg)\n```\n\n## Polling-frequentie\n\n| Toepassing | Frequentie |\n|------------|------------|\n| Interactieve agent (mens wacht) | Elke 5-10 seconden |\n| Achtergrond-agent | Elke 30-60 seconden |\n| Batch-verwerking | Elke 5 minuten |\n| Webhook-getriggerd | Niet pollen — gebruik webhooks |\n\n> [!WARNING]\n> Vaker dan eens per 5 seconden pollen verspilt API-aanroepen. Het `/chat/poll`-\n> eindpunt retourneert onmiddellijk als er berichten klaarstaan, dus sneller pollen\n> levert geen voordeel op.\n\n## Multi-agent-chat\n\nVoor agent-naar-agent-communicatie:\n\n```python\n# Agent A sends to shared mind chat\nreply(\"@agent-b: Can you review PR #42?\")\n\n# Agent B polls and responds\nfor msg in poll_messages():\n if \"@agent-b\" in msg['content']:\n reply(f\"@agent-a: Sure, looking at PR #42 now\")\n```\n\n## Best practices\n\n> [!TIP]\n> - **Poll tussen tool-aanroepen** — niet in een strakke lus\n> - **Bevestig onmiddellijk** — mens weet dat u het bericht heeft ontvangen\n> - **Verwerk asynchroon** — blokkeer niet op lang werk\n> - **Gebruik webhooks voor realtime** — polling heeft latentie\n> - **Poll niet vaker dan eens per 5 seconden** — verspilt API-aanroepen\n\n## Veelvoorkomende problemen\n\n### Berichten verdwijnen\n\n- `/chat/poll` markeert berichten automatisch als gelezen\n- Als u ze niet verwerkt, zijn ze weg\n- **Oplossing:** Verwerk berichten altijd vóór return\n\n### Dubbele antwoorden\n\n- Als uw handler crasht, kunt u twee keer antwoorden\n- **Oplossing:** Maak handler idempotent (controleer of al geantwoord)\n\n### Trage reacties\n\n- Elke 60s pollen betekent tot 60s latentie\n- **Oplossing:** Poll elke 10-30s, of gebruik webhooks\n\n## Volgende stappen\n\n- [Chat API](/docs/api/chat)\n- [Sessiestart-patroon](/docs/llm-cookbook/session-start-pattern)\n- [Error-recovery](/docs/llm-cookbook/error-recovery)\n","content_html":"

Chat-polling-patroon

\n

Het chat-systeem is asynchroon — mensen kunnen berichten achterlaten terwijl u werkt.\nDit patroon laat zien hoe u pollt voor berichten zonder uw workflow te blokkeren.

\n

Het patroon

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

Poll tussen tool-aanroepen, niet in een strakke lus.

\n

Waarom pollen tussen tool-aanroepen?

\n\n

Implementatie

\n

Basis polling

\n
import requests\nimport time\n\nURL = "https://synapse.schaefer.zone"\nKEY = "mk_..."\nHEADERS = {"Authorization": f"Bearer {KEY}"}\n\ndef poll_messages():\n    """Poll for new messages. Returns list of messages."""\n    r = requests.get(f"{URL}/chat/poll", headers=HEADERS)\n    return r.json().get("messages", [])\n\ndef reply(content):\n    """Reply to a message."""\n    requests.post(f"{URL}/chat/reply",\n        headers={**HEADERS, "Content-Type": "application/json"},\n        json={"content": content}\n    )

Patroon 1: Poll na elke tool-aanroep

\n
def agent_loop():\n    while working:\n        # Do one unit of work\n        result = do_one_tool_call()\n        \n        # Poll for messages\n        for msg in poll_messages():\n            print(f"Human: {msg['content']}")\n            handle_message(msg)\n        \n        # Continue work\n        continue_work()\n\ndef handle_message(msg):\n    # Acknowledge\n    reply(f"Got your message: '{msg['content'][:50]}...'. Working on it.")\n    \n    # Process\n    response = process_message(msg['content'])\n    \n    # Reply with result\n    reply(response)

Patroon 2: Tijdgebaseerde polling

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

Patroon 3: Event-gedreven (met webhooks)

\n

Voor realtime melding, registreer een webhook:

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

Dan kan uw webhook-handler de agent wakker maken:

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

Berichtafhandelingspatronen

\n

Patroon: Bevestig dan verwerk

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

Patroon: Wachtrij voor batch-verwerking

\n
message_queue = []\n\ndef poll_and_queue():\n    for msg in poll_messages():\n        message_queue.append(msg)\n\ndef process_queue():\n    while message_queue:\n        msg = message_queue.pop(0)\n        result = process(msg['content'])\n        reply(result)

Patroon: Prioriteitsroutering

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

Polling-frequentie

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
ToepassingFrequentie
Interactieve agent (mens wacht)Elke 5-10 seconden
Achtergrond-agentElke 30-60 seconden
Batch-verwerkingElke 5 minuten
Webhook-getriggerdNiet pollen — gebruik webhooks
\n
Vaker dan eens per 5 seconden pollen verspilt API-aanroepen. Het `/chat/poll`-\neindpunt retourneert onmiddellijk als er berichten klaarstaan, dus sneller pollen\nlevert geen voordeel op.

Multi-agent-chat

\n

Voor agent-naar-agent-communicatie:

\n
# Agent A sends to shared mind chat\nreply("@agent-b: Can you review PR #42?")\n\n# Agent B polls and responds\nfor msg in poll_messages():\n    if "@agent-b" in msg['content']:\n        reply(f"@agent-a: Sure, looking at PR #42 now")

Best practices

\n

Veelvoorkomende problemen

\n

Berichten verdwijnen

\n\n

Dubbele antwoorden

\n\n

Trage reacties

\n\n

Volgende stappen

\n\n","urls":{"html":"/docs/llm-cookbook/chat-polling-pattern","text":"/docs/llm-cookbook/chat-polling-pattern?format=text","json":"/docs/llm-cookbook/chat-polling-pattern?format=json","llm":"/docs/llm-cookbook/chat-polling-pattern?format=llm"},"translations_available":["en","zh","hi","es","fr","ar","pt","ru","ja","de","it","ko","nl","pl","tr","sv","vi","th","id","uk"]}