# Sessiestart-patroon

Elke LLM-agent-sessie moet deze canonieke opstartsequentie volgen. Stappen overslaan
leidt tot verloren context, gemiste berichten en vergeten taken.

## Het patroon

```
1. Recall all memories
2. Poll for unread chat messages
3. Check in-progress tasks
4. Build context from results
5. Process pending items before new work
```

## Implementatie

### Stap 1: Alle herinneringen ophalen

> [!CRITICAL]
> Dit is de belangrijkste aanroep. Zonder deze heeft u geen geheugen van eerdere
> sessies.

```bash
curl -H "Authorization: Bearer YOUR_MIND_KEY" \
     https://synapse.schaefer.zone/memory/recall
```

Retourneert platte-tekst samenvatting van alle herinneringen, gesorteerd op prioriteit.

### Stap 2: Poll voor ongelezen chatberichten

```bash
curl -H "Authorization: Bearer YOUR_MIND_KEY" \
     https://synapse.schaefer.zone/chat/poll
```

Retourneert ongelezen berichten van de mens. **Markeert ze automatisch als gelezen.**

### Stap 3: Controleer lopende taken

```bash
curl -H "Authorization: Bearer YOUR_MIND_KEY" \
     "https://synapse.schaefer.zone/mind/tasks?status=in_progress"
```

Retourneert taken waaraan u in de laatste sessie werkte.

### Stap 4: Bouw context

Combineer de drie responsen in uw system prompt:

```python
def build_context(memories, messages, tasks):
    context = f"""# SESSION CONTEXT

## Memories (from previous sessions)
{memories}

## Unread Messages from Human
{format_messages(messages)}

## Active Tasks
{format_tasks(tasks)}

## Instructions
- Address unread messages first
- Resume active tasks before starting new work
- Store new learnings as they happen (POST /memory)
- Poll for new messages every 30-60 seconds
"""
    return context
```

### Stap 5: Verwerk in behandeling zijnde items

```
For each unread message:
  - Acknowledge receipt (POST /chat/reply)
  - Address the message content
  - Store any new commitments as memories

For each in-progress task:
  - Recall why you were working on it
  - Continue from where you left off
  - Update task status as you progress
```

## Volledig voorbeeld

```python
import os
import requests

URL = "https://synapse.schaefer.zone"
KEY = os.environ["SYNAPSE_MIND_KEY"]

def session_start():
    """Canonical session start sequence."""
    headers = {"Authorization": f"Bearer {KEY}"}
    
    # 1. Recall memories
    r = requests.get(f"{URL}/memory/recall", headers=headers)
    memories = r.text
    
    # 2. Poll chat
    r = requests.get(f"{URL}/chat/poll", headers=headers)
    messages = r.json().get("messages", [])
    
    # 3. Check tasks
    r = requests.get(f"{URL}/mind/tasks?status=in_progress", headers=headers)
    tasks = r.json().get("tasks", [])
    
    # 4. Build context
    context = f"""You are a Synapse-enabled AI assistant.

MEMORIES FROM PREVIOUS SESSIONS:
{memories}

UNREAD MESSAGES FROM HUMAN:
{chr(10).join(f'- {m["content"]}' for m in messages) or 'None'}

ACTIVE TASKS:
{chr(10).join(f'- [{t["id"]}] {t["title"]}: {t.get("description", "")}' for t in tasks) or 'None'}

INSTRUCTIONS:
1. Acknowledge each unread message
2. Resume active tasks
3. Store new learnings via POST /memory
4. Poll /chat/poll every 30-60 seconds
"""
    return context

# At session start
system_prompt = session_start()
# Pass to LLM...
```

## Veelvoorkomende fouten

> [!WARNING]
> - **Recall overslaan** — u start zonder context, herhaalt eerdere fouten
> - **Chat-pollen vergeten** — berichten van de mens blijven onbeantwoord
> - **Actieve taken negeren** — werk wordt halverwege vergeten
> - **Niets opslaan** — sessie produceert geen permanente waarde

## Variaties

### Minimaal patroon (low-context LLM's)

Voor LLM's met kleine contextvensters, sla de volledige recall over:

```bash
# Just get stats, not full content
curl -H "Authorization: Bearer $KEY" .../memory/stats
```

Zoek dan naar specifieke onderwerpen indien nodig:

```bash
curl -H "Authorization: Bearer $KEY" ".../memory/search?q=current+project"
```

### Agressief patroon (langlopende agents)

Voor agents die uren draaien, voeg periodieke re-recall toe:

```python
while working:
    if time.time() - last_recall > 3600:  # every hour
        memories = recall()
        last_recall = time.time()
    # ... do work ...
```

## Volgende stappen

- [Memory-tagging-strategie](/docs/llm-cookbook/memory-tagging-strategy)
- [Taakgedreven workflow](/docs/llm-cookbook/task-driven-workflow)
- [Chat-polling-patroon](/docs/llm-cookbook/chat-polling-pattern)