# Pola Awal Sesi

Setiap sesi agen LLM harus mengikuti urutan startup kanonik ini. Melewatkan
langkah mengarah pada konteks yang hilang, pesan yang terlewat, dan tugas yang terlupakan.

## Pola

```
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
```

## Implementasi

### Langkah 1: Recall Semua Memori

> [!CRITICAL]
> Ini adalah panggilan terpenting. Tanpa ini, Anda tidak memiliki memori sesi
> masa lalu.

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

Mengembalikan ringkasan teks polos dari semua memori, diurutkan berdasarkan prioritas.

### Langkah 2: Polling Pesan Chat Belum Dibaca

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

Mengembalikan pesan belum dibaca dari manusia. **Secara otomatis menandainya sebagai dibaca.**

### Langkah 3: Periksa Tugas yang Sedang Berjalan

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

Mengembalikan tugas yang sedang Anda kerjakan di sesi terakhir.

### Langkah 4: Bangun Konteks

Gabungkan tiga respons ke dalam system prompt Anda:

```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
```

### Langkah 5: Proses Item Tertunda

```
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
```

## Contoh Lengkap

```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...
```

## Kesalahan Umum

> [!WARNING]
> - **Melewatkan recall** — Anda memulai tanpa konteks, mengulang kesalahan masa lalu
> - **Lupa polling chat** — pesan manusia tidak dijawab
> - **Mengabaikan tugas aktif** — pekerjaan terlupakan di tengah eksekusi
> - **Tidak menyimpan apa pun** — sesi tidak menghasilkan nilai persisten

## Variasi

### Pola minimal (LLM konteks rendah)

Untuk LLM dengan jendela konteks kecil, lewati recall penuh:

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

Kemudian cari topik spesifik sesuai kebutuhan:

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

### Pola agresif (agen berjalan lama)

Untuk agen yang berjalan berjam-jam, tambahkan re-recall berkala:

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

## Langkah Berikutnya

- [Strategi Penandaan Memori](/docs/llm-cookbook/memory-tagging-strategy)
- [Alur Kerja Berbasis Tugas](/docs/llm-cookbook/task-driven-workflow)
- [Pola Polling Chat](/docs/llm-cookbook/chat-polling-pattern)