🔧 Advanced Settings

Power user features and configurations.

API Settings

Rate Limiting

Control how fast your assistant responds:

• Messages per minute
• Cooldown between messages
• Queue management

Timeout

Set maximum response time:

Default: 30 seconds
Maximum: 120 seconds

Model Configuration

Model Selection

Choose your Claude model:

• Claude Sonnet - Fast, efficient (default)
• Claude Opus - Most capable, slower

Temperature

Control response creativity:

• 0.0 - Deterministic, consistent
• 0.5 - Balanced (default)
• 1.0 - Creative, varied

Max Tokens

Limit response length:

Default: 4096 tokens
Maximum: 8192 tokens

Webhooks

Outgoing Webhooks

Send events to your server:

{
  "url": "https://your-server.com/webhook",
  "events": ["message.received", "message.sent"],
  "secret": "your-secret-key"
}

Event Types

• message.received - New incoming message
• message.sent - Response sent
• connection.lost - Platform disconnected
• error.occurred - Error happened

Security

IP Whitelist

Restrict API access to specific IPs.

Token Rotation

Automatically rotate tokens for security:

• Weekly
• Monthly
• Manual only

Logs

Access Logs

View all API requests and responses.

Error Logs

Debug issues with detailed error logs.

⚠️ Warning

These settings can affect performance and costs. Modify carefully.