Chat Interface

The chat interface provides interactive AI conversations with context management and tool calling.

Overview

Features:

• Real-time AI responses
• Conversation history
• Tool calling support
• Multi-provider support
• Context management
• Message threading

Usage

Basic Chat

Navigate to Chat in the sidebar:

1. Type your message
2. Press Enter or click Send
3. View AI response
4. Continue the conversation

Message Types

Type	Description
user	Your messages
assistant	AI responses
system	System instructions
tool	Tool call results

Conversation Management

New Conversation

Start fresh:

• Click "New Conversation"
• Previous context is cleared
• System prompt is reset

Conversation History

View past conversations:

• Scroll to load older messages
• Search by content
• Filter by date

Clear History

curl -X DELETE https://your-domain.com/api/agents/{id}/chat

Tool Calling

The AI can call tools during conversation:

Example

User: "What's the weather in Tokyo?"

AI thinks → Calls weather tool → Returns result

{
  "role": "assistant",
  "content": "The weather in Tokyo is...",
  "tool_calls": [
    {
      "id": "call_123",
      "type": "function",
      "function": {
        "name": "get_weather",
        "arguments": "{\"location\": \"Tokyo\"}"
      }
    }
  ]
}

Tool Results

{
  "role": "tool",
  "tool_call_id": "call_123",
  "content": "{\"temperature\": 22, \"condition\": \"sunny\"}"
}

Configuration

System Prompt

Set agent behavior:

{
  "llm_system_prompt": "You are a helpful assistant specialized in customer support. Always be polite and professional."
}

Model Settings

Setting	Description
llm_provider	AI provider (workers-ai, openai, anthropic)
llm_model	Specific model
llm_temperature	Creativity (0-1)
llm_max_tokens	Response length limit

API

Send Message

curl -X POST https://your-domain.com/api/agents/{id}/chat \
  -H "Content-Type: application/json" \
  -d '{
    "message": "Hello, how can you help me?",
    "conversation_id": "conv-123"
  }'

Response:

{
  "id": 456,
  "role": "assistant",
  "content": "Hello! I'm here to help you with...",
  "conversation_id": "conv-123",
  "created_at": "2024-12-15T10:30:00Z"
}

Get History

curl "https://your-domain.com/api/agents/{id}/chat?limit=50&conversation_id=conv-123"

Response:

{
  "messages": [
    {
      "id": 1,
      "role": "user",
      "content": "Hello",
      "created_at": "2024-12-15T10:00:00Z"
    },
    {
      "id": 2,
      "role": "assistant",
      "content": "Hi there!",
      "created_at": "2024-12-15T10:00:01Z"
    }
  ]
}

Streaming Responses

For real-time response streaming:

const response = await fetch('/api/agents/{id}/chat', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    message: 'Tell me a story',
    stream: true
  })
})

const reader = response.body.getReader()
while (true) {
  const { done, value } = await reader.read()
  if (done) break
  console.log(new TextDecoder().decode(value))
}

Context Window

Managing Context

The AI maintains conversation context:

• Recent messages are included
• Older messages are summarized
• System prompt is always included

Context Limits

Provider	Context Limit
Workers AI	8K-128K tokens
OpenAI	4K-128K tokens
Anthropic	100K-200K tokens

Integrations

With Workflows

Trigger chat from workflows:

{
  "type": "chat",
  "data": {
    "message": "{{input.question}}",
    "system_prompt": "Answer briefly"
  }
}

With Tools

Enable agent tools:

{
  "tools": [
    {
      "name": "search_database",
      "description": "Search the knowledge base",
      "parameters": {
        "query": { "type": "string" }
      }
    }
  ]
}

Best Practices

1. Clear System Prompts

Write specific, clear instructions:

You are a technical support agent for Acme Software.
- Answer questions about our products
- Help troubleshoot issues
- Escalate complex cases to humans
- Never make up answers

2. Manage Context

Keep conversations focused:

• Start new conversations for new topics
• Clear history when switching contexts
• Use conversation IDs for threading

3. Enable Relevant Tools

Only enable needed tools:

• Reduces confusion
• Faster responses
• Lower costs

4. Monitor Usage

Track chat metrics:

• Response times
• Token usage
• Error rates