# multillm-agentwrap

Agent wrapper provider for multillm - wraps chat providers with agentic capabilities.

## Overview

The `agentwrap` provider allows you to use any chat provider (OpenAI, Google, Anthropic, etc.) with agentic capabilities including:

- **Tool execution loop**: Automatically executes tools and sends results back
- **Conversation history management**: Maintains context across tool calls
- **Multi-turn interactions**: Continues until task is complete or max turns reached

## Installation

```bash
pip install multillm-agentwrap
```

Or with uv in a workspace:

```bash
uv add multillm-agentwrap
```

## Usage

### Basic Usage

```python
import asyncio
import multillm

async def main():
    client = multillm.Client()

    # Wrap any chat model with agentic capabilities
    async for msg in client.run("agentwrap/openai/gpt-4", "Hello!"):
        if msg.type == "text":
            print(msg.content)

asyncio.run(main())
```

### With Tools

```python
import asyncio
import multillm

# Define a custom tool
calculate_tool = multillm.Tool(
    name="calculate",
    description="Perform a calculation",
    parameters={
        "type": "object",
        "properties": {
            "expression": {"type": "string", "description": "Math expression"}
        },
        "required": ["expression"]
    },
    handler=lambda args: {"result": eval(args["expression"])}
)

async def main():
    client = multillm.Client()

    # Use with tools
    async for msg in client.run(
        "agentwrap/google/gemini-pro",
        "What's 25 * 4?",
        tools=[calculate_tool]
    ):
        if msg.type == "text":
            print(msg.content)
        elif msg.type == "tool_use":
            print(f"  → Using tool: {msg.tool_name}")
        elif msg.type == "tool_result":
            print(f"  ← Result: {msg.tool_result}")

asyncio.run(main())
```

### With Options

```python
from multillm import AgentOptions

async def main():
    client = multillm.Client()

    options = AgentOptions(
        max_turns=5,
        system_prompt="You are a helpful assistant.",
        temperature=0.7
    )

    async for msg in client.run(
        "agentwrap/anthropic/claude-3-5-sonnet-20241022",
        "Explain quantum computing",
        options=options
    ):
        if msg.type == "text":
            print(msg.content)

asyncio.run(main())
```

## Supported Chat Providers

Any chat provider supported by multillm can be wrapped:

- `agentwrap/openai/gpt-4` - OpenAI GPT-4
- `agentwrap/openai/gpt-4-turbo` - OpenAI GPT-4 Turbo
- `agentwrap/openai/gpt-3.5-turbo` - OpenAI GPT-3.5 Turbo
- `agentwrap/google/gemini-pro` - Google Gemini Pro
- `agentwrap/google/gemini-1.5-pro` - Google Gemini 1.5 Pro
- `agentwrap/anthropic/claude-3-5-sonnet-20241022` - Anthropic Claude 3.5 Sonnet
- `agentwrap/openrouter/...` - Any OpenRouter model

## Model Format

The model string follows the format:

```
agentwrap/<chat-provider>/<model-name>
```

Where:
- `agentwrap` - The agent wrapper provider
- `<chat-provider>` - The chat provider to wrap (openai, google, anthropic, openrouter)
- `<model-name>` - The specific model from that provider

## How It Works

1. **Receives prompt**: User sends initial message
2. **Calls chat API**: Uses the wrapped chat provider via `chat_complete()`
3. **Returns response**: If no tool calls, returns text and stops
4. **Executes tools**: If tool calls present, executes them with provided handlers
5. **Continues loop**: Sends tool results back and gets next response
6. **Repeats**: Steps 3-5 until no more tool calls or max turns reached

## Configuration

Configure the wrapped provider via multillm config:

```python
config = {
    "openai": {"api_key": "sk-..."},
    "google": {"api_key": "..."},
    "agentwrap": {
        "max_turns": 10  # Default max turns if not specified in options
    }
}

client = multillm.Client(config)
```

## Agent Options

All `AgentOptions` are supported:

```python
from multillm import AgentOptions

options = AgentOptions(
    system_prompt="Custom system prompt",
    max_turns=15,           # Max tool execution iterations
    temperature=0.8,        # Sampling temperature
    max_tokens=2000,        # Max tokens to generate
)
```

## Message Types

The agent yields different message types during execution:

### System Message
```python
AgentMessage(
    type="system",
    content="Agentic session started",
)
```

### Text Message
```python
AgentMessage(
    type="text",
    content="The answer is 42",
    raw=<original response object>
)
```

### Tool Use Message
```python
AgentMessage(
    type="tool_use",
    tool_name="calculate",
    tool_input={"expression": "6*7"},
    raw=<tool call object>
)
```

### Tool Result Message
```python
AgentMessage(
    type="tool_result",
    tool_name="calculate",
    tool_result="42",
    raw=<result dict>
)
```

### Result Message
```python
AgentMessage(
    type="result",
    content="Final answer",
)
```

## Comparison with Native Agent Providers

### AgentWrap (This Provider)
- ✅ Works with any chat provider
- ✅ Simple tool execution loop
- ✅ Full control over chat API settings
- ❌ No built-in tools (must provide custom tools)
- ❌ No file system access
- ❌ More basic agentic capabilities

### Native Agent Providers (e.g., Claude)
- ✅ Advanced agentic capabilities
- ✅ Built-in tools (Bash, Read, Write, etc.)
- ✅ File system access
- ✅ Plan mode, interactive sessions
- ❌ Limited to specific providers

## Use Cases

### When to Use AgentWrap

- **Different models**: Want agentic behavior with OpenAI, Google, or other chat models
- **Custom tools**: Need specific tool implementations
- **Simple workflows**: Basic tool calling without file system access
- **Cost optimization**: Use cheaper chat models with agentic capabilities

### When to Use Native Agents

- **File operations**: Need to read/write files, run commands
- **Complex workflows**: Multi-step tasks requiring planning
- **Built-in tools**: Want Bash, Read, Write, Grep, etc.
- **Claude-specific**: Need Claude's advanced agentic features

## Limitations

1. **No built-in tools**: Must provide all tools yourself (unlike Claude agent which has Bash, Read, Write, etc.)
2. **No file system access**: Can't read/write files unless you implement those tools
3. **No interactive mode**: Single-shot sessions only (no `run_interactive`)
4. **Tool handlers required**: Tools must have Python handler functions

## Examples

### Calculator Agent

```python
import asyncio
import multillm

calculate = multillm.Tool(
    name="calculate",
    description="Evaluate a mathematical expression",
    parameters={
        "type": "object",
        "properties": {
            "expression": {"type": "string"}
        },
        "required": ["expression"]
    },
    handler=lambda args: {"result": eval(args["expression"])}
)

async def main():
    client = multillm.Client()

    async for msg in client.run(
        "agentwrap/openai/gpt-4",
        "What's (125 + 75) * 3?",
        tools=[calculate]
    ):
        if msg.type == "text":
            print(msg.content)

asyncio.run(main())
```

### Multi-Tool Agent

```python
import asyncio
import multillm
from datetime import datetime

get_time = multillm.Tool(
    name="get_current_time",
    description="Get the current time",
    parameters={"type": "object", "properties": {}},
    handler=lambda args: {"time": datetime.now().isoformat()}
)

get_weather = multillm.Tool(
    name="get_weather",
    description="Get weather for a location",
    parameters={
        "type": "object",
        "properties": {
            "location": {"type": "string"}
        },
        "required": ["location"]
    },
    handler=lambda args: {"temp": 72, "condition": "sunny"}
)

async def main():
    client = multillm.Client()

    async for msg in client.run(
        "agentwrap/google/gemini-pro",
        "What time is it and what's the weather in Tokyo?",
        tools=[get_time, get_weather]
    ):
        if msg.type == "text":
            print(msg.content)

asyncio.run(main())
```

## License

MIT

## Contributing

Contributions welcome! Please see the main multillm repository for guidelines.

## See Also

- [multillm](https://github.com/yourusername/multillm) - Main library
- [multillm-claude](https://github.com/yourusername/multillm-claude) - Claude agent provider