MCP Sampling

import asyncio
from praisonai.mcp_server.sampling import (
    SamplingHandler,
    SamplingRequest,
    SamplingMessage,
    create_sampling_request,
)

async def main():
    handler = SamplingHandler(default_model="gpt-4o-mini")

    # Create simple request
    request = create_sampling_request(
        prompt="What is the capital of France?",
        system_prompt="You are a helpful geography assistant.",
        max_tokens=100,
    )

    response = await handler.create_message(request)
    print(f"Response: {response.content}")
    print(f"Model: {response.model}")

asyncio.run(main())

from praisonai.mcp_server.sampling import ToolChoice, ToolDefinition

request = create_sampling_request(
    prompt="Search for the latest AI news",
    tools=[{
        "name": "web_search",
        "description": "Search the web",
        "inputSchema": {
            "type": "object",
            "properties": {"query": {"type": "string"}},
            "required": ["query"]
        }
    }],
    tool_choice="auto",  # or "none", "any", or specific tool name
)

response = await handler.create_message(request)
if response.tool_calls:
    print(f"Tool calls: {response.tool_calls}")

from praisonai.mcp_server.sampling import ToolChoice

# Model decides
tc = ToolChoice.auto()
print(tc.to_dict())  # {"mode": "auto"}

# No tools
tc = ToolChoice.none()
print(tc.to_dict())  # {"mode": "none"}

# Must use any tool
tc = ToolChoice.any()
print(tc.to_dict())  # {"mode": "any"}

# Must use specific tool
tc = ToolChoice.tool("web_search")
print(tc.to_dict())  # {"mode": "tool", "name": "web_search"}

from praisonai.mcp_server.sampling import ModelPreferences, SamplingRequest

prefs = ModelPreferences(
    hints=[{"name": "claude-3-sonnet"}, {"name": "gpt-4"}],
    cost_priority=0.3,      # 0-1, lower = prefer cheaper
    speed_priority=0.5,     # 0-1, lower = prefer faster
    intelligence_priority=0.8,  # 0-1, lower = prefer smarter
)

request = SamplingRequest(
    messages=[SamplingMessage(role="user", content="Hello!")],
    model_preferences=prefs,
    max_tokens=500,
)

async def my_llm_callback(request):
    """Custom LLM integration."""
    # Call your LLM here
    return SamplingResponse(
        role="assistant",
        content="Custom response",
        model="my-model",
        stop_reason="end_turn",
    )

handler = SamplingHandler()
handler.set_callback(my_llm_callback)

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "sampling/createMessage",
  "params": {
    "messages": [
      {
        "role": "user",
        "content": {"type": "text", "text": "Hello!"}
      }
    ],
    "maxTokens": 100,
    "systemPrompt": "You are helpful.",
    "modelPreferences": {
      "hints": [{"name": "claude-3-sonnet"}],
      "costPriority": 0.3,
      "speedPriority": 0.5,
      "intelligencePriority": 0.8
    },
    "tools": [
      {
        "name": "search",
        "description": "Search the web",
        "inputSchema": {"type": "object"}
      }
    ],
    "toolChoice": {"mode": "auto"}
  }
}

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "role": "assistant",
    "content": {"type": "text", "text": "Hello! How can I help?"},
    "model": "claude-3-sonnet",
    "stopReason": "end_turn"
  }
}

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "role": "assistant",
    "content": {"type": "text", "text": ""},
    "model": "claude-3-sonnet",
    "stopReason": "toolUse",
    "toolCalls": [
      {
        "id": "call_123",
        "name": "search",
        "arguments": {"query": "AI news"}
      }
    ]
  }
}