Struct ProductionSamplingHandler 

pub struct ProductionSamplingHandler { /* private fields */ }

Production-grade sampling handler with real LLM backend integration

This handler provides enterprise-ready LLM integration with:

• Multi-provider support (OpenAI, Anthropic)
• MCP protocol compliance
• Comprehensive error handling
• Conversation context management
• Retry logic and timeout handling
• Proper async patterns with Send + Sync

Example Usage

use turbomcp_client::sampling::{ProductionSamplingHandler, LLMBackendConfig, LLMProvider};

let config = LLMBackendConfig {
    provider: LLMProvider::OpenAI {
        api_key: std::env::var("OPENAI_API_KEY")?,
        base_url: None,
        organization: None,
    },
    default_model: Some("gpt-4".to_string()),
    timeout_seconds: 30,
    max_retries: 3,
};

let handler = ProductionSamplingHandler::new(config)?;

Implementations

impl ProductionSamplingHandler

pub fn new(config: LLMBackendConfig) -> Result<Self, LLMBackendError>

Create a new production sampling handler

Trait Implementations

impl Debug for ProductionSamplingHandler

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl SamplingHandler for ProductionSamplingHandler

fn handle_create_message<'life0, 'async_trait>( &'life0 self, request: CreateMessageRequest, ) -> Pin<Box<dyn Future<Output = Result<CreateMessageResult, Box<dyn Error + Send + Sync>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Handle a sampling/createMessage request from the server