//! `RustyTorch`++ Serving API
//!
//! HTTP/gRPC serving layer for the rtx-inference runtime providing:
//! - `RESTful` API endpoints for model inference
//! - Health check endpoint for service monitoring
//! - Model listing endpoint for available models
//! - Inference endpoint with streaming support
//! - Integration with rtx-inference crate
//!
//! Built with Axum for high-performance async HTTP handling.

#![deny(clippy::unwrap_used)]
#![cfg_attr(test, allow(clippy::unwrap_used))]
#![allow(clippy::module_name_repetitions)]
#![allow(clippy::too_many_lines)]

pub mod advanced_server;
pub mod billing;
pub mod cache;
pub mod continuous_batch;
pub mod error;
pub mod grammar_sampling;
pub mod grpc;
pub mod health;
pub mod inference;
pub mod inference_cached;
pub mod load_balancer;
pub mod models;
pub mod multi_model;
pub mod queue_management;
pub mod rate_limiting;
pub mod resilience;
pub mod sampling_strategies;
pub mod server;
pub mod streaming;
pub mod structured_generation;
pub mod validation;
pub mod websocket;

// Re-export key types
pub use error::{ApiError, ApiResult};
pub use health::HealthStatus;
pub use server::{ServerConfig, ServingServer};

// Re-export advanced LLM features
pub use advanced_server::{AdvancedServerConfig, AdvancedServingServer};
pub use billing::{BillingManager, BudgetConfig, CostBreakdown};
pub use continuous_batch::{
    ActiveBatch, BatchRequest, BatchingError, BatchingStats, ContinuousBatchingConfig,
    ContinuousBatchingController, FinishReason, Priority, RequestState,
};
pub use grammar_sampling::{BnfParser, ContextFreeGrammar, GrammarGuidedSampler};
pub use multi_model::{ModelConfig, ModelType, MultiModelManager};
pub use queue_management::{QueueManager, QueuedRequest, RequestPriority};
pub use rate_limiting::{RateLimitManager, TokenCost, UserTier};
pub use resilience::{
    CircuitBreaker, CircuitBreakerConfig, CircuitBreakerError, CircuitBreakerStats, CircuitState,
    ResilienceError, ResilienceHandler, RetryConfig, RetryError, RetryWithBackoff, TimeoutError,
    with_timeout,
};
pub use sampling_strategies::{AdvancedSampler, SamplingConfig, SamplingStrategy};
pub use streaming::{StreamConfig, StreamEvent, StreamManager, StreamType};
pub use structured_generation::{
    JsonSchema, OutputFormat, StructuredGenerationManager, ValidationResult,
};
pub use validation::{
    InputValidator, ValidationConfig, ValidationError, ValidationResult as InputValidationResult,
};

/// Version information
pub const VERSION: &str = env!("CARGO_PKG_VERSION");

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_version() {
        assert!(!VERSION.is_empty());
    }
}