fmt and clippy

crates/inference-engine/src/lib.rs

@@ -8,7 +8,7 @@ pub mod server;
 // Re-export key components for easier access
 pub use inference::ModelInference;
 pub use model::{Model, Which};
-pub use server::{create_router, AppState};
+pub use server::{AppState, create_router};
 
 use std::env;
 use tracing_subscriber::{layer::SubscriberExt, util::SubscriberInitExt};

crates/inference-engine/src/main.rs

@@ -1,23 +1,26 @@
-use inference_engine::{create_router, init_tracing, get_server_config, AppState};
+use inference_engine::{AppState, create_router, get_server_config, init_tracing};
 use tokio::net::TcpListener;
 use tracing::info;
 
 #[tokio::main]
 async fn main() -> Result<(), Box<dyn std::error::Error>> {
     init_tracing();
-    
+
     let app_state = AppState::default();
     let app = create_router(app_state);
-    
+
     let (server_host, server_port, server_address) = get_server_config();
     let listener = TcpListener::bind(&server_address).await?;
-    
-    info!("Inference Engine server starting on http://{}", server_address);
+
+    info!(
+        "Inference Engine server starting on http://{}",
+        server_address
+    );
     info!("Available endpoints:");
     info!("  POST /v1/chat/completions - OpenAI-compatible chat completions");
     info!("  GET  /v1/models         - List available models");
-    
+
     axum::serve(listener, app).await?;
-    
+
     Ok(())
-}
+}

crates/inference-engine/src/server.rs

@@ -1,28 +1,28 @@
 use axum::{
+    Json, Router,
     extract::State,
     http::StatusCode,
-    response::{sse::Event, sse::Sse, IntoResponse},
+    response::{IntoResponse, sse::Event, sse::Sse},
     routing::{get, post},
-    Json, Router,
 };
 use futures_util::stream::{self, Stream};
 use std::convert::Infallible;
 use std::str::FromStr;
 use std::sync::Arc;
-use tokio::sync::{mpsc, Mutex};
+use tokio::sync::{Mutex, mpsc};
 use tokio_stream::wrappers::UnboundedReceiverStream;
 use tower_http::cors::{Any, CorsLayer};
 use uuid::Uuid;
 
+use crate::Which;
 use crate::openai_types::{
     ChatCompletionChoice, ChatCompletionChunk, ChatCompletionChunkChoice, ChatCompletionRequest,
     ChatCompletionResponse, Delta, Message, MessageContent, Model, ModelListResponse, Usage,
 };
-use crate::Which;
 use either::Either;
 use embeddings_engine::models_list;
-use gemma_runner::{run_gemma_api, GemmaInferenceConfig, WhichModel};
-use llama_runner::{run_llama_inference, LlamaInferenceConfig};
+use gemma_runner::{GemmaInferenceConfig, WhichModel, run_gemma_api};
+use llama_runner::{LlamaInferenceConfig, run_llama_inference};
 use serde_json::Value;
 // -------------------------
 // Shared app state