fix clippy errors

.github/workflows/release.yml

@@ -45,7 +45,7 @@ jobs:
 
       - name: Clippy
         shell: bash
-        run: cargo clippy --all-targets
+        run: cargo clippy --all
 
       - name: Tests
         shell: bash

crates/embeddings-engine/src/lib.rs

@@ -3,7 +3,7 @@ use axum::{
     Json, Router,
     http::StatusCode,
     response::Json as ResponseJson,
-    routing::{get, post},
+    routing::post,
 };
 use fastembed::{EmbeddingModel, InitOptions, TextEmbedding};
 use once_cell::sync::Lazy;
@@ -11,7 +11,6 @@ use serde::Serialize;
 use std::collections::HashMap;
 use std::sync::{Arc, RwLock};
 use tower_http::trace::TraceLayer;
-use tracing;
 
 // Cache for multiple embedding models
 static MODEL_CACHE: Lazy<RwLock<HashMap<EmbeddingModel, Arc<TextEmbedding>>>> =

crates/predict-otron-9000/src/config.rs

@@ -39,28 +39,13 @@ impl Default for ServerMode {
     }
 }
 
-#[derive(Debug, Clone, Deserialize, Serialize)]
+#[derive(Debug, Clone, Deserialize, Serialize, Default)]
 pub struct Services {
     pub inference_url: Option<String>,
     pub embeddings_url: Option<String>,
 }
 
-impl Default for Services {
-    fn default() -> Self {
-        Self {
-            inference_url: None,
-            embeddings_url: None,
-        }
-    }
-}
 
-fn inference_service_url() -> String {
-    "http://inference-service:8080".to_string()
-}
-
-fn embeddings_service_url() -> String {
-    "http://embeddings-service:8080".to_string()
-}
 
 impl Default for ServerConfig {
     fn default() -> Self {
@@ -118,8 +103,7 @@ impl ServerConfig {
                     "HighAvailability mode configured but services not well defined! \n## Config Used:\n {}",
                     config_string
                 );
-                let err = std::io::Error::new(
-                    std::io::ErrorKind::Other,
+                let err = std::io::Error::other(
                     "HighAvailability mode configured but services not well defined!",
                 );
                 return Err(err);

crates/predict-otron-9000/src/ha_mode.rs

@@ -126,7 +126,7 @@ use crate::config::ServerConfig;
 /// - Pretty JSON is fine in TOML using `''' ... '''`, but remember the newlines are part of the string.
 /// - If you control the consumer, TOML tables (the alternative above) are more ergonomic than embedding JSON.
 
-/// HTTP client configured for proxying requests
+///   HTTP client configured for proxying requests
 #[derive(Clone)]
 pub struct ProxyClient {
     client: Client,

crates/predict-otron-9000/src/main.rs

@@ -4,12 +4,11 @@ mod middleware;
 mod standalone_mode;
 
 use crate::standalone_mode::create_standalone_router;
-use axum::handler::Handler;
 use axum::http::StatusCode as AxumStatusCode;
 use axum::http::header;
 use axum::response::IntoResponse;
 use axum::routing::get;
-use axum::{Router, ServiceExt, http::Uri, response::Html, serve};
+use axum::{Router, http::Uri, response::Html, serve};
 use config::ServerConfig;
 use ha_mode::create_ha_router;
 use inference_engine::AppState;
@@ -127,7 +126,7 @@ async fn main() {
         .layer(TraceLayer::new_for_http());
 
     // Server configuration
-    let server_host = env::var("SERVER_HOST").unwrap_or_else(|_| String::from(default_host));
+    let server_host = env::var("SERVER_HOST").unwrap_or_else(|_| default_host.to_string());
 
     let server_port = env::var("SERVER_PORT")
         .map(|v| v.parse::<u16>().unwrap_or(default_port))

crates/predict-otron-9000/src/standalone_mode.rs

@@ -2,7 +2,7 @@ use crate::config::ServerConfig;
 use axum::Router;
 use inference_engine::AppState;
 
-pub fn create_standalone_router(server_config: ServerConfig) -> Router {
+pub fn create_standalone_router(_server_config: ServerConfig) -> Router {
     // Create unified router by merging embeddings and inference routers (existing behavior)
     let embeddings_router = embeddings_engine::create_embeddings_router();
 

integration/cli/build.rs

@@ -25,7 +25,7 @@ fn run_build() -> io::Result<()> {
     let output_path = out_dir.join("client-cli");
 
     let bun_tgt = BunTarget::from_cargo_env()
-        .map_err(|e| io::Error::new(io::ErrorKind::Other, e.to_string()))?;
+        .map_err(|e| io::Error::other(e.to_string()))?;
 
     // Optional: warn if using a Bun target that’s marked unsupported in your chart
     if matches!(bun_tgt, BunTarget::WindowsArm64) {
@@ -54,13 +54,12 @@ fn run_build() -> io::Result<()> {
 
     if !install_status.success() {
         let code = install_status.code().unwrap_or(1);
-        return Err(io::Error::new(
-            io::ErrorKind::Other,
+        return Err(io::Error::other(
             format!("bun install failed with status {code}"),
         ));
     }
 
-    let target = env::var("TARGET").unwrap();
+    let _target = env::var("TARGET").unwrap();
 
     // --- bun build (in ./package), emit to OUT_DIR, keep temps inside OUT_DIR ---
     let mut build = Command::new("bun")
@@ -87,7 +86,7 @@ fn run_build() -> io::Result<()> {
     } else {
         let code = status.code().unwrap_or(1);
         warn(&format!("bun build failed with status: {code}"));
-        return Err(io::Error::new(io::ErrorKind::Other, "bun build failed"));
+        return Err(io::Error::other("bun build failed"));
     }
 
     // Ensure the output is executable (after it exists)

integration/gemma-runner/src/gemma_api.rs

@@ -191,8 +191,6 @@ impl TextGeneration {
         // Make sure stdout isn't holding anything (if caller also prints).
         std::io::stdout().flush()?;
 
-        let mut _generated_tokens = 0usize;
-
         let eos_token = match self.tokenizer.get_token("<eos>") {
             Some(token) => token,
             None => anyhow::bail!("cannot find the <eos> token"),
@@ -207,7 +205,7 @@ impl TextGeneration {
 
         let start_gen = std::time::Instant::now();
 
-        for index in 0..sample_len {
+        for (_generated_tokens, index) in (0..sample_len).enumerate() {
             let context_size = if index > 0 { 1 } else { tokens.len() };
             let start_pos = tokens.len().saturating_sub(context_size);
             let ctxt = &tokens[start_pos..];
@@ -229,7 +227,6 @@ impl TextGeneration {
 
             let next_token = self.logits_processor.sample(&logits)?;
             tokens.push(next_token);
-            _generated_tokens += 1;
 
             if next_token == eos_token || next_token == eot_token {
                 break;

integration/gemma-runner/src/gemma_cli.rs

@@ -67,7 +67,7 @@ pub fn run_cli() -> anyhow::Result<()> {
     let cfg = GemmaInferenceConfig {
         tracing: args.tracing,
         prompt: args.prompt,
-        model: args.model,
+        model: Some(args.model),
         cpu: args.cpu,
         dtype: args.dtype,
         model_id: args.model_id,

integration/llama-runner/src/lib.rs

@@ -1,6 +1,5 @@
 pub mod llama_api;
 
-use clap::ValueEnum;
 pub use llama_api::{run_llama_inference, LlamaInferenceConfig, WhichModel};
 
 // Re-export constants and types that might be needed

integration/utils/src/lib.rs

@@ -126,7 +126,7 @@ pub fn hub_load_safetensors(
         .iter()
         .map(|v| {
             repo.get(v)
-                .map_err(|e| std::io::Error::new(std::io::ErrorKind::Other, e))
+                .map_err(|e| std::io::Error::other(e))
         })
         .collect::<Result<Vec<_>, std::io::Error>>()?;
     Ok(safetensors_files)