feat: add sysinfo dependency and system metrics support

Added the sysinfo crate (v0.37.2) to gather system metrics. This includes:
- New dependencies: sysinfo, ntapi, objc2-core-foundation, objc2-io-kit
- Updated windows-core to specific version 0.62.2
- Initial system metrics integration in bot module

The change enables monitoring system resources which will be used for performance optimization and health monitoring.

Cargo.lock

@@ -1151,6 +1151,7 @@ dependencies = [
  "serde_json",
  "sha2",
  "smartstring",
+ "sysinfo",
  "tempfile",
  "time",
  "tokio",
@@ -2821,7 +2822,7 @@ dependencies = [
  "js-sys",
  "log",
  "wasm-bindgen",
- "windows-core",
+ "windows-core 0.62.2",
 ]
 
 [[package]]
@@ -3642,6 +3643,15 @@ dependencies = [
  "nom 8.0.0",
 ]
 
+[[package]]
+name = "ntapi"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e8a3895c6391c39d7fe7ebc444a87eb2991b2a0bc718fdabd071eec617fc68e4"
+dependencies = [
+ "winapi",
+]
+
 [[package]]
 name = "nu-ansi-term"
 version = "0.50.3"
@@ -3695,6 +3705,25 @@ dependencies = [
  "autocfg",
 ]
 
+[[package]]
+name = "objc2-core-foundation"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2a180dd8642fa45cdb7dd721cd4c11b1cadd4929ce112ebd8b9f5803cc79d536"
+dependencies = [
+ "bitflags",
+]
+
+[[package]]
+name = "objc2-io-kit"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "33fafba39597d6dc1fb709123dfa8289d39406734be322956a69f0931c73bb15"
+dependencies = [
+ "libc",
+ "objc2-core-foundation",
+]
+
 [[package]]
 name = "object"
 version = "0.32.2"
@@ -5229,6 +5258,20 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "sysinfo"
+version = "0.37.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "16607d5caffd1c07ce073528f9ed972d88db15dd44023fa57142963be3feb11f"
+dependencies = [
+ "libc",
+ "memchr",
+ "ntapi",
+ "objc2-core-foundation",
+ "objc2-io-kit",
+ "windows",
+]
+
 [[package]]
 name = "system-configuration"
 version = "0.6.1"
@@ -6144,6 +6187,41 @@ version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
 
+[[package]]
+name = "windows"
+version = "0.61.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9babd3a767a4c1aef6900409f85f5d53ce2544ccdfaa86dad48c91782c6d6893"
+dependencies = [
+ "windows-collections",
+ "windows-core 0.61.2",
+ "windows-future",
+ "windows-link 0.1.3",
+ "windows-numerics",
+]
+
+[[package]]
+name = "windows-collections"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3beeceb5e5cfd9eb1d76b381630e82c4241ccd0d27f1a39ed41b2760b255c5e8"
+dependencies = [
+ "windows-core 0.61.2",
+]
+
+[[package]]
+name = "windows-core"
+version = "0.61.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c0fdd3ddb90610c7638aa2b3a3ab2904fb9e5cdbecc643ddb3647212781c4ae3"
+dependencies = [
+ "windows-implement",
+ "windows-interface",
+ "windows-link 0.1.3",
+ "windows-result 0.3.4",
+ "windows-strings 0.4.2",
+]
+
 [[package]]
 name = "windows-core"
 version = "0.62.2"
@@ -6157,6 +6235,17 @@ dependencies = [
  "windows-strings 0.5.1",
 ]
 
+[[package]]
+name = "windows-future"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fc6a41e98427b19fe4b73c550f060b59fa592d7d686537eebf9385621bfbad8e"
+dependencies = [
+ "windows-core 0.61.2",
+ "windows-link 0.1.3",
+ "windows-threading",
+]
+
 [[package]]
 name = "windows-implement"
 version = "0.60.2"
@@ -6191,6 +6280,16 @@ version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
 
+[[package]]
+name = "windows-numerics"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9150af68066c4c5c07ddc0ce30421554771e528bde427614c61038bc2c92c2b1"
+dependencies = [
+ "windows-core 0.61.2",
+ "windows-link 0.1.3",
+]
+
 [[package]]
 name = "windows-registry"
 version = "0.5.3"
@@ -6331,6 +6430,15 @@ dependencies = [
  "windows_x86_64_msvc 0.53.1",
 ]
 
+[[package]]
+name = "windows-threading"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b66463ad2e0ea3bbf808b7f1d371311c80e115c0b71d60efc142cafbcfb057a6"
+dependencies = [
+ "windows-link 0.1.3",
+]
+
 [[package]]
 name = "windows_aarch64_gnullvm"
 version = "0.42.2"

Cargo.toml

@@ -89,6 +89,7 @@ serde = { version = "1.0", features = ["derive"] }
 serde_json = "1.0"
 sha2 = "0.10.9"
 smartstring = "1.0"
+sysinfo = "0.37.2"
 tempfile = "3"
 time = "0.3.44"
 tokio = { version = "1.41", features = ["full"] }

src/bot/mod.rs

@@ -1,16 +1,19 @@
 use crate::config::ConfigManager;
 use crate::drive_monitor::DriveMonitor;
 use crate::llm_models;
+use crate::nvidia::get_system_metrics;
 use crate::shared::models::{BotResponse, Suggestion, UserMessage, UserSession};
 use crate::shared::state::AppState;
 use actix_web::{web, HttpRequest, HttpResponse, Result};
 use actix_ws::Message as WsMessage;
-use chrono::Utc;
+use chrono::{Utc};
 use diesel::PgConnection;
 use log::{error, info, trace, warn};
 use serde_json;
+use tokio::time::Instant;
 use std::collections::HashMap;
 use std::sync::Arc;
+use std::time::Duration;
 use tokio::sync::mpsc;
 use tokio::sync::Mutex as AsyncMutex;
 use uuid::Uuid;
@@ -436,9 +439,10 @@ impl BotOrchestrator {
             response_tx.send(thinking_response).await?;
         }
 
+        let prompt_clone = prompt.clone();
         tokio::spawn(async move {
             if let Err(e) = llm
-                .generate_stream(&prompt, &serde_json::Value::Null, stream_tx)
+                .generate_stream(&prompt_clone, &serde_json::Value::Null, stream_tx)
                 .await
             {
                 error!("LLM streaming error: {}", e);
@@ -450,8 +454,32 @@ impl BotOrchestrator {
         let mut in_analysis = false;
         let mut chunk_count = 0;
         let mut first_word_received = false;
+        let mut last_progress_update = Instant::now();
+        let progress_interval = Duration::from_secs(1);
 
+        // Calculate initial token count
+        let initial_tokens = crate::shared::utils::estimate_token_count(&prompt);
         let config_manager = ConfigManager::new(Arc::clone(&self.state.conn));
+        let max_context_size = config_manager
+            .get_config(
+                &Uuid::parse_str(&message.bot_id).unwrap_or_default(),
+                "llm-server-ctx-size",
+                None,
+            )
+            .unwrap_or_default()
+            .parse::<usize>()
+            .unwrap_or(0);
+
+        // Show initial progress
+        if let Ok(metrics) = get_system_metrics(initial_tokens, max_context_size) {
+            eprintln!(
+                "\nNVIDIA: {:.1}% | CPU: {:.1}% | Tokens: {}/{}",
+                metrics.gpu_usage.unwrap_or(0.0),
+                metrics.cpu_usage,
+                initial_tokens,
+                max_context_size
+            );
+        }
         let model = config_manager
             .get_config(
                 &Uuid::parse_str(&message.bot_id).unwrap_or_default(),
@@ -498,6 +526,21 @@ impl BotOrchestrator {
             if !in_analysis {
                 full_response.push_str(&chunk);
 
+                // Update progress if interval elapsed
+                if last_progress_update.elapsed() >= progress_interval {
+                    let current_tokens = initial_tokens + crate::shared::utils::estimate_token_count(&full_response);
+                    if let Ok(metrics) = get_system_metrics(current_tokens, max_context_size) {
+                        eprintln!(
+                            "\nNVIDIA: {:.1}% | CPU: {:.1}% | Tokens: {}/{}",
+                            metrics.gpu_usage.unwrap_or(0.0),
+                            metrics.cpu_usage,
+                            current_tokens,
+                            max_context_size
+                        );
+                    }
+                    last_progress_update = Instant::now();
+                }
+
                 let partial = BotResponse {
                     bot_id: message.bot_id.clone(),
                     user_id: message.user_id.clone(),

src/lib.rs

@@ -20,3 +20,4 @@ pub mod tests;
 pub mod web_automation;
 pub mod web_server;
 pub mod auth;
+pub mod nvidia;

src/main.rs

@@ -31,7 +31,7 @@ pub mod tests;
 #[cfg(feature = "web_automation")]
 mod web_automation;
 mod web_server;
-
+mod nvidia;
 
 use crate::auth::auth_handler;
 use crate::automation::AutomationService;

src/nvidia/mod.rs

@@ -0,0 +1,86 @@
+use anyhow::Result;
+use log::warn;
+use std::collections::HashMap;
+use sysinfo::{System};
+
+/// System monitoring data
+pub struct SystemMetrics {
+    pub gpu_usage: Option<f32>,
+    pub cpu_usage: f32,
+    pub token_ratio: f32,
+}
+
+/// Gets current system metrics
+pub fn get_system_metrics(current_tokens: usize, max_tokens: usize) -> Result<SystemMetrics> {
+    let mut sys = System::new();
+    sys.refresh_cpu_usage();
+    
+    // Get CPU usage (average across all cores)
+    let cpu_usage = sys.global_cpu_usage();
+
+    // Get GPU usage if available
+    let gpu_usage = if has_nvidia_gpu() {
+        get_gpu_utilization()?.get("gpu").copied()
+    } else {
+        None
+    };
+
+    // Calculate token ratio
+    let token_ratio = if max_tokens > 0 {
+        current_tokens as f32 / max_tokens as f32 * 100.0
+    } else {
+        0.0
+    };
+
+    Ok(SystemMetrics {
+        gpu_usage,
+        cpu_usage,
+        token_ratio,
+    })
+}
+
+/// Checks if NVIDIA GPU is available
+pub fn has_nvidia_gpu() -> bool {
+    match std::process::Command::new("nvidia-smi")
+        .arg("--query-gpu=utilization.gpu")
+        .arg("--format=csv,noheader,nounits")
+        .output()
+    {
+        Ok(output) => output.status.success(),
+        Err(_) => {
+            warn!("No NVIDIA GPU detected or nvidia-smi not available");
+            false
+        }
+    }
+}
+
+/// Gets current GPU utilization percentages
+pub fn get_gpu_utilization() -> Result<HashMap<String, f32>> {
+    let output = std::process::Command::new("nvidia-smi")
+        .arg("--query-gpu=utilization.gpu,utilization.memory")
+        .arg("--format=csv,noheader,nounits")
+        .output()?;
+
+    if !output.status.success() {
+        return Err(anyhow::anyhow!("Failed to query GPU utilization"));
+    }
+
+    let output_str = String::from_utf8(output.stdout)?;
+    let mut util = HashMap::new();
+
+    for line in output_str.lines() {
+        let parts: Vec<&str> = line.split(',').collect();
+        if parts.len() >= 2 {
+            util.insert(
+                "gpu".to_string(),
+                parts[0].trim().parse::<f32>().unwrap_or(0.0),
+            );
+            util.insert(
+                "memory".to_string(),
+                parts[1].trim().parse::<f32>().unwrap_or(0.0),
+            );
+        }
+    }
+
+    Ok(util)
+}