agentic office

network-poc/node/src/qwen_coder.rs

@@ -76,7 +76,7 @@ async fn ensure_cached(key: &str, url: &str, ws: &Rc<RefCell<WebSocket>>) -> Res
 }
 
 /// use_3b: false = 0.5B (nopea), true = 3B (laadukas)
-pub async fn run_coder_inference(prompt: String, ws: Rc<RefCell<WebSocket>>, use_3b: bool) {
+pub async fn run_coder_inference(prompt: String, ws: Rc<RefCell<WebSocket>>, use_3b: bool, task_id: Option<String>) {
     let perf = web_sys::window().unwrap().performance().unwrap();
     let size_label = if use_3b { "3B" } else { "0.5B" };
 
@@ -271,7 +271,7 @@ pub async fn run_coder_inference(prompt: String, ws: Rc<RefCell<WebSocket>>, use
     let tokens_per_sec = if gen_time > 0.0 { (tokens_generated as f64 / gen_time) * 1000.0 } else { 0.0 };
     console_log!("[Coder] {} tokenia | {:.0}ms | {:.1} tok/s", tokens_generated, gen_time, tokens_per_sec);
 
-    let done = serde_json::json!({
+    let mut done = serde_json::json!({
         "type": "llm_done",
         "prompt": prompt,
         "model": format!("Qwen2.5-Coder-{}-Instruct", size_label),
@@ -281,5 +281,8 @@ pub async fn run_coder_inference(prompt: String, ws: Rc<RefCell<WebSocket>>, use
         "tokens_per_sec": (tokens_per_sec * 10.0).round() / 10.0,
         "load_time_ms": (load_time * 100.0).round() / 100.0,
     });
+    if let Some(tid) = task_id {
+        done.as_object_mut().unwrap().insert("task_id".to_string(), serde_json::json!(tid));
+    }
     let _ = ws.borrow().send_with_str(&done.to_string());
 }