From 4e49cfbbfa5072101fb90964bbcc8bba8fd3d896 Mon Sep 17 00:00:00 2001
From: Jaakko Vanhala <jaakko.vanhala@kamk.fi>
Date: Sat, 4 Apr 2026 21:33:54 +0300
Subject: [PATCH] puristettu qwen output tiukempaan muottiin

---
 network-poc/native-node/src/inference.rs | 13 ++++++++++++-
 network-poc/node/src/qwen_coder.rs       | 19 ++++++++++++++++---
 2 files changed, 28 insertions(+), 4 deletions(-)

diff --git a/network-poc/native-node/src/inference.rs b/network-poc/native-node/src/inference.rs
index b7e3b34..e0e023f 100644
--- a/network-poc/native-node/src/inference.rs
+++ b/network-poc/native-node/src/inference.rs
@@ -139,7 +139,7 @@ impl LlmEngine {
     }
 
     pub fn generate(&mut self, prompt: &str, max_tokens: usize) -> Result<GenerateResult, String> {
-        let formatted = format!("<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n", prompt);
+        let formatted = format!("<|im_start|>system\nYou are a coding assistant. Respond with ONLY code. No explanations, no markdown, no comments unless asked.<|im_end|>\n<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n", prompt);
 
         let encoding = self.tokenizer.encode(formatted.as_str(), true)
             .map_err(|e| format!("Encode: {}", e))?;
@@ -218,6 +218,17 @@ impl LlmEngine {
 
             if let Ok(text) = self.tokenizer.decode(&[next_token], true) {
                 generated_text.push_str(&text);
+
+                // Stop-sekvenssit: katkaistaan kun malli alkaa selittää
+                let lower = generated_text.to_lowercase();
+                if lower.contains("\n###") || lower.contains("\nexplanation") || lower.contains("\nnote:") || lower.contains("\noutput:") || lower.contains("\n```\n\n") {
+                    for stop in &["\n###", "\nExplanation", "\nNote:", "\nOutput:", "\n```\n\n"] {
+                        if let Some(pos) = generated_text.find(stop) {
+                            generated_text.truncate(pos);
+                        }
+                    }
+                    break;
+                }
             }
             all_tokens.push(next_token);
             tokens_generated += 1;
diff --git a/network-poc/node/src/qwen_coder.rs b/network-poc/node/src/qwen_coder.rs
index 9e0de37..7c43762 100644
--- a/network-poc/node/src/qwen_coder.rs
+++ b/network-poc/node/src/qwen_coder.rs
@@ -197,14 +197,14 @@ pub async fn run_coder_inference(prompt: String, ws: Rc<RefCell<WebSocket>>, use
         if let Ok(json) = serde_json::from_str::<serde_json::Value>(&prompt) {
             let p = json.get("prompt").and_then(|v| v.as_str()).unwrap_or(&prompt).to_string();
             let s = json.get("system").and_then(|v| v.as_str())
-                .unwrap_or("You are a Python coding assistant. Write only code, no explanations.").to_string();
+                .unwrap_or("You are a coding assistant. Respond with ONLY code. No explanations, no markdown, no comments unless asked.").to_string();
             let m = json.get("max_tokens").and_then(|v| v.as_u64()).unwrap_or(128) as usize;
             (p, s, m)
         } else {
-            (prompt.clone(), "You are a Python coding assistant. Write only code, no explanations.".to_string(), 128)
+            (prompt.clone(), "You are a coding assistant. Respond with ONLY code. No explanations, no markdown, no comments unless asked.".to_string(), 128)
         }
     } else {
-        (prompt.clone(), "You are a Python coding assistant. Write only code, no explanations.".to_string(), 128)
+        (prompt.clone(), "You are a coding assistant. Respond with ONLY code. No explanations, no markdown, no comments unless asked.".to_string(), 128)
     };
 
     let formatted = format!("<|im_start|>system\n{}<|im_end|>\n<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n", system_msg, actual_prompt);
@@ -286,6 +286,19 @@ pub async fn run_coder_inference(prompt: String, ws: Rc<RefCell<WebSocket>>, use
 
         if let Ok(text) = tokenizer.decode(&[next_token], true) {
             generated_text.push_str(&text);
+
+            // Stop-sekvenssit: katkaistaan kun malli alkaa selittää
+            let lower = generated_text.to_lowercase();
+            if lower.contains("\n###") || lower.contains("\nexplanation") || lower.contains("\nnote:") || lower.contains("\noutput:") || lower.contains("\n```\n\n") {
+                // Trimmataan selitysosuus pois
+                for stop in &["\n###", "\nExplanation", "\nNote:", "\nOutput:", "\n```\n\n"] {
+                    if let Some(pos) = generated_text.find(stop) {
+                        generated_text.truncate(pos);
+                    }
+                }
+                break;
+            }
+
             let mut chunk = serde_json::json!({ "type": "llm_chunk", "token": text, "prompt": prompt, "model": "Qwen2.5-Coder" });
                 if let Some(ref tid) = task_id { chunk.as_object_mut().unwrap().insert("task_id".to_string(), serde_json::json!(tid)); }
             let _ = ws.borrow().send_with_str(&chunk.to_string());