simple context added to standard mode

cortex/llm/llm_router.py

@@ -44,11 +44,22 @@ http_client = httpx.AsyncClient(timeout=120.0)
 # Public call
 # ------------------------------------------------------------
 async def call_llm(
-    prompt: str,
+    prompt: str = None,
+    messages: list = None,
     backend: str | None = None,
     temperature: float = 0.7,
     max_tokens: int = 512,
 ):
+    """
+    Call an LLM backend.
+
+    Args:
+        prompt: String prompt (for completion-style APIs like mi50)
+        messages: List of message dicts (for chat-style APIs like Ollama/OpenAI)
+        backend: Which backend to use (PRIMARY, SECONDARY, OPENAI, etc.)
+        temperature: Sampling temperature
+        max_tokens: Maximum tokens to generate
+    """
     backend = (backend or DEFAULT_BACKEND).upper()
 
     if backend not in BACKENDS:
@@ -69,7 +80,8 @@ async def call_llm(
         payload = {
             "prompt": prompt,
             "n_predict": max_tokens,
-            "temperature": temperature
+            "temperature": temperature,
+            "stop": ["User:", "\nUser:", "Assistant:", "\n\n\n"]
         }
         try:
             r = await http_client.post(f"{url}/completion", json=payload)
@@ -90,12 +102,20 @@ async def call_llm(
     # Provider: OLLAMA (your 3090)
     # -------------------------------
     if provider == "ollama":
+        # Use messages array if provided, otherwise convert prompt to single user message
+        if messages:
+            chat_messages = messages
+        else:
+            chat_messages = [{"role": "user", "content": prompt}]
+
         payload = {
             "model": model,
-            "messages": [
-                {"role": "user", "content": prompt}
-            ],
-            "stream": False
+            "messages": chat_messages,
+            "stream": False,
+            "options": {
+                "temperature": temperature,
+                "num_predict": max_tokens
+            }
         }
         try:
             r = await http_client.post(f"{url}/api/chat", json=payload)