simple context added to standard mode

cortex/router.py

@@ -351,17 +351,34 @@ async def run_simple(req: ReasonRequest):
     logger.info(f"📝 User: {req.user_prompt[:150]}...")
     logger.info(f"{'-'*100}\n")
 
-    # Get conversation history from context
+    # Get conversation history from context and intake buffer
     context_state = await collect_context(req.session_id, req.user_prompt)
 
-    # Build simple conversation history
-    messages = []
-    if context_state.get("recent_messages"):
-        for msg in context_state["recent_messages"]:
+    # Get recent messages from Intake buffer
+    from intake.intake import get_recent_messages
+    recent_msgs = get_recent_messages(req.session_id, limit=20)
+    logger.info(f"📋 Retrieved {len(recent_msgs)} recent messages from Intake buffer")
+
+    # Build simple conversation history with system message
+    system_message = {
+        "role": "system",
+        "content": (
+            "You are a helpful AI assistant. Provide direct, concise responses to the user's questions. "
+            "Maintain context from previous messages in the conversation."
+        )
+    }
+
+    messages = [system_message]
+
+    # Add conversation history
+
+    if recent_msgs:
+        for msg in recent_msgs:
             messages.append({
                 "role": msg.get("role", "user"),
                 "content": msg.get("content", "")
             })
+            logger.info(f"  - {msg.get('role')}: {msg.get('content', '')[:50]}...")
 
     # Add current user message
     messages.append({
@@ -369,30 +386,24 @@ async def run_simple(req: ReasonRequest):
         "content": req.user_prompt
     })
 
-    # Format messages into a simple prompt for the LLM
-    conversation = ""
-    for msg in messages:
-        role = msg["role"]
-        content = msg["content"]
-        if role == "user":
-            conversation += f"User: {content}\n\n"
-        elif role == "assistant":
-            conversation += f"Assistant: {content}\n\n"
-
-    conversation += "Assistant: "
+    logger.info(f"📨 Total messages being sent to LLM: {len(messages)} (including system message)")
 
     # Get backend from env (default to OPENAI for standard mode)
     backend = os.getenv("STANDARD_MODE_LLM", "OPENAI")
     temperature = req.temperature if req.temperature is not None else 0.7
 
-    # Direct LLM call
+    # Direct LLM call with messages (works for Ollama/OpenAI chat APIs)
     try:
-        response = await call_llm(
-            prompt=conversation,
+        raw_response = await call_llm(
+            messages=messages,
             backend=backend,
             temperature=temperature,
             max_tokens=2048
         )
+
+        # Clean response - just strip whitespace
+        response = raw_response.strip()
+
     except Exception as e:
         logger.error(f"❌ LLM call failed: {e}")
         response = f"Error: {str(e)}"