mode selection, settings added to ui

cortex/data/self_state.json

@@ -4,8 +4,8 @@
   "focus": "conversation",
   "confidence": 0.7,
   "curiosity": 1.0,
-  "last_updated": "2025-12-20T09:08:41.342756",
-  "interaction_count": 25,
+  "last_updated": "2025-12-21T18:50:41.582043",
+  "interaction_count": 26,
   "learning_queue": [],
   "active_goals": [],
   "preferences": {

cortex/llm/llm_router.py

@@ -141,11 +141,16 @@ async def call_llm(
             "Authorization": f"Bearer {cfg['api_key']}",
             "Content-Type": "application/json"
         }
+
+        # 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}
-            ],
+            "messages": chat_messages,
             "temperature": temperature,
             "max_tokens": max_tokens,
         }

cortex/router.py

@@ -44,6 +44,7 @@ class ReasonRequest(BaseModel):
     session_id: str
     user_prompt: str
     temperature: float | None = None
+    backend: str | None = None
 
 
 # -------------------------------------------------------------------
@@ -388,8 +389,11 @@ async def run_simple(req: ReasonRequest):
 
     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")
+    # Get backend from request, otherwise fall back to env variable
+    backend = req.backend if req.backend else os.getenv("STANDARD_MODE_LLM", "SECONDARY")
+    backend = backend.upper()  # Normalize to uppercase
+    logger.info(f"🔧 Using backend: {backend}")
+
     temperature = req.temperature if req.temperature is not None else 0.7
 
     # Direct LLM call with messages (works for Ollama/OpenAI chat APIs)