mode selection, settings added to ui

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)