feat(llm): add thinking parameter support for Ollama API calls

Add optional thinking parameter to the call_ollama function and pass it from the request. Also enhance timezone handling in prompt generation to support configurable timezone preferences.

backend/main.py

@@ -94,7 +94,12 @@ async def create_completion(request: Request, req: CompletionRequest):
             thinking_level=req.model_thinking,
             preferences=req.user_preferences
         )
-        result = await call_ollama(prompt, tag=f"{request_id}-primary", temperature=0.7)
+        result = await call_ollama(
+            prompt, 
+            tag=f"{request_id}-primary", 
+            temperature=0.7,
+            thinking=req.model_thinking if req.model_thinking != "none" else None
+        )
 
         content = result["content"] or ""
         if not content.strip():