refactor: Remove max_output_tokens from generation configuration for LLM and visualization code

connections.py

@@ -41,7 +41,7 @@ def initialize_connections():
 
         # 3. Initialize the LLM
         genai.configure(api_key=config.GEMINI_API_KEY)
-        llm_model = genai.GenerativeModel('gemini-2.5-flash', generation_config=genai.types.GenerationConfig(temperature=0, max_output_tokens=1048576))
+        llm_model = genai.GenerativeModel('gemini-2.5-flash', generation_config=genai.types.GenerationConfig(temperature=0))
         print(f"✅ LLM Model '{llm_model.model_name}' initialized.")
 
         print("✅ System Initialized Successfully.")

data_processing.py

@@ -133,7 +133,7 @@ def llm_generate_visualization_code(llm_model, query_context, facet_data):
     """Generates Python code for visualization based on query and data."""
     prompt = get_visualization_code_prompt(query_context, facet_data)
     try:
-        generation_config = genai.types.GenerationConfig(temperature=0, max_output_tokens=2048)
+        generation_config = genai.types.GenerationConfig(temperature=0)
         response = llm_model.generate_content(prompt, generation_config=generation_config)
         code = re.sub(r'^```python\s*|```$', '', response.text, flags=re.MULTILINE)
         return code