Remove max_tokens parameter from LLM request in generate_llm function for cleaner API call.

Refactor LLM functions by removing unused summarize, translate, and meme functions; update generate_llm to increase max_tokens limit for improved response handling.

Refactor error handling in generate_llm to raise LLMBadRequestError on HTTP 400; add clear_history function to reset conversation history on bad requests.

Refactor generate_llm function for improved readability; streamline parameter assignments and enhance error handling for 400 Bad Request responses.

Refactor OpenAI client initialization to use hardcoded base URL and API key; simplify generate_llm function by removing model parameter.

Refactor generate_llm function to remove max_tokens and temperature parameters; use hardcoded defaults instead.

Refactor LLM settings to use hardcoded defaults for model and max tokens; remove reliance on config.yaml for these parameters.

Enhance logging and error handling across modules; refactor image generation and upload processes; update configuration for image generation parameters.

Enhance voice reply function to include a friendly prompt; implement retry logic with delay in LLM generation

Increase max_tokens for LLM generation to 8000; update example usage comment

Refactor trivia and weather functions; remove trivia-related code and update help text

Refactor URL construction in generate_llm function for consistency; adjust parameter order for clarity.

Increase random seed range to enhance variability in image and trivia generation across multiple modules

Fix model parameter in Pollinations API URL to use 'openai-large' for improved performance

Enhance trivia question generation prompt for clarity and enforce strict JSON format; add debug logging for random seed in LLM URL construction.

Enhance app functionality with inactivity monitoring, startup messaging, and improved command responses; update configuration for text and voice replies.