fix: replace blocking ollama.generate() with streaming to eliminate 120s timeout errors

Switch to streamed generation with per-chunk timeout enforcement and
ComfyUI ProgressBar integration. Add user-configurable timeout slider
(30-600s), cold-start detection via ollama.ps(), and graceful fallback
to subprocess. Bump version to 1.1.6.

nodes/prompt_generator_node.py

@@ -226,8 +226,6 @@ Format the response as a single, detailed sci-fi prompt.""",
         Fetch available Ollama models with caching.
         Prioritizes LoRA-enhanced models (containing 'lora', 'limbicnation', 'fine').
         """
-        import time
-
         # Cache for 60 seconds
         if cls._cached_models and (time.time() - cls._cache_time) < 60:
             return cls._cached_models