Fix: ensure sampled_characteristics is initialized to prevent UnboundLocalError during LLM retries

Fix: revert google url to proper openai extension

Fix: remove trailing slash from google genai proxy base_url

Fix: brutally enforce base_url for Google GenAI in all OpenAI wrappers

Fix: allow token counting logic to intercept gemini model gracefully

Feat: Map default model to gemini-3-flash-preview

Feat: Set Google Gemini GenerativeLanguage API endpoint as default

Fix: Strip empty `stop` parameter for Google Gemini fallback

Fix: Strip unsupported payload parameters for Google Gemini OpenAI-compatible proxy

Feat: Fallback to Google gemini-3-flash-preview on primary LLM proxy error

Fix: point model to alias-huge in nested config

Fix: combine system messages to satisfy strict LLM chatml parser

Fix: allow token counting logic to intercept alias models gracefully

Fix: remove 35s wait time throttle in nested config

Fix: enforce system message to be the first in openai_utils requests

Fix: revert model to alias-large in nested config

Upload folder using huggingface_hub

Fix: revert MODEL to gpt-4o in nested config

Upload folder using huggingface_hub

Fix: remove alias-fast from nested config

Fix: Replace deprecated alias-fast with alias-large in fallback cascade

Fix: map base_url explicitely to Helmholtz endpoint in OpenAI client constructor

Fix: Explicitly provide dummy token to OpenAI client constructor if environment vars not mapped early enough

Fix SyntaxWarning for invalid escape sequence in llm.py

Fix ValueError for TOP_P parsing in tinytroupe init

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub