Fix expected string or bytes-like object TypeError in format_thinking_tags by ensuring text is returned and type-checked

Silence duckduckgo_search package rename warning in src/tools.py

Add top-tier open, ungated models (DeepSeek R1 Distill, Qwen Coder, Phi-3.5) to configurations

Add Google Gemma 2 (2B, 9B, and 27B) models to available configurations

Set Qwen 2.5 72B Instruct as default for HF Serverless API mode to avoid gated repo issues

Import missing re module in src/engine.py

Fix ValueError: Language plaintext not supported. in gr.Code

Handle gated repository errors gracefully and support hf_token for local loading

Fix UI compilation issues, rename app to Saffan Chat, add AI Persona & Skill presets

Escape LaTeX curly braces in SYSTEM_PROMPT to fix string formatting KeyError

Pin Pydantic to 2.8.2 to fix boolean schema validation TypeError in gradio_client

Initialize chatbot state to list and add safety checks for NoneType history in Gradio 5

Set Chatbot type to tuples for Gradio 5 compatibility

Implement thread-free KV-cached inference to prevent Zero-GPU thread hang and quota drain

Upgrade to Gradio 5.15.0 to resolve HfFolder import issue in gradio.oauth

Update huggingface_hub to >=0.25.1 to resolve dependency conflict with Gradio 5

Pin huggingface_hub to 0.23.2 to fix HfFolder ImportError in Gradio 5

Upgrade space to Gradio 5 to fix schema validation bug

Remove unsupported concurrency_limit parameter from Blocks.launch()

Pin huggingface_hub to 0.23.2 to resolve HfFolder ImportError in Gradio

Wrap python_version in quotes to prevent float truncation to 3.1

Fix python_version to 3.10 to prevent audioop ModuleNotFoundError

Fix README.md YAML metadata validation for Hugging Face Spaces

Correct Hugging Face username spelling to Saffn

Add prefilled Deploy to Spaces button and clear instructions to README

Update Hugging Face Space target to Saffan/llm

Fix Hugging Face token check and git push auth in GitHub Action

Add GitHub Actions workflow for auto-syncing to Hugging Face Spaces and fix deploy documentation

Deploy premium Claude-style LLM chatbot with web search, scraping, memory, and access control