Fetching metadata from the HF Docker repository...
Feb 3 12:51 wrap code lines Jan 21 07:44 Merge remote-tracking branch 'refs/remotes/origin/main' 07:44 Update model name placeholder in input field to reflect new formats for LLM usage, enhancing user guidance for model selection. 07:16 Update README.md Jan 20 16:17 Add context length error detection and implement code reduction strategy in prompt construction for LLM inference. Enhance logging and return values to indicate code truncation status. 15:15 Refactor prompt construction and token management in LLM inference process, enhancing context handling and logging for code prompts 10:30 Add context length error handling and buffer management for prompt construction in LLM inference process 09:55 Update command syntax in documentation to clarify usage of the --token parameter for GitHub repository ingestion 09:54 Add functions for redacting secrets in error messages and safely storing model configuration in session state to enhance security and prevent sensitive information exposure. 09:49 Add new model presets for GPT-5.2, GPT-5.1, and Claude 4.5 series, while removing outdated GPT-4 and Claude 3 models for improved model selection. 09:40 Refactor LLM parameter handling to improve compatibility with GPT-5 and GPT-OSS models 09:32 Add drop_params option to LLM initialization and adjust parameter handling for model compatibility 09:19 Restrict file uploads to single files for markdown and text inputs 09:19 Disable XSRF protection in Streamlit configuration for to enable file upload Jan 19 16:32 disable local models for now 16:32 Add minimal toolbar mode and enable headless server in Streamlit config 16:29 disable telemetry 16:16 do not ignore .streamlit 16:14 set blue as primary color 15:45 Update README.md to set pinned attribute to true 15:44 Refactor prompt display to use container for scrollable view 15:08 inital commit Jan 15 15:42 Update README.md 15:41 Update README.md 15:04 initial commit 
