add streak indicator and prevent concatenated word selection 04bba1d milwright commited on 4 days ago
remove word logging from console for cleaner debugging output 2ecb883 milwright commited on 10 days ago
point leaderboard to dedicated milwright/cloze-leaderboard space for shared standings 5beb699 milwright commited on 10 days ago
fix leaderboard initials entry readability with improved contrast and light background e4e854a milwright commited on 10 days ago
simplify game mechanics and consolidate to single AI model 86f177c milwright Claude commited on 10 days ago
fix ui issues: larger chat icons and proper book contextualization 37a7438 milwright commited on Sep 3
Implement level-aware word selection and performance optimizations 9e0745a milwright commited on Jun 17
feat: implement two-passage system to avoid OpenRouter rate limits 106bc8b milwright commited on Jun 13
debug: add API response logging to identify contextualization issue after first round cca074a milwright commited on Jun 13
fix: clean contextualization artifacts and ensure passages start properly 4f8034e milwright commited on Jun 12
fix: clean AI responses to remove JSON artifacts and markdown formatting dfcab2f milwright commited on Jun 12
fix: resolve HF dataset loading errors and improve word selection 6839f0d milwright commited on Jun 12
fix: implement constrained prompts matching tool-calling behavior 18f0d59 milwright commited on Jun 11
refactor: reduce technical debt by removing unused methods and tool definitions 6e0c330 milwright commited on Jun 11
refactor: proper separation of concerns - aiService as API wrapper, conversationManager builds prompts 2b8632d milwright commited on Jun 11
fix: replace tool-calling with simple direct prompts like main branch a261c04 milwright commited on Jun 11
fix: prevent AI hallucination and remove problematic tool_choice parameter 243e743 milwright commited on Jun 11
fix: correct tool-calling format and contextualization truncation 78a1f73 milwright commited on Jun 11