fix: force moderator to always produce DÉCISION FINALE on first and only round 164a810 hamba-ho commited on 20 days ago
feat: enforce extreme conciseness and reduce max rounds to 2 to save tokens and speed up consensus 74b842d hamba-ho commited on 20 days ago
fix: bind stop sequences to llm to prevent hallucination loop and rate limit 429 errors dacd14f hamba-ho commited on 21 days ago
fix: enforce language detection with explicit SystemMessage and improve final decision structure 1c24d91 hamba-ho commited on 21 days ago
feat: add automatic multilingual support and optional location field for restaurant recommendations a2eff4c hamba-ho commited on 21 days ago
style: remove emojis and update agent names to be more professional 1e366c2 hamba-ho commited on 21 days ago