docs(chatbot): sync evaluation report to Wave 5, add 4 new intents to docs

fix(chatbot): add test coverage for all 17 intents; fix dataset quality

docs(chatbot): add ML evaluation notebook with Wave 4 results and weight sensitivity analysis

feat(ML): add show_map intent + context-aware map routing

Wave 3: expand NER fixture 85->102, time_preference F1 0.40->0.98, people/duration fixes

Wave 2: compare_destinations data + NER fixes + evaluation update

eval(chatbot): Wave 1 retrain + held-out evaluation results