Live chain-of-thought in a chatbot: how to actually stream the tool calls (not just the text)

Most "streaming" LLM chatbots stream just the text. The model says "I'll search for that…" and then you wait 6 seconds while the tokens dribble in. The actual search? Hidden. The 3 scrapes it did to fact-check? Hidden. You're staring at a typing indicator that doesn't tell you anything about what's actually taking time. I just built a chatbot where every tool call surfaces as a step in real time — 🔍 search_engine, 📄 scrape_as_markdown, 📄 scrape_as_markdown — while the response streams token...