Instead of injecting research into every LLM call (which bloated prompts and caused timeouts), do one quick SearXNG search when a caller is picked up and add a relevant headline to their background. 3s timeout — if search is slow, caller just doesn't reference news. Zero impact on live conversation. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
78 KiB
78 KiB