Fibi Agent Tool & Reasoning Transparency

Problem
The Fibi agent is currently a black box with no visibility into which tools are being called (especially custom actions) and behind the scenes reasoning. This makes it difficult to triage poor responsive, evaluate how effective custom action instructions are, and know if custom actions are being called or not.

Vision

Have an expandable section within the chat thread in the support dashboard that shows tool calls and reasoning text.

Out of scope

Tool call and reasoning visibility changes to the user in the chat window.