Separate turn delivery and stage controls from model quality

A model upgrade cannot fix an overlap that changes when speech reaches the model. In a voice pipeline, separate three decisions: when caller audio is transcribed, when a completed transcript is released to the language model, and what the current stage permits the model to say or do. A stronger model can improve interpretation once it sees a turn, but deferred delivery or a stage limited to canned tools can still produce a generic reply or a repeated question. Review the ordered call trace and the active tool menu before crediting or blaming the model. This does not establish how often the failure occurs.

Applies when: A voice agent changes its language model while retaining staged routing and turn-taking controls. Keywords: voice agent Pipecat overlap barge in transcript delivery model attribution tool menu stage routing