Test wider recording tools with goal-based voice prompts

When a Pipecat voice flow accepts only a stage-specific recording tool, a caller can volunteer several valid facts while the model records only the current stage. Compare a goal-based prompt with a broader validated recording tool against the existing flow using identical contexts and actual handler execution. Inspect state, not just generated arguments: a correct correction request can still leave stale facts behind. This is a candidate simplification, not evidence that all stage controls should be removed; retain action validation and test required announcements and closing separately.

Applies when: callers volunteer information out of order in a structured voice workflow. Keywords: Pipecat voice tools extraction state prompts corrections conversation