Aleix Conchillo Flaqué e3e90d38aa Preserve full user transcript across multiple inferences in one turn ...

When a stop-strategy chain splits inference-triggered from
finalization (e.g. `LLMTurnCompletionUserTurnStopStrategy` gating a
deferred detector), more than one inference can fire inside a single
user turn — each adds the new transcription segment to the context.
Previously each inference overwrote `_pending_user_turn_aggregation`,
so the eventual `on_user_turn_stopped` event surfaced only the
segment from the last inference, dropping anything the user said
before it.

Concatenate each segment into `_full_user_turn_aggregation` instead
of overwriting, and combine that running buffer with any post-final-
inference segment when emitting the public event.

2026-05-07 17:46:15 -07:00

62 KiB

Raw Blame History

View Raw