8330c3487d
Splits ``_maybe_emit_user_turn_stopped`` into three focused methods — ``_flush_user_message_to_context`` (push aggregation, return content + timestamp), ``_finalize_user_turn`` (default-mode flow, emits both events), and ``_finalize_delayed_user_message`` (delayed-mode flow, emits only ``on_user_turn_message_finalized``). Fixes a side-issue where ``on_user_turn_stopped`` could fire from non-end-of-turn paths in delayed-transcript mode; that event now has a single origin (the end-of-turn handler). Standardizes vocabulary across docstrings and comments: - "Default mode" / "Delayed-transcript mode" (with ``_expect_delayed_transcripts == False/True``) - "End of turn" (not "audible stop" or "audible end of turn") - "User message finalization" (the moment user-text is flushed to context + ``on_user_turn_message_finalized`` fires) - "Pending finalization" (the in-between state in delayed mode) - Transcripts (plural — the aggregator combines multiple per turn) The timer that triggers user message finalization is no longer described as a "backstop" — it's the sole trigger for finalization in delayed-transcript mode, not a fallback. Renamed accordingly: ``_pending_finalization_task``, ``_pending_finalization_handler``, ``_run_pending_finalization``, ``_discard_pending_finalization``. Adds a separate message class for the two events: ``UserTurnStoppedMessage.content`` is now ``str | None`` (``None`` at end-of-turn in delayed-transcript mode), and a new ``UserMessageFinalizedMessage`` carries the always-populated ``content`` for the finalization event.
2 lines
1.4 KiB
Markdown
2 lines
1.4 KiB
Markdown
- Added the configuration surface to drive a realtime service like Gemini Live from local turn detection without paying user-transcript latency. Cascaded pipelines wait for transcripts before ending the user's turn because the downstream LLM needs the user's words recorded in context — but that wait is pure latency in pipelines using local turn detection to drive a realtime service, which consumes user audio directly. Set `wait_for_transcript_to_end_user_turn=False` on `LLMUserAggregatorParams` to turn this on: the aggregator drops `TranscriptionUserTurnStartStrategy` from the start strategies (so late-arriving realtime transcripts don't trigger new turns), sets `wait_for_transcript=False` on any stop strategies that support it (so the turn ends without waiting for transcripts), fires `on_user_turn_stopped` at the end of turn (with empty content, since no transcripts have arrived yet), and defers the context flush until after a short wait that gives the realtime service time to emit its transcripts. A new `on_user_turn_message_finalized` event fires when the user's message has been written to context — in the default mode it coincides with `on_user_turn_stopped`; in the delayed-transcript mode it fires later. Consumers that want the populated transcript should subscribe to `on_user_turn_message_finalized`. See `examples/realtime/realtime-gemini-live-local-vad.py` for the full pattern.
|