Aleix Conchillo Flaqué
4a61d5bfad
Add broadcast_interruption() to FrameProcessor
...
Replace the round-trip push_interruption_task_frame_and_wait() mechanism
with broadcast_interruption(), which pushes an InterruptionFrame both
upstream and downstream directly from the calling processor.
This eliminates race conditions (transcription arriving before the
InterruptionFrame comes back), swallowed-event timeouts (frame blocked
before reaching the sink), and the complexity of _wait_for_interruption
flag / queue bypass / frame.complete() obligations.
- Add broadcast_interruption() to FrameProcessor
- Deprecate push_interruption_task_frame_and_wait() (delegates to new method)
- Remove event field and complete() from InterruptionFrame/InterruptionTaskFrame
- Remove _wait_for_interruption flag and all special-case logic
- Remove frame.complete() calls in stt_mute_filter and llm_response_universal
- Update all 17 call sites to use broadcast_interruption()
- Update tests
2026-03-02 13:26:45 -08:00
Aleix Conchillo Flaqué
305ab44132
tests: add unittest.main() call
2026-01-30 10:07:34 -08:00
Aleix Conchillo Flaqué
2626154a64
update examples and tests copyright and use a proper dash in 2024-2026
2026-01-07 19:32:22 -08:00
Paul Kompfner
3d21faaac2
LLMAssistantAggregator now properly aggregates text that might be a mix of includes_inter_frame_spaces=True and includes_inter_frame_spaces=False frames
2025-11-18 15:12:25 -05:00
Paul Kompfner
913194844e
Make the mechanism of adding spaces when concatenating TTS (or speech-to-speech LLM) output text explicit and deterministic, rather than heuristic-based.
...
This fixes a bug where spaces were sometimes missing from assistant messages in context.
2025-11-10 14:22:32 -05:00
Aleix Conchillo Flaqué
d844829538
Revert "fix interruption task frame context ordering"
2025-11-05 12:14:03 -08:00
Aleix Conchillo Flaqué
e4212fb3c0
tests: add interruption strategies context ordering tests
2025-11-05 09:38:18 -08:00
Paul Kompfner
ac5734d0ed
Deprecate expect_stripped_words option from LLMAssistantAggregatorParams, when used with the newer LLMAssistantAggregator, which now handles word spacing automatically.
...
This commit does not change how it works in the older `LLMAssistantContextAggregator`.
2025-10-30 17:22:47 -04:00
Aleix Conchillo Flaqué
7c15a8c800
Revert "fix context order when using interruption strategies"
...
This reverts commit de8ee96927
2025-10-07 17:42:35 -07:00
Aleix Conchillo Flaqué
de8ee96927
fix context order when using interruption strategies
2025-10-06 22:43:01 -07:00
Aleix Conchillo Flaqué
57add41971
tests: add unit test for MinWordsInterruptionStrategy
2025-09-11 13:07:30 -07:00
Aleix Conchillo Flaqué
9d9f10ae0e
frames: StartInterruptionFrame is deprecated, use InterruptionFrame
2025-09-11 09:01:54 -07:00
Aleix Conchillo Flaqué
4015aedb86
tests: fix unit tests
2025-08-20 10:08:54 -07:00
Mark Backman
06c1255abe
fix: use a different aggregation timeout for emulated user speech ( #2185 )
...
* fix: use a different aggregation timeout for emulated user speech
* Add SpeechControlParamsFrame
* Update test_context_aggregator tests
2025-07-11 16:33:44 -04:00
Aleix Conchillo Flaqué
f31efa42c9
GoogleLLMService: deprecate google-generativeai
2025-05-09 09:14:43 -07:00
Aleix Conchillo Flaqué
a8405649d0
aws: use AWS prefix for all services
2025-05-07 09:26:26 -07:00
Aleix Conchillo Flaqué
ce1a72850b
tests: add bedrock context aggregator tests
2025-05-07 09:26:26 -07:00
Aleix Conchillo Flaqué
e97de43de2
add LLMUserAggregatorParams and LLMAssistantAggregatorParams
2025-04-16 15:19:19 -07:00
Aleix Conchillo Flaqué
3a37b11e56
TranscriptProcessor: send TranscriptionUpdateFrame after interruption
2025-04-01 10:21:21 -07:00
Aleix Conchillo Flaqué
7203ef6885
examples: use new services packages
2025-03-30 16:21:00 -07:00
Aleix Conchillo Flaqué
077952b658
GoogleAssistantContextAggregator: allow any value as function call result
2025-03-25 19:11:27 -07:00
Aleix Conchillo Flaqué
19b464ba23
tests: add assistant aggregator function call frame handling
2025-03-25 15:37:06 -07:00
Aleix Conchillo Flaqué
5a39f146f6
LLMUserContextAggregator: fix emulated user started/stopped speaking issues
2025-03-20 11:23:40 -07:00
Aleix Conchillo Flaqué
a98000fd1d
function calling now run in tasks
2025-03-20 08:51:25 -07:00
Aleix Conchillo Flaqué
5909dff423
LLMContextResponseAggregator: add VAD emulation support
2025-02-13 15:25:22 -08:00
Aleix Conchillo Flaqué
b28f752afa
tests: add anthropic and google aggregator tests
2025-02-13 13:20:38 -08:00
Aleix Conchillo Flaqué
463078e375
initialize assistant aggregators with context and push upstream instead
2025-02-13 13:20:38 -08:00
Aleix Conchillo Flaqué
84510fd521
LLMUserContextAggregator: add space between transcriptions
2025-02-13 13:20:38 -08:00
