livekit-agents@1.2.8

Features:

• AgentSession.start() now returns a RunResult when called with capture_run=True. This makes it possible to assert the first message when the agent initiates the conversation:

result = await sess.start(EchoAgent(), capture_run=True)
result.expect.next_event().is_agent_handoff(new_agent_type=EchoAgent)
result.expect.next_event().is_message(role="assistant")

• Agent false interruptions are now automatically resumed after the false_interruption_timeout. Audio output is paused and then resumed on the same SpeechHandle, eliminating the need to manually call generate_reply() in the agent_false_interruption event handler—please remove this call if present from earlier versions. This behavior is enabled by default; to disable automatic resume, set resume_false_interruption=False.

What's Changed

• fix: start datastream audio output right after room connected by @longcw in https://github.com/livekit/agents/pull/3270
• add AudioOutput capabilities and disable pause/resume for if output not supported by @longcw in https://github.com/livekit/agents/pull/3269
• fix (11labs): fix empty text input and timeout for the first audio chunk by @longcw in https://github.com/livekit/agents/pull/3284
• chore: switch to gpt-realtime as default OAI realtime model by @davidzhao in https://github.com/livekit/agents/pull/3287
• fix(plugins:elevenlabs): fix exception in STT when serializing bool form field tag_audio_events by @mike-r-mclaughlin in https://github.com/livekit/agents/pull/3282
• primary speaker detection with STT diarization by @longcw in https://github.com/livekit/agents/pull/3186
• add capture_run for AgentSession.start by @longcw in https://github.com/livekit/agents/pull/3288
• chore: add test for empty tts streams by @davidzhao in https://github.com/livekit/agents/pull/3286
• fix say method not being captured by RunResult by @theomonnom in https://github.com/livekit/agents/pull/3291
• support interrupting agent by interim transcripts by @longcw in https://github.com/livekit/agents/pull/3278
• allow SpeechHandle to be interrupted when long-running function tools are pending by @longcw in https://github.com/livekit/agents/pull/3280
• fix: disable false interruption resume for realtime model by @longcw in https://github.com/livekit/agents/pull/3298
• feat(langgraph): support subgraphs in LLMAdapter and normalize astream outputs by @bnovik0v in https://github.com/livekit/agents/pull/3112
• feat: add more llm and stt models to mistralai plugins by @fabitokki in https://github.com/livekit/agents/pull/3300
• chore(langchain): fix types by @davidzhao in https://github.com/livekit/agents/pull/3303

New Contributors

• @bnovik0v made their first contribution in https://github.com/livekit/agents/pull/3112

Full Changelog: https://github.com/livekit/agents/compare/livekit-agents@1.2.7...livekit-agents@1.2.8