livekit-agents@1.8.1

# Duplex Model Support

Speech models that are able to speak and listen simultaneously are now supported via the new `DuplexModel` class, with OpenAI's GPT-Live model as the first to be implemented.

```python
session = AgentSession(
        llm=GPTLiveModel(
            voice="marin",
            # backend Responses model that handles reasoning and tools
            responses_options={
                "model": "gpt-5.6-luna",
                "instructions": "Use tools when current information is required.",
            },
        ),
    )
```

Read more about duplex models in [our docs](https://docs.livekit.io/agents/models/realtime/#full-duplex).

## What's Changed
* chore: isolate ruff dependencies in ci by @chenghao-mou in https://github.com/livekit/agents/pull/7142
* fix(telemetry): describe option objects in the session report by @davidzhao in https://github.com/livekit/agents/pull/7127
* chore: remove commented-out keepalive stub from Deepgram V2 STT by @detail-app[bot] in https://github.com/livekit/agents/pull/7141
* docs: remove stale example references after examples revamp by @detail-app[bot] in https://github.com/livekit/agents/pull/6402
* fix(openai): don't replace a TTS prewarm that is still in flight by @omChauhanDev in https://github.com/livekit/agents/pull/7147
* fix: drain unused adapter metrics streams by @chenghao-mou in https://github.com/livekit/agents/pull/7146
* fix: drop unused audio forwarding buffer by @chenghao-mou in https://github.com/livekit/agents/pull/7144
* fix(tests): run the deepgram handshake redaction check in CI by @omChauhanDev in https://github.com/livekit/agents/pull/7152
* plugins/phonic: add enable_watermarking realtime config option by @arunwpm-work in https://github.com/livekit/agents/pull/7121
* speechmatics: expose end_of_turn_config and vad_config options by @rrfunde in https://github.com/livekit/agents/pull/6945
* fix(worker): discard impossible cgroup v2 cpu samples by @longcw in https://github.com/livekit/agents/pull/7113
* fix(voice): fail remote session requests when transport closes by @EPxiaoma in https://github.com/livekit/agents/pull/7149
* fix(voice): report played audio across an audio sink swap by @longcw in https://github.com/livekit/agents/pull/6967
* fix(agents): don't close in-use connections when the pool is invalidated by @Rehansanjay in https://github.com/livekit/agents/pull/7139
* feat(spatius): warm up region, TLS, and session token at process init by @3DRX in https://github.com/livekit/agents/pull/7025
* fix(asyncai): invalidate the TTS pool when connection params change by @Rehansanjay in https://github.com/livekit/agents/pull/7132
* fix(neuphonic): invalidate the TTS pool when connection params change by @Rehansanjay in https://github.com/livekit/agents/pull/7133
* fix(cartesia): honour api_version on both the pooled socket and the REST header by @Rehansanjay in https://github.com/livekit/agents/pull/7140
* fix: close temporary speech stream adapters by @chenghao-mou in https://github.com/livekit/agents/pull/7154
* fix(hotel_receptionist): don't pass simulation runs the grading never checked by @u9g in https://github.com/livekit/agents/pull/6797
* perf(anam): start engine session with API key by @ao-anam in https://github.com/livekit/agents/pull/6203
* workflows: spell the value back once the caller refuses a confirmation by @u9g in https://github.com/livekit/agents/pull/6990
* fix: name VAD in the slow-inference warning by @claude[bot] in https://github.com/livekit/agents/pull/7176
* feat(meta): add Muse Voice streaming STT plugin by @seyeong-han in https://github.com/livekit/agents/pull/7097
* fix(voice): report e2e_latency for the first reply after a handoff by @longcw in https://github.com/livekit/agents/pull/7167
* fix(tests): run the false-interruption resume tests on virtual time by @omChauhanDev in https://github.com/livekit/agents/pull/7179
* feat(telemetry): flag synchronous code blocking the event loop by @davidzhao in https://github.com/livekit/agents/pull/7128
* fix(llm): preserve Annotated tool argument metadata by @Kuang-xianxin in https://github.com/livekit/agents/pull/7126
* fix(google): skip context replay on resumed realtime sessions by @he-yufeng in https://github.com/livekit/agents/pull/6000
* perf: skip discarded trace payload construction by @chenghao-mou in https://github.com/livekit/agents/pull/7155
* plugins/phonic: make allow_tool_chaining configurable per tool by @arunwpm-work in https://github.com/livekit/agents/pull/7197
* feat(openai): add LiveKit inference realtime model by @russellmartin-livekit in https://github.com/livekit/agents/pull/6035
* feat(plugins-tavus): default to the stock Lucy face when no face or pal is given by @carolin-tavus in https://github.com/livekit/agents/pull/7211
* feat: add DuplexModel for full-duplex speech models by @longcw in https://github.com/livekit/agents/pull/6677
* feat: add openai gpt-live duplex support by @chenghao-mou in https://github.com/livekit/agents/pull/7212
* livekit-agents@1.8.1 by @github-actions[bot] in https://github.com/livekit/agents/pull/7214

## New Contributors
* @omChauhanDev made their first contribution in https://github.com/livekit/agents/pull/7147
* @EPxiaoma made their first contribution in https://github.com/livekit/agents/pull/7149
* @ao-anam made their first contribution in https://github.com/livekit/agents/pull/6203
* @claude[bot] made their first contribution in https://github.com/livekit/agents/pull/7176
* @seyeong-han made their first contribution in https://github.com/livekit/agents/pull/7097
* @Kuang-xianxin made their first contribution in https://github.com/livekit/agents/pull/7126

**Full Changelog**: https://github.com/livekit/agents/compare/livekit-agents@1.8.0...livekit-agents@1.8.1