livekit-agents@1.7.1

## What's Changed
* fix(voice): agent and user state while a tool runs by @longcw in https://github.com/livekit/agents/pull/6937
* chore: teach reviews to catch untagged PII logs by @chenghao-mou in https://github.com/livekit/agents/pull/6923
* feat(agents): serialize the inline AgentTasks awaited from one turn by @u9g in https://github.com/livekit/agents/pull/6862
* fix(openai): read TTS response by content-type, not model name by @abidullahdev in https://github.com/livekit/agents/pull/6930
* fix: avoid duplicate agent speech end by @chenghao-mou in https://github.com/livekit/agents/pull/6938
* feat(speechify): stream with timestamps via /v1/audio/stream/with-timestamps by @luke-speechify in https://github.com/livekit/agents/pull/6926
* fix(openai realtime): keep derived capabilities in sync with update_options by @longcw in https://github.com/livekit/agents/pull/6943
* fix(google): keep unspoken model text out of the realtime transcript by @rosetta-livekit-bot[bot] in https://github.com/livekit/agents/pull/6955
* fix(realtime): cancel the generation when a speech is interrupted by @longcw in https://github.com/livekit/agents/pull/6962
* fix(openai realtime): recover when the server anchors to a deleted item by @longcw in https://github.com/livekit/agents/pull/6964
* fix(voice): place recorded audio where it actually played by @longcw in https://github.com/livekit/agents/pull/6921
* fix(elevenlabs): stop routing TTS audio to an interrupted stream by @longcw in https://github.com/livekit/agents/pull/6936
* fix: raise the shared http session total timeout to 900s by @chenghao-mou in https://github.com/livekit/agents/pull/6941
* feat(sarvam): add realtime streaming STT by @dhruvladia-sarvam in https://github.com/livekit/agents/pull/6562
* feat(sarvam): add glm5.2, gemma4 and sarvam-105b-conversations model support by @dhruvladia-sarvam in https://github.com/livekit/agents/pull/6841
* Add saaras:v4 as the default and latest Sarvam STT model by @dhruvladia-sarvam in https://github.com/livekit/agents/pull/6900
* Bump `livekit` to 1.1.15 by @1egoman in https://github.com/livekit/agents/pull/6970
* (xai inference): add LLM models by @tinalenguyen in https://github.com/livekit/agents/pull/6971
* fix(dtmf): drop removed repeat_instructions arg from GetDtmfTask example and docstring by @feizhuzheng in https://github.com/livekit/agents/pull/6972
* Sunset saaras and saarika v2.5 by @dhruvladia-sarvam in https://github.com/livekit/agents/pull/6905
* feat: add the deployed region to every log record by @theomonnom in https://github.com/livekit/agents/pull/6896
* fix(llm): place a backdated chat item by its creation time by @longcw in https://github.com/livekit/agents/pull/6974
* docs(sarvam): correct STT README brand from Saarika to Saaras by @detail-app[bot] in https://github.com/livekit/agents/pull/6979
* feat(elevenlabs): stream eleven_v3/eleven_v3_conversational via text-to-dialogue by @ameyakhare in https://github.com/livekit/agents/pull/6838
* fix(aws): support transcribe streaming config rename by @mikemikimike in https://github.com/livekit/agents/pull/6959
* fix: retry recording upload connection failures by @chenghao-mou in https://github.com/livekit/agents/pull/6977
* fix: preserve cancellation during audio recognition close by @chenghao-mou in https://github.com/livekit/agents/pull/6903
* fix: support adaptive interruption without word timestamps by @chenghao-mou in https://github.com/livekit/agents/pull/6765
* fix: scope interruption verdicts to agent speech by @chenghao-mou in https://github.com/livekit/agents/pull/6957
* fix: attribute playback evidence to its own segment on the same audio output by @chenghao-mou in https://github.com/livekit/agents/pull/6470
* chore(deps): update dependency aiohttp to v3.14.3 [security] by @renovate[bot] in https://github.com/livekit/agents/pull/6692
* fix(workflows): ask before recording a volunteered value by @u9g in https://github.com/livekit/agents/pull/6980
* fix: warn about realtime audio redaction by @chenghao-mou in https://github.com/livekit/agents/pull/6987
* fix(hotel_receptionist): move book_room's sequencing and pricing rules into the tools by @u9g in https://github.com/livekit/agents/pull/6849
* fix(aws): preserve idle-timeout retry in STT stream cleanup by @tanish111 in https://github.com/livekit/agents/pull/6995
* feat(simulation): stamp the run and job ids on session telemetry by @theomonnom in https://github.com/livekit/agents/pull/6997
* (gemini stt): add gemini-3.5-transcribe-live to inference and plugin by @tinalenguyen in https://github.com/livekit/agents/pull/6991
* (speechmatics inference): add linden model by @tinalenguyen in https://github.com/livekit/agents/pull/6989
* Add Palabra STT and TTS plugins by @danlowkey in https://github.com/livekit/agents/pull/6681
* livekit-agents@1.7.1 by @github-actions[bot] in https://github.com/livekit/agents/pull/6999

## New Contributors
* @abidullahdev made their first contribution in https://github.com/livekit/agents/pull/6930
* @rosetta-livekit-bot[bot] made their first contribution in https://github.com/livekit/agents/pull/6955
* @feizhuzheng made their first contribution in https://github.com/livekit/agents/pull/6972
* @ameyakhare made their first contribution in https://github.com/livekit/agents/pull/6838
* @mikemikimike made their first contribution in https://github.com/livekit/agents/pull/6959
* @tanish111 made their first contribution in https://github.com/livekit/agents/pull/6995
* @danlowkey made their first contribution in https://github.com/livekit/agents/pull/6681

**Full Changelog**: https://github.com/livekit/agents/compare/livekit-agents@1.7.0...livekit-agents@1.7.1