fix: preserve adaptive interruption across tool calls

[rosetta-livekit-bot]

Ports livekit/agents#6564 to preserve adaptive interruption when audible playout pauses for tool execution or resumes during active user speech.

• Treat playout pauses and tool-call thinking gaps as real speech boundaries.
• Close inconclusive overlaps before resetting the detector and exclude them from backchannel metrics.
• Restart and serialize overlap inference boundaries when paused playout resumes.
• Add a patch changeset for @livekit/agents.

Source diff coverage

• Adapted: livekit-agents/livekit/agents/inference/interruption.py -> agents/src/inference/interruption/interruption_stream.ts. Excludes agentEnded overlaps from backchannel metrics; target event types already carry the marker.
• Adapted: livekit-agents/livekit/agents/voice/agent_activity.py -> agents/src/voice/agent_activity.ts. Removes pause/resume lifecycle exceptions, ends active speech at tool-call thinking gaps, rearms interruption handling, and removes duplicate pause-cancel teardown. The equivalent target realtime tool path is updated because JS separates pipeline and realtime execution.
• Adapted: livekit-agents/livekit/agents/voice/audio_recognition.py -> agents/src/voice/audio_recognition.ts. Closes overlap before detector reset, restarts inference when playout resumes over active user speech, preserves endpointing state, and serializes JS async sentinel batches to match Python send_nowait ordering.
• Adapted: livekit-agents/livekit/agents/voice/remote_session.py -> agents/src/voice/remote_session.ts. Mirrors the source TODO because the remote-session protobuf cannot yet carry agentEnded. No unsupported wire field is invented.
• Adapted: tests/test_agent_session.py -> agents/src/voice/agent_activity_tool_output_commit.test.ts. Verifies speech end is observed after entering the tool-call thinking state and later ends occur while listening.
• Adapted: tests/test_false_interruption_resume.py -> agents/src/voice/agent_activity.test.ts. Verifies cancelling already-paused speech does not report a duplicate speech end.
• Adapted in part: tests/test_interruption/test_overlapping_speech_event.py -> agents/src/inference/interruption/interruption_stream.test.ts. Ports the added agent-ended metric assertion. The existing Python/Pydantic serialization assertion is not applicable to a compile-time TypeScript interface.
• Adapted: tests/test_realtime_adaptive_interruption.py -> agents/src/voice/realtime_adaptive_interruption.test.ts. Ports overlap-before-reset ordering, idempotent user end, resumed detector restart, and real speech-end assertions.

Protocol gap

agentEnded still cannot be forwarded by remote sessions because the shared AgentSessionEvent protobuf has no field for it. This matches the authoritative source PR, which documents the same limitation with TODO(AGT-3180). Local adaptive interruption behavior and metrics preserve the marker.

Validation

• pnpm test agents (2120 passed, 5 skipped)
• pnpm build
• pnpm build:agents after final refinement
• pnpm --filter @livekit/agents typecheck
• pnpm --filter @livekit/agents lint
• pnpm format:check
• cue-cli voice run: post-tool playout was adaptively interrupted, getWeather executed for the replacement turn, and a fresh assistant response was committed

Source: livekit/agents#6564

---

Ported from livekit/agents#6564

Original PR description

Bug: Adaptive interruption could silently drop a user overlap when agent playout resumed after a tool call because the interruption stream received mismatched speech boundaries.

Treat thinking gaps as real speech boundaries and restart overlap inference when playout resumes mid-utterance. Agent-ended overlaps remain inconclusive and no longer count as backchannels; remote forwarding is noted until the protocol carries that marker.

Fixes livekit/agents#6548. Fixes livekit/agents#6548.

[changeset-bot]

🦋 Changeset detected

Latest commit: c060966

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 39 packages

Name	Type
@livekit/agents	Patch
@livekit/agents-plugin-anam	Patch
@livekit/agents-plugin-anthropic	Patch
@livekit/agents-plugin-assemblyai	Patch
@livekit/agents-plugin-azure	Patch
@livekit/agents-plugin-baseten	Patch
@livekit/agents-plugin-bey	Patch
@livekit/agents-plugin-cartesia	Patch
@livekit/agents-plugin-cerebras	Patch
@livekit/agents-plugin-deepgram	Patch
@livekit/agents-plugin-did	Patch
@livekit/agents-plugin-elevenlabs	Patch
@livekit/agents-plugin-fishaudio	Patch
@livekit/agents-plugin-google	Patch
@livekit/agents-plugin-hedra	Patch
@livekit/agents-plugin-hume	Patch
@livekit/agents-plugin-inworld	Patch
@livekit/agents-plugin-krisp	Patch
@livekit/agents-plugin-lemonslice	Patch
@livekit/agents-plugin-liveavatar	Patch
@livekit/agents-plugin-livekit	Patch
@livekit/agents-plugin-minimax	Patch
@livekit/agents-plugin-mistral	Patch
@livekit/agents-plugin-mistralai	Patch
@livekit/agents-plugin-neuphonic	Patch
@livekit/agents-plugin-openai	Patch
@livekit/agents-plugin-perplexity	Patch
@livekit/agents-plugin-phonic	Patch
@livekit/agents-plugin-protoface	Patch
@livekit/agents-plugin-resemble	Patch
@livekit/agents-plugin-rime	Patch
@livekit/agents-plugin-runway	Patch
@livekit/agents-plugin-sarvam	Patch
@livekit/agents-plugin-silero	Patch
@livekit/agents-plugin-soniox	Patch
@livekit/agents-plugin-tavus	Patch
@livekit/agents-plugins-test	Patch
@livekit/agents-plugin-trugen	Patch
@livekit/agents-plugin-xai	Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR