Back to Signal Feed
CodeTracked since May 19, 2026

Persist live voice turn audio as session artifacts

google/adk-go adds an Audio Cache Manager that buffers real-time user and model voice chunks during live sessions, merges them into turn-level audio files, saves those files through the artifact store, and writes session trace events pointing to the saved artifact URIs.

Audio Cache ManagerliveSessionImplinputCacheoutputCache

What Happened

  • google/adk-go adds an Audio Cache Manager that buffers real-time user and model voice chunks during live sessions, merges them into turn-level audio files, saves those files through the artifact store, and writes session trace events pointing to the saved artifact URIs.
  • google/adk-go adds an Audio Cache Manager that buffers real-time user and model voice chunks during live sessions, merges them into turn-level audio files, saves those files through the artifact store, and writes session trace events pointing to the saved artifact URIs.
  • 1 evidence item attached for review.

What is Different

Before

Scattered source updates, isolated context, and manual follow-up across multiple feeds.

Now

Implements thread-safe input/output audio chunk caching in live sessions, flushes and concatenates chunks at interruption/turn-complete boundaries, and persists the final PCM/MP3 artifact with a session trace event reference for later retrieval.

Why Track This

Why It Matters

Voice app operators and developers can now reliably retain complete user/model audio turns as artifacts during live conversations, reducing missing audio when debugging, replaying, or reviewing sessions; continue monitoring whether cache flush boundaries always align with conversation turns and whether artifact accumulation is bounded for long-running sessions. The implementation wires cache collection into live session flow, adds merge/flush helpers for raw binary chunks, generates timestamped filenames, stores through invocation artifact APIs, and records a trace event that references `artifact://...` so conversations become searchable and inspectable after the run.

Impact

Voice app operators and developers can now reliably retain complete user/model audio turns as artifacts during live conversations, reducing missing audio when debugging, replaying, or reviewing sessions; continue monitoring whether cache flush boundaries always align with conversation turns and whether artifact accumulation is bounded for long-running sessions. The implementation wires cache collection into live session flow, adds merge/flush helpers for raw binary chunks, generates timestamped filenames, stores through invocation artifact APIs, and records a trace event that references `artifact://...` so conversations become searchable and inspectable after the run.

What To Watch Next

  • Watch whether Audio Cache Manager becomes a repeated pattern.
  • Track follow-up changes around Observability and Tracing.
  • Compare future signals against this evidence trail.
  • Re-check risk flags: cache_flush_boundary_mismatch, artifact_store_growth.
Open Topic TimelineOpen Technical EventOpen Original Sourcecache_flush_boundary_mismatch / artifact_store_growth / trace_event_linkage_gaps / persistent_storage_write_failures

Supporting Evidence

GITHUB PULL REQUESTHigh Trust

google/adk-go PR #838: feat(live): Add audio cache for save artifact

Introduces an Audio Cache Manager to collect, aggregate, and persist real-time voice conversation chunks into permanent session artifacts and trace history.