Agents JS

• @livekit/agents@1.2.4

add extra warnings regarding gemini-3.1-flash-live-preview compatibility - #1202 (@tinalenguyen)

Explicitly close AudioResampler instances too free up resources - #1210 (@lukasIO)

Updated dependencies [3e653445119694ce1c1f67673a459c084475b53a, e399b9b3f51074f749a1946eb0ea5ce7fb03c297, b407494ca2a417584a5f0fccebfb6bda6ce0eb0c, a044ea3c8346324f1a938b32b7c412ccf4f9cc0e, 77a8355c222661e8b4256a3c6ee81f6eaed2fae7]:

• @livekit/agents@1.2.4

• @livekit/agents@1.2.4

fix(agents): release initMutex after warming to restore pool concurrency - #1214 (@drain-zine)

fix: pass queueSizeMs from RoomOutputOptions through to AudioSource - #1207 (@cxyangs)

Add prompt_cache_retention option to inference - #1212 (@s-hamdananwar)

(inference): add debug metadata headers to inference requests - #1208 (@adrian-cowham)

Explicitly close AudioResampler instances too free up resources - #1210 (@lukasIO)

• @livekit/agents@1.2.4

fix(google): align realtime behavior for Gemini 3.1 and harden session/tool handling - #1189 (@toubatbrian)

Updated dependencies [3fee5c2118e7a33b0f55843ee6f36a4f10936f8b, 3a0cf84ce9ca910b92c61eb04d180fd43471a0fc, 6ae32034457d819b5df59bc2b4e772200e0afad7, 50a650b6cb3af13007190f55a41bbe17ac2b4696, 4a94843f12746cfab47d616c3f92428a2c95a7fc]:

• @livekit/agents@1.2.3

• @livekit/agents@1.2.3

• @livekit/agents@1.2.3

• @livekit/agents@1.2.3

fix: Address 6 bugs from Detail scan (March 25) - #1182 (@toubatbrian)

• inference/llm: pass abort signal to OpenAI SDK and check abort in outer streaming loop
• llm/fallback_adapter: call tryRecovery() before throwing on mid-stream failure
• openai/realtime: clear responseCreatedFutures on reconnect to prevent generateReply() hang
• deepgram/tts: reject on network errors instead of swallowing them
• cpu: remove Math.max clamp in cgroup v1 so fractional CPU limits are reported correctly
• openai/responses: handle response.failed event in HTTP streaming

Updated dependencies [3fee5c2118e7a33b0f55843ee6f36a4f10936f8b, 3a0cf84ce9ca910b92c61eb04d180fd43471a0fc, 6ae32034457d819b5df59bc2b4e772200e0afad7, 50a650b6cb3af13007190f55a41bbe17ac2b4696, 4a94843f12746cfab47d616c3f92428a2c95a7fc]:

• @livekit/agents@1.2.3

• @livekit/agents@1.2.3

• @livekit/agents@1.2.3

fix: Address 6 bugs from Detail scan (March 25) - #1182 (@toubatbrian)

• inference/llm: pass abort signal to OpenAI SDK and check abort in outer streaming loop
• llm/fallback_adapter: call tryRecovery() before throwing on mid-stream failure
• openai/realtime: clear responseCreatedFutures on reconnect to prevent generateReply() hang
• deepgram/tts: reject on network errors instead of swallowing them
• cpu: remove Math.max clamp in cgroup v1 so fractional CPU limits are reported correctly
• openai/responses: handle response.failed event in HTTP streaming

Updated dependencies [3fee5c2118e7a33b0f55843ee6f36a4f10936f8b, 3a0cf84ce9ca910b92c61eb04d180fd43471a0fc, 6ae32034457d819b5df59bc2b4e772200e0afad7, 50a650b6cb3af13007190f55a41bbe17ac2b4696, 4a94843f12746cfab47d616c3f92428a2c95a7fc]:

• @livekit/agents@1.2.3

Fix worker draining behaviour - #1180 (@lukasIO)

Fix Queue dropping falsy items - #1190 (@lukasIO)

fix: Address 6 bugs from Detail scan (March 25) - #1182 (@toubatbrian)

• inference/llm: pass abort signal to OpenAI SDK and check abort in outer streaming loop
• llm/fallback_adapter: call tryRecovery() before throwing on mid-stream failure
• openai/realtime: clear responseCreatedFutures on reconnect to prevent generateReply() hang
• deepgram/tts: reject on network errors instead of swallowing them
• cpu: remove Math.max clamp in cgroup v1 so fractional CPU limits are reported correctly
• openai/responses: handle response.failed event in HTTP streaming

fix: address 5 Detail scan bugs from March 11 (reconnect, mutex leak, playout, ordering, retryability) - #1188 (@toubatbrian)

fix(voice): reset VAD on premature STT EOT & guard empty recorder frames - #1181 (@toubatbrian)

• @livekit/agents@1.2.3

• @livekit/agents@1.2.3

• @livekit/agents@1.2.3

• @livekit/agents@1.2.3

• @livekit/agents@1.2.2

fix: Include session usage in reports and emit usage updates - #1161 (@toubatbrian)

Handle unhandled rejection from fire-and-forget run() in SupervisedProc - #1158 (@Raysharr)

fix: add idle timeouts to TTS stream reads to prevent agent stuck in speaking state - #1174 (@toubatbrian)

Guard WritableStream close in RoomIO teardown to prevent ERR_INVALID_STATE when writer is already closed or errored during concurrent speech interruption - #1172 (@Raysharr)

fix(IPC): graceful handling when channel closes during inference - #1168 (@toubatbrian)

Add chatCtx and ChatMessage support to AgentSession.generateReply - #1170 (@toubatbrian)

fix: handle unhandled 'error' event on FfmpegCommand in audio.ts - #1173 (@enriqueespaillat-gyde)