Agents JS

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

• @livekit/agents@1.2.4

• @livekit/agents@1.2.4

• @livekit/agents@1.2.4

add serviceTier parameter to Responses API LLM for parity with Chat Completions LLM - #1206 (@piyush-gambhir)

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

• @livekit/agents@1.2.4

• @livekit/agents@1.2.4

• @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