diff --git a/Unreal/PS_AI_Agent/Bug en suspend.txt b/Unreal/PS_AI_Agent/Bug en suspend.txt deleted file mode 100644 index 358e117..0000000 --- a/Unreal/PS_AI_Agent/Bug en suspend.txt +++ /dev/null @@ -1,359 +0,0 @@ -seem to less stuck but timeout often : LogDebuggerCommands: Repeating last play command: Selected Viewport -LogPlayLevel: PlayLevel: No blueprints needed recompiling -LogPlayLevel: Creating play world package: /Game/UEDPIE_0_TestMap -LogPlayLevel: PIE: StaticDuplicateObject took: (0.005478s) -LogPlayLevel: PIE: Created PIE world by copying editor world from /Game/TestMap.TestMap to /Game/UEDPIE_0_TestMap.TestMap (0.005520s) -LogUObjectHash: Compacting FUObjectHashTables data took 0.64ms -LogChaosDD: Creating Chaos Debug Draw Scene for world TestMap -LogPlayLevel: PIE: World Init took: (0.001821s) -LogAudio: Display: Creating Audio Device: Id: 4, Scope: Unique, Realtime: True -LogAudioMixer: Display: Audio Mixer Platform Settings: -LogAudioMixer: Display: Sample Rate: 48000 -LogAudioMixer: Display: Callback Buffer Frame Size Requested: 1024 -LogAudioMixer: Display: Callback Buffer Frame Size To Use: 1024 -LogAudioMixer: Display: Number of buffers to queue: 1 -LogAudioMixer: Display: Max Channels (voices): 32 -LogAudioMixer: Display: Number of Async Source Workers: 4 -LogAudio: Display: AudioDevice MaxSources: 32 -LogAudio: Display: Audio Spatialization Plugin: None (built-in). -LogAudio: Display: Audio Reverb Plugin: None (built-in). -LogAudio: Display: Audio Occlusion Plugin: None (built-in). -LogAudioMixer: Display: Initializing audio mixer using platform API: 'XAudio2' -LogAudioMixer: Display: Using Audio Hardware Device Speakers (Realtek(R) Audio) -LogAudioMixer: Display: Initializing Sound Submixes... -LogAudioMixer: Display: Creating Master Submix 'MasterSubmixDefault' -LogAudioMixer: Display: Creating Master Submix 'MasterReverbSubmixDefault' -LogAudioMixer: FMixerPlatformXAudio2::StartAudioStream() called. InstanceID=4 -LogAudioMixer: Display: Output buffers initialized: Frames=1024, Channels=2, Samples=2048, InstanceID=4 -LogAudioMixer: Display: Starting AudioMixerPlatformInterface::RunInternal(), InstanceID=4 -LogAudioMixer: Display: FMixerPlatformXAudio2::SubmitBuffer() called for the first time. InstanceID=4 -LogInit: FAudioDevice initialized with ID 4. -LogAudio: Display: Audio Device (ID: 4) registered with world 'TestMap'. -LogAudioMixer: Initializing Audio Bus Subsystem for audio device with ID 4 -LogLoad: Game class is 'GameModeBase' -LogWorld: Bringing World /Game/UEDPIE_0_TestMap.TestMap up for play (max tick rate 60) at 2026.02.20-17.38.08 -LogWorld: Bringing up level for play took: 0.000919 -LogOnline: OSS: Created online subsystem instance for: :Context_3 -LogElevenLabsWS: Connecting to ElevenLabs: wss://api.elevenlabs.io/v1/convai/conversation?agent_id=agent_5301kc1qkq49fn2av43nrbsar65k -PIE: Server logged in -PIE: Play in editor total start time 0,075 seconds. -LogElevenLabsWS: WebSocket connected. Sending conversation_initiation_client_data... -LogElevenLabsWS: Sending initiation: { -"type": "conversation_initiation_client_data", -"conversation_config_override": -{ -"agent": -{ -"turn": -{ -"turn_timeout": 1 -} -}, -"tts": -{ -"optimize_streaming_latency": 3 -} -}, -"custom_llm_extra_body": -{ -"enable_intermediate_response": true -} -} -LogElevenLabsWS: Received message type: conversation_initiation_metadata -LogElevenLabsWS: [T+0.00s] Conversation initiated. ID=conv_2901khxymx7xed88dq8tw35b2pfk -LogElevenLabsAgent: [T+0.00s] Agent connected. ConversationID=conv_2901khxymx7xed88dq8tw35b2pfk -LogBlueprintUserMessages: [test_AI_Actor_C_2] Connected -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Listening -LogElevenLabsWS: [T+2.18s] User turn started — mic open, audio chunks will follow. -LogAudioCaptureCore: Display: WasapiCapture AudioFormat SampeRate: 48000, BitDepth: 32-Bit Floating Point -LogElevenLabsMic: Capture device: Microphone Array (Intel® Smart Sound Technology for Digital Microphones) | Rate=48000 | Channels=2 -LogElevenLabsMic: Audio capture started. -LogElevenLabsAgent: [T+2.18s] [Turn 1] Mic opened — user speaking. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Listening -LogElevenLabsMic: Audio capture stopped. -LogElevenLabsWS: [T+4.60s] User turn ended — server VAD silence detection started (turn_timeout=1s). -LogElevenLabsAgent: [T+4.60s] [Turn 1] Mic closed — user spoke 2.42s. Waiting for server response (timeout 10s)... -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: [T+5.66s] Agent started generating (1061 ms after turn end — includes VAD silence timeout + LLM start). -LogElevenLabsAgent: [T+5.66s] [Turn 1] Agent generating. (1.06s after turn end) -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Agent Start Generating -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Warning: [T+7.95s] [LATENCY] First audio: 3346 ms after turn end (3346 ms after last chunk) -LogElevenLabsAgent: [T+7.95s] [Turn 1] Agent speaking — first audio chunk. (3.35s after turn end) -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Speaking -LogElevenLabsWS: Received message type: user_transcript -LogElevenLabsWS: Warning: [T+7.95s] [LATENCY] User transcript: 3346 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Transcript : Hello, how are you? -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Received message type: agent_response -LogElevenLabsWS: Warning: [T+9.60s] [LATENCY] Agent text response: 4994 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Text Response : Hello! I'm doing well, thank you for asking. How can I assist you today? -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Speaking -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Listening -LogElevenLabsWS: [T+18.84s] User turn started — mic open, audio chunks will follow. -LogAudioCaptureCore: Display: WasapiCapture AudioFormat SampeRate: 48000, BitDepth: 32-Bit Floating Point -LogElevenLabsMic: Capture device: Microphone Array (Intel® Smart Sound Technology for Digital Microphones) | Rate=48000 | Channels=2 -LogElevenLabsMic: Audio capture started. -LogElevenLabsAgent: [T+18.84s] [Turn 2] Mic opened — user speaking. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Listening -LogElevenLabsMic: Audio capture stopped. -LogElevenLabsWS: [T+21.67s] User turn ended — server VAD silence detection started (turn_timeout=1s). -LogElevenLabsAgent: [T+21.67s] [Turn 2] Mic closed — user spoke 2.83s. Waiting for server response (timeout 10s)... -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: [T+22.45s] Agent started generating (777 ms after turn end — includes VAD silence timeout + LLM start). -LogElevenLabsAgent: [T+22.45s] [Turn 2] Agent generating. (0.78s after turn end) -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Agent Start Generating -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Warning: [T+23.85s] [LATENCY] First audio: 2180 ms after turn end (2180 ms after last chunk) -LogElevenLabsAgent: [T+23.85s] [Turn 2] Agent speaking — first audio chunk. (2.18s after turn end) -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Speaking -LogElevenLabsWS: Received message type: user_transcript -LogElevenLabsWS: Warning: [T+23.90s] [LATENCY] User transcript: 2227 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Transcript : Nothing special, just talking. -LogElevenLabsAgent: Warning: [Turn 2] Agent silence hard-timeout (2s) without agent_response — declaring agent stopped. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Speaking -LogElevenLabsWS: Received message type: audio -LogElevenLabsAgent: [T+28.55s] [Turn 2] Agent speaking — first audio chunk. (6.88s after turn end) -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Speaking -LogElevenLabsWS: Received message type: agent_response -LogElevenLabsWS: Warning: [T+28.58s] [LATENCY] Agent text response: 6910 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Text Response : That's perfectly fine! I'm here to chat if you have any questions or just want to talk. What's on your mind? -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Speaking -LogEOSSDK: LogEOS: Updating Product SDK Config, Time: 347.575653 -LogEOSSDK: LogEOS: SDK Config Product Update Request Completed - No Change -LogEOSSDK: LogEOS: ScheduleNextSDKConfigDataUpdate - Time: 347.774902, Update Interval: 340.359497 -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Listening -LogElevenLabsWS: [T+41.83s] User turn started — mic open, audio chunks will follow. -LogAudioCaptureCore: Display: WasapiCapture AudioFormat SampeRate: 48000, BitDepth: 32-Bit Floating Point -LogElevenLabsMic: Capture device: Microphone Array (Intel® Smart Sound Technology for Digital Microphones) | Rate=48000 | Channels=2 -LogElevenLabsMic: Audio capture started. -LogElevenLabsAgent: [T+41.83s] [Turn 3] Mic opened — user speaking. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Listening -LogElevenLabsMic: Audio capture stopped. -LogElevenLabsWS: [T+44.86s] User turn ended — server VAD silence detection started (turn_timeout=1s). -LogElevenLabsAgent: [T+44.86s] [Turn 3] Mic closed — user spoke 3.03s. Waiting for server response (timeout 10s)... -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: [T+45.20s] Agent started generating (343 ms after turn end — includes VAD silence timeout + LLM start). -LogElevenLabsAgent: [T+45.20s] [Turn 3] Agent generating. (0.34s after turn end) -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Agent Start Generating -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Warning: [T+48.22s] [LATENCY] First audio: 3361 ms after turn end (3361 ms after last chunk) -LogElevenLabsAgent: [T+48.22s] [Turn 3] Agent speaking — first audio chunk. (3.36s after turn end) -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Speaking -LogElevenLabsWS: Received message type: user_transcript -LogElevenLabsWS: Warning: [T+48.22s] [LATENCY] User transcript: 3361 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Transcript : I wanna... Hi agent! -LogElevenLabsWS: Received message type: agent_response -LogElevenLabsWS: Warning: [T+48.25s] [LATENCY] Agent text response: 3393 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Text Response : Hello! It's good to hear from you. How can I help you today? -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Speaking -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Listening -LogElevenLabsWS: [T+57.55s] User turn started — mic open, audio chunks will follow. -LogAudioCaptureCore: Display: WasapiCapture AudioFormat SampeRate: 48000, BitDepth: 32-Bit Floating Point -LogElevenLabsMic: Capture device: Microphone Array (Intel® Smart Sound Technology for Digital Microphones) | Rate=48000 | Channels=2 -LogElevenLabsMic: Audio capture started. -LogElevenLabsAgent: [T+57.55s] [Turn 4] Mic opened — user speaking. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Listening -LogElevenLabsMic: Audio capture stopped. -LogElevenLabsWS: [T+60.33s] User turn ended — server VAD silence detection started (turn_timeout=1s). -LogElevenLabsAgent: [T+60.33s] [Turn 4] Mic closed — user spoke 2.78s. Waiting for server response (timeout 10s)... -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: [T+60.39s] Agent started generating (61 ms after turn end — includes VAD silence timeout + LLM start). -LogElevenLabsAgent: [T+60.39s] [Turn 4] Agent generating. (0.06s after turn end) -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Agent Start Generating -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Warning: [T+62.44s] [LATENCY] First audio: 2111 ms after turn end (2111 ms after last chunk) -LogElevenLabsAgent: [T+62.44s] [Turn 4] Agent speaking — first audio chunk. (2.11s after turn end) -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Speaking -LogElevenLabsWS: Received message type: user_transcript -LogElevenLabsWS: Warning: [T+62.44s] [LATENCY] User transcript: 2112 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Transcript : Do you speak French? -LogElevenLabsAgent: Warning: [Turn 4] Agent silence hard-timeout (2s) without agent_response — declaring agent stopped. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Speaking -LogElevenLabsWS: Received message type: audio -LogElevenLabsAgent: [T+66.24s] [Turn 4] Agent speaking — first audio chunk. (5.91s after turn end) -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Speaking -LogElevenLabsWS: Received message type: agent_response -LogElevenLabsWS: Warning: [T+66.27s] [LATENCY] Agent text response: 5944 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Text Response : Yes, I can communicate in French. Would you like to ask me something in French or perhaps practice a bit? -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Speaking -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Listening -LogElevenLabsWS: [T+74.14s] User turn started — mic open, audio chunks will follow. -LogAudioCaptureCore: Display: WasapiCapture AudioFormat SampeRate: 48000, BitDepth: 32-Bit Floating Point -LogElevenLabsMic: Capture device: Microphone Array (Intel® Smart Sound Technology for Digital Microphones) | Rate=48000 | Channels=2 -LogElevenLabsMic: Audio capture started. -LogElevenLabsAgent: [T+74.14s] [Turn 5] Mic opened — user speaking. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Listening -LogElevenLabsMic: Audio capture stopped. -LogElevenLabsWS: [T+76.88s] User turn ended — server VAD silence detection started (turn_timeout=1s). -LogElevenLabsAgent: [T+76.88s] [Turn 5] Mic closed — user spoke 2.75s. Waiting for server response (timeout 10s)... -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: [T+77.28s] Agent started generating (393 ms after turn end — includes VAD silence timeout + LLM start). -LogElevenLabsAgent: [T+77.28s] [Turn 5] Agent generating. (0.39s after turn end) -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Agent Start Generating -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Warning: [T+78.31s] [LATENCY] First audio: 1428 ms after turn end (1428 ms after last chunk) -LogElevenLabsAgent: [T+78.31s] [Turn 5] Agent speaking — first audio chunk. (1.43s after turn end) -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Speaking -LogElevenLabsWS: Received message type: user_transcript -LogElevenLabsWS: Warning: [T+78.34s] [LATENCY] User transcript: 1460 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Transcript : Yes, tell me something in French. -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Received message type: audio -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Listening -LogElevenLabsAgent: StartListening: interrupting agent (speaking) to allow user to speak. -LogElevenLabsWS: Sending interrupt — ignoring incoming content until server acks. -LogElevenLabsAgent: [T+84.24s] [Turn 5] Agent stopped speaking (spoke 5.93s, full turn round-trip 7.36s). -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Speaking -LogElevenLabsWS: [T+84.24s] User turn started — mic open, audio chunks will follow. -LogAudioCaptureCore: Display: WasapiCapture AudioFormat SampeRate: 48000, BitDepth: 32-Bit Floating Point -LogElevenLabsMic: Capture device: Microphone Array (Intel® Smart Sound Technology for Digital Microphones) | Rate=48000 | Channels=2 -LogElevenLabsMic: Audio capture started. -LogElevenLabsAgent: [T+84.24s] [Turn 6] Mic opened — user speaking. -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Received message type: agent_response -LogElevenLabsWS: Warning: [T+84.43s] [LATENCY] Agent text response: 7549 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Text Response : Bien sûr! Je peux vous dire: "Bonjour, comment allez-vous aujourd'hui?" This means "Hello, how are you today?" -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Listening -LogElevenLabsMic: Audio capture stopped. -LogElevenLabsWS: [T+88.56s] User turn ended — server VAD silence detection started (turn_timeout=1s). -LogElevenLabsAgent: [T+88.56s] [Turn 6] Mic closed — user spoke 4.32s. Waiting for server response (timeout 10s)... -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Warning: [T+92.37s] [LATENCY] First audio: 3811 ms after turn end (3811 ms after last chunk) -LogElevenLabsWS: Received message type: user_transcript -LogElevenLabsWS: Warning: [T+92.37s] [LATENCY] User transcript: 3811 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Transcript : Mais c'est super! Tu parles très bien! -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Received message type: agent_response -LogElevenLabsWS: Warning: [T+97.23s] [LATENCY] Agent text response: 8677 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Text Response : Merci beaucoup! Je suis ravie que vous le pensiez. Y a-t-il autre chose que vous aimeriez savoir ou discuter en français? -LogElevenLabsAgent: Warning: [T+98.56s] [Turn 6] Response timeout — server did not start generating after 10.0s. Firing OnAgentResponseTimeout. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Listening -LogElevenLabsWS: [T+110.60s] User turn started — mic open, audio chunks will follow. -LogAudioCaptureCore: Display: WasapiCapture AudioFormat SampeRate: 48000, BitDepth: 32-Bit Floating Point -LogElevenLabsMic: Capture device: Microphone Array (Intel® Smart Sound Technology for Digital Microphones) | Rate=48000 | Channels=2 -LogElevenLabsMic: Audio capture started. -LogElevenLabsAgent: [T+110.60s] [Turn 7] Mic opened — user speaking. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Listening -LogElevenLabsMic: Audio capture stopped. -LogElevenLabsWS: [T+113.82s] User turn ended — server VAD silence detection started (turn_timeout=1s). -LogElevenLabsAgent: [T+113.82s] [Turn 7] Mic closed — user spoke 3.22s. Waiting for server response (timeout 10s)... -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Warning: [T+119.37s] [LATENCY] First audio: 5546 ms after turn end (5546 ms after last chunk) -LogElevenLabsWS: Received message type: user_transcript -LogElevenLabsWS: Warning: [T+119.37s] [LATENCY] User transcript: 5546 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Transcript : And do you speak German? -LogElevenLabsWS: Received message type: agent_response -LogElevenLabsWS: Warning: [T+119.40s] [LATENCY] Agent text response: 5577 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Text Response : Yes, I can also communicate in German. Would you like me to say something in German for you? -LogElevenLabsAgent: Warning: [T+123.83s] [Turn 7] Response timeout — server did not start generating after 10.0s. Firing OnAgentResponseTimeout. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Listening -LogElevenLabsWS: [T+131.53s] User turn started — mic open, audio chunks will follow. -LogAudioCaptureCore: Display: WasapiCapture AudioFormat SampeRate: 48000, BitDepth: 32-Bit Floating Point -LogElevenLabsMic: Capture device: Microphone Array (Intel® Smart Sound Technology for Digital Microphones) | Rate=48000 | Channels=2 -LogElevenLabsMic: Audio capture started. -LogElevenLabsAgent: [T+131.53s] [Turn 8] Mic opened — user speaking. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Listening -LogElevenLabsMic: Audio capture stopped. -LogElevenLabsWS: [T+134.42s] User turn ended — server VAD silence detection started (turn_timeout=1s). -LogElevenLabsAgent: [T+134.42s] [Turn 8] Mic closed — user spoke 2.88s. Waiting for server response (timeout 10s)... -LogElevenLabsAgent: Warning: [T+144.42s] [Turn 8] Response timeout — server did not start generating after 10.0s. Firing OnAgentResponseTimeout. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Listening -LogElevenLabsWS: [T+148.56s] User turn started — mic open, audio chunks will follow. -LogAudioCaptureCore: Display: WasapiCapture AudioFormat SampeRate: 48000, BitDepth: 32-Bit Floating Point -LogElevenLabsMic: Capture device: Microphone Array (Intel® Smart Sound Technology for Digital Microphones) | Rate=48000 | Channels=2 -LogElevenLabsMic: Audio capture started. -LogElevenLabsAgent: [T+148.56s] [Turn 9] Mic opened — user speaking. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Listening -LogElevenLabsMic: Audio capture stopped. -LogElevenLabsWS: [T+150.35s] User turn ended — server VAD silence detection started (turn_timeout=1s). -LogElevenLabsAgent: [T+150.35s] [Turn 9] Mic closed — user spoke 1.79s. Waiting for server response (timeout 10s)... -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Warning: [T+151.56s] [LATENCY] First audio: 1211 ms after turn end (1211 ms after last chunk) -LogElevenLabsWS: Received message type: user_transcript -LogElevenLabsWS: Warning: [T+151.59s] [LATENCY] User transcript: 1245 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Transcript : Hello. -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Received message type: agent_response -LogElevenLabsWS: Warning: [T+152.87s] [LATENCY] Agent text response: 2526 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Text Response : Hello! How can I help you today? -LogElevenLabsAgent: Warning: [T+160.36s] [Turn 9] Response timeout — server did not start generating after 10.0s. Firing OnAgentResponseTimeout. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Start Listening -LogElevenLabsWS: [T+162.59s] User turn started — mic open, audio chunks will follow. -LogAudioCaptureCore: Display: WasapiCapture AudioFormat SampeRate: 48000, BitDepth: 32-Bit Floating Point -LogElevenLabsMic: Capture device: Microphone Array (Intel® Smart Sound Technology for Digital Microphones) | Rate=48000 | Channels=2 -LogElevenLabsMic: Audio capture started. -LogElevenLabsAgent: [T+162.59s] [Turn 10] Mic opened — user speaking. -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Stop Listening -LogElevenLabsMic: Audio capture stopped. -LogElevenLabsWS: [T+165.69s] User turn ended — server VAD silence detection started (turn_timeout=1s). -LogElevenLabsAgent: [T+165.69s] [Turn 10] Mic closed — user spoke 3.10s. Waiting for server response (timeout 10s)... -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: agent_chat_response_part -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Warning: [T+168.47s] [LATENCY] First audio: 2778 ms after turn end (2778 ms after last chunk) -LogElevenLabsWS: Received message type: user_transcript -LogElevenLabsWS: Warning: [T+168.50s] [LATENCY] User transcript: 2810 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Transcript : Why are you so slow? -LogElevenLabsAgent: Warning: [T+175.70s] [Turn 10] Response timeout — server did not start generating after 10.0s. Firing OnAgentResponseTimeout. -LogElevenLabsWS: Received message type: audio -LogElevenLabsWS: Received message type: agent_response -LogElevenLabsWS: Warning: [T+175.85s] [LATENCY] Agent text response: 10161 ms after turn end -LogBlueprintUserMessages: [test_AI_Actor_C_2] [AI Agent] Text Response : I apologize if my response seemed slow. I'm designed to be as quick as possible while still being helpful. Is there something specific I can do to improve your experience? -LogSlate: Updating window title bar state: overlay mode, drag disabled, window buttons hidden, title bar hidden -LogWorld: BeginTearingDown for /Game/UEDPIE_0_TestMap - -Show less - - -Excellent logs — je vois deux bugs distincts : - -Bug A — bIgnoreIncomingContent jamais effacé : après l'interruption au Turn 5, le serveur n'envoie pas d'interruption_event (ou on ne le reçoit pas). Le flag reste true → tout le contenu du Turn 6, 7, 8, 9, 10 est silencieusement ignoré → timeout systématique. Preuve : les [LATENCY] First audio du WebSocketProxy s'affichent (l'audio arrive) mais JAMAIS le Agent speaking — first audio chunk de l'AgentComponent (l'audio est jeté). - -Bug B — HardSilenceTimeoutTicks = 120 (2s) trop court : l'agent répondait en deux batches audio avec 4.7s de gap (Turn 2 : T+23.85s puis T+28.55s). Le timeout de 2s s'est déclenché pendant le gap → faux "Stop Speaking" → Blueprint ouvre le mic → puis le 2e batch arrive → "Start Speaking" à nouveau. - -Fixes : \ No newline at end of file diff --git a/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Private/AnimNode_PS_AI_ConvAgent_Posture.cpp b/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Private/AnimNode_PS_AI_ConvAgent_Posture.cpp index c2f2ef7..cb757f9 100644 --- a/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Private/AnimNode_PS_AI_ConvAgent_Posture.cpp +++ b/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Private/AnimNode_PS_AI_ConvAgent_Posture.cpp @@ -323,7 +323,7 @@ void FAnimNode_PS_AI_ConvAgent_Posture::Update_AnyThread(const FAnimationUpdateC // Instead, keep the last valid cached values as a hold-over. if (PostureComponent.IsValid()) { - CachedEyeCurves = PostureComponent->GetCurrentEyeCurves(); + PostureComponent->FillCurrentEyeCurves(CachedEyeCurves); CachedHeadRotation = PostureComponent->GetCurrentHeadRotation(); CachedHeadCompensation = PostureComponent->GetHeadAnimationCompensation(); CachedEyeCompensation = PostureComponent->GetEyeAnimationCompensation(); diff --git a/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Private/PS_AI_ConvAgent_ElevenLabsComponent.cpp b/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Private/PS_AI_ConvAgent_ElevenLabsComponent.cpp index 80b9a0e..49c844f 100644 --- a/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Private/PS_AI_ConvAgent_ElevenLabsComponent.cpp +++ b/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Private/PS_AI_ConvAgent_ElevenLabsComponent.cpp @@ -151,6 +151,35 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::TickComponent(float DeltaTime, ELevel } } + // ── Reconnection ──────────────────────────────────────────────────────── + if (bWantsReconnect && FPlatformTime::Seconds() >= NextReconnectTime) + { + ++ReconnectAttemptCount; + if (ReconnectAttemptCount > MaxReconnectAttempts) + { + // Give up — full disconnect cleanup. + bWantsReconnect = false; + UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Error, + TEXT("Reconnection failed after %d attempts — giving up."), MaxReconnectAttempts); + bNetIsConversing = false; + ApplyConversationPosture(); + NetConversatingPlayer = nullptr; + NetConversatingPawn = nullptr; + OnAgentDisconnected.Broadcast(1006, TEXT("Reconnection failed")); + } + else + { + UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log, + TEXT("Reconnecting... attempt %d/%d"), ReconnectAttemptCount, MaxReconnectAttempts); + // Ensure proxy is in a clean state for reconnection. + if (WebSocketProxy) + { + WebSocketProxy->Disconnect(); + } + StartConversation_Internal(); + } + } + // Silence detection. // ISSUE-8: broadcast OnAgentStoppedSpeaking OUTSIDE AudioQueueLock. // OnProceduralUnderflow (audio thread) also acquires AudioQueueLock — if we broadcast @@ -162,7 +191,7 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::TickComponent(float DeltaTime, ELevel if (bAgentSpeaking) { FScopeLock Lock(&AudioQueueLock); - if (AudioQueue.Num() == 0) + if (AudioQueue.Num() - AudioQueueReadOffset == 0) { SilentTickCount++; @@ -290,6 +319,10 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::EndConversation() { if (GetOwnerRole() == ROLE_Authority) { + // Cancel any pending reconnection. + bWantsReconnect = false; + ReconnectAttemptCount = 0; + StopListening(); // ISSUE-4: StopListening() may set bWaitingForAgentResponse=true (normal turn end path). // Cancel it immediately — there is no response coming because we are ending the session. @@ -299,6 +332,7 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::EndConversation() if (WebSocketProxy) { + bIntentionalDisconnect = true; WebSocketProxy->Disconnect(); WebSocketProxy = nullptr; } @@ -706,6 +740,15 @@ const FPS_AI_ConvAgent_ConversationInfo_ElevenLabs& UPS_AI_ConvAgent_ElevenLabsC // ───────────────────────────────────────────────────────────────────────────── void UPS_AI_ConvAgent_ElevenLabsComponent::HandleConnected(const FPS_AI_ConvAgent_ConversationInfo_ElevenLabs& Info) { + // Reset reconnection state on successful connection. + if (bWantsReconnect) + { + UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log, + TEXT("Reconnection successful after %d attempt(s)."), ReconnectAttemptCount); + } + bWantsReconnect = false; + ReconnectAttemptCount = 0; + SessionStartTime = FPlatformTime::Seconds(); TurnIndex = 0; LastClosedTurnIndex = 0; @@ -739,6 +782,17 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::HandleDisconnected(int32 StatusCode, { UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log, TEXT("Agent disconnected. Code=%d Reason=%s"), StatusCode, *Reason); + // During reconnection, a failed attempt also triggers HandleDisconnected. + // Just schedule the next attempt without full cleanup. + if (bWantsReconnect) + { + const double Delay = FMath::Min(FMath::Pow(2.0, static_cast(ReconnectAttemptCount)), MaxReconnectDelay); + NextReconnectTime = FPlatformTime::Seconds() + Delay; + UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log, + TEXT("Reconnection attempt failed — retrying in %.0fs..."), Delay); + return; + } + // ISSUE-13: stop audio playback and clear the queue if the WebSocket drops while the // agent is speaking. Without this the audio component kept playing buffered PCM after // disconnect. StopAgentAudio also fires OnAgentStoppedSpeaking if bAgentSpeaking was true, @@ -757,6 +811,26 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::HandleDisconnected(int32 StatusCode, FScopeLock Lock(&MicSendLock); MicAccumulationBuffer.Reset(); } + + // ── Auto-reconnect on unexpected disconnect ───────────────────────────── + // StatusCode 1000 = normal close (user called EndConversation). + // bIntentionalDisconnect covers EndConversation and ServerReleaseConversation. + if (!bIntentionalDisconnect && StatusCode != 1000 + && MaxReconnectAttempts > 0 && GetOwnerRole() == ROLE_Authority) + { + bWantsReconnect = true; + ReconnectAttemptCount = 0; + const double Delay = 1.0; // First attempt after 1 second. + NextReconnectTime = FPlatformTime::Seconds() + Delay; + UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Warning, + TEXT("Unexpected disconnect — will attempt reconnection in %.0fs (max %d attempts)."), + Delay, MaxReconnectAttempts); + OnAgentError.Broadcast(TEXT("Connection lost — reconnecting...")); + // Keep bNetIsConversing / NetConversatingPawn so the NPC stays occupied. + return; + } + + bIntentionalDisconnect = false; // Reset replicated state on disconnect. if (GetOwnerRole() == ROLE_Authority) { @@ -772,6 +846,18 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::HandleDisconnected(int32 StatusCode, void UPS_AI_ConvAgent_ElevenLabsComponent::HandleError(const FString& ErrorMessage) { UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Error, TEXT("Agent error: %s"), *ErrorMessage); + + // During reconnection, a connection error should schedule the next attempt + // (OnWsConnectionError fires but OnWsClosed may not follow). + if (bWantsReconnect) + { + const double Delay = FMath::Min(FMath::Pow(2.0, static_cast(ReconnectAttemptCount)), MaxReconnectDelay); + NextReconnectTime = FPlatformTime::Seconds() + Delay; + UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log, + TEXT("Reconnection error — retrying in %.0fs..."), Delay); + return; + } + OnAgentError.Broadcast(ErrorMessage); } @@ -783,7 +869,7 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::HandleAudioReceived(const TArray= 2) { @@ -1107,13 +1193,28 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::OnProceduralUnderflow( return; } - if (AudioQueue.Num() > 0) + const int32 Available = AudioQueue.Num() - AudioQueueReadOffset; + if (Available > 0) { const int32 BytesRequired = SamplesRequired * sizeof(int16); - const int32 BytesToPush = FMath::Min(AudioQueue.Num(), BytesRequired); + const int32 BytesToPush = FMath::Min(Available, BytesRequired); - InProceduralWave->QueueAudio(AudioQueue.GetData(), BytesToPush); - AudioQueue.RemoveAt(0, BytesToPush, EAllowShrinking::No); + InProceduralWave->QueueAudio(AudioQueue.GetData() + AudioQueueReadOffset, BytesToPush); + AudioQueueReadOffset += BytesToPush; + + // Compact when read offset exceeds half the buffer to prevent unbounded growth. + // This replaces the old RemoveAt(0,N) per-callback O(n) memmove with a periodic + // compaction that happens much less frequently (~every 0.5-1s instead of 60Hz). + if (AudioQueueReadOffset > AudioQueue.Num() / 2) + { + const int32 Remaining = AudioQueue.Num() - AudioQueueReadOffset; + if (Remaining > 0) + { + FMemory::Memmove(AudioQueue.GetData(), AudioQueue.GetData() + AudioQueueReadOffset, Remaining); + } + AudioQueue.SetNum(Remaining, EAllowShrinking::No); + AudioQueueReadOffset = 0; + } // Log when queue recovers (new data arrived after being dry) if (bQueueWasDry) @@ -1124,7 +1225,7 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::OnProceduralUnderflow( const double T = FPlatformTime::Seconds() - SessionStartTime; UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log, TEXT("[T+%.2fs] [Turn %d] AudioQueue recovered — feeding real data again (%d bytes remaining)."), - T, LastClosedTurnIndex, AudioQueue.Num()); + T, LastClosedTurnIndex, AudioQueue.Num() - AudioQueueReadOffset); } } } @@ -1269,6 +1370,7 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::StopAgentAudio() { FScopeLock Lock(&AudioQueueLock); AudioQueue.Empty(); + AudioQueueReadOffset = 0; bAgentGenerating = false; // Always clear — covers interruptions during generation phase. bAgentResponseReceived = false; // Reset — next response will re-confirm when done. @@ -1536,12 +1638,17 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::ServerRequestConversation_Implementat void UPS_AI_ConvAgent_ElevenLabsComponent::ServerReleaseConversation_Implementation() { + // Cancel any pending reconnection. + bWantsReconnect = false; + ReconnectAttemptCount = 0; + StopListening(); bWaitingForAgentResponse = false; StopAgentAudio(); if (WebSocketProxy) { + bIntentionalDisconnect = true; WebSocketProxy->Disconnect(); WebSocketProxy = nullptr; } diff --git a/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Private/PS_AI_ConvAgent_WebSocket_ElevenLabsProxy.cpp b/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Private/PS_AI_ConvAgent_WebSocket_ElevenLabsProxy.cpp index 73ca198..51ad395 100644 --- a/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Private/PS_AI_ConvAgent_WebSocket_ElevenLabsProxy.cpp +++ b/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Private/PS_AI_ConvAgent_WebSocket_ElevenLabsProxy.cpp @@ -472,7 +472,7 @@ void UPS_AI_ConvAgent_WebSocket_ElevenLabsProxy::HandleAudioResponse(const TShar (*AudioEvent)->TryGetNumberField(TEXT("event_id"), EventId); if (EventId > 0 && EventId <= LastInterruptEventId) { - UE_LOG(LogPS_AI_ConvAgent_WS_ElevenLabs, Verbose, TEXT("Discarding audio event_id=%d (interrupted at %d)."), EventId, LastInterruptEventId); + UE_LOG(LogPS_AI_ConvAgent_WS_ElevenLabs, Verbose, TEXT("Discarding audio event_id=%d (interrupted at %d)."), EventId, LastInterruptEventId.load()); return; } diff --git a/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Public/PS_AI_ConvAgent_ElevenLabsComponent.h b/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Public/PS_AI_ConvAgent_ElevenLabsComponent.h index 0b02b74..a945e8d 100644 --- a/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Public/PS_AI_ConvAgent_ElevenLabsComponent.h +++ b/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Public/PS_AI_ConvAgent_ElevenLabsComponent.h @@ -175,6 +175,14 @@ public: ToolTip = "Seconds to wait for a server response after the user stops speaking.\nFires OnAgentResponseTimeout if exceeded. Normal latency is 0.1-0.8s.\nSet to 0 to disable. Default: 10s.")) float ResponseTimeoutSeconds = 10.0f; + /** Maximum auto-reconnection attempts on unexpected WebSocket disconnect. + * Uses exponential backoff (1s, 2s, 4s, ... up to 30s). + * Set to 0 to disable auto-reconnection. */ + UPROPERTY(EditAnywhere, BlueprintReadWrite, Category = "PS AI ConvAgent|ElevenLabs", + meta = (ClampMin = "0", + ToolTip = "Auto-reconnect attempts on unexpected disconnect.\n0 = disabled. Uses exponential backoff.")) + int32 MaxReconnectAttempts = 5; + // ── Multi-agent / external mic ─────────────────────────────────────────── /** When true, StartListening/StopListening manage the turn state but do NOT @@ -537,10 +545,11 @@ private: std::atomic bAgentSpeaking{false}; // True from the first agent_chat_response_part until the first audio chunk arrives. // Used to block StartListening() while the server is processing the previous turn. - bool bAgentGenerating = false; + // Atomic: defensive — currently game-thread only, but documents thread-safety contract. + std::atomic bAgentGenerating{false}; // True between StopListening() and HandleAgentResponseStarted() (first chat response part). // Used to fire OnAgentResponseTimeout if the server takes too long to start generating. - bool bWaitingForAgentResponse = false; + std::atomic bWaitingForAgentResponse{false}; // ── Turn tracking ───────────────────────────────────────────────────────── // Monotonically increasing counter. Incremented each time StartListening() successfully @@ -561,7 +570,11 @@ private: double AgentSpeakStart = 0.0; // Set in EnqueueAgentAudio (first chunk) — when audio begins. // Accumulates incoming PCM bytes until the audio component needs data. + // Uses a read offset instead of RemoveAt(0,N) to avoid O(n) memmove every + // underflow callback (~60Hz). Compacted periodically when read offset + // exceeds half the buffer. TArray AudioQueue; + int32 AudioQueueReadOffset = 0; FCriticalSection AudioQueueLock; // Pre-buffer state: delay playback start to absorb TTS inter-chunk gaps. @@ -611,6 +624,15 @@ private: * Formula: bytes = SampleRate * (ms / 1000) * BytesPerSample = 16000 * ms / 1000 * 2 = 32 * ms */ int32 GetMicChunkMinBytes() const { return MicChunkDurationMs * 32; } + // ── Reconnection ──────────────────────────────────────────────────────── + // Exponential backoff reconnection when the WebSocket drops unexpectedly. + // Only active on the Authority (server/standalone) where the WebSocket lives. + bool bWantsReconnect = false; + bool bIntentionalDisconnect = false; + int32 ReconnectAttemptCount = 0; + double NextReconnectTime = 0.0; + static constexpr double MaxReconnectDelay = 30.0; + // ── Opus codec (network audio compression) ─────────────────────────────── TSharedPtr OpusEncoder; // All: server encodes agent audio, clients encode mic audio TSharedPtr OpusDecoder; // All: clients decode agent audio, server decodes mic audio diff --git a/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Public/PS_AI_ConvAgent_PostureComponent.h b/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Public/PS_AI_ConvAgent_PostureComponent.h index 49be5a5..d8c4ac2 100644 --- a/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Public/PS_AI_ConvAgent_PostureComponent.h +++ b/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Public/PS_AI_ConvAgent_PostureComponent.h @@ -232,7 +232,8 @@ public: // ── Getters (read by AnimNode) ─────────────────────────────────────────── /** Get current eye gaze curves (8 ARKit eye look curves). - * Returns a COPY scaled by activation alpha — safe to call from any thread. */ + * Returns a COPY scaled by activation alpha — safe to call from any thread. + * NOTE: Prefer FillCurrentEyeCurves() for hot paths to avoid per-frame allocation. */ UFUNCTION(BlueprintCallable, Category = "PS AI ConvAgent|Posture") TMap GetCurrentEyeCurves() const { @@ -244,6 +245,24 @@ public: return Scaled; } + /** Fill an existing TMap with current eye gaze curves (zero-alloc after first call). + * Reuses the caller's existing hash table — no heap allocation when keys match. + * Thread-safe (takes PostureDataLock internally). */ + void FillCurrentEyeCurves(TMap& OutCurves) const + { + FScopeLock Lock(&PostureDataLock); + if (CurrentActiveAlpha < 0.001f) + { + for (auto& Pair : OutCurves) { Pair.Value = 0.0f; } + return; + } + const float Alpha = (CurrentActiveAlpha >= 0.999f) ? 1.0f : CurrentActiveAlpha; + for (const auto& Pair : CurrentEyeCurves) + { + OutCurves.FindOrAdd(Pair.Key) = Pair.Value * Alpha; + } + } + /** Get current head rotation offset (applied by AnimNode as FQuat to avoid * Euler round-trip that reintroduces parasitic tilt on diagonals). * Thread-safe copy, blended by activation alpha. */ diff --git a/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Public/PS_AI_ConvAgent_WebSocket_ElevenLabsProxy.h b/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Public/PS_AI_ConvAgent_WebSocket_ElevenLabsProxy.h index 110e07a..3945801 100644 --- a/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Public/PS_AI_ConvAgent_WebSocket_ElevenLabsProxy.h +++ b/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Source/PS_AI_ConvAgent/Public/PS_AI_ConvAgent_WebSocket_ElevenLabsProxy.h @@ -6,6 +6,7 @@ #include "UObject/NoExportTypes.h" #include "PS_AI_ConvAgent_Definitions.h" #include "IWebSocket.h" +#include #include "PS_AI_ConvAgent_WebSocket_ElevenLabsProxy.generated.h" // ───────────────────────────────────────────────────────────────────────────── @@ -239,12 +240,13 @@ private: // Timestamp when user turn ended (StopListening). double UserTurnEndTime = 0.0; // Whether we are waiting for the first response after user stopped speaking. - bool bWaitingForResponse = false; + // Atomic: defensive — documents thread-safety contract. + std::atomic bWaitingForResponse{false}; // Whether we already logged the first audio response latency for this turn. - bool bFirstAudioResponseLogged = false; + std::atomic bFirstAudioResponseLogged{false}; // Whether OnAgentResponseStarted has already been fired for the current turn. // Reset at turn start so only the first agent_chat_response_part fires the event. - bool bAgentResponseStartedFired = false; + std::atomic bAgentResponseStartedFired{false}; // Timestamp when the conversation was initiated (conversation_initiation_metadata received). // Used to compute [T+Xs] session-relative timestamps in all log messages. @@ -255,7 +257,8 @@ private: // Audio events whose event_id <= LastInterruptEventId belong to the cancelled // generation and must be discarded. Only AUDIO is filtered — transcripts, // agent_response, agent_chat_response_part etc. are always processed. - int32 LastInterruptEventId = 0; + // Atomic: defensive — documents thread-safety contract. + std::atomic LastInterruptEventId{0}; public: // Set by UPS_AI_ConvAgent_ElevenLabsComponent before calling Connect().