Decouple ForceDisableConversation from action flow + mic timing fix

- ElevenLabsComponent::ForceDisableConversation() — removed ActionName param. Now a pure conversation master-switch with no knowledge of actions. OnReadyForAction is fired by the action flow itself: PendingActionName is set when OnAgentActionRequested is broadcasted, then OnReadyForAction fires either after blend-out (if conversation was disabled) or on the next tick (if not). - Rename bConversationDisabledByAction → bConversationForceDisabled — the old name implied coupling with actions which no longer exists. - Add bPendingStartListening — when StartListening is called before the WebSocket is connected (race between StartConversation and StartListening from InteractionComponent), defer instead of silently failing. Consumed automatically in HandleConnected / ClientStartConversation. Cleared by StopListening / EndConversation. - PerceptionComponent — demote the "perceived N actors but ALL filtered out" warning to Verbose; it's a normal case for civilians surrounded by non-hostile actors, not a misconfiguration. - CLAUDE.md — workflow rule: always describe and request confirmation before code changes. - Martin.uasset — agent config tweaks. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-27 12:37:18 +02:00
parent f338c0586e
commit a1e34e6dfa
5 changed files with 109 additions and 48 deletions
--- a/Unreal/PS_AI_Agent/Plugins/PS_AI_Behavior/Source/PS_AI_Behavior/Private/PS_AI_Behavior_PerceptionComponent.cpp
+++ b/Unreal/PS_AI_Agent/Plugins/PS_AI_Behavior/Source/PS_AI_Behavior/Private/PS_AI_Behavior_PerceptionComponent.cpp
@@ -587,8 +587,10 @@ AActor* UPS_AI_Behavior_PerceptionComponent::GetHighestThreatActor(
 	}
 	else if (PerceivedActors.Num() > 0)
 	{
-		UE_LOG(LogPS_AI_Behavior, Warning,
-			TEXT("[%s] GetHighestThreatActor: perceived %d actors but ALL were filtered out (myTeam=0x%02X). Check TeamIds and attitude."),
+		// Normal case: civilian surrounded by non-hostile actors, or disguised enemy
+		// seeing allies. Only log at Verbose — not an issue.
+		UE_LOG(LogPS_AI_Behavior, Verbose,
+			TEXT("[%s] GetHighestThreatActor: perceived %d actors, none hostile (myTeam=0x%02X)."),
 			*Owner->GetName(), PerceivedActors.Num(),
 			AIC ? AIC->GetGenericTeamId().GetId() : 255);
 	}
--- a/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Content/Agents/Martin.uasset
+++ b/Unreal/PS_AI_Agent/Plugins/PS_AI_ConvAgent/Content/Agents/Martin.uasset
--- 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
@@ -101,10 +101,9 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::TickComponent(float DeltaTime, ELevel
 {
 	Super::TickComponent(DeltaTime, TickType, ThisTickFunction);

-	// ── ForceDisableConversation blend-out monitoring ─────────────────────
-	// After ForceDisableConversation(), sub-components are blending their
-	// CurrentActiveAlpha to 0. Once all are at (near) zero, fire OnReadyForAction
-	// so the game can start the physical action.
+	// ── Conversation disable: blend-out monitoring ─────────────────────────
+	// After ForceDisableConversation(), sub-components blend their CurrentActiveAlpha
+	// to 0. Once all near zero (or timeout), clear the wait flag.
 	if (bWaitingForBlendOut)
 	{
 		BlendOutElapsedTime += DeltaTime;
@@ -139,23 +138,33 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::TickComponent(float DeltaTime, ELevel
 			bWaitingForBlendOut = false;
 			BlendOutElapsedTime = 0.0f;
 			UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log,
-				TEXT("ForceDisableConversation: all components blended to neutral — firing OnReadyForAction for action '%s'."),
-				*PendingActionName);
-			OnReadyForAction.Broadcast(PendingActionName);
+				TEXT("ForceDisableConversation: all components blended to neutral."));
 		}
 		else if (bTimedOut)
 		{
 			// Safety timeout — some component didn't reach alpha 0 in time.
-			// Fire OnReadyForAction anyway to avoid blocking the game action forever.
 			bWaitingForBlendOut = false;
 			BlendOutElapsedTime = 0.0f;
 			UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Warning,
-				TEXT("ForceDisableConversation: blend-out timed out after %.1fs — not all components at neutral. Firing OnReadyForAction for action '%s' anyway."),
-				BlendOutTimeoutSeconds, *PendingActionName);
-			OnReadyForAction.Broadcast(PendingActionName);
+				TEXT("ForceDisableConversation: blend-out timed out after %.1fs — not all components at neutral."),
+				BlendOutTimeoutSeconds);
 		}
 	}

+	// ── Action flow: fire OnReadyForAction when ready ──────────────────────
+	// An action was requested via OnAgentActionRequested. Fire OnReadyForAction
+	// as soon as the agent is ready:
+	//  - If ForceDisableConversation was called, wait for blend-out to complete.
+	//  - Otherwise, fire on the next tick (quasi-immediate).
+	if (!PendingActionName.IsEmpty() && !bWaitingForBlendOut)
+	{
+		const FString ActionToFire = PendingActionName;
+		PendingActionName.Empty();
+		UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log,
+			TEXT("OnReadyForAction: firing for action '%s'."), *ActionToFire);
+		OnReadyForAction.Broadcast(ActionToFire);
+	}
+
 	// Response timeout: if the server hasn't started generating within ResponseTimeoutSeconds
 	// after the user stopped speaking, notify Blueprint so it can react (e.g. show "try again").
 	if (bWaitingForAgentResponse && ResponseTimeoutSeconds > 0.0f && TurnEndTime > 0.0)
@@ -400,7 +409,7 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::TickComponent(float DeltaTime, ELevel
 // ─────────────────────────────────────────────────────────────────────────────
 void UPS_AI_ConvAgent_ElevenLabsComponent::StartConversation()
 {
-	if (bConversationDisabledByAction)
+	if (bConversationForceDisabled)
 	{
 		UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Warning,
 			TEXT("StartConversation: blocked — conversation disabled by ForceDisableConversation(). Call ForceEnableConversation() first."));
@@ -492,6 +501,9 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::StartConversation_Internal()

 void UPS_AI_ConvAgent_ElevenLabsComponent::EndConversation()
 {
+	// Clear any pending listen request so it doesn't leak across sessions.
+	bPendingStartListening = false;
+
 	if (GetOwnerRole() == ROLE_Authority)
 	{
 		// Standalone / listen-server: leave via the local player controller.
@@ -525,7 +537,12 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::StartListening()
 	const bool bEffectivelyConnected = IsConnected() || (GetOwnerRole() != ROLE_Authority && bNetIsConversing);
 	if (!bEffectivelyConnected)
 	{
-		UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Warning, TEXT("StartListening: not connected (IsConnected=%s bNetIsConversing=%s Role=%d)."),
+		// Not ready yet — defer until HandleConnected fires.
+		// Prevents silent audio loss when StartListening is called synchronously
+		// after StartConversation (async WebSocket handshake).
+		bPendingStartListening = true;
+		UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log,
+			TEXT("StartListening deferred: WebSocket not connected yet (IsConnected=%s bNetIsConversing=%s Role=%d). Will open mic on connect."),
 			IsConnected() ? TEXT("true") : TEXT("false"),
 			bNetIsConversing ? TEXT("true") : TEXT("false"),
 			static_cast<int32>(GetOwnerRole()));
@@ -621,6 +638,10 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::StartListening()

 void UPS_AI_ConvAgent_ElevenLabsComponent::StopListening()
 {
+	// Also cancel any pending-start request (e.g. StartListening was deferred
+	// before WS connect and the user now wants to cancel).
+	bPendingStartListening = false;
+
 	if (!bIsListening) return;
 	bIsListening = false;

@@ -781,21 +802,19 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::InterruptAgent()
 // ForceDisableConversation / ForceEnableConversation
 // ─────────────────────────────────────────────────────────────────────────────

-void UPS_AI_ConvAgent_ElevenLabsComponent::ForceDisableConversation(const FString& ActionName)
+void UPS_AI_ConvAgent_ElevenLabsComponent::ForceDisableConversation()
 {
-	if (bConversationDisabledByAction)
+	if (bConversationForceDisabled)
 	{
 		UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Warning,
-			TEXT("ForceDisableConversation: already disabled (pending action: %s)."), *PendingActionName);
+			TEXT("ForceDisableConversation: already disabled."));
 		return;
 	}

 	UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log,
-		TEXT("ForceDisableConversation: shutting down conversation for action '%s', blending to neutral."), *ActionName);
+		TEXT("ForceDisableConversation: shutting down conversation, blending to neutral."));

-	PendingActionName = ActionName;
-
-	bConversationDisabledByAction = true;
+	bConversationForceDisabled = true;
 	bWaitingForBlendOut = true;
 	BlendOutElapsedTime = 0.0f;

@@ -856,7 +875,7 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::ForceDisableConversation(const FStrin

 void UPS_AI_ConvAgent_ElevenLabsComponent::ForceEnableConversation()
 {
-	if (!bConversationDisabledByAction)
+	if (!bConversationForceDisabled)
 	{
 		UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Warning,
 			TEXT("ForceEnableConversation: not currently disabled."));
@@ -866,7 +885,7 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::ForceEnableConversation()
 	UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log,
 		TEXT("ForceEnableConversation: conversation re-enabled."));

-	bConversationDisabledByAction = false;
+	bConversationForceDisabled = false;
 	bWaitingForBlendOut = false;
 	BlendOutElapsedTime = 0.0f;

@@ -1069,7 +1088,14 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::HandleConnected(const FPS_AI_ConvAgen
 	{
 		StartListening();
 	}
-
+	// Consume any pending listen request deferred before WebSocket was ready.
+	else if (bPendingStartListening)
+	{
+		bPendingStartListening = false;
+		UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log,
+			TEXT("HandleConnected: consuming pending StartListening request."));
+		StartListening();
+	}
 }

 void UPS_AI_ConvAgent_ElevenLabsComponent::HandleDisconnected(int32 StatusCode, const FString& Reason)
@@ -1451,6 +1477,10 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::HandleClientToolCall(const FPS_AI_Con
 				TEXT("[T+%.2fs] Agent action requested: %s"), T, *ActionName);
 		}

+		// Track the pending action so OnReadyForAction can fire with the same name.
+		// If the user synchronously calls ForceDisableConversation() in their handler,
+		// OnReadyForAction will wait for blend-out. Otherwise it fires on next tick.
+		PendingActionName = ActionName;
 		OnAgentActionRequested.Broadcast(ActionName);

 		// Auto-respond so the agent can continue speaking.
@@ -2100,7 +2130,7 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::ServerJoinConversation_Implementation
 	if (!Pawn) return;

 	// Block join while force-disabled (ForceDisableConversation active).
-	if (bConversationDisabledByAction)
+	if (bConversationForceDisabled)
 	{
 		UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log,
 			TEXT("[NET] ServerJoinConversation: blocked — conversation disabled by ForceDisableConversation()."));
@@ -2367,6 +2397,14 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::ClientConversationStarted_Implementat
 	{
 		StartListening();
 	}
+	// Consume any pending listen request deferred before conversation was ready.
+	else if (bPendingStartListening)
+	{
+		bPendingStartListening = false;
+		UE_LOG(LogPS_AI_ConvAgent_ElevenLabs, Log,
+			TEXT("[Client] Consuming pending StartListening request."));
+		StartListening();
+	}
 }

 void UPS_AI_ConvAgent_ElevenLabsComponent::ClientConversationFailed_Implementation(
@@ -2745,12 +2783,13 @@ void UPS_AI_ConvAgent_ElevenLabsComponent::DrawDebugHUD() const
 			bWantsReconnect ? TEXT(" (ACTIVE)") : TEXT("")));

 	// ForceDisable state
-	if (bConversationDisabledByAction || bWaitingForBlendOut)
+	if (bConversationForceDisabled || bWaitingForBlendOut)
 	{
 		const FColor DisableColor = FColor::Orange;
+		const FString PendingStr = PendingActionName.IsEmpty() ? TEXT("<none>") : PendingActionName;
 		GEngine->AddOnScreenDebugMessage(BaseKey + 9, DisplayTime, DisableColor,
-			FString::Printf(TEXT("  FORCE DISABLED — action: '%s'  blendOut: %s (%.1fs)"),
-				*PendingActionName,
+			FString::Printf(TEXT("  FORCE DISABLED — pending action: '%s'  blendOut: %s (%.1fs)"),
+				*PendingStr,
 				bWaitingForBlendOut ? TEXT("WAITING") : TEXT("DONE"),
 				BlendOutElapsedTime));

--- 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
@@ -548,25 +548,21 @@ public:
 	void InterruptAgent();

 	/**
-	 * Cleanly disable conversation on this agent so the NPC can switch to game AI.
+	 * Cleanly disable conversation on this agent.
 	 * Ends the WebSocket connection, stops all audio, and begins blending all
 	 * visual components (gaze, lip sync, facial expression, body expression)
 	 * back to their neutral state. While disabled, the InteractionComponent
 	 * cannot auto-restart a conversation with this agent.
 	 *
-	 * When all components have blended to neutral, fires OnReadyForAction.
+	 * This function ONLY handles the conversation master-switch. It has no
+	 * knowledge of action/reaction flow — if an action was pending via
+	 * OnAgentActionRequested, OnReadyForAction will fire automatically once
+	 * blend-out completes. If no action is pending, nothing else happens.
+	 *
 	 * Call ForceEnableConversation() later to allow conversation again.
-	 *
-	 * Typical usage from Blueprint (OnAgentActionRequested):
-	 *   1. ForceDisableConversation("flee")
-	 *   2. Wait for OnReadyForAction — receives the same ActionName
-	 *   3. Play action montage based on ActionName
-	 *   4. When done, call ForceEnableConversation()
-	 *
-	 * @param ActionName  The action to perform once neutral (passed through to OnReadyForAction).
 	 */
 	UFUNCTION(BlueprintCallable, Category = "ASTERION|PS_AI_ConvAgent|ElevenLabs")
-	void ForceDisableConversation(const FString& ActionName);
+	void ForceDisableConversation();

 	/**
 	 * Re-enable conversation after a ForceDisableConversation() call.
@@ -612,7 +608,7 @@ public:
 	/** True while conversation is force-disabled (ForceDisableConversation was called).
 	 *  While disabled, StartConversation and ServerJoinConversation are blocked. */
 	UFUNCTION(BlueprintPure, Category = "ASTERION|PS_AI_ConvAgent|ElevenLabs")
-	bool IsConversationDisabled() const { return bConversationDisabledByAction; }
+	bool IsConversationDisabled() const { return bConversationForceDisabled; }

 	/** True while audio is being pre-buffered (playback hasn't started yet).
 	 *  Used by the LipSync component to pause viseme queue consumption. */
@@ -706,24 +702,33 @@ private:
 	UPROPERTY()
 	USoundWaveProcedural* ProceduralSoundWave = nullptr;

-	// ── ForceDisableConversation state ───────────────────────────────────────
+	// ── Conversation disable state ───────────────────────────────────────────
 	// Set by ForceDisableConversation(), cleared by ForceEnableConversation().
 	// While true, StartConversation() and ServerJoinConversation() are blocked.
-	bool bConversationDisabledByAction = false;
-	// True while waiting for all visual components to blend back to neutral.
-	// Monitored in TickComponent — fires OnReadyForAction when complete.
+	bool bConversationForceDisabled = false;
+	// True while waiting for all visual components to blend back to neutral
+	// after ForceDisableConversation(). Monitored in TickComponent.
 	bool bWaitingForBlendOut = false;
-	// The action name passed to ForceDisableConversation(), forwarded to OnReadyForAction.
-	FString PendingActionName;
-	// Accumulated time waiting for blend-out. Safety timeout fires OnReadyForAction
+	// Accumulated time waiting for blend-out. Safety timeout to unblock
 	// if components haven't reached neutral within this limit.
 	float BlendOutElapsedTime = 0.0f;
 	static constexpr float BlendOutTimeoutSeconds = 5.0f;

+	// ── Action flow state (independent from disable state) ───────────────────
+	// Set when OnAgentActionRequested is broadcasted (LLM tool call).
+	// Cleared when OnReadyForAction is broadcasted.
+	// - If conversation is being disabled, OnReadyForAction waits for blend-out.
+	// - If not, OnReadyForAction fires on the next tick (quasi-immediate).
+	FString PendingActionName;
+
 	// ── State ─────────────────────────────────────────────────────────────────
 	// Atomic: read from WASAPI background thread (OnMicrophoneDataCaptured), written from game thread.
 	std::atomic<bool> bIsListening{false};
 	std::atomic<bool> bAgentSpeaking{false};
+	// Set when StartListening() is called before the WebSocket is connected.
+	// Consumed in HandleConnected() to open the microphone automatically once ready.
+	// Cleared by StopListening() or EndConversation() to cancel the pending request.
+	bool bPendingStartListening = 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.
 	// Atomic: defensive — currently game-thread only, but documents thread-safety contract.