Android XR、Geospatial API、Gemini を使用して複合現実ツアーガイドを構築する

// Retrieve the current geospatial pose from the ARCore session
val result = geospatial.createGeospatialPoseFromPose(arDevice.state.value.devicePose)
if (result is CreateGeospatialPoseFromPoseSuccess) {
    val pose = result.pose
    Log.d("VPS", "Accurate Location: ${pose.latitude}, ${pose.longitude}")
}

   val configForTools = ToolConfig(
      functionCallingConfig = null,
      retrievalConfig = retrievalConfig {
        latLng = FirebaseLatLng(pose.latitude, pose.longitude)
        languageCode = "en"
      }
    )

    val responseJsonSchema = Schema.obj(
      mapOf(
        "locationIntro" to Schema.string(),
        "tours" to Schema.array(
          Schema.obj(
            mapOf(
              "title" to Schema.string(),
              "description" to Schema.string(),
              "stops" to Schema.array(
                Schema.obj(
                  mapOf(
                    "name" to Schema.string(),
                    "detailedName" to Schema.string(),
                    "description" to Schema.string()
                  )
                )
              )
            )
          )
        )
      )
    )

    val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
      modelName = "gemini-3.5-flash",
      tools = listOf(Tool.googleMaps()),
      generationConfig = generationConfig {
        responseMimeType = "application/json"
        responseSchema = responseJsonSchema
      }
    )

   val result = model.generateContent("The user is at latitude ${pose.latitude} and longitude ${pose.longitude}. Generate exactly 3 diverse tours near this location (e.g., historical, food, nature). All tour ideas should be walking distance only.")

val ttsModel = Firebase.ai(backend = GenerativeBackend.googleAI())
    .generativeModel(
        modelName = "gemini-2.5-flash-tts",
        generationConfig = generationConfig {
            // Instruct the model to return Audio
            responseModalities = listOf(ResponseModality.AUDIO)
        }
    )

val response = ttsModel.generateContent("Say in a neutral but positive voice:\n$prompt")

// Extract the raw audio bytes from the response
val audioBytes = response.candidates.firstOrNull()?.content?.parts
    ?.filterIsInstance<InlineDataPart>()
    ?.firstOrNull { it.mimeType.contains("audio") }?.inlineData

@Composable
fun InfoSphere(
    content: InfoBubbleContent,
    session: Session,
    sphereModel: GltfModel,
    isSelected: Boolean,
    onClick: () -> Unit
) {
    // SpatialBox lets us arrange 3D components and SpatialPanels together
    SpatialBox(
        SubspaceModifier
            .offset(x = 2.dp, y = 1.dp, z = (-3).dp) // Positioned in 3D space
    ) {
        // Smoothly animate the visibility of our 2D Compose UI Panel
        AnimatedSpatialVisibility(visible = isSelected) {
            SpatialPanel {
                InfoBubble(content) // Regular 2D Compose UI
            }
        }
        // Render our interactive 3D sphere
        SceneCoreEntity(
            factory = {
                GltfModelEntity.create(session, sphereModel).also { entity ->
                    // Make the 3D model respond to user taps
                    entity.addComponent(InteractableComponent.create(session) { inputEvent ->
                        if (inputEvent.action == InputEvent.Action.UP) {
                            onClick()
                        }
                    })
                }
            }
        )
    }
}