@camstack/addon-vision 0.1.0 → 0.1.2

package/dist/addons/vehicle-classifier/index.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../../../src/addons/vehicle-classifier/index.ts","../../../src/catalogs/vehicle-classification-models.ts","../../../src/shared/image-utils.ts","../../../src/shared/engine-resolver.ts","../../../src/shared/node-engine.ts","../../../src/shared/python-engine.ts"],"sourcesContent":["import type {\n  IClassifierProvider,\n  IDetectionAddon,\n  AddonManifest,\n  AddonContext,\n  CropInput,\n  ClassifierOutput,\n  ConfigUISchema,\n  ClassMapDefinition,\n  ProbeResult,\n  ModelCatalogEntry,\n  DetectionModel,\n  LabelDefinition,\n  IInferenceEngine,\n  ModelRequirement,\n  ResolvedInferenceConfig,\n} from '@camstack/types'\nimport { VEHICLE_TYPE_MODELS } from '../../catalogs/vehicle-classification-models.js'\nimport { cropRegion, resizeAndNormalize } from '../../shared/image-utils.js'\nimport { resolveEngine } from '../../shared/engine-resolver.js'\nimport * as fs from 'node:fs'\nimport * as path from 'node:path'\n\nconst VEHICLE_TYPE_LABEL: LabelDefinition = { id: 'vehicle-type', name: 'Vehicle Type' }\nconst VEHICLE_TYPE_LABELS: readonly LabelDefinition[] = [VEHICLE_TYPE_LABEL]\nconst VEHICLE_CLASS_MAP: ClassMapDefinition = { mapping: {}, preserveOriginal: true }\n\n/** Load vehicle type labels from JSON file in modelsDir */\nfunction loadLabels(modelsDir: string, modelId: string): readonly string[] {\n  const labelNames = [\n    `camstack-${modelId}-labels.json`,\n    `camstack-vehicle-type-labels.json`,\n  ]\n  for (const name of labelNames) {\n    const labelPath = path.join(modelsDir, name)\n    if (fs.existsSync(labelPath)) {\n      const raw = fs.readFileSync(labelPath, 'utf-8')\n      return JSON.parse(raw) as string[]\n    }\n  }\n  throw new Error(`VehicleClassifierAddon: labels JSON not found in ${modelsDir}`)\n}\n\nfunction softmax(logits: Float32Array): Float32Array {\n  const max = logits.reduce((a, b) => Math.max(a, b), -Infinity)\n  const exps = logits.map((v) => Math.exp(v - max))\n  const sum = exps.reduce((a, b) => a + b, 0)\n  return exps.map((v) => v / sum) as unknown as Float32Array\n}\n\nexport default class VehicleClassifierAddon implements IClassifierProvider, IDetectionAddon {\n  readonly id = 'vehicle-classifier'\n  readonly slot = 'classifier' as const\n  readonly inputClasses = ['vehicle'] as const\n  readonly outputClasses = ['vehicle-type:*'] as const\n  readonly slotPriority = 0\n  readonly requiredSteps = [] as const\n  readonly manifest: AddonManifest = {\n    id: 'vehicle-classifier',\n    name: 'Vehicle Classifier',\n    version: '0.1.0',\n\n    description: 'EfficientNet-B4 — 8,949 vehicle make/model/year classes from VMMRdb',\n\n    slot: 'classifier',\n    labelOutputType: 'classification',\n    inputClasses: ['vehicle'],\n    outputClasses: ['vehicle-type:*'],\n    supportsCustomModels: false,\n    mayRequirePython: false,\n    defaultConfig: {\n      modelId: 'vehicle-type-efficientnet',\n      runtime: 'node',\n      backend: 'cpu',\n      confidence: 0.05,  // Low pipeline threshold for 8949-class model\n      minConfidence: 0.05,\n    },\n  }\n\n  private engine: IInferenceEngine | null = null\n  private modelEntry!: ModelCatalogEntry\n  private labels: readonly string[] = []\n  private minConfidence = 0.05\n  private resolvedConfig: ResolvedInferenceConfig | null = null\n  private ctx: AddonContext | null = null\n\n  getModelRequirements(): ModelRequirement[] {\n    return VEHICLE_TYPE_MODELS.map((m) => ({\n      modelId: m.id,\n      name: m.name,\n      minRAM_MB: 120,\n      accuracyScore: 80,\n      formats: Object.keys(m.formats) as readonly string[],\n    }))\n  }\n\n  configure(config: ResolvedInferenceConfig): void {\n    this.resolvedConfig = config\n  }\n\n  async initialize(ctx: AddonContext): Promise<void> {\n    this.ctx = ctx\n    const cfg = ctx.addonConfig\n    const modelId = (cfg['modelId'] as string | undefined) ?? this.resolvedConfig?.modelId ?? 'vehicle-type-efficientnet'\n    this.minConfidence = (cfg['minConfidence'] as number | undefined) ?? 0.05\n\n    const entry = VEHICLE_TYPE_MODELS.find((m) => m.id === modelId)\n    if (!entry) {\n      throw new Error(`VehicleClassifierAddon: unknown modelId \"${modelId}\"`)\n    }\n    this.modelEntry = entry\n  }\n\n  async classify(input: CropInput): Promise<ClassifierOutput> {\n    if (!this.engine) await this.ensureEngine()\n    const start = Date.now()\n    const { width: inputW, height: inputH } = this.modelEntry.inputSize\n\n    // Crop the vehicle region\n    const vehicleCrop = await cropRegion(input.frame.data, input.roi)\n\n    // Resize to 224x224, ImageNet normalization, NCHW\n    const normalized = await resizeAndNormalize(vehicleCrop, inputW, inputH, 'imagenet', 'nchw')\n\n    // Run inference\n    const rawOutput = await this.engine!.run(normalized, [1, 3, inputH, inputW])\n\n    console.log(`[VehicleClassifier] Output length: ${rawOutput.length}, labels: ${this.labels.length}, first 5 raw: [${Array.from(rawOutput.slice(0, 5)).map(v => v.toFixed(3)).join(', ')}]`)\n\n    // Softmax to get probabilities\n    const probs = softmax(rawOutput)\n\n    // Find top-3 for debugging\n    const indexed = Array.from(probs).map((v, i) => ({ score: v, idx: i }))\n    indexed.sort((a, b) => b.score - a.score)\n    const top3 = indexed.slice(0, 3)\n    console.log(`[VehicleClassifier] Top-3: ${top3.map(t => `${this.labels[t.idx] ?? t.idx}=${(t.score * 100).toFixed(1)}%`).join(', ')}`)\n\n    // Find argmax\n    const maxIdx = top3[0]?.idx ?? 0\n    const maxScore = top3[0]?.score ?? 0\n\n    if (maxScore < this.minConfidence) {\n      console.log(`[VehicleClassifier] Below confidence threshold: ${(maxScore * 100).toFixed(1)}% < ${(this.minConfidence * 100).toFixed(0)}%`)\n      return {\n        classifications: [],\n        inferenceMs: Date.now() - start,\n        modelId: this.modelEntry.id,\n      }\n    }\n\n    const label = this.labels[maxIdx] ?? `vehicle_type_${maxIdx}`\n    console.log(`[VehicleClassifier] Result: ${label} (${(maxScore * 100).toFixed(1)}%)`)\n\n    return {\n      classifications: [\n        {\n          class: label,\n          score: maxScore,\n        },\n      ],\n      inferenceMs: Date.now() - start,\n      modelId: this.modelEntry.id,\n    }\n  }\n\n  private async ensureEngine(): Promise<void> {\n    const config = this.resolvedConfig\n    const modelId = config?.modelId ?? this.modelEntry.id\n    const runtime = config?.runtime === 'python' ? 'coreml' : (config?.runtime === 'node' ? 'onnx' : 'auto')\n    const backend = config?.backend ?? 'cpu'\n    const format = config?.format ?? 'onnx'\n\n    const entry = VEHICLE_TYPE_MODELS.find((m) => m.id === modelId) ?? this.modelEntry\n    this.modelEntry = entry\n\n    const modelsDir = this.ctx!.models?.getModelsDir() ?? this.ctx!.locationPaths.models\n\n    // Ensure model + extra files (labels JSON) are downloaded via unified service\n    if (this.ctx!.models) {\n      await this.ctx!.models.ensure(modelId, format as any)\n    }\n\n    // Load labels from JSON file (lazy — only on first use)\n    this.labels = loadLabels(modelsDir, modelId)\n\n    const resolved = await resolveEngine({\n      runtime: runtime as 'auto',\n      backend,\n      modelEntry: entry,\n      modelsDir,\n      models: this.ctx!.models,\n    })\n    this.engine = resolved.engine\n  }\n\n  async shutdown(): Promise<void> {\n    await this.engine?.dispose()\n  }\n\n  getConfigSchema(): ConfigUISchema {\n    return {\n      sections: [\n        {\n          id: 'model',\n          title: 'Model',\n          columns: 1,\n          fields: [\n            {\n              key: 'modelId',\n              label: 'Model',\n              type: 'model-selector',\n              catalog: [...VEHICLE_TYPE_MODELS],\n              allowCustom: false,\n              allowConversion: false,\n              acceptFormats: ['onnx', 'coreml', 'openvino'],\n              requiredMetadata: ['inputSize', 'labels'],\n              outputFormatHint: 'classification',\n            },\n          ],\n        },\n        {\n          id: 'runtime',\n          title: 'Runtime',\n          columns: 2,\n          fields: [\n            {\n              key: 'runtime',\n              label: 'Runtime',\n              type: 'select',\n              options: [\n                { value: 'auto', label: 'Auto' },\n                { value: 'onnx', label: 'ONNX Runtime' },\n                { value: 'coreml', label: 'CoreML (Apple)' },\n                { value: 'openvino', label: 'OpenVINO (Intel)' },\n              ],\n            },\n            {\n              key: 'backend',\n              label: 'Backend',\n              type: 'select',\n              showWhen: { field: 'runtime', equals: 'onnx' },\n              options: [\n                { value: 'auto', label: 'Auto' },\n                { value: 'cpu', label: 'CPU' },\n                { value: 'coreml', label: 'CoreML' },\n                { value: 'cuda', label: 'CUDA (NVIDIA)' },\n              ],\n            },\n          ],\n        },\n        {\n          id: 'thresholds',\n          title: 'Classification Settings',\n          columns: 1,\n          fields: [\n            {\n              key: 'minConfidence',\n              label: 'Minimum Confidence',\n              type: 'slider',\n              min: 0.05,\n              max: 1.0,\n              step: 0.05,\n              default: 0.3,\n            },\n          ],\n        },\n      ],\n    }\n  }\n\n  getClassMap(): ClassMapDefinition {\n    return VEHICLE_CLASS_MAP\n  }\n\n  getModelCatalog(): ModelCatalogEntry[] {\n    return [...VEHICLE_TYPE_MODELS]\n  }\n\n  getAvailableModels(): DetectionModel[] {\n    return []\n  }\n\n  getActiveLabels(): readonly LabelDefinition[] {\n    return VEHICLE_TYPE_LABELS\n  }\n\n  async probe(): Promise<ProbeResult> {\n    return {\n      available: true,\n      runtime: this.engine?.runtime ?? 'onnx',\n      device: this.engine?.device ?? 'cpu',\n      capabilities: ['fp32'],\n    }\n  }\n}\n","import type { ModelCatalogEntry, LabelDefinition } from '@camstack/types'\nimport { hfModelUrl } from '@camstack/types'\n\nconst HF_REPO = 'camstack/camstack-models'\n\nconst hf = (path: string) => hfModelUrl(HF_REPO, path)\n\nconst VEHICLE_LABELS: readonly LabelDefinition[] = [\n  { id: 'vehicle-type', name: 'Vehicle Type' },\n]\n\nexport const VEHICLE_TYPE_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'vehicle-type-efficientnet',\n    name: 'Vehicle Type (EfficientNet)',\n    description: 'EfficientNet-B4 vehicle make/model/year classifier — 8,949 classes from VMMRdb',\n    inputSize: { width: 380, height: 380 },\n    inputNormalization: 'imagenet',\n    labels: VEHICLE_LABELS,\n    formats: {\n      onnx: { url: hf('vehicleClassification/efficientnet/onnx/camstack-vehicle-type-efficientnet.onnx'), sizeMB: 135 },\n      coreml: {\n        url: hf('vehicleClassification/efficientnet/coreml/camstack-vehicle-type-efficientnet.mlpackage'),\n        sizeMB: 10,\n        isDirectory: true,\n        files: ['Manifest.json', 'Data/com.apple.CoreML/model.mlmodel', 'Data/com.apple.CoreML/weights/weight.bin'],\n        runtimes: ['python'],\n      },\n    },\n    extraFiles: [\n      {\n        url: hf('vehicleClassification/efficientnet/camstack-vehicle-type-labels.json'),\n        filename: 'camstack-vehicle-type-labels.json',\n        sizeMB: 0.2,\n      },\n    ],\n  },\n] as const\n","import sharp from 'sharp'\nimport type { BoundingBox } from '@camstack/types'\n\n/** Decode JPEG to raw RGB pixels */\nexport async function jpegToRgb(\n  jpeg: Buffer,\n): Promise<{ data: Buffer; width: number; height: number }> {\n  const { data, info } = await sharp(jpeg)\n    .removeAlpha()\n    .raw()\n    .toBuffer({ resolveWithObject: true })\n  return { data, width: info.width, height: info.height }\n}\n\n/** Crop a region from a JPEG buffer */\nexport async function cropRegion(jpeg: Buffer, roi: BoundingBox): Promise<Buffer> {\n  return sharp(jpeg)\n    .extract({\n      left: Math.round(roi.x),\n      top: Math.round(roi.y),\n      width: Math.round(roi.w),\n      height: Math.round(roi.h),\n    })\n    .jpeg()\n    .toBuffer()\n}\n\n/** Letterbox resize for YOLO: resize preserving aspect ratio, pad to square */\nexport async function letterbox(\n  jpeg: Buffer,\n  targetSize: number,\n): Promise<{\n  data: Float32Array\n  scale: number\n  padX: number\n  padY: number\n  originalWidth: number\n  originalHeight: number\n}> {\n  const meta = await sharp(jpeg).metadata()\n  const originalWidth = meta.width ?? 0\n  const originalHeight = meta.height ?? 0\n\n  const scale = Math.min(targetSize / originalWidth, targetSize / originalHeight)\n  const scaledWidth = Math.round(originalWidth * scale)\n  const scaledHeight = Math.round(originalHeight * scale)\n\n  const padX = Math.floor((targetSize - scaledWidth) / 2)\n  const padY = Math.floor((targetSize - scaledHeight) / 2)\n\n  const { data } = await sharp(jpeg)\n    .resize(scaledWidth, scaledHeight)\n    .extend({\n      top: padY,\n      bottom: targetSize - scaledHeight - padY,\n      left: padX,\n      right: targetSize - scaledWidth - padX,\n      background: { r: 114, g: 114, b: 114 },\n    })\n    .removeAlpha()\n    .raw()\n    .toBuffer({ resolveWithObject: true })\n\n  // Convert HWC uint8 to CHW float [0,1]\n  const numPixels = targetSize * targetSize\n  const float32 = new Float32Array(3 * numPixels)\n  for (let i = 0; i < numPixels; i++) {\n    const srcBase = i * 3\n    float32[0 * numPixels + i] = (data[srcBase]! / 255)\n    float32[1 * numPixels + i] = (data[srcBase + 1]! / 255)\n    float32[2 * numPixels + i] = (data[srcBase + 2]! / 255)\n  }\n\n  return { data: float32, scale, padX, padY, originalWidth, originalHeight }\n}\n\n/** Resize and normalize to Float32Array */\nexport async function resizeAndNormalize(\n  jpeg: Buffer,\n  targetWidth: number,\n  targetHeight: number,\n  normalization: 'zero-one' | 'imagenet' | 'none',\n  layout: 'nchw' | 'nhwc',\n): Promise<Float32Array> {\n  const { data } = await sharp(jpeg)\n    .resize(targetWidth, targetHeight, { fit: 'fill' })\n    .removeAlpha()\n    .raw()\n    .toBuffer({ resolveWithObject: true })\n\n  const numPixels = targetWidth * targetHeight\n  const float32 = new Float32Array(3 * numPixels)\n\n  // ImageNet mean and std per channel\n  const mean = [0.485, 0.456, 0.406]\n  const std = [0.229, 0.224, 0.225]\n\n  if (layout === 'nchw') {\n    for (let i = 0; i < numPixels; i++) {\n      const srcBase = i * 3\n      for (let c = 0; c < 3; c++) {\n        const raw = data[srcBase + c]! / 255\n        let val: number\n        if (normalization === 'zero-one') {\n          val = raw\n        } else if (normalization === 'imagenet') {\n          val = (raw - mean[c]!) / std[c]!\n        } else {\n          val = data[srcBase + c]!\n        }\n        float32[c * numPixels + i] = val\n      }\n    }\n  } else {\n    // nhwc\n    for (let i = 0; i < numPixels; i++) {\n      const srcBase = i * 3\n      for (let c = 0; c < 3; c++) {\n        const raw = data[srcBase + c]! / 255\n        let val: number\n        if (normalization === 'zero-one') {\n          val = raw\n        } else if (normalization === 'imagenet') {\n          val = (raw - mean[c]!) / std[c]!\n        } else {\n          val = data[srcBase + c]!\n        }\n        float32[i * 3 + c] = val\n      }\n    }\n  }\n\n  return float32\n}\n\n/** Convert raw RGB to grayscale Uint8Array */\nexport function rgbToGrayscale(rgb: Buffer, width: number, height: number): Uint8Array {\n  const numPixels = width * height\n  const gray = new Uint8Array(numPixels)\n  for (let i = 0; i < numPixels; i++) {\n    const r = rgb[i * 3]!\n    const g = rgb[i * 3 + 1]!\n    const b = rgb[i * 3 + 2]!\n    // BT.601 luma\n    gray[i] = Math.round(0.299 * r + 0.587 * g + 0.114 * b)\n  }\n  return gray\n}\n","// TODO: Wire PythonInferenceEngine for PyTorch/OpenVINO/TFLite runtimes\n// Currently falls back to ONNX CPU when non-ONNX runtime is requested.\n// See: packages/addon-vision/python/ for stub implementations.\n//\n// WHY THIS FILE USES RAW FILESYSTEM PATHS (modelsDir: string):\n//\n// Model files must be loaded via absolute filesystem paths because inference\n// engines (ONNX Runtime, CoreML, etc.) require direct file access -- they do\n// not accept Buffer or stream inputs. This is fundamentally different from\n// user data (recordings, media) where IAddonFileStorage abstraction makes\n// sense. Models are closer to binaries or compiled artifacts that must live\n// on the local filesystem at runtime.\n//\n// IAddonFileStorage.readFile() returns a Buffer, but onnxruntime-node's\n// InferenceSession.create() only accepts a file path string or a Uint8Array\n// loaded into memory. For large models (hundreds of MB), loading into a\n// Uint8Array is impractical. Therefore, modelsDir stays as a raw string path\n// and is intentionally NOT replaced with IAddonFileStorage here.\n\nimport type {\n  IInferenceEngine,\n  DetectionRuntime,\n  ModelCatalogEntry,\n  ModelFormat,\n  IAddonModelManager,\n} from '@camstack/types'\nimport * as fs from 'node:fs'\nimport * as path from 'node:path'\nimport { NodeInferenceEngine } from './node-engine.js'\nimport { PythonInferenceEngine } from './python-engine.js'\n\nexport interface EngineResolverOptions {\n  readonly runtime: DetectionRuntime | 'auto'\n  readonly backend: string\n  readonly modelEntry: ModelCatalogEntry\n  readonly modelsDir: string\n  readonly pythonPath?: string\n  /** Model service for downloading models. When provided, used instead of raw filesystem probing. */\n  readonly models?: IAddonModelManager\n}\n\nexport interface ResolvedEngine {\n  readonly engine: IInferenceEngine\n  readonly format: ModelFormat\n  readonly modelPath: string\n}\n\n/** Priority order for auto-selection of ONNX backends */\nconst AUTO_BACKEND_PRIORITY = ['coreml', 'cuda', 'tensorrt', 'cpu'] as const\n\n/** Map backend names to the model format they require.\n * CoreML backend uses ONNX format -- onnxruntime-node loads the .onnx file\n * and accelerates it via the CoreML execution provider internally.\n * Native .mlpackage is only for PythonInferenceEngine. */\nconst BACKEND_TO_FORMAT: Readonly<Record<string, ModelFormat>> = {\n  cpu: 'onnx',\n  coreml: 'onnx',\n  cuda: 'onnx',\n  tensorrt: 'onnx',\n} as const\n\n/** Map DetectionRuntime to ModelFormat */\nconst RUNTIME_TO_FORMAT: Readonly<Partial<Record<DetectionRuntime, ModelFormat>>> = {\n  onnx: 'onnx',\n  coreml: 'coreml',\n  openvino: 'openvino',\n  tflite: 'tflite',\n  pytorch: 'pt',\n} as const\n\nfunction modelFilePath(modelsDir: string, modelEntry: ModelCatalogEntry, format: ModelFormat): string {\n  const formatEntry = modelEntry.formats[format]\n  if (!formatEntry) {\n    throw new Error(`Model ${modelEntry.id} has no ${format} format`)\n  }\n  // Derive filename from URL\n  const urlParts = formatEntry.url.split('/')\n  const filename = urlParts[urlParts.length - 1] ?? `${modelEntry.id}.${format}`\n  return path.join(modelsDir, filename)\n}\n\nfunction modelExists(filePath: string): boolean {\n  try {\n    return fs.existsSync(filePath)\n  } catch {\n    return false\n  }\n}\n\nexport async function resolveEngine(options: EngineResolverOptions): Promise<ResolvedEngine> {\n  const { runtime, backend, modelEntry, modelsDir, models } = options\n\n  let selectedFormat: ModelFormat\n  let selectedBackend: string\n\n  if (runtime === 'auto') {\n    // Probe available ONNX backends and pick best\n    const available = await probeOnnxBackends()\n\n    // Pick first priority backend that has a corresponding model format available\n    let chosen: { backend: string; format: ModelFormat } | null = null\n\n    for (const b of AUTO_BACKEND_PRIORITY) {\n      if (!available.includes(b)) continue\n      const fmt = BACKEND_TO_FORMAT[b]\n      if (!fmt) continue\n      if (!modelEntry.formats[fmt]) continue\n      chosen = { backend: b, format: fmt }\n      break\n    }\n\n    if (!chosen) {\n      throw new Error(\n        `resolveEngine: no compatible backend found for model ${modelEntry.id}. Available backends: ${available.join(', ')}`,\n      )\n    }\n\n    selectedFormat = chosen.format\n    selectedBackend = chosen.backend\n  } else {\n    // Explicit runtime requested\n    const fmt = RUNTIME_TO_FORMAT[runtime]\n    if (!fmt) {\n      throw new Error(`resolveEngine: unsupported runtime \"${runtime}\"`)\n    }\n    if (!modelEntry.formats[fmt]) {\n      throw new Error(\n        `resolveEngine: model ${modelEntry.id} has no ${fmt} format for runtime ${runtime}`,\n      )\n    }\n    selectedFormat = fmt\n    // For onnx runtime, use the provided backend; otherwise use the runtime name\n    selectedBackend = runtime === 'onnx' ? (backend || 'cpu') : runtime\n  }\n\n  // Download model and extra files via the unified service\n  let modelPath: string\n\n  if (models) {\n    // Use the unified ModelDownloadService\n    modelPath = await models.ensure(modelEntry.id, selectedFormat)\n  } else {\n    // Fallback: direct filesystem check (no download capability)\n    modelPath = modelFilePath(modelsDir, modelEntry, selectedFormat)\n    if (!modelExists(modelPath)) {\n      throw new Error(\n        `resolveEngine: model file not found at ${modelPath} and no model service provided`,\n      )\n    }\n  }\n\n  // NodeInferenceEngine handles ONNX format only (with any ONNX backend including CoreML provider).\n  // Native .mlpackage/.mlmodel files go to PythonInferenceEngine below.\n  if (selectedFormat === 'onnx') {\n    const engine = new NodeInferenceEngine(modelPath, selectedBackend)\n    await engine.initialize()\n    return { engine, format: selectedFormat, modelPath }\n  }\n\n  // For non-ONNX/CoreML formats, try PythonInferenceEngine when a python binary is available\n  const { pythonPath } = options\n  const PYTHON_SCRIPT_MAP: Readonly<Record<string, string>> = {\n    coreml: 'coreml_inference.py',\n    pytorch: 'pytorch_inference.py',\n    openvino: 'openvino_inference.py',\n  } as const\n\n  const effectiveRuntime = runtime === 'auto' ? selectedBackend : runtime\n  const scriptName = PYTHON_SCRIPT_MAP[effectiveRuntime]\n\n  if (scriptName && pythonPath) {\n    // Resolve python script path -- search multiple locations:\n    // - src/shared/ -> ../../python/ (source development)\n    // - dist/shared/ -> ../../python/ (installed addon with python/ at package root)\n    // - dist/ -> ../python/ (flat dist)\n    const candidates = [\n      path.join(__dirname, '../../python', scriptName),\n      path.join(__dirname, '../python', scriptName),\n      path.join(__dirname, '../../../python', scriptName),\n    ]\n    const scriptPath = candidates.find(p => fs.existsSync(p))\n    if (!scriptPath) {\n      throw new Error(\n        `resolveEngine: Python script \"${scriptName}\" not found. Searched:\\n${candidates.join('\\n')}`,\n      )\n    }\n    const inputSize = Math.max(modelEntry.inputSize.width, modelEntry.inputSize.height)\n    const engine = new PythonInferenceEngine(pythonPath, scriptPath, effectiveRuntime as DetectionRuntime, modelPath, [\n      `--input-size=${inputSize}`,\n      `--confidence=0.25`,\n    ])\n    await engine.initialize()\n    return { engine, format: selectedFormat, modelPath }\n  }\n\n  // Final fallback: use ONNX CPU if available\n  const fallbackPath = modelFilePath(modelsDir, modelEntry, 'onnx')\n  if (modelEntry.formats['onnx'] && modelExists(fallbackPath)) {\n    const engine = new NodeInferenceEngine(fallbackPath, 'cpu')\n    await engine.initialize()\n    return { engine, format: 'onnx', modelPath: fallbackPath }\n  }\n\n  throw new Error(\n    `resolveEngine: format ${selectedFormat} is not yet supported by NodeInferenceEngine, ` +\n    `no Python runtime is available, and no ONNX fallback exists`,\n  )\n}\n\n/** Probe which ONNX execution providers are available on this system */\nexport async function probeOnnxBackends(): Promise<string[]> {\n  const available: string[] = ['cpu'] // CPU is always available\n\n  try {\n    const ort = await import('onnxruntime-node')\n    // eslint-disable-next-line @typescript-eslint/no-explicit-any\n    const providers: string[] = (ort as any).env?.webgl?.disabled !== undefined\n      // eslint-disable-next-line @typescript-eslint/no-explicit-any\n      ? ((ort as any).InferenceSession?.getAvailableProviders?.() ?? [])\n      : []\n\n    for (const p of providers) {\n      const normalized = p.toLowerCase().replace('executionprovider', '')\n      if (normalized === 'coreml') available.push('coreml')\n      else if (normalized === 'cuda') available.push('cuda')\n      else if (normalized === 'tensorrt') available.push('tensorrt')\n    }\n  } catch {\n    // onnxruntime-node may not be installed; CPU only\n  }\n\n  // Platform-specific hints when getAvailableProviders isn't exposed\n  if (process.platform === 'darwin' && !available.includes('coreml')) {\n    available.push('coreml')\n  }\n\n  return [...new Set(available)]\n}\n","import type { IInferenceEngine, DetectionRuntime, DetectionDevice } from '@camstack/types'\nimport * as path from 'node:path'\n\nconst BACKEND_TO_PROVIDER: Readonly<Record<string, string>> = {\n  cpu: 'cpu',\n  coreml: 'coreml',\n  cuda: 'cuda',\n  tensorrt: 'tensorrt',\n  dml: 'dml',\n} as const\n\nconst BACKEND_TO_DEVICE: Readonly<Record<string, DetectionDevice>> = {\n  cpu: 'cpu',\n  coreml: 'gpu-mps',\n  cuda: 'gpu-cuda',\n  tensorrt: 'tensorrt',\n} as const\n\nexport class NodeInferenceEngine implements IInferenceEngine {\n  readonly runtime: DetectionRuntime = 'onnx'\n  readonly device: DetectionDevice\n  private session: unknown = null\n\n  constructor(\n    private readonly modelPath: string,\n    private readonly backend: string,\n  ) {\n    this.device = (BACKEND_TO_DEVICE[backend] ?? 'cpu') as DetectionDevice\n  }\n\n  async initialize(): Promise<void> {\n    const ort = await import('onnxruntime-node')\n    const provider = BACKEND_TO_PROVIDER[this.backend] ?? 'cpu'\n\n    // Resolve absolute path\n    const absModelPath = path.isAbsolute(this.modelPath)\n      ? this.modelPath\n      : path.resolve(process.cwd(), this.modelPath)\n\n    const sessionOptions: Record<string, unknown> = {\n      executionProviders: [provider],\n    }\n\n    // eslint-disable-next-line @typescript-eslint/no-explicit-any\n    this.session = await (ort as any).InferenceSession.create(absModelPath, sessionOptions)\n  }\n\n  async run(input: Float32Array, inputShape: readonly number[]): Promise<Float32Array> {\n    if (!this.session) {\n      throw new Error('NodeInferenceEngine: not initialized — call initialize() first')\n    }\n\n    const ort = await import('onnxruntime-node')\n    // eslint-disable-next-line @typescript-eslint/no-explicit-any\n    const sess = this.session as any\n\n    // Get the first input name\n    const inputName: string = sess.inputNames[0]\n    // eslint-disable-next-line @typescript-eslint/no-explicit-any\n    const tensor = new (ort as any).Tensor('float32', input, [...inputShape])\n    const feeds: Record<string, unknown> = { [inputName]: tensor }\n\n    const results = await sess.run(feeds)\n    const outputName: string = sess.outputNames[0]\n    const outputTensor = results[outputName]\n\n    return outputTensor.data as Float32Array\n  }\n\n  async runMultiOutput(\n    input: Float32Array,\n    inputShape: readonly number[],\n  ): Promise<Record<string, Float32Array>> {\n    if (!this.session) {\n      throw new Error('NodeInferenceEngine: not initialized — call initialize() first')\n    }\n\n    const ort = await import('onnxruntime-node')\n    // eslint-disable-next-line @typescript-eslint/no-explicit-any\n    const sess = this.session as any\n\n    const inputName: string = sess.inputNames[0]\n    // eslint-disable-next-line @typescript-eslint/no-explicit-any\n    const tensor = new (ort as any).Tensor('float32', input, [...inputShape])\n    const feeds: Record<string, unknown> = { [inputName]: tensor }\n\n    const results = await sess.run(feeds)\n\n    const out: Record<string, Float32Array> = {}\n    for (const name of sess.outputNames as string[]) {\n      out[name] = results[name].data as Float32Array\n    }\n    return out\n  }\n\n  async dispose(): Promise<void> {\n    // onnxruntime-node sessions don't have explicit close in all versions\n    // but we clear the reference\n    this.session = null\n  }\n}\n","import type { IInferenceEngine, DetectionRuntime, DetectionDevice, IAddonDepsManager } from '@camstack/types'\nimport { spawn, type ChildProcess } from 'node:child_process'\n\nexport class PythonInferenceEngine implements IInferenceEngine {\n  readonly runtime: DetectionRuntime\n  readonly device: DetectionDevice\n  private process: ChildProcess | null = null\n  private receiveBuffer: Buffer = Buffer.alloc(0)\n  private pendingResolve: ((value: Record<string, unknown>) => void) | null = null\n  private pendingReject: ((reason: Error) => void) | null = null\n\n  constructor(\n    private readonly pythonPath: string,\n    private readonly scriptPath: string,\n    runtime: DetectionRuntime,\n    private readonly modelPath: string,\n    private readonly extraArgs: readonly string[] = [],\n  ) {\n    this.runtime = runtime\n    // Determine device from runtime\n    const runtimeDeviceMap: Readonly<Record<DetectionRuntime, DetectionDevice>> = {\n      onnx: 'cpu',\n      coreml: 'gpu-mps',\n      pytorch: 'cpu',\n      openvino: 'cpu',\n      tflite: 'cpu',\n    }\n    this.device = runtimeDeviceMap[runtime]\n  }\n\n  async initialize(): Promise<void> {\n    const args = [this.scriptPath, this.modelPath, ...this.extraArgs]\n    this.process = spawn(this.pythonPath, args, {\n      stdio: ['pipe', 'pipe', 'pipe'],\n    })\n\n    if (!this.process.stdout || !this.process.stdin) {\n      throw new Error('PythonInferenceEngine: failed to create process pipes')\n    }\n\n    this.process.stderr?.on('data', (chunk: Buffer) => {\n      // Log stderr from python process for debugging\n      process.stderr.write(`[python-engine] ${chunk.toString()}`)\n    })\n\n    this.process.on('error', (err) => {\n      this.pendingReject?.(err)\n      this.pendingReject = null\n      this.pendingResolve = null\n    })\n\n    this.process.on('exit', (code) => {\n      if (code !== 0) {\n        const err = new Error(`PythonInferenceEngine: process exited with code ${code}`)\n        this.pendingReject?.(err)\n        this.pendingReject = null\n        this.pendingResolve = null\n      }\n    })\n\n    this.process.stdout.on('data', (chunk: Buffer) => {\n      this.receiveBuffer = Buffer.concat([this.receiveBuffer, chunk])\n      this._tryReceive()\n    })\n\n    // Give the process a moment to start up and load the model\n    await new Promise<void>((resolve, reject) => {\n      const timeout = setTimeout(() => resolve(), 2000)\n      this.process?.on('error', (err) => {\n        clearTimeout(timeout)\n        reject(err)\n      })\n      this.process?.on('exit', (code) => {\n        clearTimeout(timeout)\n        if (code !== 0) {\n          reject(new Error(`PythonInferenceEngine: process exited early with code ${code}`))\n        }\n      })\n    })\n  }\n\n  private _tryReceive(): void {\n    // Binary IPC: [4 bytes LE uint32 length][JSON bytes]\n    if (this.receiveBuffer.length < 4) return\n\n    const length = this.receiveBuffer.readUInt32LE(0)\n    if (this.receiveBuffer.length < 4 + length) return\n\n    const jsonBytes = this.receiveBuffer.subarray(4, 4 + length)\n    this.receiveBuffer = this.receiveBuffer.subarray(4 + length)\n\n    const resolve = this.pendingResolve\n    const reject = this.pendingReject\n    this.pendingResolve = null\n    this.pendingReject = null\n\n    if (!resolve) return\n\n    try {\n      const parsed = JSON.parse(jsonBytes.toString('utf8')) as Record<string, unknown>\n      resolve(parsed)\n    } catch (err) {\n      reject?.(err instanceof Error ? err : new Error(String(err)))\n    }\n  }\n\n  /** Send JPEG buffer, receive JSON detection results */\n  async runJpeg(jpeg: Buffer): Promise<Record<string, unknown>> {\n    if (!this.process?.stdin) {\n      throw new Error('PythonInferenceEngine: process not initialized')\n    }\n\n    return new Promise<Record<string, unknown>>((resolve, reject) => {\n      this.pendingResolve = resolve\n      this.pendingReject = reject\n\n      // Binary IPC: [4 bytes LE uint32 length][JPEG bytes]\n      const lengthBuf = Buffer.allocUnsafe(4)\n      lengthBuf.writeUInt32LE(jpeg.length, 0)\n      this.process!.stdin!.write(Buffer.concat([lengthBuf, jpeg]))\n    })\n  }\n\n  /** IInferenceEngine.run — wraps runJpeg for compatibility */\n  async run(_input: Float32Array, _inputShape: readonly number[]): Promise<Float32Array> {\n    throw new Error(\n      'PythonInferenceEngine: use runJpeg() directly — this engine operates on JPEG input',\n    )\n  }\n\n  /** IInferenceEngine.runMultiOutput — not supported by Python engine (operates on JPEG input) */\n  async runMultiOutput(\n    _input: Float32Array,\n    _inputShape: readonly number[],\n  ): Promise<Record<string, Float32Array>> {\n    throw new Error(\n      'PythonInferenceEngine: runMultiOutput() is not supported — this engine operates on JPEG input',\n    )\n  }\n\n  async dispose(): Promise<void> {\n    if (this.process) {\n      this.process.stdin?.end()\n      this.process.kill('SIGTERM')\n      this.process = null\n    }\n  }\n}\n\n/**\n * Resolve Python binary for ML inference. Priority:\n * 1. Explicit config pythonPath\n * 2. Embedded (data/deps/python/bin/python3)\n * 3. System PATH (python3, python)\n * 4. Download standalone Python\n *\n * Returns null if Python is not available.\n */\nexport async function resolvePythonBinary(\n  configPath: string | undefined,\n  deps: IAddonDepsManager,\n): Promise<string | null> {\n  if (configPath) return configPath\n  return deps.ensurePython()\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;;;ACCA,mBAA2B;AAE3B,IAAM,UAAU;AAEhB,IAAM,KAAK,CAACA,cAAiB,yBAAW,SAASA,KAAI;AAErD,IAAM,iBAA6C;AAAA,EACjD,EAAE,IAAI,gBAAgB,MAAM,eAAe;AAC7C;AAEO,IAAM,sBAAoD;AAAA,EAC/D;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,aAAa;AAAA,IACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAI;AAAA,IACrC,oBAAoB;AAAA,IACpB,QAAQ;AAAA,IACR,SAAS;AAAA,MACP,MAAM,EAAE,KAAK,GAAG,iFAAiF,GAAG,QAAQ,IAAI;AAAA,MAChH,QAAQ;AAAA,QACN,KAAK,GAAG,wFAAwF;AAAA,QAChG,QAAQ;AAAA,QACR,aAAa;AAAA,QACb,OAAO,CAAC,iBAAiB,uCAAuC,0CAA0C;AAAA,QAC1G,UAAU,CAAC,QAAQ;AAAA,MACrB;AAAA,IACF;AAAA,IACA,YAAY;AAAA,MACV;AAAA,QACE,KAAK,GAAG,sEAAsE;AAAA,QAC9E,UAAU;AAAA,QACV,QAAQ;AAAA,MACV;AAAA,IACF;AAAA,EACF;AACF;;;ACrCA,mBAAkB;AAelB,eAAsB,WAAW,MAAc,KAAmC;AAChF,aAAO,aAAAC,SAAM,IAAI,EACd,QAAQ;AAAA,IACP,MAAM,KAAK,MAAM,IAAI,CAAC;AAAA,IACtB,KAAK,KAAK,MAAM,IAAI,CAAC;AAAA,IACrB,OAAO,KAAK,MAAM,IAAI,CAAC;AAAA,IACvB,QAAQ,KAAK,MAAM,IAAI,CAAC;AAAA,EAC1B,CAAC,EACA,KAAK,EACL,SAAS;AACd;AAoDA,eAAsB,mBACpB,MACA,aACA,cACA,eACA,QACuB;AACvB,QAAM,EAAE,KAAK,IAAI,UAAM,aAAAC,SAAM,IAAI,EAC9B,OAAO,aAAa,cAAc,EAAE,KAAK,OAAO,CAAC,EACjD,YAAY,EACZ,IAAI,EACJ,SAAS,EAAE,mBAAmB,KAAK,CAAC;AAEvC,QAAM,YAAY,cAAc;AAChC,QAAM,UAAU,IAAI,aAAa,IAAI,SAAS;AAG9C,QAAM,OAAO,CAAC,OAAO,OAAO,KAAK;AACjC,QAAM,MAAM,CAAC,OAAO,OAAO,KAAK;AAEhC,MAAI,WAAW,QAAQ;AACrB,aAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,YAAM,UAAU,IAAI;AACpB,eAAS,IAAI,GAAG,IAAI,GAAG,KAAK;AAC1B,cAAM,MAAM,KAAK,UAAU,CAAC,IAAK;AACjC,YAAI;AACJ,YAAI,kBAAkB,YAAY;AAChC,gBAAM;AAAA,QACR,WAAW,kBAAkB,YAAY;AACvC,iBAAO,MAAM,KAAK,CAAC,KAAM,IAAI,CAAC;AAAA,QAChC,OAAO;AACL,gBAAM,KAAK,UAAU,CAAC;AAAA,QACxB;AACA,gBAAQ,IAAI,YAAY,CAAC,IAAI;AAAA,MAC/B;AAAA,IACF;AAAA,EACF,OAAO;AAEL,aAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,YAAM,UAAU,IAAI;AACpB,eAAS,IAAI,GAAG,IAAI,GAAG,KAAK;AAC1B,cAAM,MAAM,KAAK,UAAU,CAAC,IAAK;AACjC,YAAI;AACJ,YAAI,kBAAkB,YAAY;AAChC,gBAAM;AAAA,QACR,WAAW,kBAAkB,YAAY;AACvC,iBAAO,MAAM,KAAK,CAAC,KAAM,IAAI,CAAC;AAAA,QAChC,OAAO;AACL,gBAAM,KAAK,UAAU,CAAC;AAAA,QACxB;AACA,gBAAQ,IAAI,IAAI,CAAC,IAAI;AAAA,MACvB;AAAA,IACF;AAAA,EACF;AAEA,SAAO;AACT;;;AC3GA,SAAoB;AACpB,IAAAC,QAAsB;;;AC1BtB,WAAsB;AAEtB,IAAM,sBAAwD;AAAA,EAC5D,KAAK;AAAA,EACL,QAAQ;AAAA,EACR,MAAM;AAAA,EACN,UAAU;AAAA,EACV,KAAK;AACP;AAEA,IAAM,oBAA+D;AAAA,EACnE,KAAK;AAAA,EACL,QAAQ;AAAA,EACR,MAAM;AAAA,EACN,UAAU;AACZ;AAEO,IAAM,sBAAN,MAAsD;AAAA,EAK3D,YACmB,WACA,SACjB;AAFiB;AACA;AAEjB,SAAK,SAAU,kBAAkB,OAAO,KAAK;AAAA,EAC/C;AAAA,EATS,UAA4B;AAAA,EAC5B;AAAA,EACD,UAAmB;AAAA,EAS3B,MAAM,aAA4B;AAChC,UAAM,MAAM,MAAM,OAAO,kBAAkB;AAC3C,UAAM,WAAW,oBAAoB,KAAK,OAAO,KAAK;AAGtD,UAAM,eAAoB,gBAAW,KAAK,SAAS,IAC/C,KAAK,YACA,aAAQ,QAAQ,IAAI,GAAG,KAAK,SAAS;AAE9C,UAAM,iBAA0C;AAAA,MAC9C,oBAAoB,CAAC,QAAQ;AAAA,IAC/B;AAGA,SAAK,UAAU,MAAO,IAAY,iBAAiB,OAAO,cAAc,cAAc;AAAA,EACxF;AAAA,EAEA,MAAM,IAAI,OAAqB,YAAsD;AACnF,QAAI,CAAC,KAAK,SAAS;AACjB,YAAM,IAAI,MAAM,qEAAgE;AAAA,IAClF;AAEA,UAAM,MAAM,MAAM,OAAO,kBAAkB;AAE3C,UAAM,OAAO,KAAK;AAGlB,UAAM,YAAoB,KAAK,WAAW,CAAC;AAE3C,UAAM,SAAS,IAAK,IAAY,OAAO,WAAW,OAAO,CAAC,GAAG,UAAU,CAAC;AACxE,UAAM,QAAiC,EAAE,CAAC,SAAS,GAAG,OAAO;AAE7D,UAAM,UAAU,MAAM,KAAK,IAAI,KAAK;AACpC,UAAM,aAAqB,KAAK,YAAY,CAAC;AAC7C,UAAM,eAAe,QAAQ,UAAU;AAEvC,WAAO,aAAa;AAAA,EACtB;AAAA,EAEA,MAAM,eACJ,OACA,YACuC;AACvC,QAAI,CAAC,KAAK,SAAS;AACjB,YAAM,IAAI,MAAM,qEAAgE;AAAA,IAClF;AAEA,UAAM,MAAM,MAAM,OAAO,kBAAkB;AAE3C,UAAM,OAAO,KAAK;AAElB,UAAM,YAAoB,KAAK,WAAW,CAAC;AAE3C,UAAM,SAAS,IAAK,IAAY,OAAO,WAAW,OAAO,CAAC,GAAG,UAAU,CAAC;AACxE,UAAM,QAAiC,EAAE,CAAC,SAAS,GAAG,OAAO;AAE7D,UAAM,UAAU,MAAM,KAAK,IAAI,KAAK;AAEpC,UAAM,MAAoC,CAAC;AAC3C,eAAW,QAAQ,KAAK,aAAyB;AAC/C,UAAI,IAAI,IAAI,QAAQ,IAAI,EAAE;AAAA,IAC5B;AACA,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,UAAyB;AAG7B,SAAK,UAAU;AAAA,EACjB;AACF;;;ACnGA,gCAAyC;AAElC,IAAM,wBAAN,MAAwD;AAAA,EAQ7D,YACmB,YACA,YACjB,SACiB,WACA,YAA+B,CAAC,GACjD;AALiB;AACA;AAEA;AACA;AAEjB,SAAK,UAAU;AAEf,UAAM,mBAAwE;AAAA,MAC5E,MAAM;AAAA,MACN,QAAQ;AAAA,MACR,SAAS;AAAA,MACT,UAAU;AAAA,MACV,QAAQ;AAAA,IACV;AACA,SAAK,SAAS,iBAAiB,OAAO;AAAA,EACxC;AAAA,EAxBS;AAAA,EACA;AAAA,EACD,UAA+B;AAAA,EAC/B,gBAAwB,OAAO,MAAM,CAAC;AAAA,EACtC,iBAAoE;AAAA,EACpE,gBAAkD;AAAA,EAqB1D,MAAM,aAA4B;AAChC,UAAM,OAAO,CAAC,KAAK,YAAY,KAAK,WAAW,GAAG,KAAK,SAAS;AAChE,SAAK,cAAU,iCAAM,KAAK,YAAY,MAAM;AAAA,MAC1C,OAAO,CAAC,QAAQ,QAAQ,MAAM;AAAA,IAChC,CAAC;AAED,QAAI,CAAC,KAAK,QAAQ,UAAU,CAAC,KAAK,QAAQ,OAAO;AAC/C,YAAM,IAAI,MAAM,uDAAuD;AAAA,IACzE;AAEA,SAAK,QAAQ,QAAQ,GAAG,QAAQ,CAAC,UAAkB;AAEjD,cAAQ,OAAO,MAAM,mBAAmB,MAAM,SAAS,CAAC,EAAE;AAAA,IAC5D,CAAC;AAED,SAAK,QAAQ,GAAG,SAAS,CAAC,QAAQ;AAChC,WAAK,gBAAgB,GAAG;AACxB,WAAK,gBAAgB;AACrB,WAAK,iBAAiB;AAAA,IACxB,CAAC;AAED,SAAK,QAAQ,GAAG,QAAQ,CAAC,SAAS;AAChC,UAAI,SAAS,GAAG;AACd,cAAM,MAAM,IAAI,MAAM,mDAAmD,IAAI,EAAE;AAC/E,aAAK,gBAAgB,GAAG;AACxB,aAAK,gBAAgB;AACrB,aAAK,iBAAiB;AAAA,MACxB;AAAA,IACF,CAAC;AAED,SAAK,QAAQ,OAAO,GAAG,QAAQ,CAAC,UAAkB;AAChD,WAAK,gBAAgB,OAAO,OAAO,CAAC,KAAK,eAAe,KAAK,CAAC;AAC9D,WAAK,YAAY;AAAA,IACnB,CAAC;AAGD,UAAM,IAAI,QAAc,CAACC,UAAS,WAAW;AAC3C,YAAM,UAAU,WAAW,MAAMA,SAAQ,GAAG,GAAI;AAChD,WAAK,SAAS,GAAG,SAAS,CAAC,QAAQ;AACjC,qBAAa,OAAO;AACpB,eAAO,GAAG;AAAA,MACZ,CAAC;AACD,WAAK,SAAS,GAAG,QAAQ,CAAC,SAAS;AACjC,qBAAa,OAAO;AACpB,YAAI,SAAS,GAAG;AACd,iBAAO,IAAI,MAAM,yDAAyD,IAAI,EAAE,CAAC;AAAA,QACnF;AAAA,MACF,CAAC;AAAA,IACH,CAAC;AAAA,EACH;AAAA,EAEQ,cAAoB;AAE1B,QAAI,KAAK,cAAc,SAAS,EAAG;AAEnC,UAAM,SAAS,KAAK,cAAc,aAAa,CAAC;AAChD,QAAI,KAAK,cAAc,SAAS,IAAI,OAAQ;AAE5C,UAAM,YAAY,KAAK,cAAc,SAAS,GAAG,IAAI,MAAM;AAC3D,SAAK,gBAAgB,KAAK,cAAc,SAAS,IAAI,MAAM;AAE3D,UAAMA,WAAU,KAAK;AACrB,UAAM,SAAS,KAAK;AACpB,SAAK,iBAAiB;AACtB,SAAK,gBAAgB;AAErB,QAAI,CAACA,SAAS;AAEd,QAAI;AACF,YAAM,SAAS,KAAK,MAAM,UAAU,SAAS,MAAM,CAAC;AACpD,MAAAA,SAAQ,MAAM;AAAA,IAChB,SAAS,KAAK;AACZ,eAAS,eAAe,QAAQ,MAAM,IAAI,MAAM,OAAO,GAAG,CAAC,CAAC;AAAA,IAC9D;AAAA,EACF;AAAA;AAAA,EAGA,MAAM,QAAQ,MAAgD;AAC5D,QAAI,CAAC,KAAK,SAAS,OAAO;AACxB,YAAM,IAAI,MAAM,gDAAgD;AAAA,IAClE;AAEA,WAAO,IAAI,QAAiC,CAACA,UAAS,WAAW;AAC/D,WAAK,iBAAiBA;AACtB,WAAK,gBAAgB;AAGrB,YAAM,YAAY,OAAO,YAAY,CAAC;AACtC,gBAAU,cAAc,KAAK,QAAQ,CAAC;AACtC,WAAK,QAAS,MAAO,MAAM,OAAO,OAAO,CAAC,WAAW,IAAI,CAAC,CAAC;AAAA,IAC7D,CAAC;AAAA,EACH;AAAA;AAAA,EAGA,MAAM,IAAI,QAAsB,aAAuD;AACrF,UAAM,IAAI;AAAA,MACR;AAAA,IACF;AAAA,EACF;AAAA;AAAA,EAGA,MAAM,eACJ,QACA,aACuC;AACvC,UAAM,IAAI;AAAA,MACR;AAAA,IACF;AAAA,EACF;AAAA,EAEA,MAAM,UAAyB;AAC7B,QAAI,KAAK,SAAS;AAChB,WAAK,QAAQ,OAAO,IAAI;AACxB,WAAK,QAAQ,KAAK,SAAS;AAC3B,WAAK,UAAU;AAAA,IACjB;AAAA,EACF;AACF;;;AFnGA,IAAM,wBAAwB,CAAC,UAAU,QAAQ,YAAY,KAAK;AAMlE,IAAM,oBAA2D;AAAA,EAC/D,KAAK;AAAA,EACL,QAAQ;AAAA,EACR,MAAM;AAAA,EACN,UAAU;AACZ;AAGA,IAAM,oBAA8E;AAAA,EAClF,MAAM;AAAA,EACN,QAAQ;AAAA,EACR,UAAU;AAAA,EACV,QAAQ;AAAA,EACR,SAAS;AACX;AAEA,SAAS,cAAc,WAAmB,YAA+B,QAA6B;AACpG,QAAM,cAAc,WAAW,QAAQ,MAAM;AAC7C,MAAI,CAAC,aAAa;AAChB,UAAM,IAAI,MAAM,SAAS,WAAW,EAAE,WAAW,MAAM,SAAS;AAAA,EAClE;AAEA,QAAM,WAAW,YAAY,IAAI,MAAM,GAAG;AAC1C,QAAM,WAAW,SAAS,SAAS,SAAS,CAAC,KAAK,GAAG,WAAW,EAAE,IAAI,MAAM;AAC5E,SAAY,WAAK,WAAW,QAAQ;AACtC;AAEA,SAAS,YAAY,UAA2B;AAC9C,MAAI;AACF,WAAU,cAAW,QAAQ;AAAA,EAC/B,QAAQ;AACN,WAAO;AAAA,EACT;AACF;AAEA,eAAsB,cAAc,SAAyD;AAC3F,QAAM,EAAE,SAAS,SAAS,YAAY,WAAW,OAAO,IAAI;AAE5D,MAAI;AACJ,MAAI;AAEJ,MAAI,YAAY,QAAQ;AAEtB,UAAM,YAAY,MAAM,kBAAkB;AAG1C,QAAI,SAA0D;AAE9D,eAAW,KAAK,uBAAuB;AACrC,UAAI,CAAC,UAAU,SAAS,CAAC,EAAG;AAC5B,YAAM,MAAM,kBAAkB,CAAC;AAC/B,UAAI,CAAC,IAAK;AACV,UAAI,CAAC,WAAW,QAAQ,GAAG,EAAG;AAC9B,eAAS,EAAE,SAAS,GAAG,QAAQ,IAAI;AACnC;AAAA,IACF;AAEA,QAAI,CAAC,QAAQ;AACX,YAAM,IAAI;AAAA,QACR,wDAAwD,WAAW,EAAE,yBAAyB,UAAU,KAAK,IAAI,CAAC;AAAA,MACpH;AAAA,IACF;AAEA,qBAAiB,OAAO;AACxB,sBAAkB,OAAO;AAAA,EAC3B,OAAO;AAEL,UAAM,MAAM,kBAAkB,OAAO;AACrC,QAAI,CAAC,KAAK;AACR,YAAM,IAAI,MAAM,uCAAuC,OAAO,GAAG;AAAA,IACnE;AACA,QAAI,CAAC,WAAW,QAAQ,GAAG,GAAG;AAC5B,YAAM,IAAI;AAAA,QACR,wBAAwB,WAAW,EAAE,WAAW,GAAG,uBAAuB,OAAO;AAAA,MACnF;AAAA,IACF;AACA,qBAAiB;AAEjB,sBAAkB,YAAY,SAAU,WAAW,QAAS;AAAA,EAC9D;AAGA,MAAI;AAEJ,MAAI,QAAQ;AAEV,gBAAY,MAAM,OAAO,OAAO,WAAW,IAAI,cAAc;AAAA,EAC/D,OAAO;AAEL,gBAAY,cAAc,WAAW,YAAY,cAAc;AAC/D,QAAI,CAAC,YAAY,SAAS,GAAG;AAC3B,YAAM,IAAI;AAAA,QACR,0CAA0C,SAAS;AAAA,MACrD;AAAA,IACF;AAAA,EACF;AAIA,MAAI,mBAAmB,QAAQ;AAC7B,UAAM,SAAS,IAAI,oBAAoB,WAAW,eAAe;AACjE,UAAM,OAAO,WAAW;AACxB,WAAO,EAAE,QAAQ,QAAQ,gBAAgB,UAAU;AAAA,EACrD;AAGA,QAAM,EAAE,WAAW,IAAI;AACvB,QAAM,oBAAsD;AAAA,IAC1D,QAAQ;AAAA,IACR,SAAS;AAAA,IACT,UAAU;AAAA,EACZ;AAEA,QAAM,mBAAmB,YAAY,SAAS,kBAAkB;AAChE,QAAM,aAAa,kBAAkB,gBAAgB;AAErD,MAAI,cAAc,YAAY;AAK5B,UAAM,aAAa;AAAA,MACZ,WAAK,WAAW,gBAAgB,UAAU;AAAA,MAC1C,WAAK,WAAW,aAAa,UAAU;AAAA,MACvC,WAAK,WAAW,mBAAmB,UAAU;AAAA,IACpD;AACA,UAAM,aAAa,WAAW,KAAK,OAAQ,cAAW,CAAC,CAAC;AACxD,QAAI,CAAC,YAAY;AACf,YAAM,IAAI;AAAA,QACR,iCAAiC,UAAU;AAAA,EAA2B,WAAW,KAAK,IAAI,CAAC;AAAA,MAC7F;AAAA,IACF;AACA,UAAM,YAAY,KAAK,IAAI,WAAW,UAAU,OAAO,WAAW,UAAU,MAAM;AAClF,UAAM,SAAS,IAAI,sBAAsB,YAAY,YAAY,kBAAsC,WAAW;AAAA,MAChH,gBAAgB,SAAS;AAAA,MACzB;AAAA,IACF,CAAC;AACD,UAAM,OAAO,WAAW;AACxB,WAAO,EAAE,QAAQ,QAAQ,gBAAgB,UAAU;AAAA,EACrD;AAGA,QAAM,eAAe,cAAc,WAAW,YAAY,MAAM;AAChE,MAAI,WAAW,QAAQ,MAAM,KAAK,YAAY,YAAY,GAAG;AAC3D,UAAM,SAAS,IAAI,oBAAoB,cAAc,KAAK;AAC1D,UAAM,OAAO,WAAW;AACxB,WAAO,EAAE,QAAQ,QAAQ,QAAQ,WAAW,aAAa;AAAA,EAC3D;AAEA,QAAM,IAAI;AAAA,IACR,yBAAyB,cAAc;AAAA,EAEzC;AACF;AAGA,eAAsB,oBAAuC;AAC3D,QAAM,YAAsB,CAAC,KAAK;AAElC,MAAI;AACF,UAAM,MAAM,MAAM,OAAO,kBAAkB;AAE3C,UAAM,YAAuB,IAAY,KAAK,OAAO,aAAa,SAE5D,IAAY,kBAAkB,wBAAwB,KAAK,CAAC,IAC9D,CAAC;AAEL,eAAW,KAAK,WAAW;AACzB,YAAM,aAAa,EAAE,YAAY,EAAE,QAAQ,qBAAqB,EAAE;AAClE,UAAI,eAAe,SAAU,WAAU,KAAK,QAAQ;AAAA,eAC3C,eAAe,OAAQ,WAAU,KAAK,MAAM;AAAA,eAC5C,eAAe,WAAY,WAAU,KAAK,UAAU;AAAA,IAC/D;AAAA,EACF,QAAQ;AAAA,EAER;AAGA,MAAI,QAAQ,aAAa,YAAY,CAAC,UAAU,SAAS,QAAQ,GAAG;AAClE,cAAU,KAAK,QAAQ;AAAA,EACzB;AAEA,SAAO,CAAC,GAAG,IAAI,IAAI,SAAS,CAAC;AAC/B;;;AHzNA,IAAAC,MAAoB;AACpB,IAAAC,QAAsB;AAEtB,IAAM,qBAAsC,EAAE,IAAI,gBAAgB,MAAM,eAAe;AACvF,IAAM,sBAAkD,CAAC,kBAAkB;AAC3E,IAAM,oBAAwC,EAAE,SAAS,CAAC,GAAG,kBAAkB,KAAK;AAGpF,SAAS,WAAW,WAAmB,SAAoC;AACzE,QAAM,aAAa;AAAA,IACjB,YAAY,OAAO;AAAA,IACnB;AAAA,EACF;AACA,aAAW,QAAQ,YAAY;AAC7B,UAAM,YAAiB,WAAK,WAAW,IAAI;AAC3C,QAAO,eAAW,SAAS,GAAG;AAC5B,YAAM,MAAS,iBAAa,WAAW,OAAO;AAC9C,aAAO,KAAK,MAAM,GAAG;AAAA,IACvB;AAAA,EACF;AACA,QAAM,IAAI,MAAM,oDAAoD,SAAS,EAAE;AACjF;AAEA,SAAS,QAAQ,QAAoC;AACnD,QAAM,MAAM,OAAO,OAAO,CAAC,GAAG,MAAM,KAAK,IAAI,GAAG,CAAC,GAAG,SAAS;AAC7D,QAAM,OAAO,OAAO,IAAI,CAAC,MAAM,KAAK,IAAI,IAAI,GAAG,CAAC;AAChD,QAAM,MAAM,KAAK,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC;AAC1C,SAAO,KAAK,IAAI,CAAC,MAAM,IAAI,GAAG;AAChC;AAEA,IAAqB,yBAArB,MAA4F;AAAA,EACjF,KAAK;AAAA,EACL,OAAO;AAAA,EACP,eAAe,CAAC,SAAS;AAAA,EACzB,gBAAgB,CAAC,gBAAgB;AAAA,EACjC,eAAe;AAAA,EACf,gBAAgB,CAAC;AAAA,EACjB,WAA0B;AAAA,IACjC,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,SAAS;AAAA,IAET,aAAa;AAAA,IAEb,MAAM;AAAA,IACN,iBAAiB;AAAA,IACjB,cAAc,CAAC,SAAS;AAAA,IACxB,eAAe,CAAC,gBAAgB;AAAA,IAChC,sBAAsB;AAAA,IACtB,kBAAkB;AAAA,IAClB,eAAe;AAAA,MACb,SAAS;AAAA,MACT,SAAS;AAAA,MACT,SAAS;AAAA,MACT,YAAY;AAAA;AAAA,MACZ,eAAe;AAAA,IACjB;AAAA,EACF;AAAA,EAEQ,SAAkC;AAAA,EAClC;AAAA,EACA,SAA4B,CAAC;AAAA,EAC7B,gBAAgB;AAAA,EAChB,iBAAiD;AAAA,EACjD,MAA2B;AAAA,EAEnC,uBAA2C;AACzC,WAAO,oBAAoB,IAAI,CAAC,OAAO;AAAA,MACrC,SAAS,EAAE;AAAA,MACX,MAAM,EAAE;AAAA,MACR,WAAW;AAAA,MACX,eAAe;AAAA,MACf,SAAS,OAAO,KAAK,EAAE,OAAO;AAAA,IAChC,EAAE;AAAA,EACJ;AAAA,EAEA,UAAU,QAAuC;AAC/C,SAAK,iBAAiB;AAAA,EACxB;AAAA,EAEA,MAAM,WAAW,KAAkC;AACjD,SAAK,MAAM;AACX,UAAM,MAAM,IAAI;AAChB,UAAM,UAAW,IAAI,SAAS,KAA4B,KAAK,gBAAgB,WAAW;AAC1F,SAAK,gBAAiB,IAAI,eAAe,KAA4B;AAErE,UAAM,QAAQ,oBAAoB,KAAK,CAAC,MAAM,EAAE,OAAO,OAAO;AAC9D,QAAI,CAAC,OAAO;AACV,YAAM,IAAI,MAAM,4CAA4C,OAAO,GAAG;AAAA,IACxE;AACA,SAAK,aAAa;AAAA,EACpB;AAAA,EAEA,MAAM,SAAS,OAA6C;AAC1D,QAAI,CAAC,KAAK,OAAQ,OAAM,KAAK,aAAa;AAC1C,UAAM,QAAQ,KAAK,IAAI;AACvB,UAAM,EAAE,OAAO,QAAQ,QAAQ,OAAO,IAAI,KAAK,WAAW;AAG1D,UAAM,cAAc,MAAM,WAAW,MAAM,MAAM,MAAM,MAAM,GAAG;AAGhE,UAAM,aAAa,MAAM,mBAAmB,aAAa,QAAQ,QAAQ,YAAY,MAAM;AAG3F,UAAM,YAAY,MAAM,KAAK,OAAQ,IAAI,YAAY,CAAC,GAAG,GAAG,QAAQ,MAAM,CAAC;AAE3E,YAAQ,IAAI,sCAAsC,UAAU,MAAM,aAAa,KAAK,OAAO,MAAM,mBAAmB,MAAM,KAAK,UAAU,MAAM,GAAG,CAAC,CAAC,EAAE,IAAI,OAAK,EAAE,QAAQ,CAAC,CAAC,EAAE,KAAK,IAAI,CAAC,GAAG;AAG1L,UAAM,QAAQ,QAAQ,SAAS;AAG/B,UAAM,UAAU,MAAM,KAAK,KAAK,EAAE,IAAI,CAAC,GAAG,OAAO,EAAE,OAAO,GAAG,KAAK,EAAE,EAAE;AACtE,YAAQ,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK;AACxC,UAAM,OAAO,QAAQ,MAAM,GAAG,CAAC;AAC/B,YAAQ,IAAI,8BAA8B,KAAK,IAAI,OAAK,GAAG,KAAK,OAAO,EAAE,GAAG,KAAK,EAAE,GAAG,KAAK,EAAE,QAAQ,KAAK,QAAQ,CAAC,CAAC,GAAG,EAAE,KAAK,IAAI,CAAC,EAAE;AAGrI,UAAM,SAAS,KAAK,CAAC,GAAG,OAAO;AAC/B,UAAM,WAAW,KAAK,CAAC,GAAG,SAAS;AAEnC,QAAI,WAAW,KAAK,eAAe;AACjC,cAAQ,IAAI,oDAAoD,WAAW,KAAK,QAAQ,CAAC,CAAC,QAAQ,KAAK,gBAAgB,KAAK,QAAQ,CAAC,CAAC,GAAG;AACzI,aAAO;AAAA,QACL,iBAAiB,CAAC;AAAA,QAClB,aAAa,KAAK,IAAI,IAAI;AAAA,QAC1B,SAAS,KAAK,WAAW;AAAA,MAC3B;AAAA,IACF;AAEA,UAAM,QAAQ,KAAK,OAAO,MAAM,KAAK,gBAAgB,MAAM;AAC3D,YAAQ,IAAI,+BAA+B,KAAK,MAAM,WAAW,KAAK,QAAQ,CAAC,CAAC,IAAI;AAEpF,WAAO;AAAA,MACL,iBAAiB;AAAA,QACf;AAAA,UACE,OAAO;AAAA,UACP,OAAO;AAAA,QACT;AAAA,MACF;AAAA,MACA,aAAa,KAAK,IAAI,IAAI;AAAA,MAC1B,SAAS,KAAK,WAAW;AAAA,IAC3B;AAAA,EACF;AAAA,EAEA,MAAc,eAA8B;AAC1C,UAAM,SAAS,KAAK;AACpB,UAAM,UAAU,QAAQ,WAAW,KAAK,WAAW;AACnD,UAAM,UAAU,QAAQ,YAAY,WAAW,WAAY,QAAQ,YAAY,SAAS,SAAS;AACjG,UAAM,UAAU,QAAQ,WAAW;AACnC,UAAM,SAAS,QAAQ,UAAU;AAEjC,UAAM,QAAQ,oBAAoB,KAAK,CAAC,MAAM,EAAE,OAAO,OAAO,KAAK,KAAK;AACxE,SAAK,aAAa;AAElB,UAAM,YAAY,KAAK,IAAK,QAAQ,aAAa,KAAK,KAAK,IAAK,cAAc;AAG9E,QAAI,KAAK,IAAK,QAAQ;AACpB,YAAM,KAAK,IAAK,OAAO,OAAO,SAAS,MAAa;AAAA,IACtD;AAGA,SAAK,SAAS,WAAW,WAAW,OAAO;AAE3C,UAAM,WAAW,MAAM,cAAc;AAAA,MACnC;AAAA,MACA;AAAA,MACA,YAAY;AAAA,MACZ;AAAA,MACA,QAAQ,KAAK,IAAK;AAAA,IACpB,CAAC;AACD,SAAK,SAAS,SAAS;AAAA,EACzB;AAAA,EAEA,MAAM,WAA0B;AAC9B,UAAM,KAAK,QAAQ,QAAQ;AAAA,EAC7B;AAAA,EAEA,kBAAkC;AAChC,WAAO;AAAA,MACL,UAAU;AAAA,QACR;AAAA,UACE,IAAI;AAAA,UACJ,OAAO;AAAA,UACP,SAAS;AAAA,UACT,QAAQ;AAAA,YACN;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,SAAS,CAAC,GAAG,mBAAmB;AAAA,cAChC,aAAa;AAAA,cACb,iBAAiB;AAAA,cACjB,eAAe,CAAC,QAAQ,UAAU,UAAU;AAAA,cAC5C,kBAAkB,CAAC,aAAa,QAAQ;AAAA,cACxC,kBAAkB;AAAA,YACpB;AAAA,UACF;AAAA,QACF;AAAA,QACA;AAAA,UACE,IAAI;AAAA,UACJ,OAAO;AAAA,UACP,SAAS;AAAA,UACT,QAAQ;AAAA,YACN;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,SAAS;AAAA,gBACP,EAAE,OAAO,QAAQ,OAAO,OAAO;AAAA,gBAC/B,EAAE,OAAO,QAAQ,OAAO,eAAe;AAAA,gBACvC,EAAE,OAAO,UAAU,OAAO,iBAAiB;AAAA,gBAC3C,EAAE,OAAO,YAAY,OAAO,mBAAmB;AAAA,cACjD;AAAA,YACF;AAAA,YACA;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,UAAU,EAAE,OAAO,WAAW,QAAQ,OAAO;AAAA,cAC7C,SAAS;AAAA,gBACP,EAAE,OAAO,QAAQ,OAAO,OAAO;AAAA,gBAC/B,EAAE,OAAO,OAAO,OAAO,MAAM;AAAA,gBAC7B,EAAE,OAAO,UAAU,OAAO,SAAS;AAAA,gBACnC,EAAE,OAAO,QAAQ,OAAO,gBAAgB;AAAA,cAC1C;AAAA,YACF;AAAA,UACF;AAAA,QACF;AAAA,QACA;AAAA,UACE,IAAI;AAAA,UACJ,OAAO;AAAA,UACP,SAAS;AAAA,UACT,QAAQ;AAAA,YACN;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,KAAK;AAAA,cACL,KAAK;AAAA,cACL,MAAM;AAAA,cACN,SAAS;AAAA,YACX;AAAA,UACF;AAAA,QACF;AAAA,MACF;AAAA,IACF;AAAA,EACF;AAAA,EAEA,cAAkC;AAChC,WAAO;AAAA,EACT;AAAA,EAEA,kBAAuC;AACrC,WAAO,CAAC,GAAG,mBAAmB;AAAA,EAChC;AAAA,EAEA,qBAAuC;AACrC,WAAO,CAAC;AAAA,EACV;AAAA,EAEA,kBAA8C;AAC5C,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,QAA8B;AAClC,WAAO;AAAA,MACL,WAAW;AAAA,MACX,SAAS,KAAK,QAAQ,WAAW;AAAA,MACjC,QAAQ,KAAK,QAAQ,UAAU;AAAA,MAC/B,cAAc,CAAC,MAAM;AAAA,IACvB;AAAA,EACF;AACF;","names":["path","sharp","sharp","path","resolve","fs","path"]}

package/dist/addons/vehicle-classifier/index.mjs

@@ -0,0 +1,250 @@
+import {
+  VEHICLE_TYPE_MODELS
+} from "../../chunk-XZ6ZMXXU.mjs";
+import {
+  cropRegion,
+  resizeAndNormalize
+} from "../../chunk-22BHCDT5.mjs";
+import {
+  resolveEngine
+} from "../../chunk-2IOKI4ES.mjs";
+import "../../chunk-BJTO5JO5.mjs";
+
+// src/addons/vehicle-classifier/index.ts
+import * as fs from "fs";
+import * as path from "path";
+var VEHICLE_TYPE_LABEL = { id: "vehicle-type", name: "Vehicle Type" };
+var VEHICLE_TYPE_LABELS = [VEHICLE_TYPE_LABEL];
+var VEHICLE_CLASS_MAP = { mapping: {}, preserveOriginal: true };
+function loadLabels(modelsDir, modelId) {
+  const labelNames = [
+    `camstack-${modelId}-labels.json`,
+    `camstack-vehicle-type-labels.json`
+  ];
+  for (const name of labelNames) {
+    const labelPath = path.join(modelsDir, name);
+    if (fs.existsSync(labelPath)) {
+      const raw = fs.readFileSync(labelPath, "utf-8");
+      return JSON.parse(raw);
+    }
+  }
+  throw new Error(`VehicleClassifierAddon: labels JSON not found in ${modelsDir}`);
+}
+function softmax(logits) {
+  const max = logits.reduce((a, b) => Math.max(a, b), -Infinity);
+  const exps = logits.map((v) => Math.exp(v - max));
+  const sum = exps.reduce((a, b) => a + b, 0);
+  return exps.map((v) => v / sum);
+}
+var VehicleClassifierAddon = class {
+  id = "vehicle-classifier";
+  slot = "classifier";
+  inputClasses = ["vehicle"];
+  outputClasses = ["vehicle-type:*"];
+  slotPriority = 0;
+  requiredSteps = [];
+  manifest = {
+    id: "vehicle-classifier",
+    name: "Vehicle Classifier",
+    version: "0.1.0",
+    description: "EfficientNet-B4 \u2014 8,949 vehicle make/model/year classes from VMMRdb",
+    slot: "classifier",
+    labelOutputType: "classification",
+    inputClasses: ["vehicle"],
+    outputClasses: ["vehicle-type:*"],
+    supportsCustomModels: false,
+    mayRequirePython: false,
+    defaultConfig: {
+      modelId: "vehicle-type-efficientnet",
+      runtime: "node",
+      backend: "cpu",
+      confidence: 0.05,
+      // Low pipeline threshold for 8949-class model
+      minConfidence: 0.05
+    }
+  };
+  engine = null;
+  modelEntry;
+  labels = [];
+  minConfidence = 0.05;
+  resolvedConfig = null;
+  ctx = null;
+  getModelRequirements() {
+    return VEHICLE_TYPE_MODELS.map((m) => ({
+      modelId: m.id,
+      name: m.name,
+      minRAM_MB: 120,
+      accuracyScore: 80,
+      formats: Object.keys(m.formats)
+    }));
+  }
+  configure(config) {
+    this.resolvedConfig = config;
+  }
+  async initialize(ctx) {
+    this.ctx = ctx;
+    const cfg = ctx.addonConfig;
+    const modelId = cfg["modelId"] ?? this.resolvedConfig?.modelId ?? "vehicle-type-efficientnet";
+    this.minConfidence = cfg["minConfidence"] ?? 0.05;
+    const entry = VEHICLE_TYPE_MODELS.find((m) => m.id === modelId);
+    if (!entry) {
+      throw new Error(`VehicleClassifierAddon: unknown modelId "${modelId}"`);
+    }
+    this.modelEntry = entry;
+  }
+  async classify(input) {
+    if (!this.engine) await this.ensureEngine();
+    const start = Date.now();
+    const { width: inputW, height: inputH } = this.modelEntry.inputSize;
+    const vehicleCrop = await cropRegion(input.frame.data, input.roi);
+    const normalized = await resizeAndNormalize(vehicleCrop, inputW, inputH, "imagenet", "nchw");
+    const rawOutput = await this.engine.run(normalized, [1, 3, inputH, inputW]);
+    console.log(`[VehicleClassifier] Output length: ${rawOutput.length}, labels: ${this.labels.length}, first 5 raw: [${Array.from(rawOutput.slice(0, 5)).map((v) => v.toFixed(3)).join(", ")}]`);
+    const probs = softmax(rawOutput);
+    const indexed = Array.from(probs).map((v, i) => ({ score: v, idx: i }));
+    indexed.sort((a, b) => b.score - a.score);
+    const top3 = indexed.slice(0, 3);
+    console.log(`[VehicleClassifier] Top-3: ${top3.map((t) => `${this.labels[t.idx] ?? t.idx}=${(t.score * 100).toFixed(1)}%`).join(", ")}`);
+    const maxIdx = top3[0]?.idx ?? 0;
+    const maxScore = top3[0]?.score ?? 0;
+    if (maxScore < this.minConfidence) {
+      console.log(`[VehicleClassifier] Below confidence threshold: ${(maxScore * 100).toFixed(1)}% < ${(this.minConfidence * 100).toFixed(0)}%`);
+      return {
+        classifications: [],
+        inferenceMs: Date.now() - start,
+        modelId: this.modelEntry.id
+      };
+    }
+    const label = this.labels[maxIdx] ?? `vehicle_type_${maxIdx}`;
+    console.log(`[VehicleClassifier] Result: ${label} (${(maxScore * 100).toFixed(1)}%)`);
+    return {
+      classifications: [
+        {
+          class: label,
+          score: maxScore
+        }
+      ],
+      inferenceMs: Date.now() - start,
+      modelId: this.modelEntry.id
+    };
+  }
+  async ensureEngine() {
+    const config = this.resolvedConfig;
+    const modelId = config?.modelId ?? this.modelEntry.id;
+    const runtime = config?.runtime === "python" ? "coreml" : config?.runtime === "node" ? "onnx" : "auto";
+    const backend = config?.backend ?? "cpu";
+    const format = config?.format ?? "onnx";
+    const entry = VEHICLE_TYPE_MODELS.find((m) => m.id === modelId) ?? this.modelEntry;
+    this.modelEntry = entry;
+    const modelsDir = this.ctx.models?.getModelsDir() ?? this.ctx.locationPaths.models;
+    if (this.ctx.models) {
+      await this.ctx.models.ensure(modelId, format);
+    }
+    this.labels = loadLabels(modelsDir, modelId);
+    const resolved = await resolveEngine({
+      runtime,
+      backend,
+      modelEntry: entry,
+      modelsDir,
+      models: this.ctx.models
+    });
+    this.engine = resolved.engine;
+  }
+  async shutdown() {
+    await this.engine?.dispose();
+  }
+  getConfigSchema() {
+    return {
+      sections: [
+        {
+          id: "model",
+          title: "Model",
+          columns: 1,
+          fields: [
+            {
+              key: "modelId",
+              label: "Model",
+              type: "model-selector",
+              catalog: [...VEHICLE_TYPE_MODELS],
+              allowCustom: false,
+              allowConversion: false,
+              acceptFormats: ["onnx", "coreml", "openvino"],
+              requiredMetadata: ["inputSize", "labels"],
+              outputFormatHint: "classification"
+            }
+          ]
+        },
+        {
+          id: "runtime",
+          title: "Runtime",
+          columns: 2,
+          fields: [
+            {
+              key: "runtime",
+              label: "Runtime",
+              type: "select",
+              options: [
+                { value: "auto", label: "Auto" },
+                { value: "onnx", label: "ONNX Runtime" },
+                { value: "coreml", label: "CoreML (Apple)" },
+                { value: "openvino", label: "OpenVINO (Intel)" }
+              ]
+            },
+            {
+              key: "backend",
+              label: "Backend",
+              type: "select",
+              showWhen: { field: "runtime", equals: "onnx" },
+              options: [
+                { value: "auto", label: "Auto" },
+                { value: "cpu", label: "CPU" },
+                { value: "coreml", label: "CoreML" },
+                { value: "cuda", label: "CUDA (NVIDIA)" }
+              ]
+            }
+          ]
+        },
+        {
+          id: "thresholds",
+          title: "Classification Settings",
+          columns: 1,
+          fields: [
+            {
+              key: "minConfidence",
+              label: "Minimum Confidence",
+              type: "slider",
+              min: 0.05,
+              max: 1,
+              step: 0.05,
+              default: 0.3
+            }
+          ]
+        }
+      ]
+    };
+  }
+  getClassMap() {
+    return VEHICLE_CLASS_MAP;
+  }
+  getModelCatalog() {
+    return [...VEHICLE_TYPE_MODELS];
+  }
+  getAvailableModels() {
+    return [];
+  }
+  getActiveLabels() {
+    return VEHICLE_TYPE_LABELS;
+  }
+  async probe() {
+    return {
+      available: true,
+      runtime: this.engine?.runtime ?? "onnx",
+      device: this.engine?.device ?? "cpu",
+      capabilities: ["fp32"]
+    };
+  }
+};
+export {
+  VehicleClassifierAddon as default
+};
+//# sourceMappingURL=index.mjs.map

package/dist/addons/vehicle-classifier/index.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../../../src/addons/vehicle-classifier/index.ts"],"sourcesContent":["import type {\n  IClassifierProvider,\n  IDetectionAddon,\n  AddonManifest,\n  AddonContext,\n  CropInput,\n  ClassifierOutput,\n  ConfigUISchema,\n  ClassMapDefinition,\n  ProbeResult,\n  ModelCatalogEntry,\n  DetectionModel,\n  LabelDefinition,\n  IInferenceEngine,\n  ModelRequirement,\n  ResolvedInferenceConfig,\n} from '@camstack/types'\nimport { VEHICLE_TYPE_MODELS } from '../../catalogs/vehicle-classification-models.js'\nimport { cropRegion, resizeAndNormalize } from '../../shared/image-utils.js'\nimport { resolveEngine } from '../../shared/engine-resolver.js'\nimport * as fs from 'node:fs'\nimport * as path from 'node:path'\n\nconst VEHICLE_TYPE_LABEL: LabelDefinition = { id: 'vehicle-type', name: 'Vehicle Type' }\nconst VEHICLE_TYPE_LABELS: readonly LabelDefinition[] = [VEHICLE_TYPE_LABEL]\nconst VEHICLE_CLASS_MAP: ClassMapDefinition = { mapping: {}, preserveOriginal: true }\n\n/** Load vehicle type labels from JSON file in modelsDir */\nfunction loadLabels(modelsDir: string, modelId: string): readonly string[] {\n  const labelNames = [\n    `camstack-${modelId}-labels.json`,\n    `camstack-vehicle-type-labels.json`,\n  ]\n  for (const name of labelNames) {\n    const labelPath = path.join(modelsDir, name)\n    if (fs.existsSync(labelPath)) {\n      const raw = fs.readFileSync(labelPath, 'utf-8')\n      return JSON.parse(raw) as string[]\n    }\n  }\n  throw new Error(`VehicleClassifierAddon: labels JSON not found in ${modelsDir}`)\n}\n\nfunction softmax(logits: Float32Array): Float32Array {\n  const max = logits.reduce((a, b) => Math.max(a, b), -Infinity)\n  const exps = logits.map((v) => Math.exp(v - max))\n  const sum = exps.reduce((a, b) => a + b, 0)\n  return exps.map((v) => v / sum) as unknown as Float32Array\n}\n\nexport default class VehicleClassifierAddon implements IClassifierProvider, IDetectionAddon {\n  readonly id = 'vehicle-classifier'\n  readonly slot = 'classifier' as const\n  readonly inputClasses = ['vehicle'] as const\n  readonly outputClasses = ['vehicle-type:*'] as const\n  readonly slotPriority = 0\n  readonly requiredSteps = [] as const\n  readonly manifest: AddonManifest = {\n    id: 'vehicle-classifier',\n    name: 'Vehicle Classifier',\n    version: '0.1.0',\n\n    description: 'EfficientNet-B4 — 8,949 vehicle make/model/year classes from VMMRdb',\n\n    slot: 'classifier',\n    labelOutputType: 'classification',\n    inputClasses: ['vehicle'],\n    outputClasses: ['vehicle-type:*'],\n    supportsCustomModels: false,\n    mayRequirePython: false,\n    defaultConfig: {\n      modelId: 'vehicle-type-efficientnet',\n      runtime: 'node',\n      backend: 'cpu',\n      confidence: 0.05,  // Low pipeline threshold for 8949-class model\n      minConfidence: 0.05,\n    },\n  }\n\n  private engine: IInferenceEngine | null = null\n  private modelEntry!: ModelCatalogEntry\n  private labels: readonly string[] = []\n  private minConfidence = 0.05\n  private resolvedConfig: ResolvedInferenceConfig | null = null\n  private ctx: AddonContext | null = null\n\n  getModelRequirements(): ModelRequirement[] {\n    return VEHICLE_TYPE_MODELS.map((m) => ({\n      modelId: m.id,\n      name: m.name,\n      minRAM_MB: 120,\n      accuracyScore: 80,\n      formats: Object.keys(m.formats) as readonly string[],\n    }))\n  }\n\n  configure(config: ResolvedInferenceConfig): void {\n    this.resolvedConfig = config\n  }\n\n  async initialize(ctx: AddonContext): Promise<void> {\n    this.ctx = ctx\n    const cfg = ctx.addonConfig\n    const modelId = (cfg['modelId'] as string | undefined) ?? this.resolvedConfig?.modelId ?? 'vehicle-type-efficientnet'\n    this.minConfidence = (cfg['minConfidence'] as number | undefined) ?? 0.05\n\n    const entry = VEHICLE_TYPE_MODELS.find((m) => m.id === modelId)\n    if (!entry) {\n      throw new Error(`VehicleClassifierAddon: unknown modelId \"${modelId}\"`)\n    }\n    this.modelEntry = entry\n  }\n\n  async classify(input: CropInput): Promise<ClassifierOutput> {\n    if (!this.engine) await this.ensureEngine()\n    const start = Date.now()\n    const { width: inputW, height: inputH } = this.modelEntry.inputSize\n\n    // Crop the vehicle region\n    const vehicleCrop = await cropRegion(input.frame.data, input.roi)\n\n    // Resize to 224x224, ImageNet normalization, NCHW\n    const normalized = await resizeAndNormalize(vehicleCrop, inputW, inputH, 'imagenet', 'nchw')\n\n    // Run inference\n    const rawOutput = await this.engine!.run(normalized, [1, 3, inputH, inputW])\n\n    console.log(`[VehicleClassifier] Output length: ${rawOutput.length}, labels: ${this.labels.length}, first 5 raw: [${Array.from(rawOutput.slice(0, 5)).map(v => v.toFixed(3)).join(', ')}]`)\n\n    // Softmax to get probabilities\n    const probs = softmax(rawOutput)\n\n    // Find top-3 for debugging\n    const indexed = Array.from(probs).map((v, i) => ({ score: v, idx: i }))\n    indexed.sort((a, b) => b.score - a.score)\n    const top3 = indexed.slice(0, 3)\n    console.log(`[VehicleClassifier] Top-3: ${top3.map(t => `${this.labels[t.idx] ?? t.idx}=${(t.score * 100).toFixed(1)}%`).join(', ')}`)\n\n    // Find argmax\n    const maxIdx = top3[0]?.idx ?? 0\n    const maxScore = top3[0]?.score ?? 0\n\n    if (maxScore < this.minConfidence) {\n      console.log(`[VehicleClassifier] Below confidence threshold: ${(maxScore * 100).toFixed(1)}% < ${(this.minConfidence * 100).toFixed(0)}%`)\n      return {\n        classifications: [],\n        inferenceMs: Date.now() - start,\n        modelId: this.modelEntry.id,\n      }\n    }\n\n    const label = this.labels[maxIdx] ?? `vehicle_type_${maxIdx}`\n    console.log(`[VehicleClassifier] Result: ${label} (${(maxScore * 100).toFixed(1)}%)`)\n\n    return {\n      classifications: [\n        {\n          class: label,\n          score: maxScore,\n        },\n      ],\n      inferenceMs: Date.now() - start,\n      modelId: this.modelEntry.id,\n    }\n  }\n\n  private async ensureEngine(): Promise<void> {\n    const config = this.resolvedConfig\n    const modelId = config?.modelId ?? this.modelEntry.id\n    const runtime = config?.runtime === 'python' ? 'coreml' : (config?.runtime === 'node' ? 'onnx' : 'auto')\n    const backend = config?.backend ?? 'cpu'\n    const format = config?.format ?? 'onnx'\n\n    const entry = VEHICLE_TYPE_MODELS.find((m) => m.id === modelId) ?? this.modelEntry\n    this.modelEntry = entry\n\n    const modelsDir = this.ctx!.models?.getModelsDir() ?? this.ctx!.locationPaths.models\n\n    // Ensure model + extra files (labels JSON) are downloaded via unified service\n    if (this.ctx!.models) {\n      await this.ctx!.models.ensure(modelId, format as any)\n    }\n\n    // Load labels from JSON file (lazy — only on first use)\n    this.labels = loadLabels(modelsDir, modelId)\n\n    const resolved = await resolveEngine({\n      runtime: runtime as 'auto',\n      backend,\n      modelEntry: entry,\n      modelsDir,\n      models: this.ctx!.models,\n    })\n    this.engine = resolved.engine\n  }\n\n  async shutdown(): Promise<void> {\n    await this.engine?.dispose()\n  }\n\n  getConfigSchema(): ConfigUISchema {\n    return {\n      sections: [\n        {\n          id: 'model',\n          title: 'Model',\n          columns: 1,\n          fields: [\n            {\n              key: 'modelId',\n              label: 'Model',\n              type: 'model-selector',\n              catalog: [...VEHICLE_TYPE_MODELS],\n              allowCustom: false,\n              allowConversion: false,\n              acceptFormats: ['onnx', 'coreml', 'openvino'],\n              requiredMetadata: ['inputSize', 'labels'],\n              outputFormatHint: 'classification',\n            },\n          ],\n        },\n        {\n          id: 'runtime',\n          title: 'Runtime',\n          columns: 2,\n          fields: [\n            {\n              key: 'runtime',\n              label: 'Runtime',\n              type: 'select',\n              options: [\n                { value: 'auto', label: 'Auto' },\n                { value: 'onnx', label: 'ONNX Runtime' },\n                { value: 'coreml', label: 'CoreML (Apple)' },\n                { value: 'openvino', label: 'OpenVINO (Intel)' },\n              ],\n            },\n            {\n              key: 'backend',\n              label: 'Backend',\n              type: 'select',\n              showWhen: { field: 'runtime', equals: 'onnx' },\n              options: [\n                { value: 'auto', label: 'Auto' },\n                { value: 'cpu', label: 'CPU' },\n                { value: 'coreml', label: 'CoreML' },\n                { value: 'cuda', label: 'CUDA (NVIDIA)' },\n              ],\n            },\n          ],\n        },\n        {\n          id: 'thresholds',\n          title: 'Classification Settings',\n          columns: 1,\n          fields: [\n            {\n              key: 'minConfidence',\n              label: 'Minimum Confidence',\n              type: 'slider',\n              min: 0.05,\n              max: 1.0,\n              step: 0.05,\n              default: 0.3,\n            },\n          ],\n        },\n      ],\n    }\n  }\n\n  getClassMap(): ClassMapDefinition {\n    return VEHICLE_CLASS_MAP\n  }\n\n  getModelCatalog(): ModelCatalogEntry[] {\n    return [...VEHICLE_TYPE_MODELS]\n  }\n\n  getAvailableModels(): DetectionModel[] {\n    return []\n  }\n\n  getActiveLabels(): readonly LabelDefinition[] {\n    return VEHICLE_TYPE_LABELS\n  }\n\n  async probe(): Promise<ProbeResult> {\n    return {\n      available: true,\n      runtime: this.engine?.runtime ?? 'onnx',\n      device: this.engine?.device ?? 'cpu',\n      capabilities: ['fp32'],\n    }\n  }\n}\n"],"mappings":";;;;;;;;;;;;;AAoBA,YAAY,QAAQ;AACpB,YAAY,UAAU;AAEtB,IAAM,qBAAsC,EAAE,IAAI,gBAAgB,MAAM,eAAe;AACvF,IAAM,sBAAkD,CAAC,kBAAkB;AAC3E,IAAM,oBAAwC,EAAE,SAAS,CAAC,GAAG,kBAAkB,KAAK;AAGpF,SAAS,WAAW,WAAmB,SAAoC;AACzE,QAAM,aAAa;AAAA,IACjB,YAAY,OAAO;AAAA,IACnB;AAAA,EACF;AACA,aAAW,QAAQ,YAAY;AAC7B,UAAM,YAAiB,UAAK,WAAW,IAAI;AAC3C,QAAO,cAAW,SAAS,GAAG;AAC5B,YAAM,MAAS,gBAAa,WAAW,OAAO;AAC9C,aAAO,KAAK,MAAM,GAAG;AAAA,IACvB;AAAA,EACF;AACA,QAAM,IAAI,MAAM,oDAAoD,SAAS,EAAE;AACjF;AAEA,SAAS,QAAQ,QAAoC;AACnD,QAAM,MAAM,OAAO,OAAO,CAAC,GAAG,MAAM,KAAK,IAAI,GAAG,CAAC,GAAG,SAAS;AAC7D,QAAM,OAAO,OAAO,IAAI,CAAC,MAAM,KAAK,IAAI,IAAI,GAAG,CAAC;AAChD,QAAM,MAAM,KAAK,OAAO,CAAC,GAAG,MAAM,IAAI,GAAG,CAAC;AAC1C,SAAO,KAAK,IAAI,CAAC,MAAM,IAAI,GAAG;AAChC;AAEA,IAAqB,yBAArB,MAA4F;AAAA,EACjF,KAAK;AAAA,EACL,OAAO;AAAA,EACP,eAAe,CAAC,SAAS;AAAA,EACzB,gBAAgB,CAAC,gBAAgB;AAAA,EACjC,eAAe;AAAA,EACf,gBAAgB,CAAC;AAAA,EACjB,WAA0B;AAAA,IACjC,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,SAAS;AAAA,IAET,aAAa;AAAA,IAEb,MAAM;AAAA,IACN,iBAAiB;AAAA,IACjB,cAAc,CAAC,SAAS;AAAA,IACxB,eAAe,CAAC,gBAAgB;AAAA,IAChC,sBAAsB;AAAA,IACtB,kBAAkB;AAAA,IAClB,eAAe;AAAA,MACb,SAAS;AAAA,MACT,SAAS;AAAA,MACT,SAAS;AAAA,MACT,YAAY;AAAA;AAAA,MACZ,eAAe;AAAA,IACjB;AAAA,EACF;AAAA,EAEQ,SAAkC;AAAA,EAClC;AAAA,EACA,SAA4B,CAAC;AAAA,EAC7B,gBAAgB;AAAA,EAChB,iBAAiD;AAAA,EACjD,MAA2B;AAAA,EAEnC,uBAA2C;AACzC,WAAO,oBAAoB,IAAI,CAAC,OAAO;AAAA,MACrC,SAAS,EAAE;AAAA,MACX,MAAM,EAAE;AAAA,MACR,WAAW;AAAA,MACX,eAAe;AAAA,MACf,SAAS,OAAO,KAAK,EAAE,OAAO;AAAA,IAChC,EAAE;AAAA,EACJ;AAAA,EAEA,UAAU,QAAuC;AAC/C,SAAK,iBAAiB;AAAA,EACxB;AAAA,EAEA,MAAM,WAAW,KAAkC;AACjD,SAAK,MAAM;AACX,UAAM,MAAM,IAAI;AAChB,UAAM,UAAW,IAAI,SAAS,KAA4B,KAAK,gBAAgB,WAAW;AAC1F,SAAK,gBAAiB,IAAI,eAAe,KAA4B;AAErE,UAAM,QAAQ,oBAAoB,KAAK,CAAC,MAAM,EAAE,OAAO,OAAO;AAC9D,QAAI,CAAC,OAAO;AACV,YAAM,IAAI,MAAM,4CAA4C,OAAO,GAAG;AAAA,IACxE;AACA,SAAK,aAAa;AAAA,EACpB;AAAA,EAEA,MAAM,SAAS,OAA6C;AAC1D,QAAI,CAAC,KAAK,OAAQ,OAAM,KAAK,aAAa;AAC1C,UAAM,QAAQ,KAAK,IAAI;AACvB,UAAM,EAAE,OAAO,QAAQ,QAAQ,OAAO,IAAI,KAAK,WAAW;AAG1D,UAAM,cAAc,MAAM,WAAW,MAAM,MAAM,MAAM,MAAM,GAAG;AAGhE,UAAM,aAAa,MAAM,mBAAmB,aAAa,QAAQ,QAAQ,YAAY,MAAM;AAG3F,UAAM,YAAY,MAAM,KAAK,OAAQ,IAAI,YAAY,CAAC,GAAG,GAAG,QAAQ,MAAM,CAAC;AAE3E,YAAQ,IAAI,sCAAsC,UAAU,MAAM,aAAa,KAAK,OAAO,MAAM,mBAAmB,MAAM,KAAK,UAAU,MAAM,GAAG,CAAC,CAAC,EAAE,IAAI,OAAK,EAAE,QAAQ,CAAC,CAAC,EAAE,KAAK,IAAI,CAAC,GAAG;AAG1L,UAAM,QAAQ,QAAQ,SAAS;AAG/B,UAAM,UAAU,MAAM,KAAK,KAAK,EAAE,IAAI,CAAC,GAAG,OAAO,EAAE,OAAO,GAAG,KAAK,EAAE,EAAE;AACtE,YAAQ,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK;AACxC,UAAM,OAAO,QAAQ,MAAM,GAAG,CAAC;AAC/B,YAAQ,IAAI,8BAA8B,KAAK,IAAI,OAAK,GAAG,KAAK,OAAO,EAAE,GAAG,KAAK,EAAE,GAAG,KAAK,EAAE,QAAQ,KAAK,QAAQ,CAAC,CAAC,GAAG,EAAE,KAAK,IAAI,CAAC,EAAE;AAGrI,UAAM,SAAS,KAAK,CAAC,GAAG,OAAO;AAC/B,UAAM,WAAW,KAAK,CAAC,GAAG,SAAS;AAEnC,QAAI,WAAW,KAAK,eAAe;AACjC,cAAQ,IAAI,oDAAoD,WAAW,KAAK,QAAQ,CAAC,CAAC,QAAQ,KAAK,gBAAgB,KAAK,QAAQ,CAAC,CAAC,GAAG;AACzI,aAAO;AAAA,QACL,iBAAiB,CAAC;AAAA,QAClB,aAAa,KAAK,IAAI,IAAI;AAAA,QAC1B,SAAS,KAAK,WAAW;AAAA,MAC3B;AAAA,IACF;AAEA,UAAM,QAAQ,KAAK,OAAO,MAAM,KAAK,gBAAgB,MAAM;AAC3D,YAAQ,IAAI,+BAA+B,KAAK,MAAM,WAAW,KAAK,QAAQ,CAAC,CAAC,IAAI;AAEpF,WAAO;AAAA,MACL,iBAAiB;AAAA,QACf;AAAA,UACE,OAAO;AAAA,UACP,OAAO;AAAA,QACT;AAAA,MACF;AAAA,MACA,aAAa,KAAK,IAAI,IAAI;AAAA,MAC1B,SAAS,KAAK,WAAW;AAAA,IAC3B;AAAA,EACF;AAAA,EAEA,MAAc,eAA8B;AAC1C,UAAM,SAAS,KAAK;AACpB,UAAM,UAAU,QAAQ,WAAW,KAAK,WAAW;AACnD,UAAM,UAAU,QAAQ,YAAY,WAAW,WAAY,QAAQ,YAAY,SAAS,SAAS;AACjG,UAAM,UAAU,QAAQ,WAAW;AACnC,UAAM,SAAS,QAAQ,UAAU;AAEjC,UAAM,QAAQ,oBAAoB,KAAK,CAAC,MAAM,EAAE,OAAO,OAAO,KAAK,KAAK;AACxE,SAAK,aAAa;AAElB,UAAM,YAAY,KAAK,IAAK,QAAQ,aAAa,KAAK,KAAK,IAAK,cAAc;AAG9E,QAAI,KAAK,IAAK,QAAQ;AACpB,YAAM,KAAK,IAAK,OAAO,OAAO,SAAS,MAAa;AAAA,IACtD;AAGA,SAAK,SAAS,WAAW,WAAW,OAAO;AAE3C,UAAM,WAAW,MAAM,cAAc;AAAA,MACnC;AAAA,MACA;AAAA,MACA,YAAY;AAAA,MACZ;AAAA,MACA,QAAQ,KAAK,IAAK;AAAA,IACpB,CAAC;AACD,SAAK,SAAS,SAAS;AAAA,EACzB;AAAA,EAEA,MAAM,WAA0B;AAC9B,UAAM,KAAK,QAAQ,QAAQ;AAAA,EAC7B;AAAA,EAEA,kBAAkC;AAChC,WAAO;AAAA,MACL,UAAU;AAAA,QACR;AAAA,UACE,IAAI;AAAA,UACJ,OAAO;AAAA,UACP,SAAS;AAAA,UACT,QAAQ;AAAA,YACN;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,SAAS,CAAC,GAAG,mBAAmB;AAAA,cAChC,aAAa;AAAA,cACb,iBAAiB;AAAA,cACjB,eAAe,CAAC,QAAQ,UAAU,UAAU;AAAA,cAC5C,kBAAkB,CAAC,aAAa,QAAQ;AAAA,cACxC,kBAAkB;AAAA,YACpB;AAAA,UACF;AAAA,QACF;AAAA,QACA;AAAA,UACE,IAAI;AAAA,UACJ,OAAO;AAAA,UACP,SAAS;AAAA,UACT,QAAQ;AAAA,YACN;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,SAAS;AAAA,gBACP,EAAE,OAAO,QAAQ,OAAO,OAAO;AAAA,gBAC/B,EAAE,OAAO,QAAQ,OAAO,eAAe;AAAA,gBACvC,EAAE,OAAO,UAAU,OAAO,iBAAiB;AAAA,gBAC3C,EAAE,OAAO,YAAY,OAAO,mBAAmB;AAAA,cACjD;AAAA,YACF;AAAA,YACA;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,UAAU,EAAE,OAAO,WAAW,QAAQ,OAAO;AAAA,cAC7C,SAAS;AAAA,gBACP,EAAE,OAAO,QAAQ,OAAO,OAAO;AAAA,gBAC/B,EAAE,OAAO,OAAO,OAAO,MAAM;AAAA,gBAC7B,EAAE,OAAO,UAAU,OAAO,SAAS;AAAA,gBACnC,EAAE,OAAO,QAAQ,OAAO,gBAAgB;AAAA,cAC1C;AAAA,YACF;AAAA,UACF;AAAA,QACF;AAAA,QACA;AAAA,UACE,IAAI;AAAA,UACJ,OAAO;AAAA,UACP,SAAS;AAAA,UACT,QAAQ;AAAA,YACN;AAAA,cACE,KAAK;AAAA,cACL,OAAO;AAAA,cACP,MAAM;AAAA,cACN,KAAK;AAAA,cACL,KAAK;AAAA,cACL,MAAM;AAAA,cACN,SAAS;AAAA,YACX;AAAA,UACF;AAAA,QACF;AAAA,MACF;AAAA,IACF;AAAA,EACF;AAAA,EAEA,cAAkC;AAChC,WAAO;AAAA,EACT;AAAA,EAEA,kBAAuC;AACrC,WAAO,CAAC,GAAG,mBAAmB;AAAA,EAChC;AAAA,EAEA,qBAAuC;AACrC,WAAO,CAAC;AAAA,EACV;AAAA,EAEA,kBAA8C;AAC5C,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,QAA8B;AAClC,WAAO;AAAA,MACL,WAAW;AAAA,MACX,SAAS,KAAK,QAAQ,WAAW;AAAA,MACjC,QAAQ,KAAK,QAAQ,UAAU;AAAA,MAC/B,cAAc,CAAC,MAAM;AAAA,IACvB;AAAA,EACF;AACF;","names":[]}

package/dist/{chunk-6OR5TE7A.mjs → chunk-22BHCDT5.mjs}

@@ -39,7 +39,7 @@ async function letterbox(jpeg, targetSize) {
   return { data: float32, scale, padX, padY, originalWidth, originalHeight };
 }
 async function resizeAndNormalize(jpeg, targetWidth, targetHeight, normalization, layout) {
-  const { data } = await sharp(jpeg).resize(targetWidth, targetHeight).removeAlpha().raw().toBuffer({ resolveWithObject: true });
+  const { data } = await sharp(jpeg).resize(targetWidth, targetHeight, { fit: "fill" }).removeAlpha().raw().toBuffer({ resolveWithObject: true });
   const numPixels = targetWidth * targetHeight;
   const float32 = new Float32Array(3 * numPixels);
   const mean = [0.485, 0.456, 0.406];
@@ -98,4 +98,4 @@ export {
   resizeAndNormalize,
   rgbToGrayscale
 };
-//# sourceMappingURL=chunk-6OR5TE7A.mjs.map
+//# sourceMappingURL=chunk-22BHCDT5.mjs.map

package/dist/chunk-22BHCDT5.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/shared/image-utils.ts"],"sourcesContent":["import sharp from 'sharp'\nimport type { BoundingBox } from '@camstack/types'\n\n/** Decode JPEG to raw RGB pixels */\nexport async function jpegToRgb(\n  jpeg: Buffer,\n): Promise<{ data: Buffer; width: number; height: number }> {\n  const { data, info } = await sharp(jpeg)\n    .removeAlpha()\n    .raw()\n    .toBuffer({ resolveWithObject: true })\n  return { data, width: info.width, height: info.height }\n}\n\n/** Crop a region from a JPEG buffer */\nexport async function cropRegion(jpeg: Buffer, roi: BoundingBox): Promise<Buffer> {\n  return sharp(jpeg)\n    .extract({\n      left: Math.round(roi.x),\n      top: Math.round(roi.y),\n      width: Math.round(roi.w),\n      height: Math.round(roi.h),\n    })\n    .jpeg()\n    .toBuffer()\n}\n\n/** Letterbox resize for YOLO: resize preserving aspect ratio, pad to square */\nexport async function letterbox(\n  jpeg: Buffer,\n  targetSize: number,\n): Promise<{\n  data: Float32Array\n  scale: number\n  padX: number\n  padY: number\n  originalWidth: number\n  originalHeight: number\n}> {\n  const meta = await sharp(jpeg).metadata()\n  const originalWidth = meta.width ?? 0\n  const originalHeight = meta.height ?? 0\n\n  const scale = Math.min(targetSize / originalWidth, targetSize / originalHeight)\n  const scaledWidth = Math.round(originalWidth * scale)\n  const scaledHeight = Math.round(originalHeight * scale)\n\n  const padX = Math.floor((targetSize - scaledWidth) / 2)\n  const padY = Math.floor((targetSize - scaledHeight) / 2)\n\n  const { data } = await sharp(jpeg)\n    .resize(scaledWidth, scaledHeight)\n    .extend({\n      top: padY,\n      bottom: targetSize - scaledHeight - padY,\n      left: padX,\n      right: targetSize - scaledWidth - padX,\n      background: { r: 114, g: 114, b: 114 },\n    })\n    .removeAlpha()\n    .raw()\n    .toBuffer({ resolveWithObject: true })\n\n  // Convert HWC uint8 to CHW float [0,1]\n  const numPixels = targetSize * targetSize\n  const float32 = new Float32Array(3 * numPixels)\n  for (let i = 0; i < numPixels; i++) {\n    const srcBase = i * 3\n    float32[0 * numPixels + i] = (data[srcBase]! / 255)\n    float32[1 * numPixels + i] = (data[srcBase + 1]! / 255)\n    float32[2 * numPixels + i] = (data[srcBase + 2]! / 255)\n  }\n\n  return { data: float32, scale, padX, padY, originalWidth, originalHeight }\n}\n\n/** Resize and normalize to Float32Array */\nexport async function resizeAndNormalize(\n  jpeg: Buffer,\n  targetWidth: number,\n  targetHeight: number,\n  normalization: 'zero-one' | 'imagenet' | 'none',\n  layout: 'nchw' | 'nhwc',\n): Promise<Float32Array> {\n  const { data } = await sharp(jpeg)\n    .resize(targetWidth, targetHeight, { fit: 'fill' })\n    .removeAlpha()\n    .raw()\n    .toBuffer({ resolveWithObject: true })\n\n  const numPixels = targetWidth * targetHeight\n  const float32 = new Float32Array(3 * numPixels)\n\n  // ImageNet mean and std per channel\n  const mean = [0.485, 0.456, 0.406]\n  const std = [0.229, 0.224, 0.225]\n\n  if (layout === 'nchw') {\n    for (let i = 0; i < numPixels; i++) {\n      const srcBase = i * 3\n      for (let c = 0; c < 3; c++) {\n        const raw = data[srcBase + c]! / 255\n        let val: number\n        if (normalization === 'zero-one') {\n          val = raw\n        } else if (normalization === 'imagenet') {\n          val = (raw - mean[c]!) / std[c]!\n        } else {\n          val = data[srcBase + c]!\n        }\n        float32[c * numPixels + i] = val\n      }\n    }\n  } else {\n    // nhwc\n    for (let i = 0; i < numPixels; i++) {\n      const srcBase = i * 3\n      for (let c = 0; c < 3; c++) {\n        const raw = data[srcBase + c]! / 255\n        let val: number\n        if (normalization === 'zero-one') {\n          val = raw\n        } else if (normalization === 'imagenet') {\n          val = (raw - mean[c]!) / std[c]!\n        } else {\n          val = data[srcBase + c]!\n        }\n        float32[i * 3 + c] = val\n      }\n    }\n  }\n\n  return float32\n}\n\n/** Convert raw RGB to grayscale Uint8Array */\nexport function rgbToGrayscale(rgb: Buffer, width: number, height: number): Uint8Array {\n  const numPixels = width * height\n  const gray = new Uint8Array(numPixels)\n  for (let i = 0; i < numPixels; i++) {\n    const r = rgb[i * 3]!\n    const g = rgb[i * 3 + 1]!\n    const b = rgb[i * 3 + 2]!\n    // BT.601 luma\n    gray[i] = Math.round(0.299 * r + 0.587 * g + 0.114 * b)\n  }\n  return gray\n}\n"],"mappings":";AAAA,OAAO,WAAW;AAIlB,eAAsB,UACpB,MAC0D;AAC1D,QAAM,EAAE,MAAM,KAAK,IAAI,MAAM,MAAM,IAAI,EACpC,YAAY,EACZ,IAAI,EACJ,SAAS,EAAE,mBAAmB,KAAK,CAAC;AACvC,SAAO,EAAE,MAAM,OAAO,KAAK,OAAO,QAAQ,KAAK,OAAO;AACxD;AAGA,eAAsB,WAAW,MAAc,KAAmC;AAChF,SAAO,MAAM,IAAI,EACd,QAAQ;AAAA,IACP,MAAM,KAAK,MAAM,IAAI,CAAC;AAAA,IACtB,KAAK,KAAK,MAAM,IAAI,CAAC;AAAA,IACrB,OAAO,KAAK,MAAM,IAAI,CAAC;AAAA,IACvB,QAAQ,KAAK,MAAM,IAAI,CAAC;AAAA,EAC1B,CAAC,EACA,KAAK,EACL,SAAS;AACd;AAGA,eAAsB,UACpB,MACA,YAQC;AACD,QAAM,OAAO,MAAM,MAAM,IAAI,EAAE,SAAS;AACxC,QAAM,gBAAgB,KAAK,SAAS;AACpC,QAAM,iBAAiB,KAAK,UAAU;AAEtC,QAAM,QAAQ,KAAK,IAAI,aAAa,eAAe,aAAa,cAAc;AAC9E,QAAM,cAAc,KAAK,MAAM,gBAAgB,KAAK;AACpD,QAAM,eAAe,KAAK,MAAM,iBAAiB,KAAK;AAEtD,QAAM,OAAO,KAAK,OAAO,aAAa,eAAe,CAAC;AACtD,QAAM,OAAO,KAAK,OAAO,aAAa,gBAAgB,CAAC;AAEvD,QAAM,EAAE,KAAK,IAAI,MAAM,MAAM,IAAI,EAC9B,OAAO,aAAa,YAAY,EAChC,OAAO;AAAA,IACN,KAAK;AAAA,IACL,QAAQ,aAAa,eAAe;AAAA,IACpC,MAAM;AAAA,IACN,OAAO,aAAa,cAAc;AAAA,IAClC,YAAY,EAAE,GAAG,KAAK,GAAG,KAAK,GAAG,IAAI;AAAA,EACvC,CAAC,EACA,YAAY,EACZ,IAAI,EACJ,SAAS,EAAE,mBAAmB,KAAK,CAAC;AAGvC,QAAM,YAAY,aAAa;AAC/B,QAAM,UAAU,IAAI,aAAa,IAAI,SAAS;AAC9C,WAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,UAAM,UAAU,IAAI;AACpB,YAAQ,IAAI,YAAY,CAAC,IAAK,KAAK,OAAO,IAAK;AAC/C,YAAQ,IAAI,YAAY,CAAC,IAAK,KAAK,UAAU,CAAC,IAAK;AACnD,YAAQ,IAAI,YAAY,CAAC,IAAK,KAAK,UAAU,CAAC,IAAK;AAAA,EACrD;AAEA,SAAO,EAAE,MAAM,SAAS,OAAO,MAAM,MAAM,eAAe,eAAe;AAC3E;AAGA,eAAsB,mBACpB,MACA,aACA,cACA,eACA,QACuB;AACvB,QAAM,EAAE,KAAK,IAAI,MAAM,MAAM,IAAI,EAC9B,OAAO,aAAa,cAAc,EAAE,KAAK,OAAO,CAAC,EACjD,YAAY,EACZ,IAAI,EACJ,SAAS,EAAE,mBAAmB,KAAK,CAAC;AAEvC,QAAM,YAAY,cAAc;AAChC,QAAM,UAAU,IAAI,aAAa,IAAI,SAAS;AAG9C,QAAM,OAAO,CAAC,OAAO,OAAO,KAAK;AACjC,QAAM,MAAM,CAAC,OAAO,OAAO,KAAK;AAEhC,MAAI,WAAW,QAAQ;AACrB,aAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,YAAM,UAAU,IAAI;AACpB,eAAS,IAAI,GAAG,IAAI,GAAG,KAAK;AAC1B,cAAM,MAAM,KAAK,UAAU,CAAC,IAAK;AACjC,YAAI;AACJ,YAAI,kBAAkB,YAAY;AAChC,gBAAM;AAAA,QACR,WAAW,kBAAkB,YAAY;AACvC,iBAAO,MAAM,KAAK,CAAC,KAAM,IAAI,CAAC;AAAA,QAChC,OAAO;AACL,gBAAM,KAAK,UAAU,CAAC;AAAA,QACxB;AACA,gBAAQ,IAAI,YAAY,CAAC,IAAI;AAAA,MAC/B;AAAA,IACF;AAAA,EACF,OAAO;AAEL,aAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,YAAM,UAAU,IAAI;AACpB,eAAS,IAAI,GAAG,IAAI,GAAG,KAAK;AAC1B,cAAM,MAAM,KAAK,UAAU,CAAC,IAAK;AACjC,YAAI;AACJ,YAAI,kBAAkB,YAAY;AAChC,gBAAM;AAAA,QACR,WAAW,kBAAkB,YAAY;AACvC,iBAAO,MAAM,KAAK,CAAC,KAAM,IAAI,CAAC;AAAA,QAChC,OAAO;AACL,gBAAM,KAAK,UAAU,CAAC;AAAA,QACxB;AACA,gBAAQ,IAAI,IAAI,CAAC,IAAI;AAAA,MACvB;AAAA,IACF;AAAA,EACF;AAEA,SAAO;AACT;AAGO,SAAS,eAAe,KAAa,OAAe,QAA4B;AACrF,QAAM,YAAY,QAAQ;AAC1B,QAAM,OAAO,IAAI,WAAW,SAAS;AACrC,WAAS,IAAI,GAAG,IAAI,WAAW,KAAK;AAClC,UAAM,IAAI,IAAI,IAAI,CAAC;AACnB,UAAM,IAAI,IAAI,IAAI,IAAI,CAAC;AACvB,UAAM,IAAI,IAAI,IAAI,IAAI,CAAC;AAEvB,SAAK,CAAC,IAAI,KAAK,MAAM,QAAQ,IAAI,QAAQ,IAAI,QAAQ,CAAC;AAAA,EACxD;AACA,SAAO;AACT;","names":[]}

package/dist/{chunk-LPI42WL6.mjs → chunk-2IOKI4ES.mjs}

@@ -190,7 +190,7 @@ import * as path2 from "path";
 var AUTO_BACKEND_PRIORITY = ["coreml", "cuda", "tensorrt", "cpu"];
 var BACKEND_TO_FORMAT = {
   cpu: "onnx",
-  coreml: "coreml",
+  coreml: "onnx",
   cuda: "onnx",
   tensorrt: "onnx"
 };
@@ -218,7 +218,7 @@ function modelExists(filePath) {
   }
 }
 async function resolveEngine(options) {
-  const { runtime, backend, modelEntry, modelsDir, downloadModel } = options;
+  const { runtime, backend, modelEntry, modelsDir, models } = options;
   let selectedFormat;
   let selectedBackend;
   if (runtime === "auto") {
@@ -252,18 +252,18 @@ async function resolveEngine(options) {
     selectedFormat = fmt;
     selectedBackend = runtime === "onnx" ? backend || "cpu" : runtime;
   }
-  let modelPath = modelFilePath(modelsDir, modelEntry, selectedFormat);
-  if (!modelExists(modelPath)) {
-    if (downloadModel) {
-      const formatEntry = modelEntry.formats[selectedFormat];
-      modelPath = await downloadModel(formatEntry.url, modelsDir);
-    } else {
+  let modelPath;
+  if (models) {
+    modelPath = await models.ensure(modelEntry.id, selectedFormat);
+  } else {
+    modelPath = modelFilePath(modelsDir, modelEntry, selectedFormat);
+    if (!modelExists(modelPath)) {
       throw new Error(
-        `resolveEngine: model file not found at ${modelPath} and no downloadModel function provided`
+        `resolveEngine: model file not found at ${modelPath} and no model service provided`
       );
     }
   }
-  if (selectedFormat === "onnx" || selectedFormat === "coreml") {
+  if (selectedFormat === "onnx") {
     const engine = new NodeInferenceEngine(modelPath, selectedBackend);
     await engine.initialize();
     return { engine, format: selectedFormat, modelPath };
@@ -277,7 +277,18 @@ async function resolveEngine(options) {
   const effectiveRuntime = runtime === "auto" ? selectedBackend : runtime;
   const scriptName = PYTHON_SCRIPT_MAP[effectiveRuntime];
   if (scriptName && pythonPath) {
-    const scriptPath = path2.join(__dirname, "../../python", scriptName);
+    const candidates = [
+      path2.join(__dirname, "../../python", scriptName),
+      path2.join(__dirname, "../python", scriptName),
+      path2.join(__dirname, "../../../python", scriptName)
+    ];
+    const scriptPath = candidates.find((p) => fs.existsSync(p));
+    if (!scriptPath) {
+      throw new Error(
+        `resolveEngine: Python script "${scriptName}" not found. Searched:
+${candidates.join("\n")}`
+      );
+    }
     const inputSize = Math.max(modelEntry.inputSize.width, modelEntry.inputSize.height);
     const engine = new PythonInferenceEngine(pythonPath, scriptPath, effectiveRuntime, modelPath, [
       `--input-size=${inputSize}`,
@@ -321,4 +332,4 @@ export {
   resolveEngine,
   probeOnnxBackends
 };
-//# sourceMappingURL=chunk-LPI42WL6.mjs.map
+//# sourceMappingURL=chunk-2IOKI4ES.mjs.map

package/dist/chunk-2IOKI4ES.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/shared/node-engine.ts","../src/shared/python-engine.ts","../src/shared/engine-resolver.ts"],"sourcesContent":["import type { IInferenceEngine, DetectionRuntime, DetectionDevice } from '@camstack/types'\nimport * as path from 'node:path'\n\nconst BACKEND_TO_PROVIDER: Readonly<Record<string, string>> = {\n  cpu: 'cpu',\n  coreml: 'coreml',\n  cuda: 'cuda',\n  tensorrt: 'tensorrt',\n  dml: 'dml',\n} as const\n\nconst BACKEND_TO_DEVICE: Readonly<Record<string, DetectionDevice>> = {\n  cpu: 'cpu',\n  coreml: 'gpu-mps',\n  cuda: 'gpu-cuda',\n  tensorrt: 'tensorrt',\n} as const\n\nexport class NodeInferenceEngine implements IInferenceEngine {\n  readonly runtime: DetectionRuntime = 'onnx'\n  readonly device: DetectionDevice\n  private session: unknown = null\n\n  constructor(\n    private readonly modelPath: string,\n    private readonly backend: string,\n  ) {\n    this.device = (BACKEND_TO_DEVICE[backend] ?? 'cpu') as DetectionDevice\n  }\n\n  async initialize(): Promise<void> {\n    const ort = await import('onnxruntime-node')\n    const provider = BACKEND_TO_PROVIDER[this.backend] ?? 'cpu'\n\n    // Resolve absolute path\n    const absModelPath = path.isAbsolute(this.modelPath)\n      ? this.modelPath\n      : path.resolve(process.cwd(), this.modelPath)\n\n    const sessionOptions: Record<string, unknown> = {\n      executionProviders: [provider],\n    }\n\n    // eslint-disable-next-line @typescript-eslint/no-explicit-any\n    this.session = await (ort as any).InferenceSession.create(absModelPath, sessionOptions)\n  }\n\n  async run(input: Float32Array, inputShape: readonly number[]): Promise<Float32Array> {\n    if (!this.session) {\n      throw new Error('NodeInferenceEngine: not initialized — call initialize() first')\n    }\n\n    const ort = await import('onnxruntime-node')\n    // eslint-disable-next-line @typescript-eslint/no-explicit-any\n    const sess = this.session as any\n\n    // Get the first input name\n    const inputName: string = sess.inputNames[0]\n    // eslint-disable-next-line @typescript-eslint/no-explicit-any\n    const tensor = new (ort as any).Tensor('float32', input, [...inputShape])\n    const feeds: Record<string, unknown> = { [inputName]: tensor }\n\n    const results = await sess.run(feeds)\n    const outputName: string = sess.outputNames[0]\n    const outputTensor = results[outputName]\n\n    return outputTensor.data as Float32Array\n  }\n\n  async runMultiOutput(\n    input: Float32Array,\n    inputShape: readonly number[],\n  ): Promise<Record<string, Float32Array>> {\n    if (!this.session) {\n      throw new Error('NodeInferenceEngine: not initialized — call initialize() first')\n    }\n\n    const ort = await import('onnxruntime-node')\n    // eslint-disable-next-line @typescript-eslint/no-explicit-any\n    const sess = this.session as any\n\n    const inputName: string = sess.inputNames[0]\n    // eslint-disable-next-line @typescript-eslint/no-explicit-any\n    const tensor = new (ort as any).Tensor('float32', input, [...inputShape])\n    const feeds: Record<string, unknown> = { [inputName]: tensor }\n\n    const results = await sess.run(feeds)\n\n    const out: Record<string, Float32Array> = {}\n    for (const name of sess.outputNames as string[]) {\n      out[name] = results[name].data as Float32Array\n    }\n    return out\n  }\n\n  async dispose(): Promise<void> {\n    // onnxruntime-node sessions don't have explicit close in all versions\n    // but we clear the reference\n    this.session = null\n  }\n}\n","import type { IInferenceEngine, DetectionRuntime, DetectionDevice, IAddonDepsManager } from '@camstack/types'\nimport { spawn, type ChildProcess } from 'node:child_process'\n\nexport class PythonInferenceEngine implements IInferenceEngine {\n  readonly runtime: DetectionRuntime\n  readonly device: DetectionDevice\n  private process: ChildProcess | null = null\n  private receiveBuffer: Buffer = Buffer.alloc(0)\n  private pendingResolve: ((value: Record<string, unknown>) => void) | null = null\n  private pendingReject: ((reason: Error) => void) | null = null\n\n  constructor(\n    private readonly pythonPath: string,\n    private readonly scriptPath: string,\n    runtime: DetectionRuntime,\n    private readonly modelPath: string,\n    private readonly extraArgs: readonly string[] = [],\n  ) {\n    this.runtime = runtime\n    // Determine device from runtime\n    const runtimeDeviceMap: Readonly<Record<DetectionRuntime, DetectionDevice>> = {\n      onnx: 'cpu',\n      coreml: 'gpu-mps',\n      pytorch: 'cpu',\n      openvino: 'cpu',\n      tflite: 'cpu',\n    }\n    this.device = runtimeDeviceMap[runtime]\n  }\n\n  async initialize(): Promise<void> {\n    const args = [this.scriptPath, this.modelPath, ...this.extraArgs]\n    this.process = spawn(this.pythonPath, args, {\n      stdio: ['pipe', 'pipe', 'pipe'],\n    })\n\n    if (!this.process.stdout || !this.process.stdin) {\n      throw new Error('PythonInferenceEngine: failed to create process pipes')\n    }\n\n    this.process.stderr?.on('data', (chunk: Buffer) => {\n      // Log stderr from python process for debugging\n      process.stderr.write(`[python-engine] ${chunk.toString()}`)\n    })\n\n    this.process.on('error', (err) => {\n      this.pendingReject?.(err)\n      this.pendingReject = null\n      this.pendingResolve = null\n    })\n\n    this.process.on('exit', (code) => {\n      if (code !== 0) {\n        const err = new Error(`PythonInferenceEngine: process exited with code ${code}`)\n        this.pendingReject?.(err)\n        this.pendingReject = null\n        this.pendingResolve = null\n      }\n    })\n\n    this.process.stdout.on('data', (chunk: Buffer) => {\n      this.receiveBuffer = Buffer.concat([this.receiveBuffer, chunk])\n      this._tryReceive()\n    })\n\n    // Give the process a moment to start up and load the model\n    await new Promise<void>((resolve, reject) => {\n      const timeout = setTimeout(() => resolve(), 2000)\n      this.process?.on('error', (err) => {\n        clearTimeout(timeout)\n        reject(err)\n      })\n      this.process?.on('exit', (code) => {\n        clearTimeout(timeout)\n        if (code !== 0) {\n          reject(new Error(`PythonInferenceEngine: process exited early with code ${code}`))\n        }\n      })\n    })\n  }\n\n  private _tryReceive(): void {\n    // Binary IPC: [4 bytes LE uint32 length][JSON bytes]\n    if (this.receiveBuffer.length < 4) return\n\n    const length = this.receiveBuffer.readUInt32LE(0)\n    if (this.receiveBuffer.length < 4 + length) return\n\n    const jsonBytes = this.receiveBuffer.subarray(4, 4 + length)\n    this.receiveBuffer = this.receiveBuffer.subarray(4 + length)\n\n    const resolve = this.pendingResolve\n    const reject = this.pendingReject\n    this.pendingResolve = null\n    this.pendingReject = null\n\n    if (!resolve) return\n\n    try {\n      const parsed = JSON.parse(jsonBytes.toString('utf8')) as Record<string, unknown>\n      resolve(parsed)\n    } catch (err) {\n      reject?.(err instanceof Error ? err : new Error(String(err)))\n    }\n  }\n\n  /** Send JPEG buffer, receive JSON detection results */\n  async runJpeg(jpeg: Buffer): Promise<Record<string, unknown>> {\n    if (!this.process?.stdin) {\n      throw new Error('PythonInferenceEngine: process not initialized')\n    }\n\n    return new Promise<Record<string, unknown>>((resolve, reject) => {\n      this.pendingResolve = resolve\n      this.pendingReject = reject\n\n      // Binary IPC: [4 bytes LE uint32 length][JPEG bytes]\n      const lengthBuf = Buffer.allocUnsafe(4)\n      lengthBuf.writeUInt32LE(jpeg.length, 0)\n      this.process!.stdin!.write(Buffer.concat([lengthBuf, jpeg]))\n    })\n  }\n\n  /** IInferenceEngine.run — wraps runJpeg for compatibility */\n  async run(_input: Float32Array, _inputShape: readonly number[]): Promise<Float32Array> {\n    throw new Error(\n      'PythonInferenceEngine: use runJpeg() directly — this engine operates on JPEG input',\n    )\n  }\n\n  /** IInferenceEngine.runMultiOutput — not supported by Python engine (operates on JPEG input) */\n  async runMultiOutput(\n    _input: Float32Array,\n    _inputShape: readonly number[],\n  ): Promise<Record<string, Float32Array>> {\n    throw new Error(\n      'PythonInferenceEngine: runMultiOutput() is not supported — this engine operates on JPEG input',\n    )\n  }\n\n  async dispose(): Promise<void> {\n    if (this.process) {\n      this.process.stdin?.end()\n      this.process.kill('SIGTERM')\n      this.process = null\n    }\n  }\n}\n\n/**\n * Resolve Python binary for ML inference. Priority:\n * 1. Explicit config pythonPath\n * 2. Embedded (data/deps/python/bin/python3)\n * 3. System PATH (python3, python)\n * 4. Download standalone Python\n *\n * Returns null if Python is not available.\n */\nexport async function resolvePythonBinary(\n  configPath: string | undefined,\n  deps: IAddonDepsManager,\n): Promise<string | null> {\n  if (configPath) return configPath\n  return deps.ensurePython()\n}\n","// TODO: Wire PythonInferenceEngine for PyTorch/OpenVINO/TFLite runtimes\n// Currently falls back to ONNX CPU when non-ONNX runtime is requested.\n// See: packages/addon-vision/python/ for stub implementations.\n//\n// WHY THIS FILE USES RAW FILESYSTEM PATHS (modelsDir: string):\n//\n// Model files must be loaded via absolute filesystem paths because inference\n// engines (ONNX Runtime, CoreML, etc.) require direct file access -- they do\n// not accept Buffer or stream inputs. This is fundamentally different from\n// user data (recordings, media) where IAddonFileStorage abstraction makes\n// sense. Models are closer to binaries or compiled artifacts that must live\n// on the local filesystem at runtime.\n//\n// IAddonFileStorage.readFile() returns a Buffer, but onnxruntime-node's\n// InferenceSession.create() only accepts a file path string or a Uint8Array\n// loaded into memory. For large models (hundreds of MB), loading into a\n// Uint8Array is impractical. Therefore, modelsDir stays as a raw string path\n// and is intentionally NOT replaced with IAddonFileStorage here.\n\nimport type {\n  IInferenceEngine,\n  DetectionRuntime,\n  ModelCatalogEntry,\n  ModelFormat,\n  IAddonModelManager,\n} from '@camstack/types'\nimport * as fs from 'node:fs'\nimport * as path from 'node:path'\nimport { NodeInferenceEngine } from './node-engine.js'\nimport { PythonInferenceEngine } from './python-engine.js'\n\nexport interface EngineResolverOptions {\n  readonly runtime: DetectionRuntime | 'auto'\n  readonly backend: string\n  readonly modelEntry: ModelCatalogEntry\n  readonly modelsDir: string\n  readonly pythonPath?: string\n  /** Model service for downloading models. When provided, used instead of raw filesystem probing. */\n  readonly models?: IAddonModelManager\n}\n\nexport interface ResolvedEngine {\n  readonly engine: IInferenceEngine\n  readonly format: ModelFormat\n  readonly modelPath: string\n}\n\n/** Priority order for auto-selection of ONNX backends */\nconst AUTO_BACKEND_PRIORITY = ['coreml', 'cuda', 'tensorrt', 'cpu'] as const\n\n/** Map backend names to the model format they require.\n * CoreML backend uses ONNX format -- onnxruntime-node loads the .onnx file\n * and accelerates it via the CoreML execution provider internally.\n * Native .mlpackage is only for PythonInferenceEngine. */\nconst BACKEND_TO_FORMAT: Readonly<Record<string, ModelFormat>> = {\n  cpu: 'onnx',\n  coreml: 'onnx',\n  cuda: 'onnx',\n  tensorrt: 'onnx',\n} as const\n\n/** Map DetectionRuntime to ModelFormat */\nconst RUNTIME_TO_FORMAT: Readonly<Partial<Record<DetectionRuntime, ModelFormat>>> = {\n  onnx: 'onnx',\n  coreml: 'coreml',\n  openvino: 'openvino',\n  tflite: 'tflite',\n  pytorch: 'pt',\n} as const\n\nfunction modelFilePath(modelsDir: string, modelEntry: ModelCatalogEntry, format: ModelFormat): string {\n  const formatEntry = modelEntry.formats[format]\n  if (!formatEntry) {\n    throw new Error(`Model ${modelEntry.id} has no ${format} format`)\n  }\n  // Derive filename from URL\n  const urlParts = formatEntry.url.split('/')\n  const filename = urlParts[urlParts.length - 1] ?? `${modelEntry.id}.${format}`\n  return path.join(modelsDir, filename)\n}\n\nfunction modelExists(filePath: string): boolean {\n  try {\n    return fs.existsSync(filePath)\n  } catch {\n    return false\n  }\n}\n\nexport async function resolveEngine(options: EngineResolverOptions): Promise<ResolvedEngine> {\n  const { runtime, backend, modelEntry, modelsDir, models } = options\n\n  let selectedFormat: ModelFormat\n  let selectedBackend: string\n\n  if (runtime === 'auto') {\n    // Probe available ONNX backends and pick best\n    const available = await probeOnnxBackends()\n\n    // Pick first priority backend that has a corresponding model format available\n    let chosen: { backend: string; format: ModelFormat } | null = null\n\n    for (const b of AUTO_BACKEND_PRIORITY) {\n      if (!available.includes(b)) continue\n      const fmt = BACKEND_TO_FORMAT[b]\n      if (!fmt) continue\n      if (!modelEntry.formats[fmt]) continue\n      chosen = { backend: b, format: fmt }\n      break\n    }\n\n    if (!chosen) {\n      throw new Error(\n        `resolveEngine: no compatible backend found for model ${modelEntry.id}. Available backends: ${available.join(', ')}`,\n      )\n    }\n\n    selectedFormat = chosen.format\n    selectedBackend = chosen.backend\n  } else {\n    // Explicit runtime requested\n    const fmt = RUNTIME_TO_FORMAT[runtime]\n    if (!fmt) {\n      throw new Error(`resolveEngine: unsupported runtime \"${runtime}\"`)\n    }\n    if (!modelEntry.formats[fmt]) {\n      throw new Error(\n        `resolveEngine: model ${modelEntry.id} has no ${fmt} format for runtime ${runtime}`,\n      )\n    }\n    selectedFormat = fmt\n    // For onnx runtime, use the provided backend; otherwise use the runtime name\n    selectedBackend = runtime === 'onnx' ? (backend || 'cpu') : runtime\n  }\n\n  // Download model and extra files via the unified service\n  let modelPath: string\n\n  if (models) {\n    // Use the unified ModelDownloadService\n    modelPath = await models.ensure(modelEntry.id, selectedFormat)\n  } else {\n    // Fallback: direct filesystem check (no download capability)\n    modelPath = modelFilePath(modelsDir, modelEntry, selectedFormat)\n    if (!modelExists(modelPath)) {\n      throw new Error(\n        `resolveEngine: model file not found at ${modelPath} and no model service provided`,\n      )\n    }\n  }\n\n  // NodeInferenceEngine handles ONNX format only (with any ONNX backend including CoreML provider).\n  // Native .mlpackage/.mlmodel files go to PythonInferenceEngine below.\n  if (selectedFormat === 'onnx') {\n    const engine = new NodeInferenceEngine(modelPath, selectedBackend)\n    await engine.initialize()\n    return { engine, format: selectedFormat, modelPath }\n  }\n\n  // For non-ONNX/CoreML formats, try PythonInferenceEngine when a python binary is available\n  const { pythonPath } = options\n  const PYTHON_SCRIPT_MAP: Readonly<Record<string, string>> = {\n    coreml: 'coreml_inference.py',\n    pytorch: 'pytorch_inference.py',\n    openvino: 'openvino_inference.py',\n  } as const\n\n  const effectiveRuntime = runtime === 'auto' ? selectedBackend : runtime\n  const scriptName = PYTHON_SCRIPT_MAP[effectiveRuntime]\n\n  if (scriptName && pythonPath) {\n    // Resolve python script path -- search multiple locations:\n    // - src/shared/ -> ../../python/ (source development)\n    // - dist/shared/ -> ../../python/ (installed addon with python/ at package root)\n    // - dist/ -> ../python/ (flat dist)\n    const candidates = [\n      path.join(__dirname, '../../python', scriptName),\n      path.join(__dirname, '../python', scriptName),\n      path.join(__dirname, '../../../python', scriptName),\n    ]\n    const scriptPath = candidates.find(p => fs.existsSync(p))\n    if (!scriptPath) {\n      throw new Error(\n        `resolveEngine: Python script \"${scriptName}\" not found. Searched:\\n${candidates.join('\\n')}`,\n      )\n    }\n    const inputSize = Math.max(modelEntry.inputSize.width, modelEntry.inputSize.height)\n    const engine = new PythonInferenceEngine(pythonPath, scriptPath, effectiveRuntime as DetectionRuntime, modelPath, [\n      `--input-size=${inputSize}`,\n      `--confidence=0.25`,\n    ])\n    await engine.initialize()\n    return { engine, format: selectedFormat, modelPath }\n  }\n\n  // Final fallback: use ONNX CPU if available\n  const fallbackPath = modelFilePath(modelsDir, modelEntry, 'onnx')\n  if (modelEntry.formats['onnx'] && modelExists(fallbackPath)) {\n    const engine = new NodeInferenceEngine(fallbackPath, 'cpu')\n    await engine.initialize()\n    return { engine, format: 'onnx', modelPath: fallbackPath }\n  }\n\n  throw new Error(\n    `resolveEngine: format ${selectedFormat} is not yet supported by NodeInferenceEngine, ` +\n    `no Python runtime is available, and no ONNX fallback exists`,\n  )\n}\n\n/** Probe which ONNX execution providers are available on this system */\nexport async function probeOnnxBackends(): Promise<string[]> {\n  const available: string[] = ['cpu'] // CPU is always available\n\n  try {\n    const ort = await import('onnxruntime-node')\n    // eslint-disable-next-line @typescript-eslint/no-explicit-any\n    const providers: string[] = (ort as any).env?.webgl?.disabled !== undefined\n      // eslint-disable-next-line @typescript-eslint/no-explicit-any\n      ? ((ort as any).InferenceSession?.getAvailableProviders?.() ?? [])\n      : []\n\n    for (const p of providers) {\n      const normalized = p.toLowerCase().replace('executionprovider', '')\n      if (normalized === 'coreml') available.push('coreml')\n      else if (normalized === 'cuda') available.push('cuda')\n      else if (normalized === 'tensorrt') available.push('tensorrt')\n    }\n  } catch {\n    // onnxruntime-node may not be installed; CPU only\n  }\n\n  // Platform-specific hints when getAvailableProviders isn't exposed\n  if (process.platform === 'darwin' && !available.includes('coreml')) {\n    available.push('coreml')\n  }\n\n  return [...new Set(available)]\n}\n"],"mappings":";AACA,YAAY,UAAU;AAEtB,IAAM,sBAAwD;AAAA,EAC5D,KAAK;AAAA,EACL,QAAQ;AAAA,EACR,MAAM;AAAA,EACN,UAAU;AAAA,EACV,KAAK;AACP;AAEA,IAAM,oBAA+D;AAAA,EACnE,KAAK;AAAA,EACL,QAAQ;AAAA,EACR,MAAM;AAAA,EACN,UAAU;AACZ;AAEO,IAAM,sBAAN,MAAsD;AAAA,EAK3D,YACmB,WACA,SACjB;AAFiB;AACA;AAEjB,SAAK,SAAU,kBAAkB,OAAO,KAAK;AAAA,EAC/C;AAAA,EATS,UAA4B;AAAA,EAC5B;AAAA,EACD,UAAmB;AAAA,EAS3B,MAAM,aAA4B;AAChC,UAAM,MAAM,MAAM,OAAO,kBAAkB;AAC3C,UAAM,WAAW,oBAAoB,KAAK,OAAO,KAAK;AAGtD,UAAM,eAAoB,gBAAW,KAAK,SAAS,IAC/C,KAAK,YACA,aAAQ,QAAQ,IAAI,GAAG,KAAK,SAAS;AAE9C,UAAM,iBAA0C;AAAA,MAC9C,oBAAoB,CAAC,QAAQ;AAAA,IAC/B;AAGA,SAAK,UAAU,MAAO,IAAY,iBAAiB,OAAO,cAAc,cAAc;AAAA,EACxF;AAAA,EAEA,MAAM,IAAI,OAAqB,YAAsD;AACnF,QAAI,CAAC,KAAK,SAAS;AACjB,YAAM,IAAI,MAAM,qEAAgE;AAAA,IAClF;AAEA,UAAM,MAAM,MAAM,OAAO,kBAAkB;AAE3C,UAAM,OAAO,KAAK;AAGlB,UAAM,YAAoB,KAAK,WAAW,CAAC;AAE3C,UAAM,SAAS,IAAK,IAAY,OAAO,WAAW,OAAO,CAAC,GAAG,UAAU,CAAC;AACxE,UAAM,QAAiC,EAAE,CAAC,SAAS,GAAG,OAAO;AAE7D,UAAM,UAAU,MAAM,KAAK,IAAI,KAAK;AACpC,UAAM,aAAqB,KAAK,YAAY,CAAC;AAC7C,UAAM,eAAe,QAAQ,UAAU;AAEvC,WAAO,aAAa;AAAA,EACtB;AAAA,EAEA,MAAM,eACJ,OACA,YACuC;AACvC,QAAI,CAAC,KAAK,SAAS;AACjB,YAAM,IAAI,MAAM,qEAAgE;AAAA,IAClF;AAEA,UAAM,MAAM,MAAM,OAAO,kBAAkB;AAE3C,UAAM,OAAO,KAAK;AAElB,UAAM,YAAoB,KAAK,WAAW,CAAC;AAE3C,UAAM,SAAS,IAAK,IAAY,OAAO,WAAW,OAAO,CAAC,GAAG,UAAU,CAAC;AACxE,UAAM,QAAiC,EAAE,CAAC,SAAS,GAAG,OAAO;AAE7D,UAAM,UAAU,MAAM,KAAK,IAAI,KAAK;AAEpC,UAAM,MAAoC,CAAC;AAC3C,eAAW,QAAQ,KAAK,aAAyB;AAC/C,UAAI,IAAI,IAAI,QAAQ,IAAI,EAAE;AAAA,IAC5B;AACA,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,UAAyB;AAG7B,SAAK,UAAU;AAAA,EACjB;AACF;;;ACnGA,SAAS,aAAgC;AAElC,IAAM,wBAAN,MAAwD;AAAA,EAQ7D,YACmB,YACA,YACjB,SACiB,WACA,YAA+B,CAAC,GACjD;AALiB;AACA;AAEA;AACA;AAEjB,SAAK,UAAU;AAEf,UAAM,mBAAwE;AAAA,MAC5E,MAAM;AAAA,MACN,QAAQ;AAAA,MACR,SAAS;AAAA,MACT,UAAU;AAAA,MACV,QAAQ;AAAA,IACV;AACA,SAAK,SAAS,iBAAiB,OAAO;AAAA,EACxC;AAAA,EAxBS;AAAA,EACA;AAAA,EACD,UAA+B;AAAA,EAC/B,gBAAwB,OAAO,MAAM,CAAC;AAAA,EACtC,iBAAoE;AAAA,EACpE,gBAAkD;AAAA,EAqB1D,MAAM,aAA4B;AAChC,UAAM,OAAO,CAAC,KAAK,YAAY,KAAK,WAAW,GAAG,KAAK,SAAS;AAChE,SAAK,UAAU,MAAM,KAAK,YAAY,MAAM;AAAA,MAC1C,OAAO,CAAC,QAAQ,QAAQ,MAAM;AAAA,IAChC,CAAC;AAED,QAAI,CAAC,KAAK,QAAQ,UAAU,CAAC,KAAK,QAAQ,OAAO;AAC/C,YAAM,IAAI,MAAM,uDAAuD;AAAA,IACzE;AAEA,SAAK,QAAQ,QAAQ,GAAG,QAAQ,CAAC,UAAkB;AAEjD,cAAQ,OAAO,MAAM,mBAAmB,MAAM,SAAS,CAAC,EAAE;AAAA,IAC5D,CAAC;AAED,SAAK,QAAQ,GAAG,SAAS,CAAC,QAAQ;AAChC,WAAK,gBAAgB,GAAG;AACxB,WAAK,gBAAgB;AACrB,WAAK,iBAAiB;AAAA,IACxB,CAAC;AAED,SAAK,QAAQ,GAAG,QAAQ,CAAC,SAAS;AAChC,UAAI,SAAS,GAAG;AACd,cAAM,MAAM,IAAI,MAAM,mDAAmD,IAAI,EAAE;AAC/E,aAAK,gBAAgB,GAAG;AACxB,aAAK,gBAAgB;AACrB,aAAK,iBAAiB;AAAA,MACxB;AAAA,IACF,CAAC;AAED,SAAK,QAAQ,OAAO,GAAG,QAAQ,CAAC,UAAkB;AAChD,WAAK,gBAAgB,OAAO,OAAO,CAAC,KAAK,eAAe,KAAK,CAAC;AAC9D,WAAK,YAAY;AAAA,IACnB,CAAC;AAGD,UAAM,IAAI,QAAc,CAACA,UAAS,WAAW;AAC3C,YAAM,UAAU,WAAW,MAAMA,SAAQ,GAAG,GAAI;AAChD,WAAK,SAAS,GAAG,SAAS,CAAC,QAAQ;AACjC,qBAAa,OAAO;AACpB,eAAO,GAAG;AAAA,MACZ,CAAC;AACD,WAAK,SAAS,GAAG,QAAQ,CAAC,SAAS;AACjC,qBAAa,OAAO;AACpB,YAAI,SAAS,GAAG;AACd,iBAAO,IAAI,MAAM,yDAAyD,IAAI,EAAE,CAAC;AAAA,QACnF;AAAA,MACF,CAAC;AAAA,IACH,CAAC;AAAA,EACH;AAAA,EAEQ,cAAoB;AAE1B,QAAI,KAAK,cAAc,SAAS,EAAG;AAEnC,UAAM,SAAS,KAAK,cAAc,aAAa,CAAC;AAChD,QAAI,KAAK,cAAc,SAAS,IAAI,OAAQ;AAE5C,UAAM,YAAY,KAAK,cAAc,SAAS,GAAG,IAAI,MAAM;AAC3D,SAAK,gBAAgB,KAAK,cAAc,SAAS,IAAI,MAAM;AAE3D,UAAMA,WAAU,KAAK;AACrB,UAAM,SAAS,KAAK;AACpB,SAAK,iBAAiB;AACtB,SAAK,gBAAgB;AAErB,QAAI,CAACA,SAAS;AAEd,QAAI;AACF,YAAM,SAAS,KAAK,MAAM,UAAU,SAAS,MAAM,CAAC;AACpD,MAAAA,SAAQ,MAAM;AAAA,IAChB,SAAS,KAAK;AACZ,eAAS,eAAe,QAAQ,MAAM,IAAI,MAAM,OAAO,GAAG,CAAC,CAAC;AAAA,IAC9D;AAAA,EACF;AAAA;AAAA,EAGA,MAAM,QAAQ,MAAgD;AAC5D,QAAI,CAAC,KAAK,SAAS,OAAO;AACxB,YAAM,IAAI,MAAM,gDAAgD;AAAA,IAClE;AAEA,WAAO,IAAI,QAAiC,CAACA,UAAS,WAAW;AAC/D,WAAK,iBAAiBA;AACtB,WAAK,gBAAgB;AAGrB,YAAM,YAAY,OAAO,YAAY,CAAC;AACtC,gBAAU,cAAc,KAAK,QAAQ,CAAC;AACtC,WAAK,QAAS,MAAO,MAAM,OAAO,OAAO,CAAC,WAAW,IAAI,CAAC,CAAC;AAAA,IAC7D,CAAC;AAAA,EACH;AAAA;AAAA,EAGA,MAAM,IAAI,QAAsB,aAAuD;AACrF,UAAM,IAAI;AAAA,MACR;AAAA,IACF;AAAA,EACF;AAAA;AAAA,EAGA,MAAM,eACJ,QACA,aACuC;AACvC,UAAM,IAAI;AAAA,MACR;AAAA,IACF;AAAA,EACF;AAAA,EAEA,MAAM,UAAyB;AAC7B,QAAI,KAAK,SAAS;AAChB,WAAK,QAAQ,OAAO,IAAI;AACxB,WAAK,QAAQ,KAAK,SAAS;AAC3B,WAAK,UAAU;AAAA,IACjB;AAAA,EACF;AACF;;;ACzHA,YAAY,QAAQ;AACpB,YAAYC,WAAU;AAqBtB,IAAM,wBAAwB,CAAC,UAAU,QAAQ,YAAY,KAAK;AAMlE,IAAM,oBAA2D;AAAA,EAC/D,KAAK;AAAA,EACL,QAAQ;AAAA,EACR,MAAM;AAAA,EACN,UAAU;AACZ;AAGA,IAAM,oBAA8E;AAAA,EAClF,MAAM;AAAA,EACN,QAAQ;AAAA,EACR,UAAU;AAAA,EACV,QAAQ;AAAA,EACR,SAAS;AACX;AAEA,SAAS,cAAc,WAAmB,YAA+B,QAA6B;AACpG,QAAM,cAAc,WAAW,QAAQ,MAAM;AAC7C,MAAI,CAAC,aAAa;AAChB,UAAM,IAAI,MAAM,SAAS,WAAW,EAAE,WAAW,MAAM,SAAS;AAAA,EAClE;AAEA,QAAM,WAAW,YAAY,IAAI,MAAM,GAAG;AAC1C,QAAM,WAAW,SAAS,SAAS,SAAS,CAAC,KAAK,GAAG,WAAW,EAAE,IAAI,MAAM;AAC5E,SAAY,WAAK,WAAW,QAAQ;AACtC;AAEA,SAAS,YAAY,UAA2B;AAC9C,MAAI;AACF,WAAU,cAAW,QAAQ;AAAA,EAC/B,QAAQ;AACN,WAAO;AAAA,EACT;AACF;AAEA,eAAsB,cAAc,SAAyD;AAC3F,QAAM,EAAE,SAAS,SAAS,YAAY,WAAW,OAAO,IAAI;AAE5D,MAAI;AACJ,MAAI;AAEJ,MAAI,YAAY,QAAQ;AAEtB,UAAM,YAAY,MAAM,kBAAkB;AAG1C,QAAI,SAA0D;AAE9D,eAAW,KAAK,uBAAuB;AACrC,UAAI,CAAC,UAAU,SAAS,CAAC,EAAG;AAC5B,YAAM,MAAM,kBAAkB,CAAC;AAC/B,UAAI,CAAC,IAAK;AACV,UAAI,CAAC,WAAW,QAAQ,GAAG,EAAG;AAC9B,eAAS,EAAE,SAAS,GAAG,QAAQ,IAAI;AACnC;AAAA,IACF;AAEA,QAAI,CAAC,QAAQ;AACX,YAAM,IAAI;AAAA,QACR,wDAAwD,WAAW,EAAE,yBAAyB,UAAU,KAAK,IAAI,CAAC;AAAA,MACpH;AAAA,IACF;AAEA,qBAAiB,OAAO;AACxB,sBAAkB,OAAO;AAAA,EAC3B,OAAO;AAEL,UAAM,MAAM,kBAAkB,OAAO;AACrC,QAAI,CAAC,KAAK;AACR,YAAM,IAAI,MAAM,uCAAuC,OAAO,GAAG;AAAA,IACnE;AACA,QAAI,CAAC,WAAW,QAAQ,GAAG,GAAG;AAC5B,YAAM,IAAI;AAAA,QACR,wBAAwB,WAAW,EAAE,WAAW,GAAG,uBAAuB,OAAO;AAAA,MACnF;AAAA,IACF;AACA,qBAAiB;AAEjB,sBAAkB,YAAY,SAAU,WAAW,QAAS;AAAA,EAC9D;AAGA,MAAI;AAEJ,MAAI,QAAQ;AAEV,gBAAY,MAAM,OAAO,OAAO,WAAW,IAAI,cAAc;AAAA,EAC/D,OAAO;AAEL,gBAAY,cAAc,WAAW,YAAY,cAAc;AAC/D,QAAI,CAAC,YAAY,SAAS,GAAG;AAC3B,YAAM,IAAI;AAAA,QACR,0CAA0C,SAAS;AAAA,MACrD;AAAA,IACF;AAAA,EACF;AAIA,MAAI,mBAAmB,QAAQ;AAC7B,UAAM,SAAS,IAAI,oBAAoB,WAAW,eAAe;AACjE,UAAM,OAAO,WAAW;AACxB,WAAO,EAAE,QAAQ,QAAQ,gBAAgB,UAAU;AAAA,EACrD;AAGA,QAAM,EAAE,WAAW,IAAI;AACvB,QAAM,oBAAsD;AAAA,IAC1D,QAAQ;AAAA,IACR,SAAS;AAAA,IACT,UAAU;AAAA,EACZ;AAEA,QAAM,mBAAmB,YAAY,SAAS,kBAAkB;AAChE,QAAM,aAAa,kBAAkB,gBAAgB;AAErD,MAAI,cAAc,YAAY;AAK5B,UAAM,aAAa;AAAA,MACZ,WAAK,WAAW,gBAAgB,UAAU;AAAA,MAC1C,WAAK,WAAW,aAAa,UAAU;AAAA,MACvC,WAAK,WAAW,mBAAmB,UAAU;AAAA,IACpD;AACA,UAAM,aAAa,WAAW,KAAK,OAAQ,cAAW,CAAC,CAAC;AACxD,QAAI,CAAC,YAAY;AACf,YAAM,IAAI;AAAA,QACR,iCAAiC,UAAU;AAAA,EAA2B,WAAW,KAAK,IAAI,CAAC;AAAA,MAC7F;AAAA,IACF;AACA,UAAM,YAAY,KAAK,IAAI,WAAW,UAAU,OAAO,WAAW,UAAU,MAAM;AAClF,UAAM,SAAS,IAAI,sBAAsB,YAAY,YAAY,kBAAsC,WAAW;AAAA,MAChH,gBAAgB,SAAS;AAAA,MACzB;AAAA,IACF,CAAC;AACD,UAAM,OAAO,WAAW;AACxB,WAAO,EAAE,QAAQ,QAAQ,gBAAgB,UAAU;AAAA,EACrD;AAGA,QAAM,eAAe,cAAc,WAAW,YAAY,MAAM;AAChE,MAAI,WAAW,QAAQ,MAAM,KAAK,YAAY,YAAY,GAAG;AAC3D,UAAM,SAAS,IAAI,oBAAoB,cAAc,KAAK;AAC1D,UAAM,OAAO,WAAW;AACxB,WAAO,EAAE,QAAQ,QAAQ,QAAQ,WAAW,aAAa;AAAA,EAC3D;AAEA,QAAM,IAAI;AAAA,IACR,yBAAyB,cAAc;AAAA,EAEzC;AACF;AAGA,eAAsB,oBAAuC;AAC3D,QAAM,YAAsB,CAAC,KAAK;AAElC,MAAI;AACF,UAAM,MAAM,MAAM,OAAO,kBAAkB;AAE3C,UAAM,YAAuB,IAAY,KAAK,OAAO,aAAa,SAE5D,IAAY,kBAAkB,wBAAwB,KAAK,CAAC,IAC9D,CAAC;AAEL,eAAW,KAAK,WAAW;AACzB,YAAM,aAAa,EAAE,YAAY,EAAE,QAAQ,qBAAqB,EAAE;AAClE,UAAI,eAAe,SAAU,WAAU,KAAK,QAAQ;AAAA,eAC3C,eAAe,OAAQ,WAAU,KAAK,MAAM;AAAA,eAC5C,eAAe,WAAY,WAAU,KAAK,UAAU;AAAA,IAC/D;AAAA,EACF,QAAQ;AAAA,EAER;AAGA,MAAI,QAAQ,aAAa,YAAY,CAAC,UAAU,SAAS,QAAQ,GAAG;AAClE,cAAU,KAAK,QAAQ;AAAA,EACzB;AAEA,SAAO,CAAC,GAAG,IAAI,IAAI,SAAS,CAAC;AAC/B;","names":["resolve","path"]}

package/dist/chunk-7DYHXUPZ.mjs

@@ -0,0 +1,36 @@
+import {
+  MLPACKAGE_FILES
+} from "./chunk-BP7H4NFS.mjs";
+
+// src/catalogs/segmentation-refiner-models.ts
+import { hfModelUrl } from "@camstack/types";
+var HF_REPO = "camstack/camstack-models";
+var hf = (path) => hfModelUrl(HF_REPO, path);
+var MASK_LABELS = [
+  { id: "mask", name: "Segmentation Mask" }
+];
+var SEGMENTATION_REFINER_MODELS = [
+  {
+    id: "u2netp",
+    name: "U2-Net Portable",
+    description: "U2-Net-P \u2014 ultra-lightweight salient object segmentation (4.7 MB), no prompt needed",
+    inputSize: { width: 320, height: 320 },
+    labels: MASK_LABELS,
+    formats: {
+      onnx: { url: hf("segmentationRefiner/u2netp/onnx/camstack-u2netp.onnx"), sizeMB: 5 },
+      coreml: {
+        url: hf("segmentationRefiner/u2netp/coreml/camstack-u2netp.mlpackage"),
+        sizeMB: 3,
+        isDirectory: true,
+        files: MLPACKAGE_FILES,
+        runtimes: ["python"]
+      }
+      // OpenVINO: not yet converted
+    }
+  }
+];
+
+export {
+  SEGMENTATION_REFINER_MODELS
+};
+//# sourceMappingURL=chunk-7DYHXUPZ.mjs.map

package/dist/chunk-7DYHXUPZ.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/catalogs/segmentation-refiner-models.ts"],"sourcesContent":["import type { ModelCatalogEntry, LabelDefinition } from '@camstack/types'\nimport { hfModelUrl } from '@camstack/types'\nimport { MLPACKAGE_FILES } from './object-detection-models.js'\n\nconst HF_REPO = 'camstack/camstack-models'\n\nconst hf = (path: string) => hfModelUrl(HF_REPO, path)\n\nconst MASK_LABELS: readonly LabelDefinition[] = [\n  { id: 'mask', name: 'Segmentation Mask' },\n]\n\nexport const SEGMENTATION_REFINER_MODELS: readonly ModelCatalogEntry[] = [\n  {\n    id: 'u2netp',\n    name: 'U2-Net Portable',\n    description: 'U2-Net-P — ultra-lightweight salient object segmentation (4.7 MB), no prompt needed',\n    inputSize: { width: 320, height: 320 },\n    labels: MASK_LABELS,\n    formats: {\n      onnx: { url: hf('segmentationRefiner/u2netp/onnx/camstack-u2netp.onnx'), sizeMB: 5 },\n      coreml: {\n        url: hf('segmentationRefiner/u2netp/coreml/camstack-u2netp.mlpackage'),\n        sizeMB: 3,\n        isDirectory: true,\n        files: MLPACKAGE_FILES,\n        runtimes: ['python'],\n      },\n      // OpenVINO: not yet converted\n    },\n  },\n]\n"],"mappings":";;;;;AACA,SAAS,kBAAkB;AAG3B,IAAM,UAAU;AAEhB,IAAM,KAAK,CAAC,SAAiB,WAAW,SAAS,IAAI;AAErD,IAAM,cAA0C;AAAA,EAC9C,EAAE,IAAI,QAAQ,MAAM,oBAAoB;AAC1C;AAEO,IAAM,8BAA4D;AAAA,EACvE;AAAA,IACE,IAAI;AAAA,IACJ,MAAM;AAAA,IACN,aAAa;AAAA,IACb,WAAW,EAAE,OAAO,KAAK,QAAQ,IAAI;AAAA,IACrC,QAAQ;AAAA,IACR,SAAS;AAAA,MACP,MAAM,EAAE,KAAK,GAAG,sDAAsD,GAAG,QAAQ,EAAE;AAAA,MACnF,QAAQ;AAAA,QACN,KAAK,GAAG,6DAA6D;AAAA,QACrE,QAAQ;AAAA,QACR,aAAa;AAAA,QACb,OAAO;AAAA,QACP,UAAU,CAAC,QAAQ;AAAA,MACrB;AAAA;AAAA,IAEF;AAAA,EACF;AACF;","names":[]}

package/dist/chunk-BJTO5JO5.mjs

@@ -0,0 +1,11 @@
+var __require = /* @__PURE__ */ ((x) => typeof require !== "undefined" ? require : typeof Proxy !== "undefined" ? new Proxy(x, {
+  get: (a, b) => (typeof require !== "undefined" ? require : a)[b]
+}) : x)(function(x) {
+  if (typeof require !== "undefined") return require.apply(this, arguments);
+  throw Error('Dynamic require of "' + x + '" is not supported');
+});
+
+export {
+  __require
+};
+//# sourceMappingURL=chunk-BJTO5JO5.mjs.map