@camstack/addon-vision 0.1.7 → 0.1.9

package/dist/index.mjs

@@ -1,2730 +1,282 @@
 import {
-  require_animal_classification_models
-} from "./chunk-XD7WGXHZ.mjs";
+  BirdGlobalClassifierAddon
+} from "./chunk-ZWYXXCXP.mjs";
 import {
-  require_vehicle_classification_models
-} from "./chunk-K36R6HWY.mjs";
+  BirdNABirdsClassifierAddon
+} from "./chunk-DRYFGARD.mjs";
 import {
-  require_segmentation_refiner_models
-} from "./chunk-BS4DKYGN.mjs";
+  AnimalClassifierAddon
+} from "./chunk-YUCD2TFH.mjs";
 import {
-  require_frame_diff
-} from "./chunk-YYDM6V2F.mjs";
+  ANIMAL_TYPE_MODELS,
+  BIRD_NABIRDS_MODELS,
+  BIRD_SPECIES_MODELS
+} from "./chunk-DUN6XU3N.mjs";
 import {
-  require_segmentation_models,
-  require_yolo_seg
-} from "./chunk-ZK7P3TZN.mjs";
+  VEHICLE_TYPE_MODELS
+} from "./chunk-XZ6ZMXXU.mjs";
 import {
-  require_face_detection_models,
-  require_scrfd
-} from "./chunk-2YMA6QOV.mjs";
+  SEGMENTATION_REFINER_MODELS
+} from "./chunk-7DYHXUPZ.mjs";
 import {
-  require_arcface,
-  require_face_recognition_models
-} from "./chunk-F6D2OZ36.mjs";
+  detectMotion
+} from "./chunk-BR2FPGOX.mjs";
 import {
-  require_plate_detection_models
-} from "./chunk-GAOIFQDX.mjs";
+  ObjectDetectionAddon,
+  SEGMENTATION_MODELS
+} from "./chunk-R5J3WAUI.mjs";
 import {
-  require_yolo
-} from "./chunk-DE7I3VHO.mjs";
+  FACE_DETECTION_MODELS,
+  FaceDetectionAddon,
+  scrfdPostprocess
+} from "./chunk-ESLHNWWE.mjs";
 import {
-  require_object_detection_models
-} from "./chunk-MGT6RUVX.mjs";
+  FACE_RECOGNITION_MODELS,
+  FaceRecognitionAddon,
+  cosineSimilarity,
+  l2Normalize
+} from "./chunk-JUQEW6ON.mjs";
 import {
-  require_paddleocr,
-  require_plate_recognition_models
-} from "./chunk-HUIX2XVR.mjs";
+  PLATE_DETECTION_MODELS,
+  PlateDetectionAddon
+} from "./chunk-YPU4WTXZ.mjs";
 import {
-  require_image_utils
-} from "./chunk-WG66JYYW.mjs";
+  iou,
+  nms,
+  yoloPostprocess
+} from "./chunk-KUO2BVFY.mjs";
 import {
-  require_audio_classification_models,
-  require_yamnet
-} from "./chunk-MBTAI3WE.mjs";
+  MLPACKAGE_FILES,
+  OBJECT_DETECTION_MODELS
+} from "./chunk-BP7H4NFS.mjs";
 import {
-  require_engine_resolver,
-  require_node_engine,
-  require_python_engine
-} from "./chunk-PIFS7AIT.mjs";
+  PLATE_RECOGNITION_MODELS,
+  PlateRecognitionAddon,
+  ctcDecode
+} from "./chunk-ZTJENCFC.mjs";
 import {
-  __commonJS,
-  __export,
-  __reExport,
-  __require,
-  __toESM
-} from "./chunk-3IIFBJCD.mjs";
+  cropRegion,
+  jpegToRgb,
+  letterbox,
+  resizeAndNormalize,
+  rgbToGrayscale
+} from "./chunk-22BHCDT5.mjs";
+import {
+  AUDIO_CLASSIFICATION_MODELS,
+  AudioClassificationAddon,
+  yamnetPostprocess
+} from "./chunk-D6WEHN33.mjs";
+import {
+  NodeInferenceEngine,
+  PythonInferenceEngine,
+  probeOnnxBackends,
+  resolveEngine
+} from "./chunk-2IOKI4ES.mjs";
+import "./chunk-BJTO5JO5.mjs";
 
-// src/catalogs/general-ocr-models.js
-var require_general_ocr_models = __commonJS({
-  "src/catalogs/general-ocr-models.js"(exports) {
-    "use strict";
-    Object.defineProperty(exports, "__esModule", { value: true });
-    exports.GENERAL_OCR_MODELS = void 0;
-    var types_1 = __require("@camstack/types");
-    var HF_REPO = "camstack/camstack-models";
-    var OCR_TEXT_LABELS = [
-      { id: "text", name: "Scene Text" }
-    ];
-    exports.GENERAL_OCR_MODELS = [
-      // ── OnnxTR / docTR — lightweight general scene text recognition ──
-      {
-        id: "doctr-det-db-mobilenet",
-        name: "docTR Detection MobileNet",
-        description: "docTR DBNet MobileNet V3 \u2014 lightweight text region detection for scene text",
-        inputSize: { width: 1024, height: 1024 },
-        labels: OCR_TEXT_LABELS,
-        formats: {
-          onnx: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/doctr/onnx/camstack-doctr-det-db-mobilenet-v3.onnx"),
-            sizeMB: 15
-          },
-          coreml: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/doctr/coreml/camstack-doctr-det-db-mobilenet-v3.mlpackage"),
-            sizeMB: 8,
-            isDirectory: true,
-            files: [
-              "Manifest.json",
-              "Data/com.apple.CoreML/model.mlmodel",
-              "Data/com.apple.CoreML/weights/weight.bin"
-            ],
-            runtimes: ["python"]
-          },
-          openvino: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/doctr/openvino/camstack-doctr-det-db-mobilenet-v3.xml"),
-            sizeMB: 8,
-            runtimes: ["python"]
-          }
-        }
-      },
-      {
-        id: "doctr-rec-crnn-mobilenet",
-        name: "docTR Recognition CRNN MobileNet",
-        description: "docTR CRNN MobileNet V3 \u2014 lightweight text recognition for detected regions",
-        inputSize: { width: 128, height: 32 },
-        labels: OCR_TEXT_LABELS,
-        formats: {
-          onnx: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/doctr/onnx/camstack-doctr-rec-crnn-mobilenet-v3.onnx"),
-            sizeMB: 5
-          },
-          coreml: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/doctr/coreml/camstack-doctr-rec-crnn-mobilenet-v3.mlpackage"),
-            sizeMB: 3,
-            isDirectory: true,
-            files: [
-              "Manifest.json",
-              "Data/com.apple.CoreML/model.mlmodel",
-              "Data/com.apple.CoreML/weights/weight.bin"
-            ],
-            runtimes: ["python"]
-          },
-          openvino: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/doctr/openvino/camstack-doctr-rec-crnn-mobilenet-v3.xml"),
-            sizeMB: 3,
-            runtimes: ["python"]
-          }
-        }
+// src/catalogs/general-ocr-models.ts
+import { hfModelUrl } from "@camstack/types";
+var HF_REPO = "camstack/camstack-models";
+var OCR_TEXT_LABELS = [
+  { id: "text", name: "Scene Text" }
+];
+var GENERAL_OCR_MODELS = [
+  // ── OnnxTR / docTR — lightweight general scene text recognition ──
+  {
+    id: "doctr-det-db-mobilenet",
+    name: "docTR Detection MobileNet",
+    description: "docTR DBNet MobileNet V3 \u2014 lightweight text region detection for scene text",
+    inputSize: { width: 1024, height: 1024 },
+    labels: OCR_TEXT_LABELS,
+    formats: {
+      onnx: {
+        url: hfModelUrl(HF_REPO, "generalOcr/doctr/onnx/camstack-doctr-det-db-mobilenet-v3.onnx"),
+        sizeMB: 15
       },
-      {
-        id: "doctr-rec-parseq",
-        name: "docTR Recognition PARSeq",
-        description: "docTR PARSeq \u2014 high-accuracy scene text recognition (top ICDAR scores)",
-        inputSize: { width: 128, height: 32 },
-        labels: OCR_TEXT_LABELS,
-        formats: {
-          onnx: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/doctr/onnx/camstack-doctr-rec-parseq.onnx"),
-            sizeMB: 25
-          },
-          coreml: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/doctr/coreml/camstack-doctr-rec-parseq.mlpackage"),
-            sizeMB: 13,
-            isDirectory: true,
-            files: [
-              "Manifest.json",
-              "Data/com.apple.CoreML/model.mlmodel",
-              "Data/com.apple.CoreML/weights/weight.bin"
-            ],
-            runtimes: ["python"]
-          },
-          openvino: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/doctr/openvino/camstack-doctr-rec-parseq.xml"),
-            sizeMB: 13,
-            runtimes: ["python"]
-          }
-        }
-      },
-      // ── PaddleOCR PP-OCRv5 Mobile — general-purpose text detection + recognition ──
-      {
-        id: "ppocr-v5-det-mobile",
-        name: "PP-OCRv5 Detection Mobile",
-        description: "PP-OCRv5 mobile text detection \u2014 optimized for edge, 100+ languages",
-        inputSize: { width: 640, height: 640 },
-        labels: OCR_TEXT_LABELS,
-        formats: {
-          onnx: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/ppocr-v5/onnx/camstack-ppocr-v5-det-mobile.onnx"),
-            sizeMB: 6
-          },
-          coreml: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/ppocr-v5/coreml/camstack-ppocr-v5-det-mobile.mlpackage"),
-            sizeMB: 3,
-            isDirectory: true,
-            files: [
-              "Manifest.json",
-              "Data/com.apple.CoreML/model.mlmodel",
-              "Data/com.apple.CoreML/weights/weight.bin"
-            ],
-            runtimes: ["python"]
-          },
-          openvino: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/ppocr-v5/openvino/camstack-ppocr-v5-det-mobile.xml"),
-            sizeMB: 3,
-            runtimes: ["python"]
-          }
-        }
+      coreml: {
+        url: hfModelUrl(HF_REPO, "generalOcr/doctr/coreml/camstack-doctr-det-db-mobilenet-v3.mlpackage"),
+        sizeMB: 8,
+        isDirectory: true,
+        files: [
+          "Manifest.json",
+          "Data/com.apple.CoreML/model.mlmodel",
+          "Data/com.apple.CoreML/weights/weight.bin"
+        ],
+        runtimes: ["python"]
       },
-      {
-        id: "ppocr-v5-rec-mobile",
-        name: "PP-OCRv5 Recognition Mobile",
-        description: "PP-OCRv5 mobile text recognition \u2014 100+ languages, CTC decoding",
-        inputSize: { width: 320, height: 48 },
-        labels: OCR_TEXT_LABELS,
-        formats: {
-          onnx: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/ppocr-v5/onnx/camstack-ppocr-v5-rec-mobile.onnx"),
-            sizeMB: 8
-          },
-          coreml: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/ppocr-v5/coreml/camstack-ppocr-v5-rec-mobile.mlpackage"),
-            sizeMB: 4,
-            isDirectory: true,
-            files: [
-              "Manifest.json",
-              "Data/com.apple.CoreML/model.mlmodel",
-              "Data/com.apple.CoreML/weights/weight.bin"
-            ],
-            runtimes: ["python"]
-          },
-          openvino: {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/ppocr-v5/openvino/camstack-ppocr-v5-rec-mobile.xml"),
-            sizeMB: 4,
-            runtimes: ["python"]
-          }
-        },
-        extraFiles: [
-          {
-            url: (0, types_1.hfModelUrl)(HF_REPO, "generalOcr/ppocr-v5/camstack-ppocr-v5-keys.txt"),
-            filename: "camstack-ppocr-v5-keys.txt",
-            sizeMB: 0.1
-          }
-        ]
-      }
-    ];
-  }
-});
-
-// src/catalogs/index.js
-var require_catalogs = __commonJS({
-  "src/catalogs/index.js"(exports) {
-    "use strict";
-    var __createBinding = exports && exports.__createBinding || (Object.create ? (function(o, m, k, k2) {
-      if (k2 === void 0) k2 = k;
-      var desc = Object.getOwnPropertyDescriptor(m, k);
-      if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
-        desc = { enumerable: true, get: function() {
-          return m[k];
-        } };
-      }
-      Object.defineProperty(o, k2, desc);
-    }) : (function(o, m, k, k2) {
-      if (k2 === void 0) k2 = k;
-      o[k2] = m[k];
-    }));
-    var __exportStar = exports && exports.__exportStar || function(m, exports2) {
-      for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports2, p)) __createBinding(exports2, m, p);
-    };
-    Object.defineProperty(exports, "__esModule", { value: true });
-    __exportStar(require_object_detection_models(), exports);
-    __exportStar(require_face_detection_models(), exports);
-    __exportStar(require_face_recognition_models(), exports);
-    __exportStar(require_plate_detection_models(), exports);
-    __exportStar(require_plate_recognition_models(), exports);
-    __exportStar(require_general_ocr_models(), exports);
-    __exportStar(require_audio_classification_models(), exports);
-    __exportStar(require_segmentation_models(), exports);
-    __exportStar(require_animal_classification_models(), exports);
-    __exportStar(require_vehicle_classification_models(), exports);
-    __exportStar(require_segmentation_refiner_models(), exports);
-  }
-});
-
-// src/addons/object-detection/index.js
-var require_object_detection = __commonJS({
-  "src/addons/object-detection/index.js"(exports) {
-    "use strict";
-    var __createBinding = exports && exports.__createBinding || (Object.create ? (function(o, m, k, k2) {
-      if (k2 === void 0) k2 = k;
-      var desc = Object.getOwnPropertyDescriptor(m, k);
-      if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
-        desc = { enumerable: true, get: function() {
-          return m[k];
-        } };
-      }
-      Object.defineProperty(o, k2, desc);
-    }) : (function(o, m, k, k2) {
-      if (k2 === void 0) k2 = k;
-      o[k2] = m[k];
-    }));
-    var __setModuleDefault = exports && exports.__setModuleDefault || (Object.create ? (function(o, v) {
-      Object.defineProperty(o, "default", { enumerable: true, value: v });
-    }) : function(o, v) {
-      o["default"] = v;
-    });
-    var __importStar = exports && exports.__importStar || /* @__PURE__ */ (function() {
-      var ownKeys = function(o) {
-        ownKeys = Object.getOwnPropertyNames || function(o2) {
-          var ar = [];
-          for (var k in o2) if (Object.prototype.hasOwnProperty.call(o2, k)) ar[ar.length] = k;
-          return ar;
-        };
-        return ownKeys(o);
-      };
-      return function(mod) {
-        if (mod && mod.__esModule) return mod;
-        var result = {};
-        if (mod != null) {
-          for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
-        }
-        __setModuleDefault(result, mod);
-        return result;
-      };
-    })();
-    Object.defineProperty(exports, "__esModule", { value: true });
-    var object_detection_models_js_1 = require_object_detection_models();
-    var segmentation_models_js_1 = require_segmentation_models();
-    var types_1 = __require("@camstack/types");
-    var image_utils_js_1 = require_image_utils();
-    var yolo_js_1 = require_yolo();
-    var yolo_seg_js_1 = require_yolo_seg();
-    var engine_resolver_js_1 = require_engine_resolver();
-    function isSegModel(modelId) {
-      return modelId.includes("-seg");
-    }
-    var ALL_DETECTION_MODELS = [
-      ...object_detection_models_js_1.OBJECT_DETECTION_MODELS,
-      ...segmentation_models_js_1.SEGMENTATION_MODELS
-    ];
-    function applyClassMap(detections, classMap) {
-      return detections.filter((d) => classMap.mapping[d.class] !== void 0).map((d) => ({
-        ...d,
-        originalClass: d.class,
-        class: classMap.mapping[d.class]
-      }));
-    }
-    var RAM_ESTIMATES = {
-      "yolov8n": 80,
-      "yolov8s": 150,
-      "yolov8s-relu": 150,
-      "yolov8m": 300,
-      "yolov8l": 500,
-      "yolov8x": 800,
-      "yolov9t": 60,
-      "yolov9s": 120,
-      "yolov9c": 300,
-      "yolo11n": 70,
-      "yolo11s": 130,
-      "yolo11m": 280,
-      "yolo11l": 450,
-      "yolo11x": 750,
-      "yolo11n-seg": 84,
-      "yolo11s-seg": 156,
-      "yolo11m-seg": 336,
-      "yolov8n-seg": 96,
-      "yolov8s-seg": 180,
-      "yolov8m-seg": 360
-    };
-    var ACCURACY_SCORES = {
-      "yolov8n": 55,
-      "yolov8s": 70,
-      "yolov8s-relu": 68,
-      "yolov8m": 82,
-      "yolov8l": 88,
-      "yolov8x": 92,
-      "yolov9t": 58,
-      "yolov9s": 73,
-      "yolov9c": 86,
-      "yolo11n": 62,
-      "yolo11s": 78,
-      "yolo11m": 88,
-      "yolo11l": 93,
-      "yolo11x": 97,
-      "yolo11n-seg": 62,
-      "yolo11s-seg": 78,
-      "yolo11m-seg": 88,
-      "yolov8n-seg": 55,
-      "yolov8s-seg": 70,
-      "yolov8m-seg": 82
-    };
-    var ObjectDetectionAddon = class {
-      id = "object-detection";
-      slot = "detector";
-      inputClasses = null;
-      outputClasses = ["person", "vehicle", "animal"];
-      slotPriority = 0;
-      manifest = {
-        id: "object-detection",
-        name: "Object Detection",
-        version: "0.1.0",
-        description: "YOLO-based object detection \u2014 detects persons, vehicles, and animals",
-        slot: "detector",
-        inputClasses: void 0,
-        outputClasses: ["person", "vehicle", "animal"],
-        supportsCustomModels: true,
-        mayRequirePython: false,
-        defaultConfig: {
-          modelId: "yolo11n",
-          runtime: "node",
-          backend: "cpu",
-          confidence: 0.5,
-          iouThreshold: 0.45,
-          classMapMode: "macro"
-        }
-      };
-      engine = null;
-      modelEntry;
-      confidence = 0.5;
-      iouThreshold = 0.45;
-      classMapMode = "macro";
-      resolvedConfig = null;
-      ctx = null;
-      getModelRequirements() {
-        return ALL_DETECTION_MODELS.map((m) => ({
-          modelId: m.id,
-          name: m.name,
-          minRAM_MB: RAM_ESTIMATES[m.id] ?? 100,
-          accuracyScore: ACCURACY_SCORES[m.id] ?? 60,
-          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 ?? "yolo11n";
-        this.confidence = cfg["confidence"] ?? 0.5;
-        this.iouThreshold = cfg["iouThreshold"] ?? 0.45;
-        this.classMapMode = cfg["classMapMode"] ?? "macro";
-        const entry = ALL_DETECTION_MODELS.find((m) => m.id === modelId);
-        if (!entry) {
-          throw new Error(`ObjectDetectionAddon: unknown modelId "${modelId}"`);
-        }
-        this.modelEntry = entry;
-      }
-      async detect(frame) {
-        if (!this.engine)
-          await this.ensureEngine();
-        const start = Date.now();
-        if ("runJpeg" in this.engine && typeof this.engine.runJpeg === "function") {
-          const result = await this.engine.runJpeg(frame.data);
-          const rawDets = result.detections ?? [];
-          const detections2 = rawDets.map((d) => ({
-            class: this.classMapMode === "all" ? d.className : types_1.COCO_TO_MACRO.mapping[d.className] ?? d.className,
-            originalClass: d.className,
-            score: d.score,
-            bbox: {
-              x: d.bbox[0] * frame.width,
-              y: d.bbox[1] * frame.height,
-              w: (d.bbox[2] - d.bbox[0]) * frame.width,
-              h: (d.bbox[3] - d.bbox[1]) * frame.height
-            }
-          })).filter((d) => this.classMapMode === "all" || types_1.COCO_TO_MACRO.mapping[d.originalClass] !== void 0);
-          return {
-            detections: detections2,
-            inferenceMs: result.inferenceMs ?? Date.now() - start,
-            modelId: this.modelEntry.id
-          };
-        }
-        const { width: inputW, height: inputH } = this.modelEntry.inputSize;
-        const targetSize = Math.max(inputW, inputH);
-        const lb = await (0, image_utils_js_1.letterbox)(frame.data, targetSize);
-        const numClasses = this.modelEntry.labels.length;
-        const labels = this.modelEntry.labels.map((l) => l.id);
-        const postprocessOpts = {
-          confidence: this.confidence,
-          iouThreshold: this.iouThreshold,
-          labels,
-          scale: lb.scale,
-          padX: lb.padX,
-          padY: lb.padY,
-          originalWidth: lb.originalWidth,
-          originalHeight: lb.originalHeight
-        };
-        let rawDetections;
-        if (isSegModel(this.modelEntry.id)) {
-          const outputs = await this.engine.runMultiOutput(lb.data, [1, 3, targetSize, targetSize]);
-          const outputNames = Object.keys(outputs);
-          if (outputNames.length < 2) {
-            throw new Error(`ObjectDetectionAddon: seg model "${this.modelEntry.id}" returned ${outputNames.length} output(s); expected 2`);
-          }
-          const detectionOutput = outputs[outputNames[0]];
-          const protoOutput = outputs[outputNames[1]];
-          const numMaskCoeffs = 32;
-          const numBoxes = detectionOutput.length / (4 + numClasses + numMaskCoeffs);
-          const maskHeight = 160;
-          const maskWidth = 160;
-          rawDetections = (0, yolo_seg_js_1.yoloSegPostprocess)({
-            detectionOutput,
-            protoOutput,
-            numClasses,
-            numBoxes,
-            numMaskCoeffs,
-            maskHeight,
-            maskWidth
-          }, postprocessOpts);
-        } else {
-          const output = await this.engine.run(lb.data, [1, 3, targetSize, targetSize]);
-          const numBoxes = output.length / (4 + numClasses);
-          rawDetections = (0, yolo_js_1.yoloPostprocess)(output, numClasses, numBoxes, postprocessOpts);
-        }
-        const detections = this.classMapMode === "all" ? rawDetections : applyClassMap(rawDetections, types_1.COCO_TO_MACRO);
-        return {
-          detections,
-          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 = ALL_DETECTION_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);
-        }
-        let pythonPath;
-        if (config?.runtime === "python") {
-          for (const cmd of ["python3", "python"]) {
-            try {
-              const { execSync } = await Promise.resolve().then(() => __importStar(__require("child_process")));
-              execSync(`${cmd} --version`, { timeout: 3e3, stdio: "ignore" });
-              pythonPath = cmd;
-              break;
-            } catch {
-            }
-          }
-        }
-        const resolved = await (0, engine_resolver_js_1.resolveEngine)({
-          runtime,
-          backend,
-          modelEntry: entry,
-          modelsDir,
-          pythonPath,
-          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: [...ALL_DETECTION_MODELS],
-                  allowCustom: true,
-                  allowConversion: true,
-                  acceptFormats: ["onnx", "coreml", "openvino", "tflite"],
-                  requiredMetadata: ["inputSize", "labels", "outputFormat"],
-                  outputFormatHint: "yolo"
-                }
-              ]
-            },
-            {
-              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)" },
-                    { value: "tensorrt", label: "TensorRT (NVIDIA)" }
-                  ]
-                }
-              ]
-            },
-            {
-              id: "thresholds",
-              title: "Detection Thresholds",
-              columns: 2,
-              fields: [
-                {
-                  key: "confidence",
-                  label: "Confidence Threshold",
-                  type: "slider",
-                  min: 0.1,
-                  max: 1,
-                  step: 0.05,
-                  default: 0.5
-                },
-                {
-                  key: "iouThreshold",
-                  label: "IoU Threshold (NMS)",
-                  type: "slider",
-                  min: 0.1,
-                  max: 1,
-                  step: 0.05,
-                  default: 0.45
-                }
-              ]
-            },
-            {
-              id: "classmap",
-              title: "Class Mapping",
-              columns: 1,
-              fields: [
-                {
-                  key: "classMapMode",
-                  label: "Output classes",
-                  type: "select",
-                  options: [
-                    { value: "macro", label: "Macro (person / vehicle / animal)" },
-                    { value: "all", label: "All COCO classes (80)" }
-                  ]
-                }
-              ]
-            }
-          ]
-        };
-      }
-      getClassMap() {
-        return types_1.COCO_TO_MACRO;
-      }
-      getModelCatalog() {
-        return [...ALL_DETECTION_MODELS];
-      }
-      getAvailableModels() {
-        return [];
-      }
-      getActiveLabels() {
-        return this.classMapMode === "all" ? types_1.COCO_80_LABELS : types_1.MACRO_LABELS;
-      }
-      async probe() {
-        return {
-          available: true,
-          runtime: this.engine?.runtime ?? "onnx",
-          device: this.engine?.device ?? "cpu",
-          capabilities: ["fp32"]
-        };
-      }
-    };
-    exports.default = ObjectDetectionAddon;
-  }
-});
-
-// src/addons/face-detection/index.js
-var require_face_detection = __commonJS({
-  "src/addons/face-detection/index.js"(exports) {
-    "use strict";
-    Object.defineProperty(exports, "__esModule", { value: true });
-    var face_detection_models_js_1 = require_face_detection_models();
-    var image_utils_js_1 = require_image_utils();
-    var scrfd_js_1 = require_scrfd();
-    var engine_resolver_js_1 = require_engine_resolver();
-    var FACE_LABEL = { id: "face", name: "Face" };
-    var FACE_LABELS = [FACE_LABEL];
-    var FACE_CLASS_MAP = { mapping: {}, preserveOriginal: true };
-    var RAM_ESTIMATES = {
-      "scrfd-500m": 50,
-      "scrfd-2.5g": 80,
-      "scrfd-10g": 200
-    };
-    var ACCURACY_SCORES = {
-      "scrfd-500m": 70,
-      "scrfd-2.5g": 82,
-      "scrfd-10g": 92
-    };
-    var FaceDetectionAddon = class {
-      id = "face-detection";
-      slot = "cropper";
-      inputClasses = ["person"];
-      outputClasses = ["face"];
-      slotPriority = 0;
-      manifest = {
-        id: "face-detection",
-        name: "Face Detection",
-        version: "0.1.0",
-        description: "SCRFD-based face detector \u2014 crops face regions from person detections",
-        slot: "cropper",
-        inputClasses: ["person"],
-        outputClasses: ["face"],
-        supportsCustomModels: false,
-        mayRequirePython: false,
-        defaultConfig: {
-          modelId: "scrfd-500m",
-          runtime: "node",
-          backend: "cpu",
-          confidence: 0.5
-        }
-      };
-      engine = null;
-      modelEntry;
-      confidence = 0.5;
-      resolvedConfig = null;
-      ctx = null;
-      getModelRequirements() {
-        return face_detection_models_js_1.FACE_DETECTION_MODELS.map((m) => ({
-          modelId: m.id,
-          name: m.name,
-          minRAM_MB: RAM_ESTIMATES[m.id] ?? 50,
-          accuracyScore: ACCURACY_SCORES[m.id] ?? 70,
-          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 ?? "scrfd-500m";
-        this.confidence = cfg["confidence"] ?? 0.5;
-        const entry = face_detection_models_js_1.FACE_DETECTION_MODELS.find((m) => m.id === modelId);
-        if (!entry) {
-          throw new Error(`FaceDetectionAddon: unknown modelId "${modelId}"`);
-        }
-        this.modelEntry = entry;
-      }
-      async crop(input) {
-        if (!this.engine)
-          await this.ensureEngine();
-        const start = Date.now();
-        const { width: inputW, height: inputH } = this.modelEntry.inputSize;
-        const targetSize = Math.max(inputW, inputH);
-        const personCrop = await (0, image_utils_js_1.cropRegion)(input.frame.data, input.roi);
-        const lb = await (0, image_utils_js_1.letterbox)(personCrop, targetSize);
-        const engineWithMulti = this.engine;
-        let outputs;
-        if (typeof engineWithMulti.runMultiOutput === "function") {
-          outputs = await engineWithMulti.runMultiOutput(lb.data, [1, 3, targetSize, targetSize]);
-        } else {
-          const single = await this.engine.run(lb.data, [1, 3, targetSize, targetSize]);
-          outputs = { output0: single };
-        }
-        const crops = (0, scrfd_js_1.scrfdPostprocess)(outputs, this.confidence, targetSize, lb.originalWidth, lb.originalHeight);
-        return {
-          crops,
-          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 = face_detection_models_js_1.FACE_DETECTION_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);
-        }
-        const resolved = await (0, engine_resolver_js_1.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: [...face_detection_models_js_1.FACE_DETECTION_MODELS],
-                  allowCustom: false,
-                  allowConversion: false,
-                  acceptFormats: ["onnx", "coreml", "openvino"],
-                  requiredMetadata: ["inputSize", "labels", "outputFormat"],
-                  outputFormatHint: "ssd"
-                }
-              ]
-            },
-            {
-              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: "Detection Thresholds",
-              columns: 1,
-              fields: [
-                {
-                  key: "confidence",
-                  label: "Confidence Threshold",
-                  type: "slider",
-                  min: 0.1,
-                  max: 1,
-                  step: 0.05,
-                  default: 0.5
-                }
-              ]
-            }
-          ]
-        };
-      }
-      getClassMap() {
-        return FACE_CLASS_MAP;
+      openvino: {
+        url: hfModelUrl(HF_REPO, "generalOcr/doctr/openvino/camstack-doctr-det-db-mobilenet-v3.xml"),
+        sizeMB: 8,
+        runtimes: ["python"]
       }
-      getModelCatalog() {
-        return [...face_detection_models_js_1.FACE_DETECTION_MODELS];
-      }
-      getAvailableModels() {
-        return [];
-      }
-      getActiveLabels() {
-        return FACE_LABELS;
-      }
-      async probe() {
-        return {
-          available: true,
-          runtime: this.engine?.runtime ?? "onnx",
-          device: this.engine?.device ?? "cpu",
-          capabilities: ["fp32"]
-        };
-      }
-    };
-    exports.default = FaceDetectionAddon;
-  }
-});
-
-// src/addons/face-recognition/index.js
-var require_face_recognition = __commonJS({
-  "src/addons/face-recognition/index.js"(exports) {
-    "use strict";
-    Object.defineProperty(exports, "__esModule", { value: true });
-    var face_recognition_models_js_1 = require_face_recognition_models();
-    var image_utils_js_1 = require_image_utils();
-    var arcface_js_1 = require_arcface();
-    var engine_resolver_js_1 = require_engine_resolver();
-    var IDENTITY_LABEL = { id: "identity", name: "Identity" };
-    var IDENTITY_LABELS = [IDENTITY_LABEL];
-    var FACE_REC_CLASS_MAP = { mapping: {}, preserveOriginal: true };
-    var REQUIRED_STEPS = [
-      { slot: "cropper", outputClasses: ["face"], description: "Requires a face detector" }
-    ];
-    var FaceRecognitionAddon = class {
-      id = "face-recognition";
-      slot = "classifier";
-      inputClasses = ["face"];
-      outputClasses = ["identity:*"];
-      slotPriority = 0;
-      requiredSteps = REQUIRED_STEPS;
-      manifest = {
-        id: "face-recognition",
-        name: "Face Recognition",
-        version: "0.1.0",
-        description: "ArcFace-based face recognition \u2014 produces 512-d identity embeddings",
-        slot: "classifier",
-        labelOutputType: "face",
-        inputClasses: ["face"],
-        outputClasses: ["identity:*"],
-        requiredSteps: REQUIRED_STEPS,
-        supportsCustomModels: false,
-        mayRequirePython: false,
-        defaultConfig: {
-          modelId: "arcface-r100",
-          runtime: "node",
-          backend: "cpu"
-        }
-      };
-      engine = null;
-      modelEntry;
-      resolvedConfig = null;
-      ctx = null;
-      getModelRequirements() {
-        return face_recognition_models_js_1.FACE_RECOGNITION_MODELS.map((m) => ({
-          modelId: m.id,
-          name: m.name,
-          minRAM_MB: 400,
-          accuracyScore: 90,
-          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 ?? "arcface-r100";
-        const entry = face_recognition_models_js_1.FACE_RECOGNITION_MODELS.find((m) => m.id === modelId);
-        if (!entry) {
-          throw new Error(`FaceRecognitionAddon: 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 faceCrop = await (0, image_utils_js_1.cropRegion)(input.frame.data, input.roi);
-        const layout = this.modelEntry.inputLayout ?? "nhwc";
-        const normalization = this.modelEntry.inputNormalization ?? "zero-one";
-        const normalized = await (0, image_utils_js_1.resizeAndNormalize)(faceCrop, inputW, inputH, normalization, layout);
-        const rawEmbedding = await this.engine.run(normalized, [1, inputH, inputW, 3]);
-        const embedding = (0, arcface_js_1.l2Normalize)(rawEmbedding);
-        return {
-          classifications: [
-            {
-              class: "identity",
-              score: 1,
-              embedding
-            }
-          ],
-          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 = face_recognition_models_js_1.FACE_RECOGNITION_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);
-        }
-        const resolved = await (0, engine_resolver_js_1.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: [...face_recognition_models_js_1.FACE_RECOGNITION_MODELS],
-                  allowCustom: false,
-                  allowConversion: false,
-                  acceptFormats: ["onnx", "coreml", "openvino"],
-                  requiredMetadata: ["inputSize", "labels", "outputFormat"],
-                  outputFormatHint: "embedding"
-                }
-              ]
-            },
-            {
-              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)" }
-                  ]
-                }
-              ]
-            }
-          ]
-        };
-      }
-      getClassMap() {
-        return FACE_REC_CLASS_MAP;
-      }
-      getModelCatalog() {
-        return [...face_recognition_models_js_1.FACE_RECOGNITION_MODELS];
-      }
-      getAvailableModels() {
-        return [];
-      }
-      getActiveLabels() {
-        return IDENTITY_LABELS;
-      }
-      async probe() {
-        return {
-          available: true,
-          runtime: this.engine?.runtime ?? "onnx",
-          device: this.engine?.device ?? "cpu",
-          capabilities: ["fp32"]
-        };
-      }
-    };
-    exports.default = FaceRecognitionAddon;
-  }
-});
-
-// src/addons/plate-detection/index.js
-var require_plate_detection = __commonJS({
-  "src/addons/plate-detection/index.js"(exports) {
-    "use strict";
-    Object.defineProperty(exports, "__esModule", { value: true });
-    var plate_detection_models_js_1 = require_plate_detection_models();
-    var image_utils_js_1 = require_image_utils();
-    var yolo_js_1 = require_yolo();
-    var engine_resolver_js_1 = require_engine_resolver();
-    var PLATE_LABEL = { id: "plate", name: "License Plate" };
-    var PLATE_LABELS = [PLATE_LABEL];
-    var PLATE_CLASS_MAP = { mapping: {}, preserveOriginal: true };
-    var PlateDetectionAddon = class {
-      id = "plate-detection";
-      slot = "cropper";
-      inputClasses = ["vehicle"];
-      outputClasses = ["plate"];
-      slotPriority = 0;
-      manifest = {
-        id: "plate-detection",
-        name: "License Plate Detection",
-        version: "0.1.0",
-        description: "YOLO-based license plate detector \u2014 crops plate regions from vehicle detections",
-        slot: "cropper",
-        inputClasses: ["vehicle"],
-        outputClasses: ["plate"],
-        supportsCustomModels: false,
-        mayRequirePython: false,
-        defaultConfig: {
-          modelId: "yolov8n-plate",
-          runtime: "node",
-          backend: "cpu",
-          confidence: 0.5,
-          iouThreshold: 0.45
-        }
-      };
-      engine = null;
-      modelEntry;
-      confidence = 0.5;
-      iouThreshold = 0.45;
-      resolvedConfig = null;
-      ctx = null;
-      getModelRequirements() {
-        return plate_detection_models_js_1.PLATE_DETECTION_MODELS.map((m) => ({
-          modelId: m.id,
-          name: m.name,
-          minRAM_MB: 80,
-          accuracyScore: 60,
-          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 ?? "yolov8n-plate";
-        this.confidence = cfg["confidence"] ?? 0.5;
-        this.iouThreshold = cfg["iouThreshold"] ?? 0.45;
-        const entry = plate_detection_models_js_1.PLATE_DETECTION_MODELS.find((m) => m.id === modelId);
-        if (!entry) {
-          throw new Error(`PlateDetectionAddon: unknown modelId "${modelId}"`);
-        }
-        this.modelEntry = entry;
-      }
-      async crop(input) {
-        if (!this.engine)
-          await this.ensureEngine();
-        const start = Date.now();
-        const { width: inputW, height: inputH } = this.modelEntry.inputSize;
-        const targetSize = Math.max(inputW, inputH);
-        const vehicleCrop = await (0, image_utils_js_1.cropRegion)(input.frame.data, input.roi);
-        const lb = await (0, image_utils_js_1.letterbox)(vehicleCrop, targetSize);
-        const output = await this.engine.run(lb.data, [1, 3, targetSize, targetSize]);
-        const numClasses = this.modelEntry.labels.length;
-        const numBoxes = output.length / (4 + numClasses);
-        const labels = this.modelEntry.labels.map((l) => l.id);
-        const plates = (0, yolo_js_1.yoloPostprocess)(output, numClasses, numBoxes, {
-          confidence: this.confidence,
-          iouThreshold: this.iouThreshold,
-          labels,
-          scale: lb.scale,
-          padX: lb.padX,
-          padY: lb.padY,
-          originalWidth: lb.originalWidth,
-          originalHeight: lb.originalHeight
-        });
-        const crops = plates.map((p) => ({ ...p, class: "plate", originalClass: p.originalClass }));
-        return {
-          crops,
-          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 = plate_detection_models_js_1.PLATE_DETECTION_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);
-        }
-        const resolved = await (0, engine_resolver_js_1.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: [...plate_detection_models_js_1.PLATE_DETECTION_MODELS],
-                  allowCustom: false,
-                  allowConversion: false,
-                  acceptFormats: ["onnx", "coreml", "openvino"],
-                  requiredMetadata: ["inputSize", "labels", "outputFormat"],
-                  outputFormatHint: "yolo"
-                }
-              ]
-            },
-            {
-              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: "Detection Thresholds",
-              columns: 2,
-              fields: [
-                {
-                  key: "confidence",
-                  label: "Confidence Threshold",
-                  type: "slider",
-                  min: 0.1,
-                  max: 1,
-                  step: 0.05,
-                  default: 0.5
-                },
-                {
-                  key: "iouThreshold",
-                  label: "IoU Threshold (NMS)",
-                  type: "slider",
-                  min: 0.1,
-                  max: 1,
-                  step: 0.05,
-                  default: 0.45
-                }
-              ]
-            }
-          ]
-        };
-      }
-      getClassMap() {
-        return PLATE_CLASS_MAP;
-      }
-      getModelCatalog() {
-        return [...plate_detection_models_js_1.PLATE_DETECTION_MODELS];
-      }
-      getAvailableModels() {
-        return [];
-      }
-      getActiveLabels() {
-        return PLATE_LABELS;
-      }
-      async probe() {
-        return {
-          available: true,
-          runtime: this.engine?.runtime ?? "onnx",
-          device: this.engine?.device ?? "cpu",
-          capabilities: ["fp32"]
-        };
-      }
-    };
-    exports.default = PlateDetectionAddon;
-  }
-});
-
-// src/addons/plate-recognition/index.js
-var require_plate_recognition = __commonJS({
-  "src/addons/plate-recognition/index.js"(exports) {
-    "use strict";
-    var __createBinding = exports && exports.__createBinding || (Object.create ? (function(o, m, k, k2) {
-      if (k2 === void 0) k2 = k;
-      var desc = Object.getOwnPropertyDescriptor(m, k);
-      if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
-        desc = { enumerable: true, get: function() {
-          return m[k];
-        } };
-      }
-      Object.defineProperty(o, k2, desc);
-    }) : (function(o, m, k, k2) {
-      if (k2 === void 0) k2 = k;
-      o[k2] = m[k];
-    }));
-    var __setModuleDefault = exports && exports.__setModuleDefault || (Object.create ? (function(o, v) {
-      Object.defineProperty(o, "default", { enumerable: true, value: v });
-    }) : function(o, v) {
-      o["default"] = v;
-    });
-    var __importStar = exports && exports.__importStar || /* @__PURE__ */ (function() {
-      var ownKeys = function(o) {
-        ownKeys = Object.getOwnPropertyNames || function(o2) {
-          var ar = [];
-          for (var k in o2) if (Object.prototype.hasOwnProperty.call(o2, k)) ar[ar.length] = k;
-          return ar;
-        };
-        return ownKeys(o);
-      };
-      return function(mod) {
-        if (mod && mod.__esModule) return mod;
-        var result = {};
-        if (mod != null) {
-          for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
-        }
-        __setModuleDefault(result, mod);
-        return result;
-      };
-    })();
-    Object.defineProperty(exports, "__esModule", { value: true });
-    var plate_recognition_models_js_1 = require_plate_recognition_models();
-    var image_utils_js_1 = require_image_utils();
-    var paddleocr_js_1 = require_paddleocr();
-    var engine_resolver_js_1 = require_engine_resolver();
-    var PLATE_TEXT_LABEL = { id: "plate-text", name: "Plate Text" };
-    var PLATE_TEXT_LABELS = [PLATE_TEXT_LABEL];
-    var PLATE_REC_CLASS_MAP = { mapping: {}, preserveOriginal: true };
-    var fs = __importStar(__require("fs"));
-    var path = __importStar(__require("path"));
-    function loadCharset(modelsDir, modelId) {
-      const dictNames = [
-        `camstack-${modelId}-dict.txt`,
-        `camstack-paddleocr-latin-dict.txt`,
-        `camstack-paddleocr-en-dict.txt`,
-        `camstack-crnn-mobilenet-charset.txt`
-      ];
-      for (const name of dictNames) {
-        const dictPath = path.join(modelsDir, name);
-        if (fs.existsSync(dictPath)) {
-          const lines = fs.readFileSync(dictPath, "utf-8").split("\n").filter((l) => l.length > 0);
-          return ["", ...lines, " "];
-        }
-      }
-      throw new Error(`PlateRecognitionAddon: dict.txt not found in ${modelsDir}`);
     }
-    var REQUIRED_STEPS = [
-      { slot: "cropper", outputClasses: ["plate"], description: "Requires a plate detector" }
-    ];
-    var PlateRecognitionAddon = class {
-      id = "plate-recognition";
-      slot = "classifier";
-      inputClasses = ["plate"];
-      outputClasses = ["plate-text:*"];
-      slotPriority = 0;
-      requiredSteps = REQUIRED_STEPS;
-      manifest = {
-        id: "plate-recognition",
-        name: "License Plate Recognition (OCR)",
-        version: "0.1.0",
-        description: "PaddleOCR-based license plate text recognition",
-        slot: "classifier",
-        labelOutputType: "plate",
-        inputClasses: ["plate"],
-        outputClasses: ["plate-text:*"],
-        requiredSteps: REQUIRED_STEPS,
-        supportsCustomModels: false,
-        mayRequirePython: false,
-        defaultConfig: {
-          modelId: "paddleocr-latin",
-          runtime: "node",
-          backend: "cpu",
-          minConfidence: 0.5
-        }
-      };
-      engine = null;
-      modelEntry;
-      minConfidence = 0.5;
-      charset = [];
-      resolvedConfig = null;
-      ctx = null;
-      getModelRequirements() {
-        const scores = {
-          "paddleocr-latin": { ram: 100, accuracy: 80 },
-          "paddleocr-en": { ram: 100, accuracy: 80 }
-        };
-        return plate_recognition_models_js_1.PLATE_RECOGNITION_MODELS.map((m) => ({
-          modelId: m.id,
-          name: m.name,
-          minRAM_MB: scores[m.id]?.ram ?? 100,
-          accuracyScore: scores[m.id]?.accuracy ?? 75,
-          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 ?? "paddleocr-latin";
-        this.minConfidence = cfg["minConfidence"] ?? 0.5;
-        const entry = plate_recognition_models_js_1.PLATE_RECOGNITION_MODELS.find((m) => m.id === modelId);
-        if (!entry) {
-          throw new Error(`PlateRecognitionAddon: 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;
-        console.log(`[plate-recognition] ROI: x=${input.roi?.x}, y=${input.roi?.y}, w=${input.roi?.w}, h=${input.roi?.h}, frameSize=${input.frame?.data?.length}`);
-        const plateCrop = await (0, image_utils_js_1.cropRegion)(input.frame.data, input.roi);
-        console.log(`[plate-recognition] Crop size: ${plateCrop.length} bytes`);
-        try {
-          __require("fs").writeFileSync("/tmp/plate-recognition-crop.jpg", plateCrop);
-        } catch {
-        }
-        const normalized = await (0, image_utils_js_1.resizeAndNormalize)(plateCrop, inputW, inputH, "zero-one", "nchw");
-        const output = await this.engine.run(normalized, [1, 3, inputH, inputW]);
-        const numChars = this.charset.length;
-        const seqLen = output.length / numChars;
-        const { text, confidence } = (0, paddleocr_js_1.ctcDecode)(output, seqLen, numChars, this.charset);
-        return {
-          classifications: [
-            {
-              class: "plate-text",
-              score: confidence,
-              text: text.trim() || "(unreadable)"
-            }
-          ],
-          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 = plate_recognition_models_js_1.PLATE_RECOGNITION_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.charset = loadCharset(modelsDir, modelId);
-        const resolved = await (0, engine_resolver_js_1.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: [...plate_recognition_models_js_1.PLATE_RECOGNITION_MODELS],
-                  allowCustom: false,
-                  allowConversion: false,
-                  acceptFormats: ["onnx", "openvino"],
-                  requiredMetadata: ["inputSize", "labels", "outputFormat"],
-                  outputFormatHint: "ocr"
-                }
-              ]
-            },
-            {
-              id: "runtime",
-              title: "Runtime",
-              columns: 2,
-              fields: [
-                {
-                  key: "runtime",
-                  label: "Runtime",
-                  type: "select",
-                  options: [
-                    { value: "auto", label: "Auto" },
-                    { value: "onnx", label: "ONNX Runtime" },
-                    { 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: "cuda", label: "CUDA (NVIDIA)" }
-                  ]
-                }
-              ]
-            },
-            {
-              id: "thresholds",
-              title: "Recognition Settings",
-              columns: 1,
-              fields: [
-                {
-                  key: "minConfidence",
-                  label: "Minimum Confidence",
-                  type: "slider",
-                  min: 0.1,
-                  max: 1,
-                  step: 0.05,
-                  default: 0.5
-                }
-              ]
-            }
-          ]
-        };
-      }
-      getClassMap() {
-        return PLATE_REC_CLASS_MAP;
-      }
-      getModelCatalog() {
-        return [...plate_recognition_models_js_1.PLATE_RECOGNITION_MODELS];
-      }
-      getAvailableModels() {
-        return [];
-      }
-      getActiveLabels() {
-        return PLATE_TEXT_LABELS;
-      }
-      async probe() {
-        return {
-          available: true,
-          runtime: this.engine?.runtime ?? "onnx",
-          device: this.engine?.device ?? "cpu",
-          capabilities: ["fp32"]
-        };
-      }
-    };
-    exports.default = PlateRecognitionAddon;
-  }
-});
-
-// src/addons/audio-classification/index.js
-var require_audio_classification = __commonJS({
-  "src/addons/audio-classification/index.js"(exports) {
-    "use strict";
-    Object.defineProperty(exports, "__esModule", { value: true });
-    var audio_classification_models_js_1 = require_audio_classification_models();
-    var yamnet_js_1 = require_yamnet();
-    var engine_resolver_js_1 = require_engine_resolver();
-    var YAMNET_NUM_CLASSES = 521;
-    var AUDIO_EVENT_LABEL = { id: "audio-event", name: "Audio Event" };
-    var AUDIO_LABELS = [AUDIO_EVENT_LABEL];
-    var AUDIO_CLASS_MAP = { mapping: {}, preserveOriginal: true };
-    var AudioClassificationAddon = class {
-      id = "audio-classification";
-      slot = "classifier";
-      inputClasses = null;
-      outputClasses = ["audio-event:*"];
-      slotPriority = 0;
-      manifest = {
-        id: "audio-classification",
-        name: "Audio Classification",
-        version: "0.1.0",
-        description: "YAMNet-based audio event classification from audio waveform",
-        slot: "classifier",
-        labelOutputType: "classification",
-        inputClasses: void 0,
-        outputClasses: ["audio-event:*"],
-        supportsCustomModels: false,
-        mayRequirePython: false,
-        defaultConfig: {
-          modelId: "yamnet",
-          runtime: "node",
-          backend: "cpu",
-          minScore: 0.3
-        }
-      };
-      engine = null;
-      modelEntry;
-      minScore = 0.3;
-      resolvedConfig = null;
-      ctx = null;
-      getModelRequirements() {
-        return audio_classification_models_js_1.AUDIO_CLASSIFICATION_MODELS.map((m) => ({
-          modelId: m.id,
-          name: m.name,
-          minRAM_MB: 100,
-          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 ?? "yamnet";
-        this.minScore = cfg["minScore"] ?? 0.3;
-        const entry = audio_classification_models_js_1.AUDIO_CLASSIFICATION_MODELS.find((m) => m.id === modelId);
-        if (!entry) {
-          throw new Error(`AudioClassificationAddon: unknown modelId "${modelId}"`);
-        }
-        this.modelEntry = entry;
-      }
-      /**
-       * classify() receives a CropInput but internally treats input.frame.data as raw audio context.
-       * For audio, the actual audio chunk data should be stored in frame.data as a Float32Array
-       * serialized into a Buffer (little-endian float32 samples at 16 kHz).
-       *
-       * The CropInput.roi is not used for audio — it is ignored.
-       */
-      async classify(input) {
-        if (!this.engine)
-          await this.ensureEngine();
-        const start = Date.now();
-        const buf = input.frame.data;
-        const numSamples = Math.floor(buf.length / 4);
-        const audioData = new Float32Array(numSamples);
-        for (let i = 0; i < numSamples; i++) {
-          audioData[i] = buf.readFloatLE(i * 4);
-        }
-        const output = await this.engine.run(audioData, [numSamples]);
-        const numFrames = output.length / YAMNET_NUM_CLASSES;
-        const classNames = this.modelEntry.labels.map((l) => l.id);
-        while (classNames.length < YAMNET_NUM_CLASSES) {
-          classNames.push(`class_${classNames.length}`);
-        }
-        const results = (0, yamnet_js_1.yamnetPostprocess)(output, Math.round(numFrames), YAMNET_NUM_CLASSES, classNames, this.minScore);
-        const classifications = results.map((r) => ({
-          class: `audio-event:${r.className}`,
-          score: r.score
-        }));
-        return {
-          classifications,
-          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 = audio_classification_models_js_1.AUDIO_CLASSIFICATION_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);
-        }
-        const resolved = await (0, engine_resolver_js_1.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: [...audio_classification_models_js_1.AUDIO_CLASSIFICATION_MODELS],
-                  allowCustom: false,
-                  allowConversion: false,
-                  acceptFormats: ["onnx", "openvino"],
-                  requiredMetadata: ["inputSize", "labels", "outputFormat"],
-                  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: "minScore",
-                  label: "Minimum Score",
-                  type: "slider",
-                  min: 0.05,
-                  max: 1,
-                  step: 0.05,
-                  default: 0.3
-                }
-              ]
-            }
-          ]
-        };
-      }
-      getClassMap() {
-        return AUDIO_CLASS_MAP;
-      }
-      getModelCatalog() {
-        return [...audio_classification_models_js_1.AUDIO_CLASSIFICATION_MODELS];
-      }
-      getAvailableModels() {
-        return [];
-      }
-      getActiveLabels() {
-        return AUDIO_LABELS;
-      }
-      async probe() {
-        return {
-          available: true,
-          runtime: this.engine?.runtime ?? "onnx",
-          device: this.engine?.device ?? "cpu",
-          capabilities: ["fp32"]
-        };
-      }
-    };
-    exports.default = AudioClassificationAddon;
-  }
-});
-
-// src/addons/bird-global-classifier/index.js
-var require_bird_global_classifier = __commonJS({
-  "src/addons/bird-global-classifier/index.js"(exports) {
-    "use strict";
-    var __createBinding = exports && exports.__createBinding || (Object.create ? (function(o, m, k, k2) {
-      if (k2 === void 0) k2 = k;
-      var desc = Object.getOwnPropertyDescriptor(m, k);
-      if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
-        desc = { enumerable: true, get: function() {
-          return m[k];
-        } };
-      }
-      Object.defineProperty(o, k2, desc);
-    }) : (function(o, m, k, k2) {
-      if (k2 === void 0) k2 = k;
-      o[k2] = m[k];
-    }));
-    var __setModuleDefault = exports && exports.__setModuleDefault || (Object.create ? (function(o, v) {
-      Object.defineProperty(o, "default", { enumerable: true, value: v });
-    }) : function(o, v) {
-      o["default"] = v;
-    });
-    var __importStar = exports && exports.__importStar || /* @__PURE__ */ (function() {
-      var ownKeys = function(o) {
-        ownKeys = Object.getOwnPropertyNames || function(o2) {
-          var ar = [];
-          for (var k in o2) if (Object.prototype.hasOwnProperty.call(o2, k)) ar[ar.length] = k;
-          return ar;
-        };
-        return ownKeys(o);
-      };
-      return function(mod) {
-        if (mod && mod.__esModule) return mod;
-        var result = {};
-        if (mod != null) {
-          for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
-        }
-        __setModuleDefault(result, mod);
-        return result;
-      };
-    })();
-    Object.defineProperty(exports, "__esModule", { value: true });
-    var animal_classification_models_js_1 = require_animal_classification_models();
-    var image_utils_js_1 = require_image_utils();
-    var engine_resolver_js_1 = require_engine_resolver();
-    var fs = __importStar(__require("fs"));
-    var path = __importStar(__require("path"));
-    var SPECIES_LABEL = { id: "species", name: "Bird Species" };
-    var SPECIES_LABELS = [SPECIES_LABEL];
-    var BIRD_CLASS_MAP = { mapping: {}, preserveOriginal: true };
-    function loadLabels(modelsDir, modelId) {
-      const labelNames = [
-        `camstack-${modelId}-labels.json`,
-        `camstack-bird-species-525-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);
-        }
+  },
+  {
+    id: "doctr-rec-crnn-mobilenet",
+    name: "docTR Recognition CRNN MobileNet",
+    description: "docTR CRNN MobileNet V3 \u2014 lightweight text recognition for detected regions",
+    inputSize: { width: 128, height: 32 },
+    labels: OCR_TEXT_LABELS,
+    formats: {
+      onnx: {
+        url: hfModelUrl(HF_REPO, "generalOcr/doctr/onnx/camstack-doctr-rec-crnn-mobilenet-v3.onnx"),
+        sizeMB: 5
+      },
+      coreml: {
+        url: hfModelUrl(HF_REPO, "generalOcr/doctr/coreml/camstack-doctr-rec-crnn-mobilenet-v3.mlpackage"),
+        sizeMB: 3,
+        isDirectory: true,
+        files: [
+          "Manifest.json",
+          "Data/com.apple.CoreML/model.mlmodel",
+          "Data/com.apple.CoreML/weights/weight.bin"
+        ],
+        runtimes: ["python"]
+      },
+      openvino: {
+        url: hfModelUrl(HF_REPO, "generalOcr/doctr/openvino/camstack-doctr-rec-crnn-mobilenet-v3.xml"),
+        sizeMB: 3,
+        runtimes: ["python"]
       }
-      throw new Error(`BirdGlobalClassifierAddon: 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 BirdGlobalClassifierAddon = class {
-      id = "bird-global-classifier";
-      slot = "classifier";
-      inputClasses = ["animal"];
-      outputClasses = ["species:*"];
-      slotPriority = 0;
-      requiredSteps = [];
-      manifest = {
-        id: "bird-global-classifier",
-        name: "Bird Classifier (Global, 525 species)",
-        version: "0.1.0",
-        description: "EfficientNet \u2014 525 worldwide bird species (MIT license, ONNX only)",
-        slot: "classifier",
-        labelOutputType: "classification",
-        inputClasses: ["animal"],
-        outputClasses: ["species:*"],
-        supportsCustomModels: false,
-        mayRequirePython: false,
-        defaultConfig: {
-          modelId: "bird-species-525",
-          runtime: "node",
-          backend: "cpu",
-          minConfidence: 0.3
-        }
-      };
-      engine = null;
-      modelEntry;
-      labels = [];
-      minConfidence = 0.3;
-      resolvedConfig = null;
-      ctx = null;
-      getModelRequirements() {
-        return animal_classification_models_js_1.BIRD_SPECIES_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 ?? "bird-species-525";
-        this.minConfidence = cfg["minConfidence"] ?? 0.3;
-        const entry = animal_classification_models_js_1.BIRD_SPECIES_MODELS.find((m) => m.id === modelId);
-        if (!entry) {
-          throw new Error(`BirdGlobalClassifierAddon: 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 animalCrop = await (0, image_utils_js_1.cropRegion)(input.frame.data, input.roi);
-        const normalized = await (0, image_utils_js_1.resizeAndNormalize)(animalCrop, inputW, inputH, "imagenet", "nchw");
-        const rawOutput = await this.engine.run(normalized, [1, 3, inputH, inputW]);
-        const probs = softmax(rawOutput);
-        let maxIdx = 0;
-        let maxScore = probs[0] ?? 0;
-        for (let i = 1; i < probs.length; i++) {
-          const score = probs[i] ?? 0;
-          if (score > maxScore) {
-            maxScore = score;
-            maxIdx = i;
-          }
-        }
-        if (maxScore < this.minConfidence) {
-          return {
-            classifications: [],
-            inferenceMs: Date.now() - start,
-            modelId: this.modelEntry.id
-          };
-        }
-        const label = this.labels[maxIdx] ?? `species_${maxIdx}`;
-        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 = animal_classification_models_js_1.BIRD_SPECIES_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 (0, engine_resolver_js_1.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: [...animal_classification_models_js_1.BIRD_SPECIES_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 BIRD_CLASS_MAP;
-      }
-      getModelCatalog() {
-        return [...animal_classification_models_js_1.BIRD_SPECIES_MODELS];
-      }
-      getAvailableModels() {
-        return [];
-      }
-      getActiveLabels() {
-        return SPECIES_LABELS;
-      }
-      async probe() {
-        return {
-          available: true,
-          runtime: this.engine?.runtime ?? "onnx",
-          device: this.engine?.device ?? "cpu",
-          capabilities: ["fp32"]
-        };
-      }
-    };
-    exports.default = BirdGlobalClassifierAddon;
-  }
-});
-
-// src/addons/bird-nabirds-classifier/index.js
-var require_bird_nabirds_classifier = __commonJS({
-  "src/addons/bird-nabirds-classifier/index.js"(exports) {
-    "use strict";
-    var __createBinding = exports && exports.__createBinding || (Object.create ? (function(o, m, k, k2) {
-      if (k2 === void 0) k2 = k;
-      var desc = Object.getOwnPropertyDescriptor(m, k);
-      if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
-        desc = { enumerable: true, get: function() {
-          return m[k];
-        } };
-      }
-      Object.defineProperty(o, k2, desc);
-    }) : (function(o, m, k, k2) {
-      if (k2 === void 0) k2 = k;
-      o[k2] = m[k];
-    }));
-    var __setModuleDefault = exports && exports.__setModuleDefault || (Object.create ? (function(o, v) {
-      Object.defineProperty(o, "default", { enumerable: true, value: v });
-    }) : function(o, v) {
-      o["default"] = v;
-    });
-    var __importStar = exports && exports.__importStar || /* @__PURE__ */ (function() {
-      var ownKeys = function(o) {
-        ownKeys = Object.getOwnPropertyNames || function(o2) {
-          var ar = [];
-          for (var k in o2) if (Object.prototype.hasOwnProperty.call(o2, k)) ar[ar.length] = k;
-          return ar;
-        };
-        return ownKeys(o);
-      };
-      return function(mod) {
-        if (mod && mod.__esModule) return mod;
-        var result = {};
-        if (mod != null) {
-          for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
-        }
-        __setModuleDefault(result, mod);
-        return result;
-      };
-    })();
-    Object.defineProperty(exports, "__esModule", { value: true });
-    var animal_classification_models_js_1 = require_animal_classification_models();
-    var image_utils_js_1 = require_image_utils();
-    var engine_resolver_js_1 = require_engine_resolver();
-    var fs = __importStar(__require("fs"));
-    var path = __importStar(__require("path"));
-    var SPECIES_LABEL = { id: "species", name: "Bird Species" };
-    var SPECIES_LABELS = [SPECIES_LABEL];
-    var BIRD_CLASS_MAP = { mapping: {}, preserveOriginal: true };
-    function loadLabels(modelsDir, modelId) {
-      const labelNames = [
-        `camstack-${modelId}-labels.json`,
-        `camstack-bird-nabirds-404-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);
-        }
+  },
+  {
+    id: "doctr-rec-parseq",
+    name: "docTR Recognition PARSeq",
+    description: "docTR PARSeq \u2014 high-accuracy scene text recognition (top ICDAR scores)",
+    inputSize: { width: 128, height: 32 },
+    labels: OCR_TEXT_LABELS,
+    formats: {
+      onnx: {
+        url: hfModelUrl(HF_REPO, "generalOcr/doctr/onnx/camstack-doctr-rec-parseq.onnx"),
+        sizeMB: 25
+      },
+      coreml: {
+        url: hfModelUrl(HF_REPO, "generalOcr/doctr/coreml/camstack-doctr-rec-parseq.mlpackage"),
+        sizeMB: 13,
+        isDirectory: true,
+        files: [
+          "Manifest.json",
+          "Data/com.apple.CoreML/model.mlmodel",
+          "Data/com.apple.CoreML/weights/weight.bin"
+        ],
+        runtimes: ["python"]
+      },
+      openvino: {
+        url: hfModelUrl(HF_REPO, "generalOcr/doctr/openvino/camstack-doctr-rec-parseq.xml"),
+        sizeMB: 13,
+        runtimes: ["python"]
       }
-      throw new Error(`BirdNABirdsClassifierAddon: 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 BirdNABirdsClassifierAddon = class {
-      id = "bird-nabirds-classifier";
-      slot = "classifier";
-      inputClasses = ["animal"];
-      outputClasses = ["species:*"];
-      slotPriority = 0;
-      requiredSteps = [];
-      manifest = {
-        id: "bird-nabirds-classifier",
-        name: "Bird Classifier (NABirds, 404 species)",
-        version: "0.1.0",
-        description: "ResNet50 \u2014 404 North American bird species (NABirds dataset, ONNX + CoreML + OpenVINO)",
-        slot: "classifier",
-        labelOutputType: "classification",
-        inputClasses: ["animal"],
-        outputClasses: ["species:*"],
-        supportsCustomModels: false,
-        mayRequirePython: false,
-        defaultConfig: {
-          modelId: "bird-nabirds-404",
-          runtime: "node",
-          backend: "cpu",
-          minConfidence: 0.3
-        }
-      };
-      engine = null;
-      modelEntry;
-      labels = [];
-      minConfidence = 0.3;
-      allowedSpecies;
-      resolvedConfig = null;
-      ctx = null;
-      getModelRequirements() {
-        return animal_classification_models_js_1.BIRD_NABIRDS_MODELS.map((m) => ({
-          modelId: m.id,
-          name: m.name,
-          minRAM_MB: 300,
-          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 ?? "bird-nabirds-404";
-        this.minConfidence = cfg["minConfidence"] ?? 0.3;
-        this.allowedSpecies = cfg["allowedSpecies"];
-        const entry = animal_classification_models_js_1.BIRD_NABIRDS_MODELS.find((m) => m.id === modelId);
-        if (!entry) {
-          throw new Error(`BirdNABirdsClassifierAddon: unknown modelId "${modelId}"`);
-        }
-        this.modelEntry = entry;
-      }
-      applyRegionFilter(scores, labels) {
-        if (!this.allowedSpecies || this.allowedSpecies.length === 0)
-          return;
-        const allowedSet = new Set(this.allowedSpecies.map((s) => s.toLowerCase()));
-        for (let i = 0; i < scores.length; i++) {
-          if (!allowedSet.has(labels[i].toLowerCase())) {
-            scores[i] = 0;
-          }
-        }
-      }
-      async classify(input) {
-        if (!this.engine)
-          await this.ensureEngine();
-        const start = Date.now();
-        const { width: inputW, height: inputH } = this.modelEntry.inputSize;
-        const animalCrop = await (0, image_utils_js_1.cropRegion)(input.frame.data, input.roi);
-        const normalized = await (0, image_utils_js_1.resizeAndNormalize)(animalCrop, inputW, inputH, "imagenet", "nchw");
-        const rawOutput = await this.engine.run(normalized, [1, 3, inputH, inputW]);
-        const probs = softmax(rawOutput);
-        this.applyRegionFilter(probs, this.labels);
-        const filteredSum = probs.reduce((a, b) => a + b, 0);
-        if (filteredSum > 0) {
-          for (let i = 0; i < probs.length; i++) {
-            probs[i] = (probs[i] ?? 0) / filteredSum;
-          }
-        }
-        let maxIdx = 0;
-        let maxScore = probs[0] ?? 0;
-        for (let i = 1; i < probs.length; i++) {
-          const score = probs[i] ?? 0;
-          if (score > maxScore) {
-            maxScore = score;
-            maxIdx = i;
-          }
-        }
-        if (maxScore < this.minConfidence) {
-          return {
-            classifications: [],
-            inferenceMs: Date.now() - start,
-            modelId: this.modelEntry.id
-          };
-        }
-        const label = this.labels[maxIdx] ?? `species_${maxIdx}`;
-        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 = animal_classification_models_js_1.BIRD_NABIRDS_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 (0, engine_resolver_js_1.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: [...animal_classification_models_js_1.BIRD_NABIRDS_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
-                }
-              ]
-            },
-            {
-              id: "region",
-              title: "Regional Filter",
-              columns: 1,
-              fields: [
-                {
-                  key: "regionFilter",
-                  label: "Region Preset",
-                  type: "select",
-                  options: [
-                    { value: "", label: "None (all 404 species)" },
-                    { value: "north-america-east", label: "North America \u2014 Eastern" },
-                    { value: "north-america-west", label: "North America \u2014 Western" },
-                    { value: "north-america-south", label: "North America \u2014 Southern" }
-                  ]
-                },
-                {
-                  key: "allowedSpecies",
-                  label: "Custom Allowed Species (comma-separated)",
-                  type: "text"
-                }
-              ]
-            }
-          ]
-        };
-      }
-      getClassMap() {
-        return BIRD_CLASS_MAP;
-      }
-      getModelCatalog() {
-        return [...animal_classification_models_js_1.BIRD_NABIRDS_MODELS];
-      }
-      getAvailableModels() {
-        return [];
-      }
-      getActiveLabels() {
-        return SPECIES_LABELS;
-      }
-      async probe() {
-        return {
-          available: true,
-          runtime: this.engine?.runtime ?? "onnx",
-          device: this.engine?.device ?? "cpu",
-          capabilities: ["fp32"]
-        };
+  },
+  // ── PaddleOCR PP-OCRv5 Mobile — general-purpose text detection + recognition ──
+  {
+    id: "ppocr-v5-det-mobile",
+    name: "PP-OCRv5 Detection Mobile",
+    description: "PP-OCRv5 mobile text detection \u2014 optimized for edge, 100+ languages",
+    inputSize: { width: 640, height: 640 },
+    labels: OCR_TEXT_LABELS,
+    formats: {
+      onnx: {
+        url: hfModelUrl(HF_REPO, "generalOcr/ppocr-v5/onnx/camstack-ppocr-v5-det-mobile.onnx"),
+        sizeMB: 6
+      },
+      coreml: {
+        url: hfModelUrl(HF_REPO, "generalOcr/ppocr-v5/coreml/camstack-ppocr-v5-det-mobile.mlpackage"),
+        sizeMB: 3,
+        isDirectory: true,
+        files: [
+          "Manifest.json",
+          "Data/com.apple.CoreML/model.mlmodel",
+          "Data/com.apple.CoreML/weights/weight.bin"
+        ],
+        runtimes: ["python"]
+      },
+      openvino: {
+        url: hfModelUrl(HF_REPO, "generalOcr/ppocr-v5/openvino/camstack-ppocr-v5-det-mobile.xml"),
+        sizeMB: 3,
+        runtimes: ["python"]
       }
-    };
-    exports.default = BirdNABirdsClassifierAddon;
-  }
-});
-
-// src/addons/animal-classifier/index.js
-var require_animal_classifier = __commonJS({
-  "src/addons/animal-classifier/index.js"(exports) {
-    "use strict";
-    Object.defineProperty(exports, "__esModule", { value: true });
-    var animal_classification_models_js_1 = require_animal_classification_models();
-    var image_utils_js_1 = require_image_utils();
-    var engine_resolver_js_1 = require_engine_resolver();
-    var ANIMAL_TYPE_LABEL = { id: "animal-type", name: "Animal Type" };
-    var ANIMAL_TYPE_LABELS = [ANIMAL_TYPE_LABEL];
-    var ANIMAL_CLASS_MAP = { mapping: {}, preserveOriginal: true };
-    var ANIMAL_10_CLASSES = [
-      "cat",
-      "cow",
-      "dog",
-      "dolphin",
-      "eagle",
-      "giant panda",
-      "horse",
-      "monkey",
-      "sheep",
-      "spider"
-    ];
-    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 AnimalClassifierAddon = class {
-      id = "animal-classifier";
-      slot = "classifier";
-      inputClasses = ["animal"];
-      outputClasses = ["animal-type:*"];
-      slotPriority = 0;
-      requiredSteps = [];
-      manifest = {
-        id: "animal-classifier",
-        name: "Animal Classifier",
-        version: "0.1.0",
-        description: "ViT-based animal type classifier \u2014 10 common species",
-        slot: "classifier",
-        labelOutputType: "classification",
-        inputClasses: ["animal"],
-        outputClasses: ["animal-type:*"],
-        supportsCustomModels: false,
-        mayRequirePython: false,
-        defaultConfig: {
-          modelId: "animals-10",
-          runtime: "node",
-          backend: "cpu",
-          minConfidence: 0.3
-        }
-      };
-      engine = null;
-      modelEntry;
-      minConfidence = 0.3;
-      resolvedConfig = null;
-      ctx = null;
-      getModelRequirements() {
-        return animal_classification_models_js_1.ANIMAL_TYPE_MODELS.map((m) => ({
-          modelId: m.id,
-          name: m.name,
-          minRAM_MB: 800,
-          accuracyScore: 75,
-          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 ?? "animals-10";
-        this.minConfidence = cfg["minConfidence"] ?? 0.3;
-        const entry = animal_classification_models_js_1.ANIMAL_TYPE_MODELS.find((m) => m.id === modelId);
-        if (!entry) {
-          throw new Error(`AnimalClassifierAddon: 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 animalCrop = await (0, image_utils_js_1.cropRegion)(input.frame.data, input.roi);
-        const normalized = await (0, image_utils_js_1.resizeAndNormalize)(animalCrop, inputW, inputH, "imagenet", "nchw");
-        const rawOutput = await this.engine.run(normalized, [1, 3, inputH, inputW]);
-        const probs = softmax(rawOutput);
-        let maxIdx = 0;
-        let maxScore = probs[0] ?? 0;
-        for (let i = 1; i < probs.length; i++) {
-          const score = probs[i] ?? 0;
-          if (score > maxScore) {
-            maxScore = score;
-            maxIdx = i;
-          }
-        }
-        if (maxScore < this.minConfidence) {
-          return {
-            classifications: [],
-            inferenceMs: Date.now() - start,
-            modelId: this.modelEntry.id
-          };
-        }
-        const label = ANIMAL_10_CLASSES[maxIdx] ?? `animal_${maxIdx}`;
-        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 = animal_classification_models_js_1.ANIMAL_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);
-        }
-        const resolved = await (0, engine_resolver_js_1.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: [...animal_classification_models_js_1.ANIMAL_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 ANIMAL_CLASS_MAP;
-      }
-      getModelCatalog() {
-        return [...animal_classification_models_js_1.ANIMAL_TYPE_MODELS];
-      }
-      getAvailableModels() {
-        return [];
-      }
-      getActiveLabels() {
-        return ANIMAL_TYPE_LABELS;
+  },
+  {
+    id: "ppocr-v5-rec-mobile",
+    name: "PP-OCRv5 Recognition Mobile",
+    description: "PP-OCRv5 mobile text recognition \u2014 100+ languages, CTC decoding",
+    inputSize: { width: 320, height: 48 },
+    labels: OCR_TEXT_LABELS,
+    formats: {
+      onnx: {
+        url: hfModelUrl(HF_REPO, "generalOcr/ppocr-v5/onnx/camstack-ppocr-v5-rec-mobile.onnx"),
+        sizeMB: 8
+      },
+      coreml: {
+        url: hfModelUrl(HF_REPO, "generalOcr/ppocr-v5/coreml/camstack-ppocr-v5-rec-mobile.mlpackage"),
+        sizeMB: 4,
+        isDirectory: true,
+        files: [
+          "Manifest.json",
+          "Data/com.apple.CoreML/model.mlmodel",
+          "Data/com.apple.CoreML/weights/weight.bin"
+        ],
+        runtimes: ["python"]
+      },
+      openvino: {
+        url: hfModelUrl(HF_REPO, "generalOcr/ppocr-v5/openvino/camstack-ppocr-v5-rec-mobile.xml"),
+        sizeMB: 4,
+        runtimes: ["python"]
       }
-      async probe() {
-        return {
-          available: true,
-          runtime: this.engine?.runtime ?? "onnx",
-          device: this.engine?.device ?? "cpu",
-          capabilities: ["fp32"]
-        };
+    },
+    extraFiles: [
+      {
+        url: hfModelUrl(HF_REPO, "generalOcr/ppocr-v5/camstack-ppocr-v5-keys.txt"),
+        filename: "camstack-ppocr-v5-keys.txt",
+        sizeMB: 0.1
       }
-    };
-    exports.default = AnimalClassifierAddon;
+    ]
   }
-});
-
-// src/index.ts
-var src_exports = {};
-__export(src_exports, {
-  AnimalClassifierAddon: () => import_animal_classifier.default,
-  AudioClassificationAddon: () => import_audio_classification.default,
-  BirdGlobalClassifierAddon: () => import_bird_global_classifier.default,
-  BirdNABirdsClassifierAddon: () => import_bird_nabirds_classifier.default,
-  FaceDetectionAddon: () => import_face_detection.default,
-  FaceRecognitionAddon: () => import_face_recognition.default,
-  NodeInferenceEngine: () => import_node_engine.NodeInferenceEngine,
-  ObjectDetectionAddon: () => import_object_detection.default,
-  PlateDetectionAddon: () => import_plate_detection.default,
-  PlateRecognitionAddon: () => import_plate_recognition.default,
-  PythonInferenceEngine: () => import_python_engine.PythonInferenceEngine,
-  cosineSimilarity: () => import_arcface.cosineSimilarity,
-  cropRegion: () => import_image_utils.cropRegion,
-  ctcDecode: () => import_paddleocr.ctcDecode,
-  detectMotion: () => import_frame_diff.detectMotion,
-  iou: () => import_yolo.iou,
-  jpegToRgb: () => import_image_utils.jpegToRgb,
-  l2Normalize: () => import_arcface.l2Normalize,
-  letterbox: () => import_image_utils.letterbox,
-  nms: () => import_yolo.nms,
-  probeOnnxBackends: () => import_engine_resolver.probeOnnxBackends,
-  resizeAndNormalize: () => import_image_utils.resizeAndNormalize,
-  resolveEngine: () => import_engine_resolver.resolveEngine,
-  rgbToGrayscale: () => import_image_utils.rgbToGrayscale,
-  scrfdPostprocess: () => import_scrfd.scrfdPostprocess,
-  yamnetPostprocess: () => import_yamnet.yamnetPostprocess,
-  yoloPostprocess: () => import_yolo.yoloPostprocess
-});
-var import_image_utils = __toESM(require_image_utils());
-var import_yolo = __toESM(require_yolo());
-var import_scrfd = __toESM(require_scrfd());
-var import_arcface = __toESM(require_arcface());
-var import_paddleocr = __toESM(require_paddleocr());
-var import_yamnet = __toESM(require_yamnet());
-var import_node_engine = __toESM(require_node_engine());
-var import_python_engine = __toESM(require_python_engine());
-var import_engine_resolver = __toESM(require_engine_resolver());
-var import_frame_diff = __toESM(require_frame_diff());
-__reExport(src_exports, __toESM(require_catalogs()));
-var import_object_detection = __toESM(require_object_detection());
-var import_face_detection = __toESM(require_face_detection());
-var import_face_recognition = __toESM(require_face_recognition());
-var import_plate_detection = __toESM(require_plate_detection());
-var import_plate_recognition = __toESM(require_plate_recognition());
-var import_audio_classification = __toESM(require_audio_classification());
-var import_bird_global_classifier = __toESM(require_bird_global_classifier());
-var import_bird_nabirds_classifier = __toESM(require_bird_nabirds_classifier());
-var import_animal_classifier = __toESM(require_animal_classifier());
-var export_AnimalClassifierAddon = import_animal_classifier.default;
-var export_AudioClassificationAddon = import_audio_classification.default;
-var export_BirdGlobalClassifierAddon = import_bird_global_classifier.default;
-var export_BirdNABirdsClassifierAddon = import_bird_nabirds_classifier.default;
-var export_FaceDetectionAddon = import_face_detection.default;
-var export_FaceRecognitionAddon = import_face_recognition.default;
-var export_NodeInferenceEngine = import_node_engine.NodeInferenceEngine;
-var export_ObjectDetectionAddon = import_object_detection.default;
-var export_PlateDetectionAddon = import_plate_detection.default;
-var export_PlateRecognitionAddon = import_plate_recognition.default;
-var export_PythonInferenceEngine = import_python_engine.PythonInferenceEngine;
-var export_cosineSimilarity = import_arcface.cosineSimilarity;
-var export_cropRegion = import_image_utils.cropRegion;
-var export_ctcDecode = import_paddleocr.ctcDecode;
-var export_detectMotion = import_frame_diff.detectMotion;
-var export_iou = import_yolo.iou;
-var export_jpegToRgb = import_image_utils.jpegToRgb;
-var export_l2Normalize = import_arcface.l2Normalize;
-var export_letterbox = import_image_utils.letterbox;
-var export_nms = import_yolo.nms;
-var export_probeOnnxBackends = import_engine_resolver.probeOnnxBackends;
-var export_resizeAndNormalize = import_image_utils.resizeAndNormalize;
-var export_resolveEngine = import_engine_resolver.resolveEngine;
-var export_rgbToGrayscale = import_image_utils.rgbToGrayscale;
-var export_scrfdPostprocess = import_scrfd.scrfdPostprocess;
-var export_yamnetPostprocess = import_yamnet.yamnetPostprocess;
-var export_yoloPostprocess = import_yolo.yoloPostprocess;
+];
 export {
-  export_AnimalClassifierAddon as AnimalClassifierAddon,
-  export_AudioClassificationAddon as AudioClassificationAddon,
-  export_BirdGlobalClassifierAddon as BirdGlobalClassifierAddon,
-  export_BirdNABirdsClassifierAddon as BirdNABirdsClassifierAddon,
-  export_FaceDetectionAddon as FaceDetectionAddon,
-  export_FaceRecognitionAddon as FaceRecognitionAddon,
-  export_NodeInferenceEngine as NodeInferenceEngine,
-  export_ObjectDetectionAddon as ObjectDetectionAddon,
-  export_PlateDetectionAddon as PlateDetectionAddon,
-  export_PlateRecognitionAddon as PlateRecognitionAddon,
-  export_PythonInferenceEngine as PythonInferenceEngine,
-  export_cosineSimilarity as cosineSimilarity,
-  export_cropRegion as cropRegion,
-  export_ctcDecode as ctcDecode,
-  export_detectMotion as detectMotion,
-  export_iou as iou,
-  export_jpegToRgb as jpegToRgb,
-  export_l2Normalize as l2Normalize,
-  export_letterbox as letterbox,
-  export_nms as nms,
-  export_probeOnnxBackends as probeOnnxBackends,
-  export_resizeAndNormalize as resizeAndNormalize,
-  export_resolveEngine as resolveEngine,
-  export_rgbToGrayscale as rgbToGrayscale,
-  export_scrfdPostprocess as scrfdPostprocess,
-  export_yamnetPostprocess as yamnetPostprocess,
-  export_yoloPostprocess as yoloPostprocess
+  ANIMAL_TYPE_MODELS,
+  AUDIO_CLASSIFICATION_MODELS,
+  AnimalClassifierAddon,
+  AudioClassificationAddon,
+  BIRD_NABIRDS_MODELS,
+  BIRD_SPECIES_MODELS,
+  BirdGlobalClassifierAddon,
+  BirdNABirdsClassifierAddon,
+  FACE_DETECTION_MODELS,
+  FACE_RECOGNITION_MODELS,
+  FaceDetectionAddon,
+  FaceRecognitionAddon,
+  GENERAL_OCR_MODELS,
+  MLPACKAGE_FILES,
+  NodeInferenceEngine,
+  OBJECT_DETECTION_MODELS,
+  ObjectDetectionAddon,
+  PLATE_DETECTION_MODELS,
+  PLATE_RECOGNITION_MODELS,
+  PlateDetectionAddon,
+  PlateRecognitionAddon,
+  PythonInferenceEngine,
+  SEGMENTATION_MODELS,
+  SEGMENTATION_REFINER_MODELS,
+  VEHICLE_TYPE_MODELS,
+  cosineSimilarity,
+  cropRegion,
+  ctcDecode,
+  detectMotion,
+  iou,
+  jpegToRgb,
+  l2Normalize,
+  letterbox,
+  nms,
+  probeOnnxBackends,
+  resizeAndNormalize,
+  resolveEngine,
+  rgbToGrayscale,
+  scrfdPostprocess,
+  yamnetPostprocess,
+  yoloPostprocess
 };
 //# sourceMappingURL=index.mjs.map