@camstack/addon-pipeline 1.2.328 → 1.2.330

package/THIRD_PARTY_MODELS.md

@@ -134,7 +134,7 @@ entry kept resolvable for a saved selection but no longer offered.
 
 | Catalog ids | Upstream | Code / weights | Training data | CamStack changes | Downloaded from |
 | --- | --- | --- | --- | --- | --- |
-| `yunet-2023mar` (default) | [OpenCV Zoo YuNet](https://github.com/opencv/opencv_zoo/tree/main/models/face_detection_yunet) | BSD-3-Clause (`BSD-3-Clause.txt`) / MIT (`MIT-yunet-reference.txt`) | WIDER FACE: research-oriented terms; images CC BY-NC-ND | input contract baked into the graph (the pool RGB /255 becomes the upstream BGR 0..255: Mul(255) plus a channel Gather); internal tensor names cleared in the OpenVINO IR; ONNX fp32, OpenVINO IR fp32, CoreML fp16 (scripts/build-yunet-model.py) | mirror `faceDetection/yunet` |
+| `yunet-2023mar` (default) | [OpenCV Zoo YuNet](https://github.com/opencv/opencv_zoo/tree/main/models/face_detection_yunet) | BSD-3-Clause (`BSD-3-Clause.txt`) / MIT (`MIT-yunet-reference.txt`) | WIDER FACE: research-oriented terms; images CC BY-NC-ND | input contract baked into the graph (the pool RGB /255 becomes the upstream BGR 0..255: Mul(255) plus a channel Gather); internal tensor names cleared in the OpenVINO IR; ONNX fp32, OpenVINO IR fp32, CoreML fp16 (scripts/build-yunet-model.py); Edge TPU build: the bake folded into the first Conv, full-integer int8 post-training quantisation calibrated on CamStack person crops, compiled with edgetpu_compiler 14 (scripts/build-yunet-edgetpu.py) | mirror `faceDetection/yunet` |
 
 ### Face recognition
 
@@ -146,7 +146,7 @@ entry kept resolvable for a saved selection but no longer offered.
 
 | Catalog ids | Upstream | Code / weights | Training data | CamStack changes | Downloaded from |
 | --- | --- | --- | --- | --- | --- |
-| `yolox-tiny-plate` (default) | [open-lpr models (faisalthaheem/open-lpr-models), YOLOX-tiny](https://huggingface.co/faisalthaheem/open-lpr-models) | Apache-2.0 / Apache-2.0 (`Apache-2.0.txt`) | Simanno annotated plate corpus plus community-contributed photographs, pseudo-labelled by a teacher model (not published; the upstream NOTICE says the photographs were uploaded without consent obtained): UNKNOWN | input contract baked into the graph (static 1x3x640x640 RGB /255 becomes the upstream BGR 0..255: Mul(255) plus a channel Gather) and the output reshaped to the YOLOv8 layout (cx, cy, w, h, obj*cls); ONNX fp32, OpenVINO IR fp16, CoreML fp16 (scripts/build-yolox-plate-model.py) | mirror `plateDetection/yolox-tiny-plate` |
+| `yolox-tiny-plate` (default) | [open-lpr models (faisalthaheem/open-lpr-models), YOLOX-tiny](https://huggingface.co/faisalthaheem/open-lpr-models) | Apache-2.0 / Apache-2.0 (`Apache-2.0.txt`) | Simanno annotated plate corpus plus community-contributed photographs, pseudo-labelled by a teacher model (not published; the upstream NOTICE says the photographs were uploaded without consent obtained): UNKNOWN | input contract baked into the graph (static 1x3x640x640 RGB /255 becomes the upstream BGR 0..255: Mul(255) plus a channel Gather) and the output reshaped to the YOLOv8 layout (cx, cy, w, h, obj*cls); ONNX fp32, OpenVINO IR fp16, CoreML fp16 (scripts/build-yolox-plate-model.py); Edge TPU build: the Focus stem rewritten as the equivalent 6x6 stride-2 Conv with the input bake folded into it, the graph cut before the grid decode (raw per-stride head), full-integer int8 post-training quantisation calibrated on CamStack vehicle crops, compiled with edgetpu_compiler 14 (scripts/build-yolox-plate-edgetpu.py) | mirror `plateDetection/yolox-tiny-plate` |
 
 ### Licence plate reading
 

package/dist/audio-analyzer/index.js

@@ -3,8 +3,8 @@ Object.defineProperties(exports, {
 	[Symbol.toStringTag]: { value: "Module" }
 });
 const require_chunk = require("../chunk-emK7D4bc.js");
-const require_dist = require("../dist-wJO7mXeO.js");
-const require_process_memory = require("../process-memory-iUJuTpXs.js");
+const require_dist = require("../dist-CMeICL07.js");
+const require_process_memory = require("../process-memory-o4LFWbBN.js");
 let node_fs = require("node:fs");
 node_fs = require_chunk.__toESM(node_fs);
 let node_path = require("node:path");

package/dist/audio-analyzer/index.mjs

@@ -1,6 +1,6 @@
 import { n as __require } from "../chunk-DnnnRqeS.mjs";
-import { An as hydrateSchema, F as PoolMemoryWatchdog, J as audioAnalysisCapability, Pn as nodePin, Sn as BaseAddon, Tn as audioChunkBytesPerSample, Y as audioAnalyzerCapability, Zn as EventCategory, bn as errMsg, en as resolvePoolMemoryPolicy, k as HF_BASE_URL, kn as expandAudioChunkToF32le, kt as mapAudioLabelToMacro, m as DEFAULT_AUDIO_ANALYZER_CONFIG, r as AUDIO_BACKEND_CHOICES } from "../dist-Bpub2VcJ.mjs";
-import { n as pickNodePlatformArch, t as readProcessMemory } from "../process-memory-BaKQ8u2G.mjs";
+import { Cn as errMsg, D as HF_BASE_URL, J as audioAnalysisCapability, Ln as nodePin, Mn as expandAudioChunkToF32le, N as PoolMemoryWatchdog, Nn as hydrateSchema, On as audioChunkBytesPerSample, Tn as BaseAddon, Y as audioAnalyzerCapability, er as EventCategory, h as DEFAULT_AUDIO_ANALYZER_CONFIG, jt as mapAudioLabelToMacro, r as AUDIO_BACKEND_CHOICES, tn as resolvePoolMemoryPolicy } from "../dist-CuPEyZY2.mjs";
+import { n as pickNodePlatformArch, t as readProcessMemory } from "../process-memory-07XYts8V.mjs";
 import * as fs from "node:fs";
 import * as path$1 from "node:path";
 import { downloadFile } from "@camstack/system/addon-utils";

package/dist/{default-detection-model-1SadEKsW.js → default-detection-model-B6gKGnfx.js}

@@ -1,4 +1,4 @@
-const require_dist = require("./dist-wJO7mXeO.js");
+const require_dist = require("./dist-CMeICL07.js");
 const require_worker_protocol = require("./worker-protocol-C-G8qmye.js");
 let node_crypto = require("node:crypto");
 //#region src/detection-pipeline/registry/effective-confidence.ts
@@ -90,7 +90,7 @@ var YUNET_MIT = {
 	},
 	url: "https://github.com/opencv/opencv_zoo/blob/main/models/face_detection_yunet/LICENSE",
 	attribution: "YuNet weights Copyright (c) 2020 Shiqi Yu, MIT. Training code: ShiqiYu/libfacedetection.train, BSD-3-Clause.",
-	modifications: "input contract baked into the graph (the pool RGB /255 becomes the upstream BGR 0..255: Mul(255) plus a channel Gather); internal tensor names cleared in the OpenVINO IR; ONNX fp32, OpenVINO IR fp32, CoreML fp16 (scripts/build-yunet-model.py)",
+	modifications: "input contract baked into the graph (the pool RGB /255 becomes the upstream BGR 0..255: Mul(255) plus a channel Gather); internal tensor names cleared in the OpenVINO IR; ONNX fp32, OpenVINO IR fp32, CoreML fp16 (scripts/build-yunet-model.py); Edge TPU build: the bake folded into the first Conv, full-integer int8 post-training quantisation calibrated on CamStack person crops, compiled with edgetpu_compiler 14 (scripts/build-yunet-edgetpu.py)",
 	hosting: "camstack-hf"
 };
 var AURAFACE_APACHE = {
@@ -125,7 +125,7 @@ var OPEN_LPR_YOLOX_APACHE = {
 	},
 	url: "https://huggingface.co/faisalthaheem/open-lpr-models/blob/aed0df35ec2891c5a90437041ebeadb592cc516b/LICENSE",
 	attribution: "open-lpr models, Copyright the open-lpr contributors, Apache-2.0 (https://huggingface.co/faisalthaheem/open-lpr-models, tag detector-2026.10.1). YOLOX architecture and COCO pretraining by Megvii (https://github.com/Megvii-BaseDetection/YOLOX), Apache-2.0. The upstream NOTICE is reproduced verbatim (`NOTICE-open-lpr.txt`).",
-	modifications: "input contract baked into the graph (static 1x3x640x640 RGB /255 becomes the upstream BGR 0..255: Mul(255) plus a channel Gather) and the output reshaped to the YOLOv8 layout (cx, cy, w, h, obj*cls); ONNX fp32, OpenVINO IR fp16, CoreML fp16 (scripts/build-yolox-plate-model.py)",
+	modifications: "input contract baked into the graph (static 1x3x640x640 RGB /255 becomes the upstream BGR 0..255: Mul(255) plus a channel Gather) and the output reshaped to the YOLOv8 layout (cx, cy, w, h, obj*cls); ONNX fp32, OpenVINO IR fp16, CoreML fp16 (scripts/build-yolox-plate-model.py); Edge TPU build: the Focus stem rewritten as the equivalent 6x6 stride-2 Conv with the input bake folded into it, the graph cut before the grid decode (raw per-stride head), full-integer int8 post-training quantisation calibrated on CamStack vehicle crops, compiled with edgetpu_compiler 14 (scripts/build-yolox-plate-edgetpu.py)",
 	hosting: "camstack-hf"
 };
 var FAST_PLATE_OCR_MIT = {
@@ -752,7 +752,12 @@ var FACE_DETECTION_MODELS = [{
 			files: [...MLPACKAGE_FILES],
 			runtimes: ["python"]
 		},
-		openvino: ovFormat(hf("faceDetection/yunet/openvino/camstack-yunet-2023mar.xml"), .36)
+		openvino: ovFormat(hf("faceDetection/yunet/openvino/camstack-yunet-2023mar.xml"), .36),
+		tflite: {
+			url: hf("faceDetection/yunet/tflite/camstack-yunet-2023mar_edgetpu.tflite"),
+			sizeMB: .7,
+			runtimes: ["python"]
+		}
 	}
 }];
 var FACE_EMBEDDING_MODELS = [{
@@ -812,7 +817,12 @@ var PLATE_DETECTION_MODELS = [{
 			files: [...MLPACKAGE_FILES],
 			runtimes: ["python"]
 		},
-		openvino: ovFormat(hf("plateDetection/yolox-tiny-plate/openvino/camstack-yolox-tiny-plate.xml"), 10)
+		openvino: ovFormat(hf("plateDetection/yolox-tiny-plate/openvino/camstack-yolox-tiny-plate.xml"), 10),
+		tflite: {
+			url: hf("plateDetection/yolox-tiny-plate/tflite/camstack-yolox-tiny-plate_edgetpu.tflite"),
+			sizeMB: 6.9,
+			runtimes: ["python"]
+		}
 	}
 }];
 var PACKAGE_DETECTION_MODELS = [{
@@ -1174,27 +1184,8 @@ var ANIMAL_10_LABELS = [
 	"sheep",
 	"spider"
 ];
-var ANIMAL_CLASSIFIER_LABELS = require_dist.FILLABLE_STEP_VOCABULARIES["animal-classifier"];
-var VEHICLE_CLASSIFIER_LABELS = require_dist.FILLABLE_STEP_VOCABULARIES["vehicle-classifier"];
-/**
-* The `labelLink` policy field (D715) — offered on every step a root detector
-* can fill. Stored in the step's own settings (`DeviceStepConfig.settings` /
-* `CameraStepOverridePatch.settings`), so it has ONE authority. It changes
-* nothing unless the camera's root model declares it fills this step.
-*/
-function labelLinkField(stepName) {
-	return {
-		type: "select",
-		key: require_dist.LABEL_LINK_SETTING_KEY,
-		label: "When the detector already fills this step",
-		description: `Only matters when the root detection model declares it fills ${stepName} (e.g. a Frigate+ model). "Skip" does not run ${stepName} for a subject the detector already named, and makes the detector's label the one answer — but only once every class the detector cannot produce is switched off in this step's class list. "Run" always runs ${stepName}; the detector's label is then a fallback any answer of the step outranks.`,
-		options: require_dist.LABEL_LINK_POLICIES.map((p) => ({
-			value: p,
-			label: p === "run" ? "Run anyway" : "Skip when filled"
-		})),
-		default: require_dist.DEFAULT_LABEL_LINK_POLICY
-	};
-}
+var ANIMAL_CLASSIFIER_LABELS = require_dist.LABEL_SUPPLY_VOCABULARIES["animal-classifier"];
+var VEHICLE_CLASSIFIER_LABELS = require_dist.LABEL_SUPPLY_VOCABULARIES["vehicle-classifier"];
 var VGG_G2_CHARSET = [
 	"",
 	..."0123456789".split(""),
@@ -1410,31 +1401,27 @@ var AnimalClassifierStep = class {
 		}
 	};
 	getConfigSchema(model) {
-		return [
-			{
-				type: "multiselect",
-				key: "enabledClasses",
-				label: "Species",
-				description: "Which animal species to keep (empty = all). The classifier still scores every label but only the selected classes are returned on the detection.",
-				options: ANIMAL_CLASSIFIER_LABELS.map((l) => ({
-					value: l,
-					label: l
-				})),
-				default: []
-			},
-			labelLinkField("the animal classifier"),
-			{
-				type: "slider",
-				key: "minConfidence",
-				label: "Min Confidence",
-				description: "Drop classifications whose score is below this threshold.",
-				default: resolveModelDefaultConfidence(this.definition, model),
-				min: 0,
-				max: 1,
-				step: .05,
-				showValue: true
-			}
-		];
+		return [{
+			type: "multiselect",
+			key: "enabledClasses",
+			label: "Species",
+			description: "Which animal species to keep (empty = all). The classifier still scores every label but only the selected classes are returned on the detection. When the root model is the source, the same list decides which of its labels become the species; a switched-off species stays \"animal\".",
+			options: ANIMAL_CLASSIFIER_LABELS.map((l) => ({
+				value: l,
+				label: l
+			})),
+			default: []
+		}, {
+			type: "slider",
+			key: "minConfidence",
+			label: "Min Confidence",
+			description: "Drop classifications whose score is below this threshold.",
+			default: resolveModelDefaultConfidence(this.definition, model),
+			min: 0,
+			max: 1,
+			step: .05,
+			showValue: true
+		}];
 	}
 };
 /**
@@ -1472,7 +1459,7 @@ var PackageDetectionStep = class extends PipelineStepBase {
 			step: .05,
 			default: resolveModelDefaultConfidence(this.definition, model),
 			showValue: true
-		}, labelLinkField("package detection")];
+		}];
 	}
 };
 var ClassifierWithMinConfidence = class extends PipelineStepBase {
@@ -1688,28 +1675,23 @@ var STEP_BIRD_CLASSIFIER = new ClassifierWithMinConfidence({
 	}
 });
 /**
-* `vehicle-classifier` — the `minConfidence` slider plus the two fields a
-* root-detector fill needs (D715): the class allow-list (a coverage gap the
-* detector cannot produce, e.g. `Van` for Frigate+, is switched off HERE before
-* the skip applies) and the `labelLink` policy.
+* `vehicle-classifier` — the `minConfidence` slider plus the class allow-list.
+* When the step takes the root model's labels (`useRootModel`, D730) the same
+* allow-list filters which root labels become the vehicle type.
 */
 var VehicleClassifierStep = class extends ClassifierWithMinConfidence {
 	getConfigSchema(model) {
-		return [
-			{
-				type: "multiselect",
-				key: "enabledClasses",
-				label: "Vehicle types",
-				description: "Which vehicle types to keep (empty = all). The classifier still scores every type but only the selected ones are returned on the detection.",
-				options: VEHICLE_CLASSIFIER_LABELS.map((l) => ({
-					value: l,
-					label: l
-				})),
-				default: []
-			},
-			...super.getConfigSchema(model),
-			labelLinkField("the vehicle classifier")
-		];
+		return [{
+			type: "multiselect",
+			key: "enabledClasses",
+			label: "Vehicle types",
+			description: "Which vehicle types to keep (empty = all). The classifier still scores every type but only the selected ones are returned on the detection. When the root model is the source, the same list decides which of its labels become the type; a switched-off type stays \"vehicle\".",
+			options: VEHICLE_CLASSIFIER_LABELS.map((l) => ({
+				value: l,
+				label: l
+			})),
+			default: []
+		}, ...super.getConfigSchema(model)];
 	}
 };
 var STEP_VEHICLE_CLASSIFIER = new VehicleClassifierStep({

package/dist/{default-detection-model-CMeVTcPZ.mjs → default-detection-model-CPDT_eFT.mjs}

@@ -1,4 +1,4 @@
-import { A as LABEL_LINK_POLICIES, Ct as inferModelProvider, E as FILLABLE_STEP_VOCABULARIES, St as hfModelUrl, X as audioKindId, b as DEVICE_BACKEND_TO_FORMAT, f as COCO_80_LABELS, i as AUDIO_MACRO_LABELS, j as LABEL_LINK_SETTING_KEY, p as COCO_TO_MACRO, rn as stepModelRunsOnFormat, v as DEFAULT_LABEL_LINK_POLICY } from "./dist-Bpub2VcJ.mjs";
+import { Tt as inferModelProvider, X as audioKindId, b as DEVICE_BACKEND_TO_FORMAT, f as COCO_80_LABELS, i as AUDIO_MACRO_LABELS, k as LABEL_SUPPLY_VOCABULARIES, on as stepModelRunsOnFormat, p as COCO_TO_MACRO, wt as hfModelUrl } from "./dist-CuPEyZY2.mjs";
 import { t as isWorkerReply } from "./worker-protocol-D_NzPcnh.mjs";
 import { randomUUID } from "node:crypto";
 //#region src/detection-pipeline/registry/effective-confidence.ts
@@ -90,7 +90,7 @@ var YUNET_MIT = {
 	},
 	url: "https://github.com/opencv/opencv_zoo/blob/main/models/face_detection_yunet/LICENSE",
 	attribution: "YuNet weights Copyright (c) 2020 Shiqi Yu, MIT. Training code: ShiqiYu/libfacedetection.train, BSD-3-Clause.",
-	modifications: "input contract baked into the graph (the pool RGB /255 becomes the upstream BGR 0..255: Mul(255) plus a channel Gather); internal tensor names cleared in the OpenVINO IR; ONNX fp32, OpenVINO IR fp32, CoreML fp16 (scripts/build-yunet-model.py)",
+	modifications: "input contract baked into the graph (the pool RGB /255 becomes the upstream BGR 0..255: Mul(255) plus a channel Gather); internal tensor names cleared in the OpenVINO IR; ONNX fp32, OpenVINO IR fp32, CoreML fp16 (scripts/build-yunet-model.py); Edge TPU build: the bake folded into the first Conv, full-integer int8 post-training quantisation calibrated on CamStack person crops, compiled with edgetpu_compiler 14 (scripts/build-yunet-edgetpu.py)",
 	hosting: "camstack-hf"
 };
 var AURAFACE_APACHE = {
@@ -125,7 +125,7 @@ var OPEN_LPR_YOLOX_APACHE = {
 	},
 	url: "https://huggingface.co/faisalthaheem/open-lpr-models/blob/aed0df35ec2891c5a90437041ebeadb592cc516b/LICENSE",
 	attribution: "open-lpr models, Copyright the open-lpr contributors, Apache-2.0 (https://huggingface.co/faisalthaheem/open-lpr-models, tag detector-2026.10.1). YOLOX architecture and COCO pretraining by Megvii (https://github.com/Megvii-BaseDetection/YOLOX), Apache-2.0. The upstream NOTICE is reproduced verbatim (`NOTICE-open-lpr.txt`).",
-	modifications: "input contract baked into the graph (static 1x3x640x640 RGB /255 becomes the upstream BGR 0..255: Mul(255) plus a channel Gather) and the output reshaped to the YOLOv8 layout (cx, cy, w, h, obj*cls); ONNX fp32, OpenVINO IR fp16, CoreML fp16 (scripts/build-yolox-plate-model.py)",
+	modifications: "input contract baked into the graph (static 1x3x640x640 RGB /255 becomes the upstream BGR 0..255: Mul(255) plus a channel Gather) and the output reshaped to the YOLOv8 layout (cx, cy, w, h, obj*cls); ONNX fp32, OpenVINO IR fp16, CoreML fp16 (scripts/build-yolox-plate-model.py); Edge TPU build: the Focus stem rewritten as the equivalent 6x6 stride-2 Conv with the input bake folded into it, the graph cut before the grid decode (raw per-stride head), full-integer int8 post-training quantisation calibrated on CamStack vehicle crops, compiled with edgetpu_compiler 14 (scripts/build-yolox-plate-edgetpu.py)",
 	hosting: "camstack-hf"
 };
 var FAST_PLATE_OCR_MIT = {
@@ -752,7 +752,12 @@ var FACE_DETECTION_MODELS = [{
 			files: [...MLPACKAGE_FILES],
 			runtimes: ["python"]
 		},
-		openvino: ovFormat(hf("faceDetection/yunet/openvino/camstack-yunet-2023mar.xml"), .36)
+		openvino: ovFormat(hf("faceDetection/yunet/openvino/camstack-yunet-2023mar.xml"), .36),
+		tflite: {
+			url: hf("faceDetection/yunet/tflite/camstack-yunet-2023mar_edgetpu.tflite"),
+			sizeMB: .7,
+			runtimes: ["python"]
+		}
 	}
 }];
 var FACE_EMBEDDING_MODELS = [{
@@ -812,7 +817,12 @@ var PLATE_DETECTION_MODELS = [{
 			files: [...MLPACKAGE_FILES],
 			runtimes: ["python"]
 		},
-		openvino: ovFormat(hf("plateDetection/yolox-tiny-plate/openvino/camstack-yolox-tiny-plate.xml"), 10)
+		openvino: ovFormat(hf("plateDetection/yolox-tiny-plate/openvino/camstack-yolox-tiny-plate.xml"), 10),
+		tflite: {
+			url: hf("plateDetection/yolox-tiny-plate/tflite/camstack-yolox-tiny-plate_edgetpu.tflite"),
+			sizeMB: 6.9,
+			runtimes: ["python"]
+		}
 	}
 }];
 var PACKAGE_DETECTION_MODELS = [{
@@ -1174,27 +1184,8 @@ var ANIMAL_10_LABELS = [
 	"sheep",
 	"spider"
 ];
-var ANIMAL_CLASSIFIER_LABELS = FILLABLE_STEP_VOCABULARIES["animal-classifier"];
-var VEHICLE_CLASSIFIER_LABELS = FILLABLE_STEP_VOCABULARIES["vehicle-classifier"];
-/**
-* The `labelLink` policy field (D715) — offered on every step a root detector
-* can fill. Stored in the step's own settings (`DeviceStepConfig.settings` /
-* `CameraStepOverridePatch.settings`), so it has ONE authority. It changes
-* nothing unless the camera's root model declares it fills this step.
-*/
-function labelLinkField(stepName) {
-	return {
-		type: "select",
-		key: LABEL_LINK_SETTING_KEY,
-		label: "When the detector already fills this step",
-		description: `Only matters when the root detection model declares it fills ${stepName} (e.g. a Frigate+ model). "Skip" does not run ${stepName} for a subject the detector already named, and makes the detector's label the one answer — but only once every class the detector cannot produce is switched off in this step's class list. "Run" always runs ${stepName}; the detector's label is then a fallback any answer of the step outranks.`,
-		options: LABEL_LINK_POLICIES.map((p) => ({
-			value: p,
-			label: p === "run" ? "Run anyway" : "Skip when filled"
-		})),
-		default: DEFAULT_LABEL_LINK_POLICY
-	};
-}
+var ANIMAL_CLASSIFIER_LABELS = LABEL_SUPPLY_VOCABULARIES["animal-classifier"];
+var VEHICLE_CLASSIFIER_LABELS = LABEL_SUPPLY_VOCABULARIES["vehicle-classifier"];
 var VGG_G2_CHARSET = [
 	"",
 	..."0123456789".split(""),
@@ -1410,31 +1401,27 @@ var AnimalClassifierStep = class {
 		}
 	};
 	getConfigSchema(model) {
-		return [
-			{
-				type: "multiselect",
-				key: "enabledClasses",
-				label: "Species",
-				description: "Which animal species to keep (empty = all). The classifier still scores every label but only the selected classes are returned on the detection.",
-				options: ANIMAL_CLASSIFIER_LABELS.map((l) => ({
-					value: l,
-					label: l
-				})),
-				default: []
-			},
-			labelLinkField("the animal classifier"),
-			{
-				type: "slider",
-				key: "minConfidence",
-				label: "Min Confidence",
-				description: "Drop classifications whose score is below this threshold.",
-				default: resolveModelDefaultConfidence(this.definition, model),
-				min: 0,
-				max: 1,
-				step: .05,
-				showValue: true
-			}
-		];
+		return [{
+			type: "multiselect",
+			key: "enabledClasses",
+			label: "Species",
+			description: "Which animal species to keep (empty = all). The classifier still scores every label but only the selected classes are returned on the detection. When the root model is the source, the same list decides which of its labels become the species; a switched-off species stays \"animal\".",
+			options: ANIMAL_CLASSIFIER_LABELS.map((l) => ({
+				value: l,
+				label: l
+			})),
+			default: []
+		}, {
+			type: "slider",
+			key: "minConfidence",
+			label: "Min Confidence",
+			description: "Drop classifications whose score is below this threshold.",
+			default: resolveModelDefaultConfidence(this.definition, model),
+			min: 0,
+			max: 1,
+			step: .05,
+			showValue: true
+		}];
 	}
 };
 /**
@@ -1472,7 +1459,7 @@ var PackageDetectionStep = class extends PipelineStepBase {
 			step: .05,
 			default: resolveModelDefaultConfidence(this.definition, model),
 			showValue: true
-		}, labelLinkField("package detection")];
+		}];
 	}
 };
 var ClassifierWithMinConfidence = class extends PipelineStepBase {
@@ -1688,28 +1675,23 @@ var STEP_BIRD_CLASSIFIER = new ClassifierWithMinConfidence({
 	}
 });
 /**
-* `vehicle-classifier` — the `minConfidence` slider plus the two fields a
-* root-detector fill needs (D715): the class allow-list (a coverage gap the
-* detector cannot produce, e.g. `Van` for Frigate+, is switched off HERE before
-* the skip applies) and the `labelLink` policy.
+* `vehicle-classifier` — the `minConfidence` slider plus the class allow-list.
+* When the step takes the root model's labels (`useRootModel`, D730) the same
+* allow-list filters which root labels become the vehicle type.
 */
 var VehicleClassifierStep = class extends ClassifierWithMinConfidence {
 	getConfigSchema(model) {
-		return [
-			{
-				type: "multiselect",
-				key: "enabledClasses",
-				label: "Vehicle types",
-				description: "Which vehicle types to keep (empty = all). The classifier still scores every type but only the selected ones are returned on the detection.",
-				options: VEHICLE_CLASSIFIER_LABELS.map((l) => ({
-					value: l,
-					label: l
-				})),
-				default: []
-			},
-			...super.getConfigSchema(model),
-			labelLinkField("the vehicle classifier")
-		];
+		return [{
+			type: "multiselect",
+			key: "enabledClasses",
+			label: "Vehicle types",
+			description: "Which vehicle types to keep (empty = all). The classifier still scores every type but only the selected ones are returned on the detection. When the root model is the source, the same list decides which of its labels become the type; a switched-off type stays \"vehicle\".",
+			options: VEHICLE_CLASSIFIER_LABELS.map((l) => ({
+				value: l,
+				label: l
+			})),
+			default: []
+		}, ...super.getConfigSchema(model)];
 	}
 };
 var STEP_VEHICLE_CLASSIFIER = new VehicleClassifierStep({