@camstack/addon-pipeline 1.2.294 → 1.2.296

package/THIRD_PARTY_MODELS.md

@@ -0,0 +1,241 @@
+<!--
+  THIRD_PARTY_MODELS.md: the product notice for every model CamStack can download.
+
+  HAND-WRITTEN FOR NOW. Task 7 of docs/superpowers/plans/2026-09-26-model-license-compliance.md
+  replaces this file with generator output (scripts/gen-model-licenses.ts), built from the
+  licence records on the model catalogs. Until then this root file is the single source:
+  - packages/addon-pipeline, packages/addon-post-analysis, packages/addon-ai and server/backend
+    each carry a byte-identical COPY (npm cannot ship a file from outside the package).
+    Edit this root file, then copy it:  for d in packages/addon-pipeline packages/addon-post-analysis
+    packages/addon-ai server/backend; do cp THIRD_PARTY_MODELS.md "$d/"; done
+    scripts/check-model-notices-shipped.ts fails CI when a copy drifts.
+  - The Hugging Face mirror (camstack/camstack-models) receives this same file, staged by
+    hf/camstack-models/upload.sh. Its model card points at the "Source offer" section below.
+  Facts: docs/superpowers/specs/2026-09-26-model-license-compliance.md (verified 2026-09-26).
+  Not legal advice.
+-->
+
+# Third-party models
+
+CamStack's own source code is MIT-licensed (see `LICENSE`). CamStack does not
+include model weights in its npm packages or its Docker image. It downloads
+them, on demand, from the locations listed below. **Each model stays under its
+own licence.** Converting a model to another format does not change its
+licence: every CamStack-made build is a modified version (a "model derivative")
+of the upstream weights, and the change is stated per model.
+
+Full licence texts: `licenses/models/` in the CamStack source repository, and
+[`LICENSES/`](https://huggingface.co/camstack/camstack-models/tree/main/LICENSES)
+in the model mirror https://huggingface.co/camstack/camstack-models.
+
+Some of these models are **not licensed for commercial use**. They are listed
+under [Non-commercial models](#non-commercial-models).
+
+## Required attributions
+
+- **Ultralytics YOLO26, YOLOv9 and YOLOv8** — © Ultralytics. Licensed under
+  AGPL-3.0 (`AGPL-3.0.txt`). See the [source offer](#source-offer-for-the-agpl-30-weights).
+  https://github.com/ultralytics/ultralytics
+- **YOLOv9** (architecture) — Chien-Yao Wang, I-Hau Yeh, Hong-Yuan Mark Liao,
+  GPL-3.0 (`GPL-3.0.txt`). https://github.com/WongKinYiu/yolov9
+- **SCRFD / InsightFace** — code MIT. The pretrained weights are released by
+  InsightFace for non-commercial research purposes only (`InsightFace-terms.txt`).
+  https://github.com/deepinsight/insightface
+- **MobileCLIP** — © Apple Inc. *Apple Machine Learning Research Model is
+  licensed under the Apple Machine Learning Research Model License Agreement.*
+  (`Apple-AMLR.txt`). CamStack's MobileCLIP files are **Model Derivatives**:
+  the image encoders are converted to OpenVINO IR and CoreML at FP16; the text
+  encoders are quantised to INT8 ONNX and converted to OpenVINO IR.
+  https://github.com/apple/ml-mobileclip
+- **Llama 3.2** — **Built with Llama.** Llama 3.2 is licensed under the Llama
+  3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
+  (`Llama-3.2-Community.txt`; Acceptable Use Policy:
+  https://www.llama.com/llama3_2/use-policy)
+- **fast-plate-ocr** — Copyright (c) 2024 ankandrew, MIT (`MIT-fast-plate-ocr.txt`).
+  https://github.com/ankandrew/fast-plate-ocr
+- **RF-DETR** — © Roboflow, Apache-2.0. https://github.com/roboflow/rf-detr
+- **YuNet** — weights Copyright (c) 2020 Shiqi Yu, MIT (`MIT-yunet-reference.txt`).
+  https://github.com/opencv/opencv_zoo/tree/main/models/face_detection_yunet ·
+  [license](https://github.com/opencv/opencv_zoo/blob/main/models/face_detection_yunet/LICENSE).
+  Training code BSD-3-Clause (`BSD-3-Clause.txt`),
+  https://github.com/ShiqiYu/libfacedetection.train.
+  Trained on WIDER FACE, whose images are CC BY-NC-ND.
+- **AuraFace v1** — fal.ai, Apache-2.0. https://huggingface.co/fal/AuraFace-v1
+- **SigLIP 2** — © Google LLC, Apache-2.0 (`Apache-2.0.txt`).
+  https://huggingface.co/google/siglip2-base-patch16-224 ·
+  https://github.com/google-research/big_vision. CamStack's SigLIP 2 files are
+  modified: the vision input scaling `2x - 1` is baked into the graph, the text
+  graph slices its input to the model's 64 positions, the tokenizer lower-cases,
+  and the towers are converted to ONNX, OpenVINO IR and CoreML FP16.
+- **EasyOCR** — JaidedAI, Apache-2.0. https://github.com/JaidedAI/EasyOCR
+- **U²-Net** — Xuebin Qin et al., Apache-2.0. https://github.com/xuebinqin/U-2-Net
+- **YAMNet** — © Google LLC, Apache-2.0.
+  https://github.com/tensorflow/models/tree/master/research/audioset/yamnet
+- **AIY Vision Birds V1** and the **Coral Edge TPU models** — © Google LLC,
+  Apache-2.0. https://github.com/google-coral/test_data
+- **EfficientNet-Lite0** via **timm** — Ross Wightman, Apache-2.0.
+  https://github.com/huggingface/pytorch-image-models
+- **torchvision MobileNetV3** — BSD-3-Clause (`BSD-3-Clause.txt`). https://github.com/pytorch/vision
+- **Scrypted plugin models** — Koushik Dutta, repository tagged MIT
+  (`MIT-scrypted-plugin-models.txt`). https://huggingface.co/scrypted/plugin-models
+- **Qwen2.5, Qwen3-VL, Qwen3.6** — Alibaba Cloud, Apache-2.0. https://huggingface.co/Qwen
+- **Open Images V7** (animal-classifier training data) — annotations © Google
+  LLC, licensed under CC BY 4.0 (`CC-BY-4.0.txt`). Images are listed by Google
+  as CC BY 2.0, without warranty.
+  https://storage.googleapis.com/openimages/web/factsfigures_v7.html
+- **Vehicle classification dataset** (vehicle-type-v1 training data) — by
+  DrBimmer, https://huggingface.co/datasets/DrBimmer/vehicle-classification,
+  licensed under CC BY-NC 4.0 (`CC-BY-NC-4.0.txt`). CamStack fine-tuned a model
+  on it; the resulting weights are treated as non-commercial.
+- **AudioSet** ontology and labels (YAMNet) — © Google LLC, CC BY 4.0.
+  https://research.google.com/audioset/
+- **COCO** annotations (YOLO pretraining) — COCO Consortium, CC BY 4.0. Images
+  remain under the terms of their Flickr owners. https://cocodataset.org/#termsofuse
+
+## Source offer for the AGPL-3.0 weights
+
+<!--
+  This section is the ONE place the source offer is written. The package copies are
+  byte-identical copies of this file, and the Hugging Face model card, its LICENSE and its folder
+  cards link here instead of repeating it.
+-->
+
+The folders `objectDetection/yolo26`, `objectDetection/yolov9`,
+`segmentation/yolo26-seg`, `plateDetection/yolov8-plate` and
+`packageDetection/yolov8-package` of the model mirror hold Ultralytics weights,
+modified by CamStack and distributed under AGPL-3.0. Their Corresponding Source
+is the public CamStack source repository, **https://github.com/camstack/server**
+(MIT), together with the upstream checkpoints it starts from:
+
+1. **The upstream checkpoints**, published by Ultralytics at
+   https://github.com/ultralytics/assets/releases: `yolo26{n,s,m,l,x}.pt`,
+   `yolov9{t,s,m,c}.pt`, `yolo26{n,s,m}-seg.pt`.
+2. **The export scripts** in https://github.com/camstack/server:
+   `scripts/build-camstack-models.py` (ONNX with a dynamic batch axis, CoreML
+   FP16, OpenVINO IR, OpenVINO NNCF INT8) and `scripts/export-models.py`. The
+   build instructions (Python environment, invocation, calibration images for
+   INT8) are in each script's header.
+3. **The software** that downloads and runs these weights, CamStack itself, is
+   the same repository.
+
+What the repository does **not** cover yet:
+
+- **Some hosted sizes and input resolutions.** The export scripts do not list
+  every variant in the mirror (for example the `-320`/`-256` YOLO26 exports,
+  `yolov9m`/`yolov9c`, and the `yolo26*-seg` models). Each one is the same
+  Ultralytics `export()` with a different model id or `imgsz`, but no script in
+  the repository reproduces it as-is.
+- **`yolov8n-plate` has no training checkpoint.** It is a third-party model
+  (trained 2023-12-05 according to its own metadata, origin not identified).
+  The ONNX file is the only form CamStack has.
+- **The `yolov8n-package` checkpoint is not published yet.** CamStack
+  fine-tuned it with Ultralytics.
+
+## Non-commercial models
+
+These are downloaded by default or selectable, and their terms **do not allow
+commercial use**:
+
+| Model | Terms |
+| --- | --- |
+| `scrfd-2.5g` (face detection, selectable, not the default since 2026-09-26) | InsightFace pretrained models: non-commercial research purposes only |
+| `mobileclip-s1`, `mobileclip-s2`, `mobileclip-s1-text`, `mobileclip-s2-text` (semantic search, `mobileclip-s1` default) | Apple Machine Learning Research Model License: research purposes only, no commercial product or service |
+| `vehicle-type-v1` (vehicle classifier) | trained on a CC BY-NC 4.0 dataset; weights treated as non-commercial |
+| `bird-nabirds-404` (hidden, pending removal) | NABirds: no reproduction, distribution or products without the Cornell Lab's written permission |
+
+## Models
+
+"Mirror" means https://huggingface.co/camstack/camstack-models, folder given.
+"Code / weights" gives the two licences separately because they often differ.
+**Unknown** means no licence could be traced; it does not mean free to use.
+
+### Object detection
+
+| Catalog ids | Upstream | Code / weights | Training data | CamStack changes | Downloaded from |
+| --- | --- | --- | --- | --- | --- |
+| `yolo26n`, `yolo26s`, `yolo26m`, `yolo26l`, `yolo26x`, with every `-fp16`, `-int8`, `-320`, `-256`, `-320-int8`, `-256-int8` variant | Ultralytics YOLO26, COCO-pretrained | AGPL-3.0 / AGPL-3.0 | COCO 2017 (annotations CC BY 4.0) | exported to ONNX, OpenVINO IR (FP32/FP16) and CoreML FP16; `-320`/`-256` re-exported at that input size; `-int8` OpenVINO NNCF post-training INT8 | Mirror `objectDetection/yolo26` |
+| `yolov9{t,s,m,c}-320`, `yolov9{t,s,m,c}-640`, and their `-int8` twins | Ultralytics YOLOv9 weights, COCO-pretrained; architecture by WongKinYiu | AGPL-3.0 / AGPL-3.0 (original YOLOv9 repository GPL-3.0) | COCO 2017 | exported to ONNX, OpenVINO IR FP16 and CoreML at 320 and 640; `-int8` NNCF INT8 | Mirror `objectDetection/yolov9` |
+| `ssd-mobilenet-v2-coco-edgetpu`, `efficientdet-lite0-edgetpu` | Google Coral `test_data` | Apache-2.0 / Apache-2.0 | COCO | none | https://github.com/google-coral/test_data |
+| `ssdlite-mobiledet-coco-edgetpu` (selectable, not the default) | Google Coral `test_data`, `ssdlite_mobiledet_coco_qat_postprocess_edgetpu.tflite` (sha256 `b69e508e…434a2e`); MobileDets (Xiong et al., CVPR 2021) trained with the TensorFlow Object Detection API, https://github.com/tensorflow/models/tree/master/research/object_detection | Apache-2.0 / Apache-2.0 (`Apache-2.0.txt`; https://github.com/google-coral/test_data/blob/master/LICENSE) | COCO 2017 (annotations CC BY 4.0, images under Flickr terms) | none: mirrored byte for byte, with the CPU build and `coco_labels.txt` beside it (`scripts/build-ssdlite-mobiledet-model.py`) | Mirror `objectDetection/ssdlite-mobiledet` |
+
+### Package detection
+
+| Catalog ids | Upstream | Code / weights | Training data | CamStack changes | Downloaded from |
+| --- | --- | --- | --- | --- | --- |
+| `rfdetr-package` | Roboflow RF-DETR-M | Apache-2.0 / Apache-2.0 | fine-tuning set not recorded (unverified) | fine-tuned to 2 classes at 576; exported to ONNX, OpenVINO IR and CoreML; training checkpoint `.pth` also published | Mirror `packageDetection/rfdetr-package` |
+| `yolov8n-package` | Ultralytics YOLOv8n | AGPL-3.0 / AGPL-3.0 | most likely Roboflow Universe `package-at-front-door` (unverified) | fine-tuned by CamStack with Ultralytics; exported to ONNX, OpenVINO IR and CoreML | Mirror `packageDetection/yolov8-package` |
+
+### Face detection
+
+| Catalog ids | Upstream | Code / weights | Training data | CamStack changes | Downloaded from |
+| --- | --- | --- | --- | --- | --- |
+| `scrfd-2.5g` | InsightFace SCRFD 2.5G (bnkps), via the ONNX re-upload `RuteNL/SCRFD-face-detection-ONNX` | MIT / **InsightFace: non-commercial research only** | WIDER FACE (research-oriented terms) | converted to OpenVINO IR and CoreML FP16 | Mirror `faceDetection/scrfd` |
+| `yunet-2023mar` (face-detection default since 2026-09-26) | OpenCV Zoo YuNet 2023mar, `face_detection_yunet_2023mar.onnx` (fp32), https://github.com/opencv/opencv_zoo/tree/main/models/face_detection_yunet | BSD-3-Clause (training code, https://github.com/ShiqiYu/libfacedetection.train; `BSD-3-Clause.txt`) / MIT, Copyright (c) 2020 Shiqi Yu (opencv_zoo; `MIT-yunet-reference.txt`; https://github.com/opencv/opencv_zoo/blob/main/models/face_detection_yunet/LICENSE) | WIDER FACE (images CC BY-NC-ND) | input contract baked into the graph: the pool's 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` |
+| `scrypted-yolov9t-face` (retired from the catalog, D643; nothing downloads it) | Scrypted `plugin-models` (YOLOv9t ReLU face) | repository tagged MIT; YOLOv9 architecture GPL-3.0 upstream / **Unknown** per model | unknown | OpenVINO IR converted by CamStack | its OpenVINO IR is still on mirror `faceDetection/scrypted-yolov9-face` |
+| `ssd-mobilenet-v2-face-edgetpu` (hidden) | Google Coral `test_data` | Apache-2.0 / Apache-2.0 | — | none | https://github.com/google-coral/test_data |
+
+### Face recognition
+
+| Catalog ids | Upstream | Code / weights | Training data | CamStack changes | Downloaded from |
+| --- | --- | --- | --- | --- | --- |
+| `arcface-r100` (a ResNet34) | re-upload `onnx-community/arcface-onnx` (itself pointing at `garavv/arcface-onnx`); original author not stated | **Unknown** / **Unknown** | not stated | converted to OpenVINO IR and CoreML FP16 | Mirror `faceRecognition/arcface` |
+| `auraface-r100` | fal.ai AuraFace v1 (`glintr100.onnx` only) | Apache-2.0 / Apache-2.0 | stated upstream as commercially and publicly available sources | input scaling `y = 2x - 1` baked ahead of the first Conv (`scripts/build-auraface-model.py`); converted to OpenVINO IR and CoreML FP16 | Mirror `faceRecognition/auraface` |
+| `inception-resnet-v1` | Scrypted `plugin-models` | repository tagged MIT / **Unknown** per model | not stated | OpenVINO IR converted by CamStack | ONNX and CoreML: https://huggingface.co/scrypted/plugin-models · OpenVINO: mirror `faceRecognition/inception-resnet-v1` |
+
+### Licence plate detection and OCR
+
+| Catalog ids | Upstream | Code / weights | Training data | CamStack changes | Downloaded from |
+| --- | --- | --- | --- | --- | --- |
+| `yolov8n-plate` | Ultralytics YOLOv8n fine-tuned for plates by a third party (trained 2023-12-05 per its metadata) | AGPL-3.0 / AGPL-3.0 | **unknown** | converted to OpenVINO IR, CoreML and TFLite fp32 (`tflite/camstack-yolov8n-plate_float32.tflite`, mirrored but not referenced by the catalog) | Mirror `plateDetection/yolov8-plate` |
+| `cct-s-v2-global` | `ankandrew/fast-plate-ocr` release model | MIT / MIT | private, not released upstream | input head removed (recorded in the ONNX `doc_string`); converted to OpenVINO IR and CoreML | Mirror `plateRecognition/cct-s-v2-global` |
+| `vgg-english-g2` | JaidedAI EasyOCR, via Scrypted `plugin-models` | Apache-2.0 / Apache-2.0 | — | OpenVINO IR converted by CamStack | ONNX and CoreML: https://huggingface.co/scrypted/plugin-models · OpenVINO: mirror `plateRecognition/vgg_english_g2` |
+
+### Classifiers
+
+| Catalog ids | Upstream | Code / weights | Training data | CamStack changes | Downloaded from |
+| --- | --- | --- | --- | --- | --- |
+| `animal-classifier` | timm EfficientNet-Lite0 | Apache-2.0 / Apache-2.0 | Open Images V7 animal subset (annotations CC BY 4.0, © Google LLC) | fine-tuned by CamStack (8 classes); exported to ONNX, OpenVINO IR and CoreML | Mirror `animalClassification/animal-classifier` |
+| `animals-10` (hidden, pending removal) | origin not identified | **Unknown** / **Unknown** | unknown | converted to ONNX, OpenVINO IR and CoreML | Mirror `animalClassification/animals-10` |
+| `bird-classifier` | Google AIY Vision `birds_V1` | Apache-2.0 / Apache-2.0 | — | converted from TensorFlow with tf2onnx; OpenVINO IR and CoreML derived from it | Mirror `animalClassification/bird-classifier` |
+| `bird-classifier-aiy-edgetpu` (hidden) | Google Coral `test_data` | Apache-2.0 / Apache-2.0 | — | none | https://github.com/google-coral/test_data |
+| `bird-nabirds-404` (hidden, pending removal) | ResNet50 trained on NABirds (origin not recorded) | **Unknown** / NABirds: no products without Cornell Lab permission | NABirds (Cornell Lab of Ornithology) | converted to ONNX, OpenVINO IR and CoreML | Mirror `animalClassification/bird-nabirds` |
+| `vehicle-type-v1` | torchvision MobileNetV3-Large | BSD-3-Clause / **CC BY-NC 4.0** (from its data) | DrBimmer `vehicle-classification`, CC BY-NC 4.0 | fine-tuned by CamStack (8 classes); exported to ONNX, OpenVINO IR and CoreML | Mirror `vehicleClassification/vehicle-type-v1` |
+| `vehicle-type-efficientnet` (hidden, pending removal) | trained on VMMRdb (origin not recorded) | **Unknown** / VMMRdb terms unverified | VMMRdb | converted to ONNX, OpenVINO IR and CoreML | Mirror `vehicleClassification/efficientnet` |
+
+### Semantic search (CLIP)
+
+| Catalog ids | Upstream | Code / weights | Training data | CamStack changes | Downloaded from |
+| --- | --- | --- | --- | --- | --- |
+| `mobileclip-s1`, `mobileclip-s2` (image) | Apple `ml-mobileclip` | MIT / **Apple Machine Learning Research Model License** | per Apple | Model Derivative: converted to OpenVINO IR and CoreML FP16 | Mirror `clip/mobileclip-s1`, `clip/mobileclip-s2` |
+| `mobileclip-s1-text`, `mobileclip-s2-text` | Apple `ml-mobileclip`, with the CLIP tokenizer | MIT / **Apple Machine Learning Research Model License** | per Apple | Model Derivative: quantised to INT8 ONNX and converted to OpenVINO IR | Mirror `clip/mobileclip-s1`, `clip/mobileclip-s2` |
+| `siglip2-b16-224` (image) | Google SigLIP 2 base patch16-224 (`google/siglip2-base-patch16-224`) | Apache-2.0 / Apache-2.0 | WebLI (Google internal, not released) | input scaling `y = 2x - 1` baked ahead of the patch embedding; converted to OpenVINO IR and CoreML FP16 (an FP32 ONNX is hosted as the verification reference) (`scripts/build-siglip2-model.py`) | Mirror `clip/siglip2` |
+| `siglip2-b16-224-text` | Google SigLIP 2 base patch16-224, with its Gemma tokenizer | Apache-2.0 / Apache-2.0 | WebLI (Google internal, not released) | input sliced to the model's 64 positions in the graph; ONNX weights FP16, OpenVINO IR and CoreML FP16; a `Lowercase` normalizer prepended to the tokenizer | Mirror `clip/siglip2` |
+
+### Segmentation
+
+| Catalog ids | Upstream | Code / weights | Training data | CamStack changes | Downloaded from |
+| --- | --- | --- | --- | --- | --- |
+| `u2netp` | `xuebinqin/U-2-Net` | Apache-2.0 / Apache-2.0 | DUTS-TR (terms not checked) | converted to ONNX, OpenVINO IR and CoreML | Mirror `segmentationRefiner/u2netp` |
+| `yolo26n-seg`, `yolo26s-seg`, `yolo26m-seg` | Ultralytics YOLO26-seg, COCO-pretrained | AGPL-3.0 / AGPL-3.0 | COCO 2017 | exported to ONNX, OpenVINO IR and CoreML | Mirror `segmentation/yolo26-seg` |
+
+### Audio
+
+| Catalog ids | Upstream | Code / weights | Training data | CamStack changes | Downloaded from |
+| --- | --- | --- | --- | --- | --- |
+| `yamnet-onnx` | `tensorflow/models` `research/audioset/yamnet` | Apache-2.0 / Apache-2.0 | AudioSet (labels CC BY 4.0, © Google LLC) | converted from TensorFlow with tf2onnx; OpenVINO IR derived from it | Mirror `audioClassification/yamnet` |
+| `apple-soundanalysis` | Apple SoundAnalysis, built into macOS | under Apple's macOS licence | — | nothing downloaded | built in |
+
+### Language and vision-language models (AI addon, not hosted by CamStack)
+
+| Catalog ids | Upstream | Code / weights | CamStack changes | Downloaded from |
+| --- | --- | --- | --- | --- |
+| `llm-qwen2.5-1.5b-instruct-q4` | Qwen2.5 1.5B Instruct | — / Apache-2.0 | none (GGUF Q4_K_M by Qwen) | https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct-GGUF |
+| `llm-llama3.2-3b-instruct-q4` | Meta Llama 3.2 3B Instruct | — / Llama 3.2 Community License | none by CamStack (GGUF Q4_K_M by bartowski) | https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF |
+| `llm-qwen3-vl-2b-instruct-q4`, `llm-qwen3-vl-4b-instruct-q4`, `llm-qwen3-vl-8b-instruct-q4` | Qwen3-VL Instruct | — / Apache-2.0 | none by CamStack (GGUF by unsloth) | https://huggingface.co/unsloth (`Qwen3-VL-{2B,4B,8B}-Instruct-GGUF`) |
+| `llm-qwen3.6-35b-a3b-ud-q4` | Qwen3.6 35B-A3B | — / Apache-2.0 | none by CamStack (GGUF UD-Q4_K_M by unsloth) | https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF |
+
+### Your own models
+
+A model you import through Model Studio (uploaded, converted, or pulled from
+Frigate+ or Scrypted) keeps whatever licence its author published. CamStack
+does not change it and does not record it.

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-CJR259Xf.js");
-const require_process_memory = require("../process-memory-BJUXvTjd.js");
+const require_dist = require("../dist-8up-f2TX.js");
+const require_process_memory = require("../process-memory-CX_92V_r.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 { $t as errMsg, A as PoolMemoryWatchdog, Ln as EventCategory, T as HF_BASE_URL, U as audioAnalysisCapability, Ut as resolvePoolMemoryPolicy, W as audioAnalyzerCapability, bn as nodePin, d as DEFAULT_AUDIO_ANALYZER_CONFIG, dn as audioChunkBytesPerSample, gn as hydrateSchema, hn as expandAudioChunkToF32le, n as AUDIO_BACKEND_CHOICES, on as BaseAddon, yt as mapAudioLabelToMacro } from "../dist-RXbmRAwP.mjs";
-import { n as pickNodePlatformArch, t as readProcessMemory } from "../process-memory-BgFOHFnx.mjs";
+import { E as HF_BASE_URL, G as audioAnalyzerCapability, Gt as resolvePoolMemoryPolicy, Sn as nodePin, W as audioAnalysisCapability, _n as expandAudioChunkToF32le, bt as mapAudioLabelToMacro, cn as BaseAddon, f as DEFAULT_AUDIO_ANALYZER_CONFIG, j as PoolMemoryWatchdog, n as AUDIO_BACKEND_CHOICES, pn as audioChunkBytesPerSample, tn as errMsg, vn as hydrateSchema, zn as EventCategory } from "../dist-CCd0Q3nr.mjs";
+import { n as pickNodePlatformArch, t as readProcessMemory } from "../process-memory-DFC_O5zE.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-0dPKRKUD.mjs → default-detection-model-Co578D8C.mjs}

@@ -1,4 +1,4 @@
-import { G as audioKindId, l as COCO_80_LABELS, mt as hfModelUrl, r as AUDIO_MACRO_LABELS, u as COCO_TO_MACRO } from "./dist-RXbmRAwP.mjs";
+import { K as audioKindId, d as COCO_TO_MACRO, ht as hfModelUrl, r as AUDIO_MACRO_LABELS, u as COCO_80_LABELS } from "./dist-CCd0Q3nr.mjs";
 import { randomUUID } from "node:crypto";
 //#region src/detection-pipeline/pipeline/landmark-precision-gate.ts
 /**
@@ -384,6 +384,24 @@ var OBJECT_DETECTION_MODELS = [
 			runtimes: ["python"]
 		} }
 	},
+	{
+		id: "ssdlite-mobiledet-coco-edgetpu",
+		name: "SSDLite MobileDet (Coral)",
+		description: "SSDLite MobileDet COCO (QAT) — EdgeTPU-compiled full-integer TFLite, 320×320; runs on the Coral USB Edge TPU. More accurate than SSD MobileNet V2 (32.9 vs 25.6 % COCO mAP, Coral-published). Scores top out near 0.77.",
+		inputSize: {
+			width: 320,
+			height: 320
+		},
+		labels: [],
+		preprocessMode: "letterbox",
+		postprocessor: "ssd",
+		license: "Apache-2.0",
+		formats: { tflite: {
+			url: hf("objectDetection/ssdlite-mobiledet/edgetpu/ssdlite_mobiledet_coco_qat_postprocess_edgetpu.tflite"),
+			sizeMB: 5.1,
+			runtimes: ["python"]
+		} }
+	},
 	ovPrecisionVariant("yolo26n", "objectDetection/yolo26/openvino", "YOLO26 Nano", "fp16", 5, true),
 	ovPrecisionVariant("yolo26n", "objectDetection/yolo26/openvino", "YOLO26 Nano", "int8", 3),
 	ovPrecisionVariant("yolo26s", "objectDetection/yolo26/openvino", "YOLO26 Small", "fp16", 19, true),
@@ -502,57 +520,90 @@ var OBJECT_DETECTION_MODELS = [
 * A retired id resolves to the step's format default instead.
 */
 var RETIRED_MODEL_IDS = { "face-detection": ["scrypted-yolov9t-face"] };
-var FACE_DETECTION_MODELS = [{
-	id: "scrfd-2.5g",
-	name: "SCRFD 2.5G",
-	description: "SCRFD 2.5G bnkps — balanced face detection with 5 keypoints (WIDER FACE 93.80/92.02/77.13). InsightFace pretrained weights.",
-	inputSize: {
-		width: 640,
-		height: 640
+var FACE_DETECTION_MODELS = [
+	{
+		id: "scrfd-2.5g",
+		name: "SCRFD 2.5G",
+		description: "SCRFD 2.5G bnkps — balanced face detection with 5 keypoints (WIDER FACE 93.80/92.02/77.13). InsightFace pretrained weights.",
+		inputSize: {
+			width: 640,
+			height: 640
+		},
+		labels: [{
+			id: "face",
+			name: "Face"
+		}],
+		preprocessMode: "letterbox",
+		inputNormalization: "scrfd",
+		license: "InsightFace-NonCommercial-Research",
+		formats: {
+			onnx: {
+				url: hf("faceDetection/scrfd/onnx/camstack-scrfd-2.5g.onnx"),
+				sizeMB: 3.1
+			},
+			coreml: {
+				url: hf("faceDetection/scrfd/coreml/camstack-scrfd-2.5g.mlpackage"),
+				sizeMB: 1.7,
+				isDirectory: true,
+				files: [...MLPACKAGE_FILES],
+				runtimes: ["python"]
+			},
+			openvino: ovFormat(hf("faceDetection/scrfd/openvino/camstack-scrfd-2.5g.xml"), 1.8)
+		}
 	},
-	labels: [{
-		id: "face",
-		name: "Face"
-	}],
-	preprocessMode: "letterbox",
-	inputNormalization: "scrfd",
-	license: "InsightFace-NonCommercial-Research",
-	formats: {
-		onnx: {
-			url: hf("faceDetection/scrfd/onnx/camstack-scrfd-2.5g.onnx"),
-			sizeMB: 3.1
+	{
+		id: "yunet-2023mar",
+		name: "YuNet 2023mar",
+		description: "YuNet (OpenCV Zoo, 2023mar) — tiny face detector with 5 keypoints, MIT weights (WIDER FACE AP 0.884/0.866/0.750). ~0.2 MB. Trained on WIDER FACE (CC BY-NC-ND images).",
+		inputSize: {
+			width: 640,
+			height: 640
 		},
-		coreml: {
-			url: hf("faceDetection/scrfd/coreml/camstack-scrfd-2.5g.mlpackage"),
-			sizeMB: 1.7,
-			isDirectory: true,
-			files: [...MLPACKAGE_FILES],
-			runtimes: ["python"]
+		labels: [{
+			id: "face",
+			name: "Face"
+		}],
+		preprocessMode: "letterbox",
+		postprocessor: "yunet",
+		license: "MIT",
+		formats: {
+			onnx: {
+				url: hf("faceDetection/yunet/onnx/camstack-yunet-2023mar.onnx"),
+				sizeMB: .23
+			},
+			coreml: {
+				url: hf("faceDetection/yunet/coreml/camstack-yunet-2023mar.mlpackage"),
+				sizeMB: .2,
+				isDirectory: true,
+				files: [...MLPACKAGE_FILES],
+				runtimes: ["python"]
+			},
+			openvino: ovFormat(hf("faceDetection/yunet/openvino/camstack-yunet-2023mar.xml"), .36)
+		}
+	},
+	{
+		id: "ssd-mobilenet-v2-face-edgetpu",
+		legacy: true,
+		name: "SSD MobileNet V2 Face (Coral)",
+		description: "SSD MobileNet V2 face detector — EdgeTPU-compiled full-integer TFLite, 320×320; runs on the Coral USB Edge TPU. Requires an ssd-face postprocessor (not yet available).",
+		inputSize: {
+			width: 320,
+			height: 320
 		},
-		openvino: ovFormat(hf("faceDetection/scrfd/openvino/camstack-scrfd-2.5g.xml"), 1.8)
+		labels: [{
+			id: "face",
+			name: "Face"
+		}],
+		preprocessMode: "letterbox",
+		postprocessor: "ssd",
+		license: "Apache-2.0",
+		formats: { tflite: {
+			url: "https://github.com/google-coral/test_data/raw/master/ssd_mobilenet_v2_face_quant_postprocess_edgetpu.tflite",
+			sizeMB: 6.7,
+			runtimes: ["python"]
+		} }
 	}
-}, {
-	id: "ssd-mobilenet-v2-face-edgetpu",
-	legacy: true,
-	name: "SSD MobileNet V2 Face (Coral)",
-	description: "SSD MobileNet V2 face detector — EdgeTPU-compiled full-integer TFLite, 320×320; runs on the Coral USB Edge TPU. Requires an ssd-face postprocessor (not yet available).",
-	inputSize: {
-		width: 320,
-		height: 320
-	},
-	labels: [{
-		id: "face",
-		name: "Face"
-	}],
-	preprocessMode: "letterbox",
-	postprocessor: "ssd",
-	license: "Apache-2.0",
-	formats: { tflite: {
-		url: "https://github.com/google-coral/test_data/raw/master/ssd_mobilenet_v2_face_quant_postprocess_edgetpu.tflite",
-		sizeMB: 6.7,
-		runtimes: ["python"]
-	} }
-}];
+];
 var FACE_EMBEDDING_MODELS = [
 	{
 		id: "arcface-r100",
@@ -1133,55 +1184,84 @@ var INSTANCE_SEGMENTATION_MODELS = [
 		}
 	}
 ];
-var CLIP_EMBEDDING_MODELS = [{
-	id: "mobileclip-s1",
-	name: "MobileCLIP S1",
-	description: "MobileCLIP S1 — Apple balanced CLIP vision encoder, 512-dim, 256×256 (fp16 OpenVINO/CoreML)",
-	inputSize: {
-		width: 256,
-		height: 256
+var CLIP_EMBEDDING_MODELS = [
+	{
+		id: "mobileclip-s1",
+		name: "MobileCLIP S1",
+		description: "MobileCLIP S1 — Apple balanced CLIP vision encoder, 512-dim, 256×256 (fp16 OpenVINO/CoreML)",
+		inputSize: {
+			width: 256,
+			height: 256
+		},
+		labels: [{
+			id: "embedding",
+			name: "CLIP Embedding"
+		}],
+		preprocessMode: "resize",
+		inputNormalization: "none",
+		formats: {
+			openvino: ovFormat(hf("clip/mobileclip-s1/openvino/camstack-mobileclip-s1-vision.xml"), 55),
+			coreml: {
+				url: hf("clip/mobileclip-s1/coreml/camstack-mobileclip-s1-vision.mlpackage"),
+				sizeMB: 65,
+				isDirectory: true,
+				files: [...MLPACKAGE_FILES],
+				runtimes: ["python"]
+			}
+		}
 	},
-	labels: [{
-		id: "embedding",
-		name: "CLIP Embedding"
-	}],
-	preprocessMode: "resize",
-	inputNormalization: "none",
-	formats: {
-		openvino: ovFormat(hf("clip/mobileclip-s1/openvino/camstack-mobileclip-s1-vision.xml"), 55),
-		coreml: {
-			url: hf("clip/mobileclip-s1/coreml/camstack-mobileclip-s1-vision.mlpackage"),
-			sizeMB: 65,
-			isDirectory: true,
-			files: [...MLPACKAGE_FILES],
-			runtimes: ["python"]
+	{
+		id: "mobileclip-s2",
+		name: "MobileCLIP S2",
+		description: "MobileCLIP S2 — Apple high-accuracy CLIP vision encoder, 512-dim, 256×256 (fp16 OpenVINO/CoreML)",
+		inputSize: {
+			width: 256,
+			height: 256
+		},
+		labels: [{
+			id: "embedding",
+			name: "CLIP Embedding"
+		}],
+		preprocessMode: "resize",
+		inputNormalization: "none",
+		formats: {
+			openvino: ovFormat(hf("clip/mobileclip-s2/openvino/camstack-mobileclip-s2-vision.xml"), 90),
+			coreml: {
+				url: hf("clip/mobileclip-s2/coreml/camstack-mobileclip-s2-vision.mlpackage"),
+				sizeMB: 110,
+				isDirectory: true,
+				files: [...MLPACKAGE_FILES],
+				runtimes: ["python"]
+			}
 		}
-	}
-}, {
-	id: "mobileclip-s2",
-	name: "MobileCLIP S2",
-	description: "MobileCLIP S2 — Apple high-accuracy CLIP vision encoder, 512-dim, 256×256 (fp16 OpenVINO/CoreML)",
-	inputSize: {
-		width: 256,
-		height: 256
 	},
-	labels: [{
-		id: "embedding",
-		name: "CLIP Embedding"
-	}],
-	preprocessMode: "resize",
-	inputNormalization: "none",
-	formats: {
-		openvino: ovFormat(hf("clip/mobileclip-s2/openvino/camstack-mobileclip-s2-vision.xml"), 90),
-		coreml: {
-			url: hf("clip/mobileclip-s2/coreml/camstack-mobileclip-s2-vision.mlpackage"),
-			sizeMB: 110,
-			isDirectory: true,
-			files: [...MLPACKAGE_FILES],
-			runtimes: ["python"]
+	{
+		id: "siglip2-b16-224",
+		name: "SigLIP2 B/16",
+		description: "Google SigLIP2 base, patch 16, 224×224 — Apache-2.0 CLIP vision encoder, 768-dim (fp16 OpenVINO/CoreML)",
+		inputSize: {
+			width: 224,
+			height: 224
+		},
+		labels: [{
+			id: "embedding",
+			name: "CLIP Embedding"
+		}],
+		preprocessMode: "resize",
+		inputNormalization: "none",
+		license: "Apache-2.0",
+		formats: {
+			openvino: ovFormat(hf("clip/siglip2/openvino/camstack-siglip2-b16-224-vision.xml"), 186),
+			coreml: {
+				url: hf("clip/siglip2/coreml/camstack-siglip2-b16-224-vision.mlpackage"),
+				sizeMB: 185,
+				isDirectory: true,
+				files: [...MLPACKAGE_FILES],
+				runtimes: ["python"]
+			}
 		}
 	}
-}];
+];
 var AUDIO_CLASSIFIER_MODELS = [{
 	id: "yamnet-onnx",
 	name: "YAMNet",
@@ -1574,7 +1654,8 @@ var STEP_FACE_DETECTION = new PipelineStepBase({
 	inputClasses: ["person"],
 	outputClasses: ["face"],
 	models: [...FACE_DETECTION_MODELS],
-	defaultModelId: "scrfd-2.5g",
+	defaultModelId: "yunet-2023mar",
+	defaultModelIdByFormat: { tflite: "scrfd-2.5g" },
 	defaultConfidence: .5,
 	defaultMinParentScore: .7,
 	cadence: {
@@ -1619,7 +1700,7 @@ var STEP_FACE_EMBEDDING = new FaceEmbeddingStep({
 	outputClasses: ["identity"],
 	labelTier: 2,
 	models: [...FACE_EMBEDDING_MODELS],
-	defaultModelId: "arcface-r100",
+	defaultModelId: "auraface-r100",
 	modelScope: "cluster",
 	defaultConfidence: 0,
 	cadence: {
@@ -1819,11 +1900,12 @@ function getStepDefinition(stepId) {
 *      has a build for `format`.
 *   2. `def.defaultModelId` — the step's plain declared default — if it
 *      exists in `def.models` AND has a build for `format`.
-*   3. The smallest-by-size model among those with a `format` build
-*      (legacy fallback, preserved for steps/formats with no declared
+*   3. The smallest-by-size NON-legacy model among those with a `format`
+*      build (fallback, preserved for steps/formats with no declared
 *      preference reachable).
-*   4. `def.defaultModelId` unchanged, when ZERO models have a `format`
-*      build — an unloadable case flagged elsewhere, not resolved here.
+*   4. When NO non-legacy model has a `format` build — an unloadable case
+*      flagged elsewhere, not resolved here — the declared per-format id if
+*      there is one, else `def.defaultModelId`, unchanged.
 */
 function getDefaultModelForFormat(stepId, format) {
 	return getDefaultModelForFormatFromDef(getStepDefinition(stepId), format);
@@ -1841,7 +1923,7 @@ function getDefaultModelForFormatFromDef(def, format) {
 	if (declaredForFormat !== void 0 && hasFormatBuild(declaredForFormat)) return declaredForFormat;
 	if (hasFormatBuild(def.defaultModelId)) return def.defaultModelId;
 	const available = def.models.filter((m) => m.formats[format] && m.legacy !== true);
-	if (available.length === 0) return def.defaultModelId;
+	if (available.length === 0) return declaredForFormat ?? def.defaultModelId;
 	return [...available].toSorted((a, b) => {
 		return (a.formats[format]?.sizeMB ?? Infinity) - (b.formats[format]?.sizeMB ?? Infinity);
 	})[0].id;