visionpack 0.0.1__tar.gz

visionpack-0.0.1/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

visionpack-0.0.1/PKG-INFO

@@ -0,0 +1,248 @@
+Metadata-Version: 2.4
+Name: visionpack
+Version: 0.0.1
+Summary: DatasetOps for computer vision datasets
+Author-email: Caio Wingeter <caio@airis-tech.com>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/CaioWing/VisionPack
+Project-URL: Repository, https://github.com/CaioWing/VisionPack
+Project-URL: Issues, https://github.com/CaioWing/VisionPack/issues
+Keywords: computer-vision,dataset,datasetops,yolo,coco,mlops,machine-learning,annotations,reproducibility,deduplication
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Image Recognition
+Classifier: Typing :: Typed
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: orjson>=3.11.9
+Requires-Dist: pillow>=12.2.0
+Requires-Dist: pydantic>=2.13.4
+Requires-Dist: pyyaml>=6.0.3
+Requires-Dist: rich>=15.0.0
+Requires-Dist: zstandard>=0.25.0
+Dynamic: license-file
+
+# VisionPack
+
+**DatasetOps for Computer Vision** — a Git/Docker-like CLI for the messy part of
+training models: turning scattered images and labels into a clean, versioned,
+leak-free, ready-to-train dataset.
+
+[![CI](https://github.com/CaioWing/VisionPack/actions/workflows/ci.yml/badge.svg)](https://github.com/CaioWing/VisionPack/actions/workflows/ci.yml)
+![Python](https://img.shields.io/badge/python-3.11%2B-blue)
+![License](https://img.shields.io/badge/license-Apache--2.0-blue)
+![Status](https://img.shields.io/badge/status-active%20development-orange)
+![Tests](https://img.shields.io/badge/tests-79%20passing-brightgreen)
+
+```bash
+vp init --name factory-defects --task detection
+vp sync                 # pull images + labels from the sources in visionpack.yaml
+vp validate             # catch corrupt images, bad boxes, near-duplicate leakage
+vp split create         # deterministic, reproducible train/val/test
+vp snapshot create -m "baseline"
+vp export --format yolo --split          # ready-to-train layout
+```
+
+---
+
+## Why VisionPack
+
+Most of the pain in a CV project isn't the model — it's the dataset. VisionPack
+targets the failures that quietly cost you accuracy and reproducibility:
+
+- **Train/test leakage that inflates your metrics.** Exact-duplicate detection is
+  not enough: a re-encoded or resized copy of a training image landing in the test
+  set makes your reported numbers a lie. VisionPack catches **near-duplicate**
+  leakage with perceptual hashing.
+- **Splits you can't reproduce.** "I shuffled with `random.seed(42)`" breaks the
+  moment data is added or reordered. VisionPack splits are a function of image
+  *content*, so they're identical across machines and stable as the dataset grows.
+- **Data scattered across places.** Images in one bucket, labels in another repo,
+  classes in a third. Declare them once and `vp sync` assembles the dataset.
+- **"Which dataset trained this model?"** Content-addressed snapshots make that
+  answerable instead of a guess.
+
+It's built to **complement, not replace** CVAT, FiftyOne, DVC, Roboflow, and Label
+Studio — VisionPack is the DatasetOps layer that imports, validates, versions,
+splits, packs, and exports.
+
+---
+
+## Install
+
+VisionPack uses [`uv`](https://github.com/astral-sh/uv). From the repo root:
+
+```bash
+uv sync
+uv run vp --help
+```
+
+Requires Python 3.11+.
+
+---
+
+## Quickstart (60 seconds)
+
+```bash
+# 1. create a project (the manifest is visionpack.yaml)
+uv run vp init --name factory-defects --task detection
+
+# 2. bring in a YOLO dataset
+uv run vp import ./raw --format yolo
+
+# 3. check it for real problems
+uv run vp validate
+
+# 4. a deterministic, reproducible split
+uv run vp split create --train 0.8 --val 0.1 --test 0.1 --strategy stratified
+uv run vp split lock
+
+# 5. freeze a reproducible version
+uv run vp snapshot create -m "initial import"
+
+# 6. comparable metrics as the dataset grows
+uv run vp stats --by split
+
+# 7. a ready-to-train layout
+uv run vp export --format yolo --split
+```
+
+---
+
+## Works across the common CV tasks
+
+VisionPack's annotation model carries a tagged geometry, so one tool covers the
+tasks you actually use:
+
+| Task | Import | Geometry |
+|------|--------|----------|
+| **Classification** | ImageFolder (folder-per-class) | whole-image label |
+| **Detection** | YOLO, COCO | bounding box |
+| **Instance segmentation** | COCO | polygon |
+| **Keypoints / pose** | COCO | keypoints |
+
+```bash
+# classification from a folder-per-class layout
+uv run vp init --name product-grades --task classification
+uv run vp import ./train --format imagefolder
+uv run vp export --format imagefolder --split        # train/val/test/<class>/…
+
+# detection or instance segmentation from COCO
+uv run vp init --name cells --task segmentation
+uv run vp import ./instances.json --format coco --images ./images
+```
+
+---
+
+## Assemble a dataset from many sources
+
+Images and labels rarely live together. Declare them in `visionpack.yaml`:
+
+```yaml
+sources:
+  - name: camera-A
+    format: yolo
+    images: ./repoA/images        # images here…
+    labels: ./repoB               # …labels in another repo
+    classes: ./repoB/classes.txt
+    match: stem                   # pair by filename (or `relpath` for parallel trees)
+    copy: ingest
+```
+
+Then reconcile the dataset — idempotently, so re-running only pulls what's new:
+
+```bash
+uv run vp sync --dry-run     # preview: found / matched / unmatched / classes
+uv run vp sync               # ingest; classes merge by name, provenance recorded
+```
+
+Classes from different sources merge **by name** (YOLO indices are mapped through
+each source's own class order, never positionally), so reordered class lists don't
+mislabel your data.
+
+A one-off `vp import` also records what it imported as a source in
+`visionpack.yaml`, so the manifest stays the single source of truth and the data
+can be re-pulled later with `vp sync` (use `--no-record` for a throwaway import).
+
+---
+
+## What's in the box
+
+- **Deterministic, lockable splits** — `stratified` / `random` / `hash`
+  (growth-stable), captured in snapshots.
+- **Near-duplicate & cross-split leakage detection** — perceptual-hash tier, no
+  extra dependencies, scale-proof via LSH bucketing; surfaced in `vp validate`.
+- **Multi-source sync** — declarative `sources:` + `vp sync`, with per-asset
+  provenance and a resolver layer ready for remote backends.
+- **Content-addressed snapshots & diff** — reproducible versions; compare any two.
+- **Strong validation** — unreadable images, missing/orphan labels, unknown
+  classes, invalid/out-of-bounds boxes, exact + near duplicates, split leakage.
+- **Comparable metrics** — per-split stats so class balance stays auditable as data
+  grows.
+- **Packing** — `archive` (`.tar.zst`, self-contained) and `training`
+  (split-aware WebDataset shards).
+- **Interoperable I/O** — YOLO, COCO, ImageFolder in and out.
+
+Full command reference and per-command options live in the
+[usage guide](docs/usage.md).
+
+---
+
+## Release process
+
+Releases are prepared locally, reviewed as a GitHub Release draft, and published
+to PyPI only when the GitHub Release is published.
+
+```powershell
+.\scripts\prepare-release.ps1 0.1.1
+git push origin HEAD
+git push origin v0.1.1
+gh release create v0.1.1 --draft --title "v0.1.1" --notes-file CHANGELOG.md
+```
+
+Review the draft release notes in GitHub. Publishing the release triggers
+`.github/workflows/publish.yml`, which builds the package, validates the
+artifacts with `twine check`, and publishes to PyPI through Trusted Publishing.
+
+Use `-NoCommit -NoTag` to update files and run the checks without creating the
+release commit or tag:
+
+```powershell
+.\scripts\prepare-release.ps1 0.1.1 -NoCommit -NoTag
+```
+
+---
+
+## How it works
+
+VisionPack is **manifest-driven** and **content-addressed**: `visionpack.yaml`
+declares the dataset, raw images are stored once by `sha256` (immutable), and
+annotations / splits / snapshots are the versioned layer on top. The truth is the
+manifest + index, never "a folder with the right name".
+
+For the design principles, module map, data model, subsystems, and the full
+roadmap, see **[ARCHITECTURE.md](ARCHITECTURE.md)**. For the original product
+vision, see **[docs/DESIGN.md](docs/DESIGN.md)**.
+
+---
+
+## Status
+
+VisionPack is in **active development** (early but usable). The core workflow —
+multi-source ingestion → validation → deterministic splits → snapshots →
+ready-to-train export/packing — works end-to-end across classification, detection,
+instance segmentation, and keypoints, with 55 passing tests. APIs may still shift;
+feedback and contributions are welcome.
+
+```bash
+uv run python -m unittest discover -s tests -q
+```

visionpack-0.0.1/README.md

@@ -0,0 +1,215 @@
+# VisionPack
+
+**DatasetOps for Computer Vision** — a Git/Docker-like CLI for the messy part of
+training models: turning scattered images and labels into a clean, versioned,
+leak-free, ready-to-train dataset.
+
+[![CI](https://github.com/CaioWing/VisionPack/actions/workflows/ci.yml/badge.svg)](https://github.com/CaioWing/VisionPack/actions/workflows/ci.yml)
+![Python](https://img.shields.io/badge/python-3.11%2B-blue)
+![License](https://img.shields.io/badge/license-Apache--2.0-blue)
+![Status](https://img.shields.io/badge/status-active%20development-orange)
+![Tests](https://img.shields.io/badge/tests-79%20passing-brightgreen)
+
+```bash
+vp init --name factory-defects --task detection
+vp sync                 # pull images + labels from the sources in visionpack.yaml
+vp validate             # catch corrupt images, bad boxes, near-duplicate leakage
+vp split create         # deterministic, reproducible train/val/test
+vp snapshot create -m "baseline"
+vp export --format yolo --split          # ready-to-train layout
+```
+
+---
+
+## Why VisionPack
+
+Most of the pain in a CV project isn't the model — it's the dataset. VisionPack
+targets the failures that quietly cost you accuracy and reproducibility:
+
+- **Train/test leakage that inflates your metrics.** Exact-duplicate detection is
+  not enough: a re-encoded or resized copy of a training image landing in the test
+  set makes your reported numbers a lie. VisionPack catches **near-duplicate**
+  leakage with perceptual hashing.
+- **Splits you can't reproduce.** "I shuffled with `random.seed(42)`" breaks the
+  moment data is added or reordered. VisionPack splits are a function of image
+  *content*, so they're identical across machines and stable as the dataset grows.
+- **Data scattered across places.** Images in one bucket, labels in another repo,
+  classes in a third. Declare them once and `vp sync` assembles the dataset.
+- **"Which dataset trained this model?"** Content-addressed snapshots make that
+  answerable instead of a guess.
+
+It's built to **complement, not replace** CVAT, FiftyOne, DVC, Roboflow, and Label
+Studio — VisionPack is the DatasetOps layer that imports, validates, versions,
+splits, packs, and exports.
+
+---
+
+## Install
+
+VisionPack uses [`uv`](https://github.com/astral-sh/uv). From the repo root:
+
+```bash
+uv sync
+uv run vp --help
+```
+
+Requires Python 3.11+.
+
+---
+
+## Quickstart (60 seconds)
+
+```bash
+# 1. create a project (the manifest is visionpack.yaml)
+uv run vp init --name factory-defects --task detection
+
+# 2. bring in a YOLO dataset
+uv run vp import ./raw --format yolo
+
+# 3. check it for real problems
+uv run vp validate
+
+# 4. a deterministic, reproducible split
+uv run vp split create --train 0.8 --val 0.1 --test 0.1 --strategy stratified
+uv run vp split lock
+
+# 5. freeze a reproducible version
+uv run vp snapshot create -m "initial import"
+
+# 6. comparable metrics as the dataset grows
+uv run vp stats --by split
+
+# 7. a ready-to-train layout
+uv run vp export --format yolo --split
+```
+
+---
+
+## Works across the common CV tasks
+
+VisionPack's annotation model carries a tagged geometry, so one tool covers the
+tasks you actually use:
+
+| Task | Import | Geometry |
+|------|--------|----------|
+| **Classification** | ImageFolder (folder-per-class) | whole-image label |
+| **Detection** | YOLO, COCO | bounding box |
+| **Instance segmentation** | COCO | polygon |
+| **Keypoints / pose** | COCO | keypoints |
+
+```bash
+# classification from a folder-per-class layout
+uv run vp init --name product-grades --task classification
+uv run vp import ./train --format imagefolder
+uv run vp export --format imagefolder --split        # train/val/test/<class>/…
+
+# detection or instance segmentation from COCO
+uv run vp init --name cells --task segmentation
+uv run vp import ./instances.json --format coco --images ./images
+```
+
+---
+
+## Assemble a dataset from many sources
+
+Images and labels rarely live together. Declare them in `visionpack.yaml`:
+
+```yaml
+sources:
+  - name: camera-A
+    format: yolo
+    images: ./repoA/images        # images here…
+    labels: ./repoB               # …labels in another repo
+    classes: ./repoB/classes.txt
+    match: stem                   # pair by filename (or `relpath` for parallel trees)
+    copy: ingest
+```
+
+Then reconcile the dataset — idempotently, so re-running only pulls what's new:
+
+```bash
+uv run vp sync --dry-run     # preview: found / matched / unmatched / classes
+uv run vp sync               # ingest; classes merge by name, provenance recorded
+```
+
+Classes from different sources merge **by name** (YOLO indices are mapped through
+each source's own class order, never positionally), so reordered class lists don't
+mislabel your data.
+
+A one-off `vp import` also records what it imported as a source in
+`visionpack.yaml`, so the manifest stays the single source of truth and the data
+can be re-pulled later with `vp sync` (use `--no-record` for a throwaway import).
+
+---
+
+## What's in the box
+
+- **Deterministic, lockable splits** — `stratified` / `random` / `hash`
+  (growth-stable), captured in snapshots.
+- **Near-duplicate & cross-split leakage detection** — perceptual-hash tier, no
+  extra dependencies, scale-proof via LSH bucketing; surfaced in `vp validate`.
+- **Multi-source sync** — declarative `sources:` + `vp sync`, with per-asset
+  provenance and a resolver layer ready for remote backends.
+- **Content-addressed snapshots & diff** — reproducible versions; compare any two.
+- **Strong validation** — unreadable images, missing/orphan labels, unknown
+  classes, invalid/out-of-bounds boxes, exact + near duplicates, split leakage.
+- **Comparable metrics** — per-split stats so class balance stays auditable as data
+  grows.
+- **Packing** — `archive` (`.tar.zst`, self-contained) and `training`
+  (split-aware WebDataset shards).
+- **Interoperable I/O** — YOLO, COCO, ImageFolder in and out.
+
+Full command reference and per-command options live in the
+[usage guide](docs/usage.md).
+
+---
+
+## Release process
+
+Releases are prepared locally, reviewed as a GitHub Release draft, and published
+to PyPI only when the GitHub Release is published.
+
+```powershell
+.\scripts\prepare-release.ps1 0.1.1
+git push origin HEAD
+git push origin v0.1.1
+gh release create v0.1.1 --draft --title "v0.1.1" --notes-file CHANGELOG.md
+```
+
+Review the draft release notes in GitHub. Publishing the release triggers
+`.github/workflows/publish.yml`, which builds the package, validates the
+artifacts with `twine check`, and publishes to PyPI through Trusted Publishing.
+
+Use `-NoCommit -NoTag` to update files and run the checks without creating the
+release commit or tag:
+
+```powershell
+.\scripts\prepare-release.ps1 0.1.1 -NoCommit -NoTag
+```
+
+---
+
+## How it works
+
+VisionPack is **manifest-driven** and **content-addressed**: `visionpack.yaml`
+declares the dataset, raw images are stored once by `sha256` (immutable), and
+annotations / splits / snapshots are the versioned layer on top. The truth is the
+manifest + index, never "a folder with the right name".
+
+For the design principles, module map, data model, subsystems, and the full
+roadmap, see **[ARCHITECTURE.md](ARCHITECTURE.md)**. For the original product
+vision, see **[docs/DESIGN.md](docs/DESIGN.md)**.
+
+---
+
+## Status
+
+VisionPack is in **active development** (early but usable). The core workflow —
+multi-source ingestion → validation → deterministic splits → snapshots →
+ready-to-train export/packing — works end-to-end across classification, detection,
+instance segmentation, and keypoints, with 55 passing tests. APIs may still shift;
+feedback and contributions are welcome.
+
+```bash
+uv run python -m unittest discover -s tests -q
+```