VLM-AutoYOLO v1.5.11

What's Changed

• chore: optimize install scripts and bump version to v1.5.11 (2625757)

Installation

Docker (Recommended)

curl -O https://raw.githubusercontent.com/Somnusochi/VLM-AutoYOLO/master/docker-compose.yml
docker compose up -d

Access:

• Frontend: http://localhost
• API Docs: http://localhost:8000/docs

Docker Images

docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-frontend:v1.5.11
docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-backend:v1.5.11

Manual Setup

See README for detailed instructions.

Full Changelog: v1.5.10...v1.5.11

VLM-AutoYOLO v1.5.10

What's Changed

• fix: make SAM3 Docker dependencies opt-in (b999eb7)
• fix: set alembic script_location as absolute path (df999d5)
• fix: pass backend ruff checks (69acf2b)
• chore: add .cli_pids.json to .gitignore (bd7af97)
• docs: bump changelog to v1.5.10, add CUDA spawn fix (316419d)
• fix: set multiprocessing start method to spawn for CUDA compatibility (2c8b148)
• docs: move new changes to v1.5.10, keep v1.5.9 as tagged (72b6cc2)
• docs: update CHANGELOG + READMEs with CLI, security fixes, refactoring (742f4d2)
• feat: CLI --models flag to select which models to download (faeb8cf)
• feat: CLI checks SAM3 HF_TOKEN, guides setup with step-by-step instructions (bd3a7cd)
• feat: complete CLI — stop, status, pnpm check, Windows paths, port fallback (4cdf7b7)
• feat: add model download to CLI setup (LocateAnything-3B, ~6GB) (ec12226)
• feat: add CLI — python3 cli.py setup|start|all for one-command launch (fafb554)
• fix: bulk delete always query page=1 to avoid skipping on offset drift (a423cc3)
• fix: chunkSize validation, Content-Length guard, bulk delete pagination (67873d6)
• fix: P2/P3 — chunk upload security, migration fail-fast, SSE leak, bulk delete (2166d57)
• refactor: rename useInfiniteScroll → useScrollLoad (avoid ahooks conflict) (1294778)
• fix: use Path.is_relative_to for ZIP path traversal check (cross-platform) (8a7786b)
• fix: increase overscan 10→20 for all virtual lists to reduce white flash (174c646)
• refactor: extract Header + DetectionControls from Sidebar (496→233 lines) (8042f63)
• refactor: extract VideoList + ExtractionPanel from VideoPanel (591→224 lines) (aea84be)
• refactor: split dataset_import.py into package (yolo, coco, voc, createml) (e345562)

Installation

Docker (Recommended)

curl -O https://raw.githubusercontent.com/Somnusochi/VLM-AutoYOLO/master/docker-compose.yml
docker compose up -d

Access:

• Frontend: http://localhost
• API Docs: http://localhost:8000/docs

Docker Images

docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-frontend:v1.5.10
docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-backend:v1.5.10

Manual Setup

See README for detailed instructions.

Full Changelog: v1.5.9...v1.5.10

VLM-AutoYOLO v1.5.9

What's Changed

• fix: ZIP path traversal protection, Docker alembic/, remove scratch file (6f14f3d)
• ci: run CI (lint+test+build) on every push, keep docker/release on tags (cf01f27)
• style: fix ruff E501 line-too-long in test_api_integration.py (2c33d4e)
• test: rewrite train_and_validate — detect 10 images, train, verify, download model (559879b)
• docs: add v1.5.8/v1.5.9 changelog, update READMEs (ce2aa6c)
• docs: add v1.5.8 changelog (551df12)
• fix: clamp label position at image edges in training preview canvas (649fd83)
• feat: scroll hint text at bottom of virtual lists (loading/loaded status) (58492a6)
• fix: update stale component tests and type fixes for new API (70fc76e)
• test: add useLoadAll and useInfiniteScroll hook unit tests (0a8372e)
• test: add rename_job + rename_job_404 integration tests (a76b2bf)
• feat: infinite queries + load-all button for detections/training/videos (ab90f67)
• refactor: virtualize lists, extract useInfiniteScroll & useLoadAll hooks (2a309f8)
• feat: training job rename via Popconfirm with input (ff33391)
• feat: per-request timeouts (10min detect, 5min upload, 1min default) (ed2a586)
• feat: increase video pageSize limit 100 → 1000 (4c3860d)
• fix: async rename_job endpoint + migration down_revision (6d1140c)
• feat: increase pageSize limit — detection/train 100000, video 100 (8ee04d4)
• feat: per-request timeouts — 10min detect, 5min upload, 1min default (4acb900)
• feat: inline rename for training job names in UI (5d2a263)
• feat: add POST /train/jobs/{id}/rename endpoint (e3e786d)
• feat: add name column to TrainingJob model + migration (fbdefe8)
• feat: increase video upload limit 100MB → 500MB (2caefc9)
• depr: mark direct upload endpoint as deprecated (cb2ee7e)
• feat: frontend file size check + i18n/docs updated for 10GB limit (d195747)
• perf: increase chunk size 5MB → 20MB for faster uploads (8ddecb2)
• feat: add max_import_size_mb (10GB) and validate in chunk_init (cf761c1)
• style: color num_classes link in training job list (64f2a8c)

Installation

Docker (Recommended)

curl -O https://raw.githubusercontent.com/Somnusochi/VLM-AutoYOLO/master/docker-compose.yml
docker compose up -d

Access:

• Frontend: http://localhost
• API Docs: http://localhost:8000/docs

Docker Images

docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-frontend:v1.5.9
docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-backend:v1.5.9

Manual Setup

See README for detailed instructions.

Full Changelog: v1.5.8...v1.5.9

VLM-AutoYOLO v1.5.8

What's Changed

• feat: show class names on hover for num_classes in training job list (244aa54)
• fix: add disk cleanup step before Docker build in CI (630bb10)
• feat: add .dockerignore to exclude venv/node_modules from build context (c83f252)

Installation

Docker (Recommended)

curl -O https://raw.githubusercontent.com/Somnusochi/VLM-AutoYOLO/master/docker-compose.yml
docker compose up -d

Access:

• Frontend: http://localhost
• API Docs: http://localhost:8000/docs

Docker Images

docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-frontend:v1.5.8
docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-backend:v1.5.8

Manual Setup

See README for detailed instructions.

Full Changelog: v1.5.7...v1.5.8

VLM-AutoYOLO v1.5.7

What's Changed

• style: ruff format dataset_import files (f70b25c)
• feat: embed GPU passthrough into docker-compose.yml (90d3114)
• docs: update STRUCTURE.md with new modules and services (c3a3ef9)
• fix: replace PUT/DELETE with POST for chunk upload routes (d5571bd)
• fix: add fileUrlCache WeakMap to deduplicate blob URLs, expose isRedetecting (fe18da8)
• fix: destructure signal in useDetectMutation mutationFn params (998c40a)
• docs: add v1.5.7 changelog, update READMEs with import/queue features (0f1e32c)
• test: add 21 unit tests for dataset import parsers (0aeedd8)
• style: ruff format import_dataset.py (fb2ff2d)
• fix: initialize names dict before conditional in _read_yolo_names (d879c99)
• fix: prevent dual active border on batch thumbnails (4f301dc)
• fix: blob URL lifecycle - remove auto-revoke in Zustand, use useState+useEffect (6b6f16f)
• fix: skip optimisticModelLoading when model is already loaded (a0cbf50)
• fix: add missing setPreviewUrl destructuring in Home.tsx (4b99a3b)
• fix: pending thumbnail selection uses cached blob URL, fix maskClosable deprecation (7b6817a)
• fix: allow clicking pending batch thumbnails to preview image (844ab25)
• fix: stop showing spinner on cancelled/ended batch detection thumbnails (af9bc28)
• fix: stable blob URLs for batch thumbnails with ref-based caching (5361370)
• fix: clear old result and batchResults on new detection, show first new image (47590d9)
• fix: batch detection shows all images immediately with local blob previews (93b571b)
• fix: chunk_init async body read, missing format in worker, i18n bbox/mask keys (e0b3336)
• feat: chunked upload with Web Worker + resume support for dataset import (d1407dc)
• chore: rewrite ja.json with kanji-heavy Japanese, minimize katakana (bf07bc0)
• chore: sync ja.json i18n keys with zh/en - add cancel, import, delete confirm (2b5d034)
• fix: remove duplicate closing brace in en.json (19bd092)
• feat: dataset import from YOLO/COCO/VOC/CreateML ZIP archives (06eb321)
• fix: allow queuing training jobs while another is running (3cd8cb8)
• fix: add explicit Popconfirm import to avoid auto-import issue (be11422)
• fix: replace window.confirm() with antd Popconfirm for delete/cancel actions (b018c8b)
• feat: cancel in-flight detection requests with AbortController (acdf518)
• feat: training job queue with cancel support (d124ac9)
• fix: add confirm dialogs for destructive delete operations (23bdd61)
• fix: SAM3 health check race condition and test skip logic (c2352cb)
• refactor: restructure frontend components, split hooks, add vitest (d770273)
• refactor: extract detection service, add enum types, DI strategy pattern (c5e221e)
• fix: E2E detection test selector - text=cat matched multiple elements (dc291e0)
• chore: add prettier, format codebase, update pre-commit (b9beb11)
• chore: auto-fix lint in pre-commit hook (b4d60e3)
• chore: add husky hooks (pre-commit + commit-msg) (8646e8b)
• chore: remove unused main-page.png (15dd085)
• docs: add English architecture diagram document (7f6a87e)
• docs: add Mermaid architecture & workflow diagrams (544f325)
• fix: swap EN/ZH architecture diagram files (5e15042)
• docs: add architecture diagram (EN) and workflow diagram (ZH) (bef7e85)
• docs: add architecture and workflow diagrams (03a95b6)
• ci: opt into Node.js 24 for GitHub Actions (f4776b9)

Installation

Docker (Recommended)

curl -O https://raw.githubusercontent.com/Somnusochi/VLM-AutoYOLO/master/docker-compose.yml
docker compose up -d

Access:

• Frontend: http://localhost
• API Docs: http://localhost:8000/docs

Docker Images

docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-frontend:v1.5.7
docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-backend:v1.5.7

Manual Setup

See README for detailed instructions.

Full Changelog: v1.5.6...v1.5.7

VLM-AutoYOLO v1.5.6

What's Changed

• fix: skip integration/regression tests when backend not running (4197f56)
• refactor(v1.5.6): Zustand state management, optimistic model status, UX polish (46ee327)

Installation

Docker (Recommended)

curl -O https://raw.githubusercontent.com/Somnusochi/VLM-AutoYOLO/master/docker-compose.yml
docker compose up -d

Access:

• Frontend: http://localhost
• API Docs: http://localhost:8000/docs

Docker Images

docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-frontend:v1.5.6
docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-backend:v1.5.6

Manual Setup

See README for detailed instructions.

Full Changelog: v1.5.5...v1.5.6

VLM-AutoYOLO v1.5.5

What's Changed

• chore: bump to v1.5.5 — refactoring, E2E, integration & regression tests (d34f2f2)

Installation

Docker (Recommended)

curl -O https://raw.githubusercontent.com/Somnusochi/VLM-AutoYOLO/master/docker-compose.yml
docker compose up -d

Access:

• Frontend: http://localhost
• API Docs: http://localhost:8000/docs

Docker Images

docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-frontend:v1.5.5
docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-backend:v1.5.5

Manual Setup

See README for detailed instructions.

Full Changelog: v1.5.4...v1.5.5

VLM-AutoYOLO v1.5.4

What's Changed

• chore: remove accidentally committed db and test thumbnails (e611f1f)
• feat: SAM3 stability, batch UX, Docker, and core fixes (3cad515)
• feat: integrate SAM3 text-driven detection + segmentation strategy (675a8f8)
• docs: update Mac model to MacBook Pro M4 Pro (281f36c)
• docs: add comprehensive macOS benchmark metrics (5f0f3c6)
• test: add detailed benchmark script with macOS memory tracking support (eb7e1a1)

Installation

Docker (Recommended)

curl -O https://raw.githubusercontent.com/Somnusochi/VLM-AutoYOLO/master/docker-compose.yml
docker compose up -d

Access:

• Frontend: http://localhost
• API Docs: http://localhost:8000/docs

Docker Images

docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-frontend:v1.5.4
docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-backend:v1.5.4

Manual Setup

See README for detailed instructions.

Full Changelog: v1.5.2...v1.5.4

VLM-AutoYOLO v1.5.3

What's Changed

• fix: fetch full detection detail on history select for mask display (a16f832)
• style: ruff format detection_strategy.py (264b2c9)
• fix: add missing modelType field in useYoloValidation Detection object (c73ff84)
• feat: batch UX, Docker SAM3, and core tests (188dcd5)
• style: increase sidebar width 420→440px, padding 1→1.25rem (38c26b8)
• docs: update structure and user guides for SAM3 integration (db5e421)
• docs: update HF_TOKEN guide - Read token inherits account permissions (2c455ea)
• docs: add HF_TOKEN requirement to SAM3 sections in README (EN/ZH) (632da47)
• chore: remove accidentally committed db and test images from git (fead419)
• fix: SAM3 unload fallback via port when process reference is lost (bca2f8e)
• feat: integrate SAM3 text-driven detection + segmentation strategy (7a7f2ac)
• docs: update Windows RTX 3080 10GB benchmark with clean-state results (53967ab)
• docs: update Mac model to MacBook Pro M4 Pro (281f36c)
• docs: add comprehensive macOS benchmark metrics (5f0f3c6)
• test: add detailed benchmark script with macOS memory tracking support (eb7e1a1)

Installation

Docker (Recommended)

curl -O https://raw.githubusercontent.com/Somnusochi/VLM-AutoYOLO/master/docker-compose.yml
docker compose up -d

Access:

• Frontend: http://localhost
• API Docs: http://localhost:8000/docs

Docker Images

docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-frontend:v1.5.3
docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-backend:v1.5.3

Manual Setup

See README for detailed instructions.

Full Changelog: v1.5.2...v1.5.3

VLM-AutoYOLO v1.5.2

What's Changed

• fix: move import os to top of main.py (ruff E402) (4f83f9e)
• feat: integrate cloud benchmark records, optimize global loading UI, and enhance frontend deployment compatibility (ed1c024)
• chore(license): update open source license to AGPL-3.0 (be6da90)
• docs: move Open to Work badge before Stars (560fbc0)
• docs: add Open to Work badge with mailto link to README headers (a60fff5)

Installation

Docker (Recommended)

curl -O https://raw.githubusercontent.com/Somnusochi/VLM-AutoYOLO/master/docker-compose.yml
docker compose up -d

Access:

• Frontend: http://localhost
• API Docs: http://localhost:8000/docs

Docker Images

docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-frontend:v1.5.2
docker pull ghcr.io/Somnusochi/VLM-AutoYOLO-backend:v1.5.2

Manual Setup

See README for detailed instructions.

Full Changelog: v1.5.1...v1.5.2