mirror of
https://github.com/snapotter-hq/SnapOtter.git
synced 2026-08-03 07:46:42 +02:00
* fix(docker): pin CUDA base to 12.6 so the GPU image starts on R560+ drivers The amd64 base nvidia/cuda:12.9.2-cudnn-runtime bakes a cuda>=12.9 driver gate enforced by nvidia-container-toolkit at container start, so the image fails to launch on common production drivers (e.g. 570.x / CUDA 12.8). The AI bundles are all cu126 wheels and the image installs libcublas-12-6, so 12.9 was misaligned with the workload. Pin to nvidia/cuda:12.6.3-cudnn-runtime-ubuntu24.04 to match the wheels and lower the driver floor to R560+. * fix(ai): broaden OOM detection so the rembg lighter-model fallback fires onnxruntime/CUDA allocation failures surface as 'Failed to allocate memory for requested buffer', CUBLAS_STATUS_ALLOC_FAILED, or bad_alloc, not just 'out of memory'. The background-removal and transparency-fixer fallback-to-lighter-model paths only matched the literal 'out of memory', so the fallback was dead code and transparency-fixer (default birefnet-hr-matting) always failed with an allocation error. Add isMemoryAllocError() and use it in both checks. * fix(ai): use bundled PaddleOCR models so OCR runs offline ocr.py passed no model dirs to PaddleOCR, so PaddleX resolved models from ~/.paddlex and downloaded them from HuggingFace at runtime (slow first use, broken air-gapped), ignoring the models the OCR bundle ships in MODELS_PATH; it also pulled doc-orientation/unwarping models that are not bundled. Pin detection, recognition and textline models to the bundled dirs in MODELS_PATH (per language) and disable use_doc_orientation_classify / use_doc_unwarping, with per-component fallback when a model is absent. Verified: OCR runs with zero HuggingFace requests. * fix(docker): add CAP_KILL so container shutdown is graceful cap_drop: ALL without re-adding KILL meant tini (PID 1, root) could not forward SIGTERM to the gosu-dropped snapotter process (root minus CAP_KILL cannot signal a different UID). docker stop logged '[FATAL tini] forwarding signal: Operation not permitted', never delivered the signal, and fell back to SIGKILL after the 10s timeout. Add KILL to cap_add in both compose files. Verified: docker stop completes in 0s with SIGTERM delivered (exit 143) and no FATAL tini. * fix(ai): serialize bundle installs against AI jobs to prevent sidecar segfault A feature bundle install rewrites the shared Python venv (pip + copytree of site-packages/*.so) as a background subprocess, with no coordination against AI tool jobs that dlopen native libs (torch / onnxruntime CUDA) from the same venv; a job loading a shared object while it is overwritten segfaults the sidecar. Add a process-wide async mutex (venv-lock.ts): bridge.run() acquires it before every AI script and the install route holds it across the installer subprocess. Both run in the same Node process so a module-level lock suffices. Verified: concurrent install + AI job produces zero segfaults and the job serializes behind the install. * fix(ai): make the venv lock read/write so concurrent AI jobs are not serialized The first cut used an exclusive mutex, which (a) deferred the dispatcher spawn by a microtask and broke unit tests that synchronously drive the mocked spawn, and (b) serialized AI jobs against each other, removing the dispatcher's by-id request multiplexing. Make it a writer-preferring read/write lock: AI jobs are shared readers (with a synchronous fast path so spawn still happens in-tick) and a bundle install is the exclusive writer. Verified: all 764 AI unit tests pass. * fix(ai): degrade OCR to Tesseract on CPU-only hosts instead of segfaulting The amd64 AI bundle ships paddlepaddle-gpu, whose native libs dlopen libcuda.so.1 at import and segfault on a host without a GPU (libcuda is the driver lib, injected only by nvidia-container-toolkit on GPU hosts). The segfault crashed the shared long-lived AI dispatcher and, after a few attempts, tripped the bridge crash-recovery permanent-disable, wedging all AI until a container restart. The standalone ocr tool defaults to quality=balanced (PaddleOCR), so it hit this on every CPU-only deployment; ocr-pdf already hardcoded Tesseract and was unaffected. ocr.py now gates the PaddleOCR tiers on gpu_available(): balanced/best transparently fall back to fast (Tesseract, CPU-capable) when no usable GPU is present, and run_paddleocr_v5/run_paddleocr_vl refuse before importing paddle so the GPU build is never dlopen'd on CPU. GPU hosts are unchanged. Verified on a CPU-only Windows/WSL2 box: ocr returns Tesseract text across repeated runs with the dispatcher staying healthy (no wedge).
161 lines
5.6 KiB
YAML
161 lines
5.6 KiB
YAML
name: SnapOtter
|
|
|
|
# CPU deployment — no GPU required.
|
|
# Usage: docker compose up -d
|
|
# GPU: docker compose -f docker-compose-gpu.yml up -d
|
|
|
|
services:
|
|
SnapOtter:
|
|
build:
|
|
context: ..
|
|
dockerfile: docker/Dockerfile
|
|
image: snapotter/snapotter:latest
|
|
container_name: SnapOtter
|
|
ports:
|
|
# For internet-facing deployments, bind to localhost only:
|
|
# - "127.0.0.1:1349:1349"
|
|
- "1349:1349"
|
|
volumes:
|
|
- SnapOtter-data:/data # AI models, user files
|
|
- SnapOtter-workspace:/tmp/workspace # Temp processing (auto-cleaned)
|
|
environment:
|
|
- AUTH_ENABLED=true
|
|
- DEFAULT_USERNAME=admin
|
|
# Set a strong password. Default is 'admin' -- CHANGE THIS for any non-local deployment.
|
|
# - DEFAULT_PASSWORD=your-strong-password-here
|
|
- DEFAULT_PASSWORD=admin
|
|
- SKIP_MUST_CHANGE_PASSWORD=${SKIP_MUST_CHANGE_PASSWORD:-false}
|
|
- MAX_UPLOAD_SIZE_MB=${MAX_UPLOAD_SIZE_MB:-0}
|
|
- MAX_BATCH_SIZE=${MAX_BATCH_SIZE:-0}
|
|
- MAX_MEGAPIXELS=${MAX_MEGAPIXELS:-0}
|
|
- CONCURRENT_JOBS=${CONCURRENT_JOBS:-0}
|
|
- MAX_WORKER_THREADS=${MAX_WORKER_THREADS:-0}
|
|
- PROCESSING_TIMEOUT_S=${PROCESSING_TIMEOUT_S:-0}
|
|
- MAX_PIPELINE_STEPS=${MAX_PIPELINE_STEPS:-20}
|
|
- RATE_LIMIT_PER_MIN=${RATE_LIMIT_PER_MIN:-300}
|
|
- MAX_USERS=${MAX_USERS:-0}
|
|
- SESSION_DURATION_HOURS=${SESSION_DURATION_HOURS:-168}
|
|
- TRUST_PROXY=${TRUST_PROXY:-true}
|
|
- DATABASE_URL=postgres://${POSTGRES_USER:-snapotter}:${POSTGRES_PASSWORD:-snapotter}@postgres:5432/${POSTGRES_DB:-snapotter}
|
|
- REDIS_URL=redis://:${REDIS_PASSWORD:-snapotter}@redis:6379
|
|
# 1.x upgrade: uncomment to import the old SQLite database on first boot;
|
|
# re-comment after the migration succeeds.
|
|
# - SQLITE_MIGRATE_PATH=/data/snapotter.db
|
|
# OIDC Authentication (optional)
|
|
# - EXTERNAL_URL=https://photos.example.com
|
|
# - OIDC_ENABLED=false
|
|
# - OIDC_ISSUER_URL=
|
|
# - OIDC_CLIENT_ID=
|
|
# - OIDC_CLIENT_SECRET=
|
|
# - OIDC_SCOPES=openid profile email
|
|
# - OIDC_AUTO_CREATE_USERS=true
|
|
# - OIDC_DEFAULT_ROLE=user
|
|
# - OIDC_AUTO_LINK_USERS=false
|
|
# - OIDC_PROVIDER_NAME=
|
|
# - OIDC_USERNAME_CLAIM=preferred_username
|
|
# - OIDC_CLOCK_TOLERANCE=30
|
|
# - COOKIE_SECRET=
|
|
#
|
|
# Docker secrets (_FILE convention): mount secrets as files instead of
|
|
# passing them as plain-text env vars. Supported for sensitive vars only.
|
|
# - DEFAULT_PASSWORD_FILE=/run/secrets/snapotter_password
|
|
# - S3_ACCESS_KEY_ID_FILE=/run/secrets/s3_access_key
|
|
# - S3_SECRET_ACCESS_KEY_FILE=/run/secrets/s3_secret_key
|
|
# - OIDC_CLIENT_SECRET_FILE=/run/secrets/oidc_secret
|
|
# - COOKIE_SECRET_FILE=/run/secrets/cookie_secret
|
|
# - SNAPOTTER_LICENSE_KEY_FILE=/run/secrets/license_key
|
|
restart: unless-stopped
|
|
depends_on:
|
|
postgres:
|
|
condition: service_healthy
|
|
redis:
|
|
condition: service_healthy
|
|
# --- Security hardening ---
|
|
mem_limit: 6g
|
|
memswap_limit: 6g
|
|
cpus: 4
|
|
pids_limit: 512
|
|
cap_drop:
|
|
- ALL
|
|
cap_add:
|
|
- CHOWN
|
|
- SETUID
|
|
- SETGID
|
|
- DAC_OVERRIDE
|
|
- FOWNER
|
|
# KILL lets tini (PID 1, root) forward SIGTERM to the gosu-dropped
|
|
# snapotter process on shutdown. Without it, root minus CAP_KILL cannot
|
|
# signal a different-UID process, so docker stop is ungraceful
|
|
# ("[FATAL tini] forwarding signal: Operation not permitted" -> SIGKILL).
|
|
- KILL
|
|
# NOTE: security_opt: [no-new-privileges:true] is intentionally omitted.
|
|
# gosu requires setuid to drop from root to the snapotter user.
|
|
# Mitigation: cap_drop: ALL limits available capabilities after privilege drop.
|
|
# NOTE: read_only: true is not set because PUID/PGID remapping requires
|
|
# writing to /etc/passwd and /etc/group. Consider using Docker --user flag
|
|
# instead of PUID/PGID for read-only rootfs support.
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-sf", "--max-time", "5", "http://localhost:1349/api/v1/health"]
|
|
interval: 30s
|
|
timeout: 5s
|
|
start_period: 60s
|
|
retries: 3
|
|
shm_size: '2gb'
|
|
logging:
|
|
driver: json-file
|
|
options:
|
|
max-size: "50m"
|
|
max-file: "5"
|
|
|
|
postgres:
|
|
image: postgres:17-alpine
|
|
container_name: SnapOtter-postgres
|
|
environment:
|
|
POSTGRES_USER: ${POSTGRES_USER:-snapotter}
|
|
# Set a strong password -- CHANGE THIS for any non-local deployment.
|
|
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-snapotter}
|
|
POSTGRES_DB: ${POSTGRES_DB:-snapotter}
|
|
volumes:
|
|
- SnapOtter-pgdata:/var/lib/postgresql/data
|
|
restart: unless-stopped
|
|
mem_limit: 1g
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-snapotter}"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 12
|
|
start_period: 15s
|
|
|
|
redis:
|
|
image: redis:8-alpine
|
|
container_name: SnapOtter-redis
|
|
command: >-
|
|
redis-server
|
|
--maxmemory-policy noeviction
|
|
--maxmemory 512mb
|
|
--appendonly yes
|
|
--requirepass ${REDIS_PASSWORD:-snapotter}
|
|
volumes:
|
|
- SnapOtter-redisdata:/data
|
|
restart: unless-stopped
|
|
mem_limit: 1g
|
|
healthcheck:
|
|
test: ["CMD", "redis-cli", "-a", "${REDIS_PASSWORD:-snapotter}", "--no-auth-warning", "ping"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 12
|
|
start_period: 10s
|
|
|
|
# Uncomment to use Docker secrets (requires Docker Swarm or compose v2.23+):
|
|
# secrets:
|
|
# snapotter_password:
|
|
# file: ./secrets/snapotter_password.txt
|
|
# oidc_secret:
|
|
# file: ./secrets/oidc_secret.txt
|
|
|
|
volumes:
|
|
SnapOtter-data:
|
|
SnapOtter-workspace:
|
|
SnapOtter-pgdata:
|
|
SnapOtter-redisdata:
|