shopdb-flask/Dockerfile

# shopdb-flask single-site container.
#
# One image, one site. Per ADR-004, each adopting facility runs its own
# stack with its own DB, secrets, and enabled-plugin list. This image
# bundles all 13 catalog plugins (computers, employees, geenforce,
# knowledgebase, machines, measuringtools, network, notifications,
# printedparts, printers, slides, usb, warranty); a site installs + enables
# the ones it wants with `flask plugin install <name>` (or, declaratively,
# `flask plugin apply-profile <profile.json>`). Per ADR-013 a future lean
# build stages only the chosen plugin directories into this image.
#
# The frontend is built in a first stage and its dist output is copied into
# the final image so Flask can serve the SPA (register_frontend_routes in
# shopdb/__init__.py resolves <repo>/frontend/dist).
#
# Build:
#   docker build -t shopdb-flask .
# Run (with .env):
#   docker run --env-file .env -p 5001:5001 shopdb-flask

# ---- Stage 1: build the Vue frontend ----
FROM node:20-slim AS frontendbuild

WORKDIR /build

# Optionally trust the site's corporate root CA so npm's TLS to the registry
# validates behind an inspecting proxy. The .pem is gitignored and absent from a
# clean checkout, so the copy is made optional by pairing it with a file that
# always exists; the cert is installed only when actually provided. Without it
# npm 10.x behind an inspecting proxy fails silently and leaves an incomplete
# node_modules; a clean build with no proxy is unaffected.
COPY corp-root-ca.pem* frontend/package.json /tmp/corpca/
# node:20-slim ships without the ca-certificates package (no update-ca-certificates
# and no /usr/local/share/ca-certificates), so install it before trusting the cert.
RUN if [ -f /tmp/corpca/corp-root-ca.pem ]; then \
        apt-get update && apt-get install -y --no-install-recommends ca-certificates && \
        rm -rf /var/lib/apt/lists/* && \
        cp /tmp/corpca/corp-root-ca.pem /usr/local/share/ca-certificates/corp-root-ca.crt && \
        update-ca-certificates; \
    fi

# Copy only the manifests first so `npm ci` caches on dependency changes.
COPY frontend/package*.json ./frontend/
# Trust the corp CA for npm's TLS only when it was actually installed above. The
# guard keeps NODE_EXTRA_CA_CERTS unset on a clean checkout (no cert), so Node
# does not warn about a missing cert path; a proxy-inspected build still gets
# the cert because the file is present.
# Install the frontend dependencies. vite and the rest of the build toolchain
# live under devDependencies, so include them explicitly (--include=dev).
# Behind an inspecting proxy (Zscaler) each package fetch is slow (40-50s) and
# npm's default concurrency piles up parallel sockets that the proxy resets
# mid-stream, making npm abort with "Exit handler never called" and leaving an
# incomplete node_modules with no vite. Serializing to a single socket
# (maxsockets 1) lets every fetch complete; the retry loop and raised timeouts
# ride out any remaining transient reset, and the final test hard-verifies the
# toolchain landed so a truncated install fails loudly here rather than as a
# confusing "vite: not found" three steps later.
RUN if [ -f /usr/local/share/ca-certificates/corp-root-ca.crt ]; then \
        export NODE_EXTRA_CA_CERTS=/usr/local/share/ca-certificates/corp-root-ca.crt; \
    fi; \
    cd frontend && \
    npm config set fetch-retries 5 && \
    npm config set fetch-retry-factor 2 && \
    npm config set fetch-retry-mintimeout 20000 && \
    npm config set fetch-retry-maxtimeout 120000 && \
    npm config set fetch-timeout 600000 && \
    npm config set maxsockets 1 && \
    ( npm ci --include=dev --no-audit --no-fund \
        || { echo "npm ci attempt 1 failed, retrying..."; sleep 5; npm ci --include=dev --no-audit --no-fund; } \
        || { echo "npm ci attempt 2 failed, retrying..."; sleep 10; npm ci --include=dev --no-audit --no-fund; } ) && \
    test -x node_modules/.bin/vite || { \
        echo "ERROR: node_modules/.bin/vite missing after npm ci (proxy likely truncated the install)."; \
        exit 1; \
    }

# The frontend keeps its repo-relative layout here, because npm prebuild runs
# `node ../scripts/stage-frontend.mjs`, which stages each plugin's frontend/ into
# the Vite tree and codegens routes.gen.js. That script resolves its repo root as
# its own directory's parent, so it needs scripts/ and plugins/ as SIBLINGS of
# frontend/. Building with frontend/ flattened to the stage root made `../scripts`
# resolve to /scripts and the build failed on a missing module.
COPY scripts/stage-frontend.mjs ./scripts/
COPY plugins/ ./plugins/

COPY frontend/ ./frontend/
RUN if [ -f /usr/local/share/ca-certificates/corp-root-ca.crt ]; then \
        export NODE_EXTRA_CA_CERTS=/usr/local/share/ca-certificates/corp-root-ca.crt; \
    fi; \
    cd frontend && npm run build
# Output lands in /build/frontend/dist (Vite default), copied into the final
# stage below.

# ---- Stage 2: Python application image ----
FROM python:3.14-slim AS base

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1

WORKDIR /app

RUN apt-get update \
    && apt-get install -y --no-install-recommends \
        build-essential \
        default-libmysqlclient-dev \
        pkg-config \
        curl \
    && rm -rf /var/lib/apt/lists/*

COPY requirements.txt ./
# gunicorn and gevent are container-only: requirements.txt is a universal,
# hash-checked lockfile that also serves the Windows/IIS install, where waitress
# is the server and neither of these is used. gevent is the worker class (see
# the CMD below) because the endpoint long-poll holds a connection per agent,
# which a thread pool cannot absorb at fleet scale.
RUN pip install --no-cache-dir -r requirements.txt \
    && pip install --no-cache-dir gunicorn gevent

COPY shopdb/ ./shopdb/
COPY plugins/ ./plugins/
COPY migrations/ ./migrations/
COPY scripts/ ./scripts/
COPY wsgi.py ./

# Make entrypoint and bootstrap scripts executable
RUN chmod +x /app/scripts/docker-entrypoint.sh /app/scripts/bootstrap-plugins.sh

# Built SPA from stage 1. Flask serves it via register_frontend_routes.
COPY --from=frontendbuild /build/frontend/dist ./frontend/dist

# Create instance/ IN THE IMAGE, owned by the app user, before the chown below.
# Docker seeds an empty named volume from the image's content at the mountpoint,
# ownership included. Without this the mountpoint is created root-owned 0755 and
# the container, which runs as shopdb, cannot write plugins.json or any upload
# into its own instance directory.
RUN mkdir -p /app/instance

RUN useradd --create-home --shell /bin/bash shopdb \
    && chown -R shopdb:shopdb /app
USER shopdb

EXPOSE 5001

# Entrypoint runs migrations and bootstraps plugins on first deployment
ENTRYPOINT ["/app/scripts/docker-entrypoint.sh"]

# Probe the public health route, not the login endpoint. Probing POST
# /api/auth/login logged a 400 every 30s and ran the credential path from a
# health check. The route answers 200 even when the database is degraded, so the
# body's status field is what decides health. Compose files that terminate TLS
# override this with an https probe; plain http is correct for the pull and
# airgap stacks, which inherit this unchanged.
HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=3 \
    CMD curl --silent http://localhost:5001/api/dashboard/health \
        | grep -q '"status":"ok"' || exit 1

# Async workers, matching docker-compose.yml - see the reasoning there. A
# compose file overrides this CMD, but an image run without one (a plain
# `docker run`, a site's own orchestrator) would otherwise still get the
# blocking sync default and the same starvation.
CMD ["gunicorn", \
     "--bind", "0.0.0.0:5001", \
     "--worker-class", "gevent", \
     "--workers", "4", \
     "--worker-connections", "2000", \
     "--timeout", "60", \
     "--access-logfile", "-", \
     "--access-logformat", "%(h)s %(l)s %(u)s %(t)s \"%(r)s\" %(s)s %(b)s %(D)sus \"%(f)s\" \"%(a)s\"", \
     "--error-logfile", "-", \
     "wsgi:app"]