Merge branch 'develop' into fix/auth-frontend-remediation

apps/orchestrator/Dockerfile

@@ -1,6 +1,3 @@
-# syntax=docker/dockerfile:1
-# Enable BuildKit features for cache mounts
-
 # Base image for all stages
 # Uses Debian slim (glibc) instead of Alpine (musl) for native addon compatibility.
 FROM node:24-slim AS base
@@ -26,9 +23,8 @@ COPY packages/config/package.json ./packages/config/
 COPY apps/orchestrator/package.json ./apps/orchestrator/
 
 # Install ALL dependencies (not just production)
-# This ensures NestJS packages and other required deps are available
-RUN --mount=type=cache,id=pnpm-store,target=/root/.local/share/pnpm/store \
-    pnpm install --frozen-lockfile
+# No cache mount — Kaniko builds are ephemeral in CI
+RUN pnpm install --frozen-lockfile
 
 # ======================
 # Builder stage
@@ -69,15 +65,14 @@ LABEL org.opencontainers.image.vendor="Mosaic Stack"
 LABEL org.opencontainers.image.title="Mosaic Orchestrator"
 LABEL org.opencontainers.image.description="Agent orchestration service for Mosaic Stack"
 
-# Remove npm (unused in production — we use pnpm) to reduce attack surface
-RUN rm -rf /usr/local/lib/node_modules/npm /usr/local/bin/npm /usr/local/bin/npx
+# Install dumb-init for proper signal handling (static binary from GitHub,
+# avoids apt-get which fails under Kaniko with bookworm GPG signature errors)
+ADD https://github.com/Yelp/dumb-init/releases/download/v1.2.5/dumb-init_1.2.5_x86_64 /usr/local/bin/dumb-init
 
-# Install wget and dumb-init
-RUN apt-get update && apt-get install -y --no-install-recommends wget dumb-init \
-    && rm -rf /var/lib/apt/lists/*
-
-# Create non-root user
-RUN groupadd -g 1001 nodejs && useradd -m -u 1001 -g nodejs nestjs
+# Single RUN to minimize Kaniko filesystem snapshots (each RUN = full snapshot)
+RUN rm -rf /usr/local/lib/node_modules/npm /usr/local/bin/npm /usr/local/bin/npx \
+    && chmod 755 /usr/local/bin/dumb-init \
+    && groupadd -g 1001 nodejs && useradd -m -u 1001 -g nodejs nestjs
 
 WORKDIR /app
 
@@ -105,7 +100,7 @@ EXPOSE 3001
 
 # Health check
 HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
-  CMD wget --no-verbose --tries=1 --spider http://localhost:3001/health || exit 1
+  CMD node -e "require('http').get('http://localhost:3001/health', (r) => {process.exit(r.statusCode === 200 ? 0 : 1)})"
 
 # Use dumb-init to handle signals properly
 ENTRYPOINT ["dumb-init", "--"]