feat(crawler): system Chromium via CRAWLER_CHROMIUM_BINARY (0.45.0) (#2)

backend/Dockerfile

@@ -25,8 +25,23 @@ FROM debian:trixie-slim
 # binary ("GLIBC_2.39 not found"). Keep these two in lockstep on bumps.
 # `curl` is for the container HEALTHCHECK; `ca-certificates` is for
 # outbound HTTPS (crawler covers/pages).
+#
+# INSTALL_CHROMIUM is an opt-in for deployments that can't use the
+# chromiumoxide fetcher path (notably Linux_arm64 / Raspberry Pi, where
+# the upstream snapshot bucket has no usable build). When `true`, adds
+# Debian's apt-packaged headless chromium plus a baseline font set —
+# pair with `CRAWLER_CHROMIUM_BINARY=/usr/bin/chromium-headless-shell`
+# at runtime so the launcher uses it. Default `false` keeps cloud/x86
+# images slim.
+#
+# Build the Pi image with:
+#   docker compose build --build-arg INSTALL_CHROMIUM=true backend
+ARG INSTALL_CHROMIUM=false
 RUN apt-get update \
  && apt-get install -y --no-install-recommends ca-certificates curl \
+ && if [ "$INSTALL_CHROMIUM" = "true" ]; then \
+      apt-get install -y --no-install-recommends chromium-headless-shell fonts-liberation; \
+    fi \
  && rm -rf /var/lib/apt/lists/*
 
 # Non-root runtime user. The API binary doesn't need any root