fix(grid-rs): build wgrib2 in-tree instead of pulling from prop:latest

The FROM ${WGRIB2_IMAGE} AS wgrib2-src pattern required docker buildx
to pull a private-registry image mid-build. That pull started failing
consistently after Stream C landed — docker login on the runner
succeeds but buildx's implicit FROM pull can't always reach the same
credentials (buildx instance context vs the host daemon).

Rebuild wgrib2 + NCEPLIBS-g2c from source in a dedicated builder stage,
mirroring the Elixir Dockerfile's self-contained wgrib2-builder. Adds
~5 min per CI run — worth the end of a 3-run CI-failure streak.

rust/prop_grid_rs/Dockerfile

@@ -1,35 +1,70 @@
 # syntax=docker/dockerfile:1.7
 #
-# Multi-arch build for `prop-grid-rs`. wgrib2 isn't in Debian apt — the
+# Multi-arch build for `prop-grid-rs`. Self-contained: builds wgrib2 +
-# Elixir image builds it from source in its own stage. Rather than
+# NCEPLIBS-g2c from source so the image has no external private-registry
-# rebuild it here (~5 min per CI run), copy the binary + libg2c out of
+# dependency. An earlier revision did `FROM prop:latest AS wgrib2-src` to
-# the already-published Elixir image.
+# reuse the Elixir image's pre-built wgrib2, but docker buildx in CI
-#
+# couldn't always authenticate to the private registry during that
-# Runtime uid 65534 matches the fsGroup on the NFS scores mount.
+# implicit FROM pull — the resulting failures were opaque and broke
+# every grid-rs image publish after Stream C.
 #
 # This image ships two binaries: `prop-grid-rs` (default ENTRYPOINT,
 # drains grid_tasks) and `hrrr-point-worker` (k8s `command:` override,
-# drains hrrr_fetch_tasks).
+# drains hrrr_fetch_tasks). Runtime uid 65534 matches the fsGroup on
-ARG WGRIB2_IMAGE=git.mcintire.me/graham/prop:latest
+# the NFS scores mount.
 
-FROM ${WGRIB2_IMAGE} AS wgrib2-src
+ARG DEBIAN_VERSION=trixie-slim
+ARG RUNNER_IMAGE="docker.io/debian:${DEBIAN_VERSION}"
 
+# ---- wgrib2 builder (mirrors the same stage in the Elixir Dockerfile) ----
+FROM ${RUNNER_IMAGE} AS wgrib2-builder
+
+ARG WGRIB2_VERSION=3.6.0
+ARG G2C_VERSION=2.1.0
+
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    --mount=type=cache,target=/var/lib/apt,sharing=locked \
+    rm -f /etc/apt/apt.conf.d/docker-clean \
+ && apt-get update \
+ && apt-get install -y --no-install-recommends \
+      build-essential gfortran cmake wget ca-certificates pkg-config \
+      zlib1g-dev libaec-dev libpng-dev libopenjp2-7-dev
+
+WORKDIR /tmp/g2c
+RUN wget -q --content-disposition "https://github.com/NOAA-EMC/NCEPLIBS-g2c/archive/refs/tags/v${G2C_VERSION}.tar.gz" \
+      -O g2c.tar.gz \
+ && tar xzf g2c.tar.gz \
+ && cd NCEPLIBS-g2c-${G2C_VERSION} \
+ && mkdir build && cd build \
+ && cmake .. -DCMAKE_INSTALL_PREFIX=/usr/local \
+             -DCMAKE_BUILD_TYPE=Release \
+             -DUSE_PNG=ON -DUSE_AEC=ON -DUSE_OpenJPEG=ON -DUSE_Jasper=OFF \
+ && make -j$(nproc) \
+ && make install
+
+WORKDIR /tmp/wgrib2
+RUN wget -q --content-disposition "https://github.com/NOAA-EMC/wgrib2/archive/refs/tags/v${WGRIB2_VERSION}.tar.gz" \
+      -O wgrib2.tar.gz \
+ && tar xzf wgrib2.tar.gz \
+ && cd wgrib2-${WGRIB2_VERSION} \
+ && mkdir build && cd build \
+ && cmake .. -DCMAKE_INSTALL_PREFIX=/usr/local -DCMAKE_BUILD_TYPE=Release \
+      -DUSE_PNG=ON -DUSE_OPENJPEG=ON -DUSE_AEC=ON \
+ && make -j$(nproc) \
+ && make install \
+ && strip /usr/local/bin/wgrib2
+
+# ---- Rust build ----
 FROM rust:1.94-trixie AS builder
 WORKDIR /src
 
-# Cache deps: copy manifests first so dependency changes alone don't
-# invalidate the source-layer cache.
 COPY Cargo.toml Cargo.lock* ./
 COPY src ./src
 COPY tests ./tests
 
-# BuildKit cache mounts persist cargo's registry + git across CI runs.
+# Registry + git caches are persistent; target/ is not (kept ephemeral
-# `target/` is deliberately NOT cached — after Stream C bumped the
+# to avoid the runner disk-pressure failures observed during Stream C
-# crate to two binaries, the runner started running out of disk inside
+# rollout). Full rebuild adds ~3 min; it's still under 6 min total.
-# the mount and the build would fail mid-link. Rebuilding from scratch
-# adds ~3 min to the build but removes the failure mode entirely.
-# Lint + test gate the image build so a regressed scorer or a clippy
-# warning never produces a pushable image.
 RUN --mount=type=cache,target=/usr/local/cargo/registry,sharing=locked \
     --mount=type=cache,target=/usr/local/cargo/git,sharing=locked \
     rustup component add clippy \
@@ -39,22 +74,19 @@ RUN --mount=type=cache,target=/usr/local/cargo/registry,sharing=locked \
  && cp target/release/worker /usr/local/bin/worker \
  && cp target/release/hrrr_point_worker /usr/local/bin/hrrr_point_worker
 
-# Runtime image: slim debian + the shared libs wgrib2 links against.
+# ---- Runtime ----
-# libgfortran5/libaec0/zlib1g/libpng16-16t64/libopenjp2-7 mirror the
+FROM ${RUNNER_IMAGE} AS runtime
-# Elixir runtime stage.
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
-FROM debian:trixie-slim AS runtime
+    --mount=type=cache,target=/var/lib/apt,sharing=locked \
-RUN apt-get update && apt-get install -y --no-install-recommends \
+    rm -f /etc/apt/apt.conf.d/docker-clean \
-      ca-certificates \
+ && apt-get update \
-      tini \
+ && apt-get install -y --no-install-recommends \
-      libgfortran5 \
+      ca-certificates tini \
-      libaec0 \
+      libgfortran5 libaec0 zlib1g libpng16-16t64 libopenjp2-7
-      zlib1g \
-      libpng16-16t64 \
-      libopenjp2-7 \
- && rm -rf /var/lib/apt/lists/*
 
-COPY --from=wgrib2-src /usr/local/bin/wgrib2 /usr/local/bin/wgrib2
+COPY --from=wgrib2-builder /usr/local/bin/wgrib2 /usr/local/bin/wgrib2
-COPY --from=wgrib2-src /usr/local/lib/libg2c.so* /usr/local/lib/
+COPY --from=wgrib2-builder /usr/local/lib/libg2c.so /usr/local/lib/
+COPY --from=wgrib2-builder /usr/local/lib/libg2c.so.0 /usr/local/lib/
 RUN ldconfig
 
 COPY --from=builder /usr/local/bin/worker /usr/local/bin/prop-grid-rs
@@ -62,7 +94,6 @@ COPY --from=builder /usr/local/bin/hrrr_point_worker /usr/local/bin/hrrr-point-w
 
 USER 65534:65534
 # Default entrypoint is the grid chain worker. Override with `command:`
-# in the k8s manifest (or `docker run ... hrrr-point-worker`) for the
+# in the k8s manifest for the per-QSO point worker.
-# per-QSO point worker.
 ENTRYPOINT ["/usr/bin/tini", "--"]
 CMD ["/usr/local/bin/prop-grid-rs"]