Merge pull request 'promote: dev → stage' (#29) from dev into stage

.gitea/workflows/dev.yaml

@@ -75,17 +75,6 @@ jobs:
         if: github.event_name != 'pull_request'
         run: gcloud auth configure-docker us-central1-docker.pkg.dev --quiet
 
-      - name: Prune Docker to reclaim disk
-        run: |
-          # Remove stopped containers, dangling images, unused volumes/networks.
-          # Do NOT prune build cache — that keeps Docker builds fast and under
-          # the ~26min runner restart window. Selective pruning frees ~4-5GB
-          # which is enough to prevent overlay2 "no space left on device" errors.
-          docker container prune -f 2>&1 || true
-          docker image prune -f 2>&1 || true
-          docker volume prune -f 2>&1 || true
-          df -h /
-
       # ── El SDK setup ──────────────────────────────────────────────────────
       # Push builds: extract elb + elc + runtime from ci-base (always latest).
       # PR builds:   use committed bin/elb-linux-amd64 + bin/elc-linux-amd64 + runtime/.

.gitea/workflows/stage.yaml

@@ -96,17 +96,6 @@ jobs:
       - name: Configure docker auth for Artifact Registry
         run: gcloud auth configure-docker us-central1-docker.pkg.dev --quiet
 
-      - name: Prune Docker to reclaim disk
-        run: |
-          # Remove stopped containers, dangling images, unused volumes/networks.
-          # Do NOT prune build cache — that keeps Docker builds fast and under
-          # the ~26min runner restart window. Selective pruning frees ~4-5GB
-          # which is enough to prevent overlay2 "no space left on device" errors.
-          docker container prune -f 2>&1 || true
-          docker image prune -f 2>&1 || true
-          docker volume prune -f 2>&1 || true
-          df -h /
-
       - name: Compute image tag
         id: tag
         run: |
@@ -154,70 +143,25 @@ jobs:
         if: steps.changetype.outputs.asset_only != 'true'
         run: |
           set -euo pipefail
-          echo "ELC=$ELC"
-          echo "EL_RUNTIME=$EL_RUNTIME"
-          echo "el_runtime.js: $(ls -lh "$EL_RUNTIME/el_runtime.js" 2>&1)"
           cp "$EL_RUNTIME/el_runtime.js" src/js/
           mkdir -p dist/js
           for f in src/js/*.el; do
             [ -f "$f" ] || continue
             name=$(basename "$f" .el)
-            echo "Compiling $f..."
-            "$ELC" --target=js --bundle --minify --obfuscate "$f" > "dist/js/${name}.js" || {
-              echo "elc FAILED on $f"
-              exit 1
-            }
+            "$ELC" --target=js --bundle --minify --obfuscate "$f" > "dist/js/${name}.js"
             echo "  compiled: $f -> dist/js/${name}.js"
           done
           rm -f src/js/el_runtime.js
 
       # ── Docker build + push ───────────────────────────────────────────────
 
-      - name: Build soul-demo image tar
-        # Dockerfile.stage COPYs dist/soul-demo-image.tar so k3s can import
-        # soul-demo:local at runtime. We compile soul-demo from source on the
-        # host runner (ci-base has gcc), build a minimal OCI image, and save it.
-        # Moved AFTER JS compilation to avoid Docker memory pressure killing elc.
-        if: steps.changetype.outputs.asset_only != 'true'
-        run: |
-          set -euo pipefail
-          # Compile el_runtime.o and soul-demo on the host runner
-          cc -O2 -DHAVE_CURL -c runtime/el_runtime.c -I runtime/ -o /tmp/el_runtime.o
-          cc -O2 -rdynamic -DEL_SOUL_DEMO_BUILD \
-             -I runtime/ \
-             -o dist/soul-demo \
-             dist/soul-demo.c dist/vessel_stubs.c /tmp/el_runtime.o \
-             -lcurl -lpthread -ldl -lm -lssl -lcrypto
-          echo "soul-demo compiled: $(ls -lh dist/soul-demo)"
-          # Package as minimal OCI image for k3s import
-          # --no-cache: prevents reuse of corrupted overlay2 layers from prior failed runs
-          docker build --no-cache -f dist/Dockerfile.soul-demo -t soul-demo:local dist/
-          docker save soul-demo:local -o dist/soul-demo-image.tar
-          echo "soul-demo-image.tar: $(du -sh dist/soul-demo-image.tar | cut -f1)"
-          docker rmi soul-demo:local 2>/dev/null || true
-
-      - name: Download k3s binary
-        # Pre-download k3s on the host runner so Dockerfile.stage can COPY it
-        # directly. Previously k3s was downloaded inside the Docker builder stage,
-        # which combined with build-essential and C compilation caused RWLayer nil
-        # corruption on the runner's overlay2 driver. Host-runner download is safe.
-        if: steps.changetype.outputs.asset_only != 'true'
-        run: |
-          set -euo pipefail
-          curl -fL --retry 3 --retry-delay 10 \
-            https://github.com/k3s-io/k3s/releases/download/v1.32.4%2Bk3s1/k3s \
-            -o dist/k3s
-          chmod +x dist/k3s
-          echo "k3s: $(ls -lh dist/k3s)"
-
       - name: Build and tag image
         if: steps.changetype.outputs.asset_only != 'true'
         run: |
           set -euo pipefail
-          # --no-cache: prevents reuse of corrupted overlay2 layers from prior failed runs.
-          # Dockerfile.stage is now single-stage (no builder) so build is fast even without cache.
           docker build \
-            --no-cache \
+            --build-arg BUILDKIT_INLINE_CACHE=1 \
+            --cache-from us-central1-docker.pkg.dev/neuron-785695/neuron-marketing/marketing:stage-latest \
             -f Dockerfile.stage \
             -t "marketing:${{ steps.tag.outputs.tag }}" \
             .

Dockerfile.stage

@@ -4,16 +4,50 @@
 #   - neuron-web  on port 8080 (landing page server)
 #   - soul-demo   on port 7772 (demo chat, localhost only)
 #
-# All binaries (neuron-web, soul-demo, k3s) are pre-built by CI on the host
-# runner before this Dockerfile runs. This keeps the Docker build single-stage
-# with no compilation and no network downloads, eliminating the multi-stage
-# complexity that caused RWLayer corruption on the runner's overlay2 driver.
+# neuron-web is built by `elb build` in CI (not here). elb compiles each
+# .el source independently and links the result — no combined mega-file,
+# no exponential memory growth. The binary lands at dist/neuron-landing
+# (linux/amd64) and is COPY'd directly into the runtime image.
 #
-# CI pre-build steps (in stage.yaml):
-#   - neuron-web: built by `elb build` → dist/neuron-landing
-#   - soul-demo:  compiled by cc on host → dist/soul-demo
-#   - k3s:        downloaded by curl on host → dist/k3s
+# soul-demo.c is pre-committed (small, no OOM risk) and compiled here.
 
+# ── Stage 1: compile soul-demo ────────────────────────────────────────────────
+FROM debian:bookworm-slim AS builder
+
+RUN apt-get update \
+ && apt-get install -y --no-install-recommends \
+        build-essential \
+        curl \
+        libcurl4-openssl-dev \
+        libssl-dev \
+        ca-certificates \
+ && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /build
+
+COPY runtime/el_runtime.c runtime/el_runtime.h ./
+
+# Pre-compile el_runtime as a separate cached layer.
+# el_runtime.c changes rarely; main.c changes every run.
+# Splitting this out means el_runtime.o is cached across builds when only main.c changes.
+# -DHAVE_CURL: the staged el_runtime.c (from el.git) guards the OTLP observability
+# section (emit_metric, emit_log, trace_span_*) behind #ifdef HAVE_CURL.
+# libcurl IS installed above, so define HAVE_CURL to enable those functions.
+RUN cc -O2 -DHAVE_CURL -c el_runtime.c -I. -o el_runtime.o
+
+COPY dist/soul-demo.c dist/vessel_stubs.c ./
+
+RUN cc -O2 -rdynamic \
+       -DEL_SOUL_DEMO_BUILD \
+       -o soul-demo \
+       soul-demo.c vessel_stubs.c el_runtime.o \
+       -lcurl -lpthread -ldl -lm -lssl -lcrypto
+
+# ── Download k3s binary ───────────────────────────────────────────────────────
+RUN curl -fL https://github.com/k3s-io/k3s/releases/download/v1.32.4%2Bk3s1/k3s -o /usr/local/bin/k3s \
+ && chmod +x /usr/local/bin/k3s
+
+# ── Stage 2: runtime image ────────────────────────────────────────────────────
 FROM debian:bookworm-slim
 
 RUN apt-get update \
@@ -33,13 +67,10 @@ RUN apt-get update \
 COPY dist/neuron-landing /usr/local/bin/neuron-web
 RUN chmod +x /usr/local/bin/neuron-web
 
-# soul-demo binary — compiled by cc on host runner in CI
-COPY dist/soul-demo /usr/local/bin/soul-demo
-RUN chmod +x /usr/local/bin/soul-demo
+COPY --from=builder /build/soul-demo /usr/local/bin/soul-demo
 
-# k3s binary — downloaded from GitHub releases by CI
-COPY dist/k3s /usr/local/bin/k3s
-RUN chmod +x /usr/local/bin/k3s
+# k3s binary
+COPY --from=builder /usr/local/bin/k3s /usr/local/bin/k3s
 
 # soul-demo OCI image tar — k3s imports this at startup (no registry needed)
 RUN mkdir -p /var/lib/rancher/k3s/agent/images