From 77d560ddaece0f30566fef420a8b27b8154e03fd Mon Sep 17 00:00:00 2001
From: Nguyen Minh Phuc <son.luong@skylabteam.com>
Date: Sat, 18 Jul 2026 11:24:44 +0000
Subject: [PATCH] ci: move buildx layer cache to the registry

act_runner's cache PVC is 1Gi and also holds .runner, the runner's own
registration file. --cache-to type=gha,mode=max for three images is several GB;
filling that volume breaks the runner, not just the cache. act_runner also
evicts by age with no size cap, so it fills whatever it is given.

type=registry has no such limit and lives beside the images it caches. The uv
cache still uses the runner's cache service, which is a few hundred MB.

Registry login is no longer gated to master: the build now reads and writes the
cache on every run. Pushing the release image keeps its own master-only gate.
---
 .gitea/workflows/ci.yaml | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/.gitea/workflows/ci.yaml b/.gitea/workflows/ci.yaml
index 2aec22e..986d012 100644
--- a/.gitea/workflows/ci.yaml
+++ b/.gitea/workflows/ci.yaml
@@ -211,7 +211,9 @@ jobs:
       - uses: docker/setup-buildx-action@c47758b77c9736f4b2ef4073d4d51994fabfe349 # v3.7.1
 
       - name: registry login
-        if: github.ref == 'refs/heads/master' && github.event_name == 'push'
+        # Not gated to master any more: the build step now reads AND writes the layer cache
+        # in the registry, so every run needs credentials. Pushing the release image is
+        # still master-only — that gate lives on the `push by digest` step, where it belongs.
         uses: docker/login-action@9780b0c442fbb1117ed29e0efdff1e18412f7567 # v3.3.0
         with:
           registry: ${{ env.REGISTRY }}
@@ -226,12 +228,26 @@ jobs:
         # Loaded locally, not pushed. Trivy scans this exact image next; only then does it
         # get pushed. The alternative — push, scan, and hope nobody pulled meanwhile — is
         # how a CRITICAL ends up in the registry with a green checkmark next to it.
+        #
+        # The layer cache is `type=registry`, NOT `type=gha`. Two reasons, both hard:
+        #
+        # 1. act_runner's cache server is backed by a 1Gi PVC that also holds `.runner`,
+        #    the runner's own registration file. `mode=max` stores every intermediate layer
+        #    of three images — several GB. Filling that volume does not merely lose the
+        #    cache: the runner cannot write its state and has to be re-registered by hand.
+        #    Trading "slow CI" for "broken CI" is not a trade.
+        # 2. act_runner evicts by AGE, with no size cap in its config. It will fill whatever
+        #    it is given and then wedge. The registry has no such limit and already holds
+        #    the images anyway.
+        #
+        # The uv/pip cache still uses the runner's cache service — that one is a few hundred
+        # MB and fits.
         run: |
           docker buildx build \
             -f services/${{ matrix.svc }}/Dockerfile \
             --build-arg BUILD_SHA=${{ github.sha }} \
-            --cache-from type=gha,scope=${{ matrix.svc }} \
-            --cache-to type=gha,mode=max,scope=${{ matrix.svc }} \
+            --cache-from type=registry,ref=${REGISTRY}/${IMAGE_NS}/svcforge-${{ matrix.svc }}:buildcache \
+            --cache-to type=registry,ref=${REGISTRY}/${IMAGE_NS}/svcforge-${{ matrix.svc }}:buildcache,mode=max \
             --load \
             -t svcforge/${{ matrix.svc }}:ci \
             .
@@ -281,7 +297,7 @@ jobs:
           docker buildx build \
             -f services/${{ matrix.svc }}/Dockerfile \
             --build-arg BUILD_SHA=${{ github.sha }} \
-            --cache-from type=gha,scope=${{ matrix.svc }} \
+            --cache-from type=registry,ref=${REGISTRY}/${IMAGE_NS}/svcforge-${{ matrix.svc }}:buildcache \
             --push \
             -t "${IMAGE}:${GITHUB_SHA}" \
             .