ci: read the org-scoped ZEGIT_CI_PACKAGE_TOKEN, not a repo-local name

The publish path failed at registry login on every dispatch (runs 18,
20) because it read `secrets.ZEGIT_PACKAGE_TOKEN`, a name that exists
nowhere. The package-write token every zegit-zoo image workflow uses is
ZEGIT_CI_PACKAGE_TOKEN, held above repository scope, so this repository
can read it under that name — no second token, no second copy to rotate.

.github/workflows/build-image-gitea.yml

@@ -0,0 +1,174 @@
+name: build image (gitea)
+
+# Publishes the runner toolchain image from the SELF-HOSTED Gitea runners, via
+# the in-cluster rootless buildkitd — the same path zegit's own images already
+# use (zegit .github/workflows/image-gitea.yml).
+#
+# Why this exists alongside build-image.yml: that workflow is GitHub-only, so
+# the image the Gitea runners are BUILT FROM could only be produced by GitHub.
+# When GitHub Actions became unavailable on 2026-08-29 that circularity bit —
+# the fix for a missing tool in this very image (openssl/jq, whose absence
+# blocked v0.0.134 and v0.0.135) could not be published on the forge the project
+# is moving to. This removes the dependency.
+#
+# build-image.yml's header says the runners cannot build images because rootless
+# buildah needs user namespaces the pod does not have. That is true of buildah
+# IN THE JOB, and irrelevant here: buildkitd is its own hardened workload in
+# buildkit-system, and this job only speaks to it over the network with
+# buildctl. Nothing is built inside the runner container.
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Image tag, e.g. 12.11.1-ci6 (upstream runner version + ci revision)'
+        required: true
+        type: string
+  push:
+    branches: [master]
+    paths:
+      - 'Dockerfile'
+      - '.github/workflows/build-image-gitea.yml'
+
+env:
+  BUILDKIT_HOST: tcp://buildkitd.buildkit-system.svc.cluster.local:1234
+  BUILDKIT_VERSION: v0.32.2
+  REGISTRY: gitea.langenoja.se
+  IMAGE_PATH: zegit-zoo/zegit-forgejo-runner
+
+jobs:
+  build:
+    # Gitea-only: buildkitd is an in-cluster service that GitHub runners cannot
+    # reach. build-image.yml still covers the GitHub/ghcr.io side.
+    if: ${{ github.server_url != 'https://github.com' }}
+    runs-on: ubuntu-latest
+    timeout-minutes: 45
+    steps:
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+        with:
+          persist-credentials: false
+
+      # Workspace-local because the runner is non-root and cannot write to
+      # /usr/local/bin. The smoke test uses the FULL PATH deliberately:
+      # $GITHUB_PATH only takes effect for SUBSEQUENT steps, so a bare
+      # `buildctl --version` here would be command-not-found.
+      - name: Install buildctl
+        run: |
+          set -euo pipefail
+          case "$(uname -m)" in
+            x86_64) arch=amd64;;
+            aarch64) arch=arm64;;
+            *) echo "::error::unsupported arch $(uname -m)"; exit 1;;
+          esac
+          mkdir -p "$GITHUB_WORKSPACE/.bin"
+          curl -fsSL "https://github.com/moby/buildkit/releases/download/${BUILDKIT_VERSION}/buildkit-${BUILDKIT_VERSION}.linux-${arch}.tar.gz" \
+            | tar -xz -C "$GITHUB_WORKSPACE/.bin" --strip-components=1 bin/buildctl
+          echo "$GITHUB_WORKSPACE/.bin" >> "$GITHUB_PATH"
+          "$GITHUB_WORKSPACE/.bin/buildctl" --version
+
+      - name: buildkitd reachable
+        run: buildctl debug workers
+
+      # A master push VALIDATES that the Dockerfile still builds on both arches
+      # but publishes nothing; only an explicit dispatch names a tag and pushes.
+      # Guessing a tag from a branch push would silently mint versions.
+      - id: meta
+        run: |
+          set -euo pipefail
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            echo "push=true"  >> "$GITHUB_OUTPUT"
+            echo "tag=${{ inputs.tag }}" >> "$GITHUB_OUTPUT"
+          else
+            echo "push=false" >> "$GITHUB_OUTPUT"
+            echo "tag=ci-validation" >> "$GITHUB_OUTPUT"
+          fi
+
+      # Refuse a publish that cannot complete, rather than reporting success
+      # having pushed nothing. A validation run needs no credentials.
+      # The Gitea Actions token cannot write packages; this needs an explicit
+      # package-write PAT (read:package is pull-only).
+      - name: Registry login
+        if: ${{ steps.meta.outputs.push == 'true' }}
+        env:
+          TOKEN: ${{ secrets.ZEGIT_CI_PACKAGE_TOKEN }}
+        run: |
+          set -euo pipefail
+          if [ -z "${TOKEN:-}" ]; then
+            echo "::error::ZEGIT_CI_PACKAGE_TOKEN is not visible to this run. It is the org-scoped package-write token every zegit-zoo image workflow uses (docs: flux-config docs/rotation/forge-secrets.yaml); this repository must be able to read the org secret, and the name must match."
+            exit 1
+          fi
+          mkdir -p "$HOME/.docker"
+          printf '{"auths":{"%s":{"auth":"%s"}}}\n' \
+            "$REGISTRY" "$(printf 'zegit-zoo:%s' "$TOKEN" | base64 -w0)" \
+            > "$HOME/.docker/config.json"
+
+      - name: Build multi-arch
+        run: |
+          set -euo pipefail
+          REF="${REGISTRY}/${IMAGE_PATH}:${{ steps.meta.outputs.tag }}"
+          # No --output on a validation run: buildctl v0.32 has no "cacheonly"
+          # exporter (run 16, 2026-09-08: 'exporter "cacheonly" could not be
+          # found'), so every push-triggered validation since this workflow
+          # was added had failed — silently, since nothing depended on it. A
+          # build without an exporter still builds every stage on both arches.
+          if [ "${{ steps.meta.outputs.push }}" = "true" ]; then
+            buildctl build --progress=plain \
+              --frontend dockerfile.v0 \
+              --local context=. \
+              --local dockerfile=. \
+              --opt platform=linux/amd64,linux/arm64 \
+              --output "type=image,name=${REF},push=true"
+          else
+            buildctl build --progress=plain \
+              --frontend dockerfile.v0 \
+              --local context=. \
+              --local dockerfile=. \
+              --opt platform=linux/amd64,linux/arm64
+          fi
+
+      # The image is a TOOLCHAIN, so "it built" is not the property that matters
+      # — "it still contains what the gates shell out to" is. build-image.yml
+      # asserts that with `docker run`, which does not exist on these runners;
+      # buildkit can do it directly by building a stage FROM the published image
+      # whose RUN fails when a tool is absent. That is strictly better: buildkit
+      # runs it natively per platform, so a package that resolves on amd64 but
+      # not on arm64 cannot reach half the nodes unnoticed.
+      #
+      # openssl and jq are on this list because their absence blocked v0.0.134
+      # and v0.0.135: the release tag gate shells out to both to verify the
+      # Control Plane's signed quorum verdict, and a missing tool was reported
+      # as "verdict not signed" and "signature FAILED verification" — a tooling
+      # gap narrated as a security verdict. Extend this list whenever a gate
+      # grows a shell dependency; it only covers what someone remembered to add.
+      - name: Assert the published image carries the toolchain the gates need
+        if: ${{ steps.meta.outputs.push == 'true' }}
+        run: |
+          set -euo pipefail
+          REF="${REGISTRY}/${IMAGE_PATH}:${{ steps.meta.outputs.tag }}"
+          work=$(mktemp -d)
+          {
+            echo "FROM ${REF}"
+            echo 'RUN set -eu; \'
+            echo '    python3 -c "import yaml, sys; print(\"python3+yaml\", sys.version.split()[0])"; \'
+            echo '    for t in gcc node bash make curl tar openssl jq chromium-browser psql; do \'
+            echo '      command -v "$t" >/dev/null || { echo "MISSING: $t" >&2; exit 1; }; \'
+            echo '      echo "ok: $t"; \'
+            echo '    done; \'
+            echo '    test -x "$(git --exec-path)/git-http-backend" || { echo "MISSING: git-http-backend" >&2; exit 1; }; \'
+            echo '    echo "ok: git-http-backend"'
+          } > "$work/Dockerfile"
+          cat "$work/Dockerfile"
+          buildctl build --progress=plain \
+            --frontend dockerfile.v0 \
+            --local context="$work" \
+            --local dockerfile="$work" \
+            --opt platform=linux/amd64,linux/arm64
+          echo "✓ toolchain intact on linux/amd64 and linux/arm64"
+
+      - name: Summary
+        run: |
+          if [ "${{ steps.meta.outputs.push }}" = "true" ]; then
+            echo "published ${REGISTRY}/${IMAGE_PATH}:${{ steps.meta.outputs.tag }} (amd64+arm64), toolchain asserted on both"
+          else
+            echo "validation only — the Dockerfile builds on both arches; nothing published"
+          fi

.github/workflows/build-image.yml

@@ -109,6 +109,22 @@ jobs:
       # missing tool, blocking v0.0.134 and v0.0.135. The list only covers what
       # someone remembered to add, so add to it whenever a gate grows a new
       # shell dependency.
+      #
+      # DERIVED once, 2026-08-31, rather than remembered: every command invoked
+      # from a `run:` block across zegit's Gitea-executed workflows and its
+      # composite actions was extracted and checked against this list. Result:
+      # no missing apk package. Everything resolved to one of three sources —
+      # baked in here; provided by busybox/coreutils; or downloaded per-run and
+      # immediately version-checked (go via setup-go, buildctl, flux, cosign,
+      # syft, goreleaser). The download path needs nothing from this image
+      # beyond curl and tar, both already asserted.
+      #
+      # What the audit DID find is that the busybox/coreutils layer was entirely
+      # unasserted, so dropping `coreutils` from the apk line above would pass
+      # this check while base64, mktemp, seq and sort silently vanished — and by
+      # the history above, their absence would be narrated as whatever the gate
+      # using them happened to be doing. They are asserted below now. They are
+      # cheap to check and the failure they prevent is expensive to read.
       - name: Verify the image still contains the toolchain the gates need
         if: ${{ steps.meta.outputs.push == 'true' }}
         run: |
@@ -129,6 +145,11 @@ jobs:
               command -v tar      >/dev/null && echo "tar=ok"      || echo "tar=MISSING"
               command -v openssl  >/dev/null && echo "openssl=ok"  || echo "openssl=MISSING"
               command -v jq       >/dev/null && echo "jq=ok"       || echo "jq=MISSING"
+              # busybox/coreutils layer: used across zegit's gates for base64
+              # decoding of DSSE payloads, temp dirs, poll loops and sorting.
+              for t in base64 mktemp seq sort sed grep cut head wc uname date; do
+                command -v "$t" >/dev/null && echo "$t=ok" || echo "$t=MISSING"
+              done
               [ -x "$(git --exec-path)/git-http-backend" ] \
                 && echo "git-http-backend=ok" || echo "git-http-backend=MISSING"
             ' 2>&1) || { echo "::error::could not run $REF on $plat"; fail=1; continue; }

Dockerfile

@@ -58,6 +58,19 @@ USER root
 #             validate-admission.sh and feature-lint.sh all shell out to
 #             python3, and credentials-coverage parses manifests with yaml
 #
+# chromium, font-noto -> the browser gates (2026-09-08): zegit's `browser
+#             tests` (chromedp + a CDP virtual authenticator over the WebAuthn
+#             ceremony pages) and `lighthouse` (treosh/lighthouse-ci-action
+#             via chrome-launcher) were github.com-only jobs, so when `ci`
+#             was routed to this runner on 2026-08-31 they stopped running
+#             anywhere. chromedp finds `chromium`/`chromium-browser` on PATH;
+#             chrome-launcher honours CHROME_PATH. font-noto so text renders
+#             (an empty font set makes layout/contrast audits meaningless).
+# postgresql-client -> `psql`, so the lighthouse job can CREATE/DROP its own
+#             database on the runner's ci-postgres (ZEGIT_TESTPG_DSN) instead
+#             of migrating the shared maintenance database from under the
+#             integration suite's template.
+#
 # Go is intentionally NOT baked in: actions/setup-go fetches the pinned version
 # per-run (node + tar are present), so the image needs no rebuild on Go bumps.
 RUN apk add --no-cache \
@@ -75,7 +88,10 @@ RUN apk add --no-cache \
       python3 \
       py3-yaml \
       openssl \
-      jq
+      jq \
+      chromium \
+      font-noto \
+      postgresql-client
 
 # Match the runner pod's runAsUser (1000); keep the image non-root by default.
 USER 1000

push-image.sh

@@ -99,15 +99,27 @@ for arch in amd64 arm64; do
   docker push "$REPO:$TAG-$arch" || die "push failed for $arch"
 done
 
-docker manifest rm "$REPO:$TAG" >/dev/null 2>&1 || true
+# `docker manifest create` REFUSES a source that is itself a manifest list:
-docker manifest create "$REPO:$TAG" --amend "$REPO:$TAG-amd64" --amend "$REPO:$TAG-arm64"
+#   ERROR: gitea.langenoja.se/...:<tag>-amd64 is a manifest list
-docker manifest push "$REPO:$TAG"
+# With Docker's containerd image store, `docker build --platform linux/amd64`
+# produces an OCI index rather than a plain manifest, so both per-arch tags are
+# lists and the combine step fails after the (slow, large) pushes have already
+# succeeded — leaving the per-arch tags published and the plain tag absent,
+# which is the one the Deployments reference. Seen on 12.11.1-ci6, 2026-08-31.
+#
+# `buildx imagetools create` accepts indexes as sources and does the combine
+# registry-side, so it works with either image store.
+docker buildx imagetools create -t "$REPO:$TAG" "$REPO:$TAG-amd64" "$REPO:$TAG-arm64" \
+  || die "failed to combine the per-arch tags into $REPO:$TAG"
 
 # Verify by reading it back, rather than trusting the push's exit code.
 echo "verifying the published manifest lists both architectures"
-got=$(docker manifest inspect "$REPO:$TAG" | grep -o '"architecture": *"[a-z0-9]*"' | sort -u | wc -l)
+inspect=$(docker buildx imagetools inspect "$REPO:$TAG") \
-[ "$got" -ge 2 ] || die "published manifest does not list two architectures"
+  || die "published $REPO:$TAG cannot be read back"
-docker manifest inspect "$REPO:$TAG" | grep -o '"architecture": *"[a-z0-9]*"' | sort -u
+got=$(echo "$inspect" | grep -o 'linux/[a-z0-9]*' | sort -u | grep -cE 'linux/(amd64|arm64)')
+[ "$got" -ge 2 ] || die "published manifest does not list both architectures:
+$inspect"
+echo "$inspect" | grep -o 'linux/[a-z0-9]*' | sort -u
 
 cat <<EOF