# Custom toolchain image for the self-hosted Gitea Actions (Forgejo) runner.
#
# The cluster runs act_runner in *host mode* (docker disabled), so workflow steps
# execute INSIDE this image. The stock forgejo/runner image is minimal and lacks
# node (needed by JS actions: actions/checkout, setup-go, ...), git, make, etc.
# The runner pod is non-root with all caps dropped, so it cannot apt/apk-add at
# runtime -- the tools must be baked in here.
#
# PUBLISHING IS AUTOMATED. Run the "build image" workflow on GitHub with a tag
# (e.g. 12.11.1-ci4); it builds both architectures and pushes to
# ghcr.io/zegit-zoo/zegit-forgejo-runner. ./push-image.sh remains for building
# by hand. README.md explains why the registry moved off Gitea (Cloudflare's
# request-body cap returns 413 on a registry layer) and why the build cannot run
# on our own runners (host mode, all capabilities dropped).
#
# Then in flux-config set the image on BOTH deployment-zegit-runner and
# deployment-forgejo-runner, digest-pinned.
#
# The image is NOT public. Pulls need a registry credential in
# forgejo-runner-system -- github-registry-credentials for ghcr.io. An earlier
# version of this comment claimed the package was public and needed no secret;
# that was wrong for the Gitea registry too, which is private.
# The runner binary is built from upstream v12.11.1 with one patch: Gitea 28 adds
# job-index and job-total under `strategy` in the workflow it sends for a matrix
# job, and the stock schema refuses them ("Unknown Property job-total ... the
# workflow file is not usable"), so every matrix job dies before its first step.
# No forgejo-runner release accepts them (checked through 13.2.1). Drop this stage
# when upstream does, or when the runner is replaced.
FROM --platform=$BUILDPLATFORM data.forgejo.org/oci/golang:1.25-alpine3.23@sha256:27b3069b25647beacd3745b0b2c83e2f9b8d3935455a32cd4531236ee1c960e0 AS runner-build
ARG TARGETOS
ARG TARGETARCH
RUN apk add --no-cache git
ADD --keep-git-dir=false https://code.forgejo.org/forgejo/runner.git#8e01d43cd27e0732a1cff664996a92739472d42b /srv
COPY patches/ /patches/
WORKDIR /srv
RUN git apply --verbose /patches/*.patch
# The patch's own tests, so a build cannot ship a patch that stopped working.
RUN go test -count=1 ./act/schema/ ./internal/app/run/ -run 'StrategyJobIndexAndTotal|Gitea28MatrixJob'
RUN CGO_ENABLED=0 GOOS="$TARGETOS" GOARCH="$TARGETARCH" go build -trimpath -tags 'netgo osusergo' \
      -ldflags '-s -w -X code.forgejo.org/forgejo/runner/v12/internal/pkg/ver.version=v12.11.1' \
      -o /out/forgejo-runner .

FROM code.forgejo.org/forgejo/runner:12.11.1@sha256:a1a2885261a0b8337d4791dd6949651117206741ba66423c24a57c107a64d4a8

USER root

# nodejs   -> JS actions runtime (actions/checkout, actions/setup-go, ...)
# git      -> checkout
# git-daemon -> provides git-http-backend, which Alpine splits OUT of the `git`
#             package (git alone ships git-remote-http/https but NOT the CGI
#             backend). Without it, internal/forgeprobe's smart-HTTP tests died
#             with "fork/exec git-http-backend: no such file or directory" and
#             reported three FAILURES for a missing tool — which turned Gitea CI
#             red on every zegit master commit while GitHub stayed green, for
#             hours, unnoticed.
# bash     -> `shell: bash` steps and many action entrypoints
# coreutils-> GNU userland (alpine busybox tools trip up some scripts)
# curl,tar -> setup-go / gitleaks download + extract their own arch-specific binaries
# make     -> zegit Makefile targets
# ca-certificates -> trusted roots for HTTPS to gitea/github/goproxy
# openssl  -> the release tag gate verifies the Control Plane's SIGNED quorum
#             verdict (Ed25519 DSSE) with `openssl pkeyutl -verify -rawin`.
#             Absent, that command failed "command not found" and the gate's
#             `|| { echo ...; exit 1; }` reported it as "Quorum verdict
#             signature FAILED verification" -- a TOOLING gap narrated as a
#             SECURITY verdict, pointing the investigation at a perfectly
#             valid signed approval instead of at this image. It blocked
#             v0.0.134 and v0.0.135 on 2026-08-31.
# jq       -> the same story one step earlier: the gate parsed that envelope
#             with `jq -e`, and a missing jq was reported as "not a signed
#             DSSE envelope". jq is the reflex tool for JSON in shell steps,
#             so its absence keeps resurfacing as a misleading failure in
#             whichever step reaches for it next.
# gcc,musl-dev -> C toolchain for cgo; `go test -race` (the Makefile test
#             target) requires cgo, which needs a C compiler + libc headers
#             (musl on Alpine)
# python3,py3-yaml -> the repo's own gates are Python: credentials-coverage.sh,
#             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).
# openssh-keygen -> `ssh-keygen`: zegit's SSHSIG oracle test
#             (TestSSHSIG_ChecksumsVerifyWithSSHKeygen_441) verifies release-checksum
#             signatures with `ssh-keygen -Y verify` and fails under CI without it,
#             so the v0.1.56 cut was refused on this runner (zegit#575).
# 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 \
      nodejs \
      git \
      git-daemon \
      bash \
      coreutils \
      curl \
      tar \
      make \
      ca-certificates \
      gcc \
      musl-dev \
      python3 \
      py3-yaml \
      openssl \
      jq \
      chromium \
      font-noto \
      postgresql-client \
      openssh-keygen

# ssh-keygen signs and verifies an SSHSIG in namespace "file", the form zegit's
# test uses, so a build without a working ssh-keygen fails here, not in CI.
RUN set -eu; d=$(mktemp -d); \
    ssh-keygen -q -t ed25519 -N '' -f "$d/k"; \
    echo smoke > "$d/f"; \
    ssh-keygen -q -Y sign -n file -f "$d/k" "$d/f"; \
    printf 'smoke %s\n' "$(cat "$d/k.pub")" > "$d/allowed"; \
    ssh-keygen -Y verify -f "$d/allowed" -I smoke -n file -s "$d/f.sig" < "$d/f"; \
    rm -rf "$d"

# CVE-2026-111497 (brotli decoder out-of-bounds write, CISA KEV, due 2026-11-10): the
# forgejo/runner:12.11.1 base ships brotli-libs 1.2.0-r0, and `apk add` above never
# upgrades a package the base already has. git-remote-http and curl link it through
# libcurl. Upgrade it explicitly and fail the build if it is still behind, so a base
# bump can never quietly bring the vulnerable version back. Drop this once the upstream
# runner base ships brotli-libs >= 1.2.1.
RUN set -eux; \
    apk upgrade --no-cache brotli-libs; \
    v="$(apk list --installed brotli-libs | sed -n 's/^brotli-libs-\([0-9][^ ]*\) .*/\1/p')"; \
    echo "brotli-libs ${v}"; \
    [ "$(apk version -t "${v}" 1.2.1-r0)" != "<" ] || { echo "brotli-libs ${v} is older than 1.2.1-r0 (CVE-2026-111497)"; exit 1; }

# The patched binary replaces the stock one (see the runner-build stage).
COPY --from=runner-build /out/forgejo-runner /bin/forgejo-runner

# Match the runner pod's runAsUser (1000); keep the image non-root by default.
USER 1000