Run lint and tests as Dockerfile phases built with --no-cache (closes #202)

script/check, cibuild, docker, lint, test, setup and install-precommit
are now the sneak/prompts main copies, unchanged: lint and test each
build their Dockerfile phase with --no-cache. The lint phase runs
golangci-lint from the image REPO_POLICIES.md names, with libvips-dev
from apt-get; the test phase runs the tests with a 90-second timeout;
the build stage depends on both. script/bootstrap installs the C
compiler and image libraries only with --cgo, which the test phase and
build stage pass, and refreshes the apt lists before its first apt
install. Dockerfile.lint and CHECK_EPOCH are gone, and make
docker-versioned and docker-test call the scripts. Without VERSION the
build stage still uses git describe, per issue 166.

Model: opus-5-5

script/bootstrap

@@ -4,11 +4,15 @@
 # installed tools are skipped. Base tooling comes from nix, apt, brew,
 # or apk (detected in that order); assumes NOTHING is present (not git,
 # make, or go). The linter is never installed on the host: golangci-lint
-# runs only inside a container, Dockerfile.lint or the Dockerfile lint
-# stage (see script/lint). A C compiler and the CGO image libraries
-# (pkg-config, vips, libheif) are installed for the govips bindings.
-# Both Dockerfiles run this script too, so their build dependencies are
-# the ones listed here.
+# runs only in the lint phase of the Dockerfile (see script/lint).
+#
+#   script/bootstrap         git, make and Go, all the host needs: the
+#                            checks compile pixa in Docker
+#   script/bootstrap --cgo   also a C compiler and the CGO image
+#                            libraries (pkg-config, vips, libheif) for
+#                            the govips bindings, to compile pixa; the
+#                            Dockerfile's test phase and build stage
+#                            run this
 set -eu
 
 ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
@@ -35,6 +39,10 @@ detect_pkgmgr() {
         if [ "$(id -u)" != "0" ]; then
             SUDO="sudo"
         fi
+        # This runs before the first install only. A fresh image, such
+        # as a CI runner's, has no package lists, and apt-get install
+        # finds no package without them.
+        $SUDO apt-get update
     fi
 }
 
@@ -71,7 +79,16 @@ ensure_cgo_deps() {
     fi
 }
 
+usage() {
+    echo "usage: script/bootstrap [--cgo]" >&2
+    exit 2
+}
+
 main() {
+    case "$*" in
+        "" | --cgo) ;;
+        *) usage ;;
+    esac
     cd "$ROOT"
 
     # Base tooling
@@ -81,8 +98,10 @@ main() {
     # Go toolchain
     if missing go; then pkg_install go golang go go; fi
 
-    # CGO image libraries
-    ensure_cgo_deps
+    # CGO image libraries, only where pixa is compiled
+    if [ "$*" = "--cgo" ]; then
+        ensure_cgo_deps
+    fi
 
     go mod download
 

script/check

@@ -1,7 +1,8 @@
 #!/bin/sh
 # script/check: run all checks (test, lint, fmt-check). Our own
-# extension to scripts-to-rule-them-all. Must not modify any files.
-# Generic: usually needs no adaptation.
+# extension to scripts-to-rule-them-all. test and lint are Docker
+# phases; fmt-check is native, because a formatter writes the working
+# tree. Must not modify any files.
 set -eu
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"

script/cibuild

@@ -1,18 +1,29 @@
 #!/bin/sh
-# script/cibuild: run the CI build. The Dockerfile runs the checks
-# (make fmt-check, lint, test) as build steps. This script passes a new
-# CHECK_EPOCH on every run, so Docker runs those steps instead of
-# reusing cached results: a successful run means the checks ran and
-# passed on this tree. Generic: needs no adaptation. The Gitea workflow
-# runs this on push.
+# script/cibuild: run the CI build. It bootstraps first: a CI runner
+# checks out and runs this and nothing else, and script/fmt-check runs
+# the formatter on the host, which a pristine checkout cannot do.
+# --no-cache for the same reason as script/docker: the gate phases the
+# final stage depends on are RUN steps, and a cached one is a check that
+# did not run.
 set -eu
 
-ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
+ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
-    epoch="$(date +%s)$$"
-    docker build --build-arg CHECK_EPOCH="$epoch" .
+    "$SCRIPT_DIR/bootstrap"
+    "$SCRIPT_DIR/check"
+    # Own line: a failing command substitution inside an argument does
+    # not trip `set -e`, so the inline form degrades silently to an
+    # empty constant. VERSION is computed here because .dockerignore
+    # excludes .git, so `git describe` in a build stage yields an empty
+    # version without failing.
+    version="$(git describe --tags --always --dirty 2>/dev/null || true)"
+    [ -n "$version" ] || version="unknown"
+    docker build --no-cache \
+        --build-arg VERSION="$version" \
+        -t "$("$SCRIPT_DIR/projectname")" .
 }
 
 main "$@"

script/docker

@@ -1,9 +1,8 @@
 #!/bin/sh
 # script/docker: build the Docker image tagged with the project name.
-# Identical in all repos; the tag comes from script/projectname. Like
-# script/cibuild, it passes a new CHECK_EPOCH, so the build runs the
-# checks instead of reusing cached results. Generic: needs no
-# adaptation.
+# Identical in all repos; the tag comes from script/projectname.
+# --no-cache because the gate phases the final stage depends on are RUN
+# steps, and a cached one is a check that did not run.
 set -eu
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
@@ -11,8 +10,15 @@ ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
-    epoch="$(date +%s)$$"
-    docker build --build-arg CHECK_EPOCH="$epoch" \
+    # Own line: a failing command substitution inside an argument does
+    # not trip `set -e`, so the inline form degrades silently to an
+    # empty constant. VERSION is computed here because .dockerignore
+    # excludes .git, so `git describe` in a build stage yields an empty
+    # version without failing.
+    version="$(git describe --tags --always --dirty 2>/dev/null || true)"
+    [ -n "$version" ] || version="unknown"
+    docker build --no-cache \
+        --build-arg VERSION="$version" \
         -t "$("$SCRIPT_DIR/projectname")" .
 }
 

script/install-precommit

@@ -1,13 +1,13 @@
 #!/bin/sh
 # script/install-precommit: install the git pre-commit hook that runs
 # script/precommit. Our own extension to scripts-to-rule-them-all.
-# Generic: needs no adaptation.
 set -eu
 
 ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
+    hook=".git/hooks/pre-commit"
     printf '#!/bin/sh\nset -e\nscript/precommit\n' > .git/hooks/pre-commit
     chmod +x .git/hooks/pre-commit
     echo "pre-commit hook installed: runs script/precommit"

script/lint

@@ -1,37 +1,23 @@
 #!/bin/sh
-# script/lint: run golangci-lint over the whole tree. This is the only
-# way the linter is run, everywhere; it is never installed on the host.
+# script/lint: run the linter. Linting is a phase of the Dockerfile and
+# this builds that phase alone; the linter is never installed or run on
+# a developer host, where a shared result cache and a host-global lock
+# make its answer untrustworthy.
 #
-# Inside a container it runs the linter. Anywhere else it builds
-# Dockerfile.lint, whose last step runs this script again inside that
-# container.
-#
-# Dockerfile.lint and the Dockerfile lint stage set container=docker
-# (the systemd convention for marking a container) to say where we are.
-# /.dockerenv cannot: it is missing inside build steps, and present on
-# hosts that are themselves containers.
+# The phase is not the last stage in the file, so it is built only when
+# --target names it. --no-cache because a cached lint layer is a lint
+# that did not run. The tag makes each build replace the previous image
+# instead of leaving a dangling one behind.
 set -eu
 
-ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
+ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
-    if [ "${container:-}" = docker ]; then
-        # `golangci-lint config verify` is not run: it fetches its JSON
-        # schema over an unpinned live HTTPS call, which REPO_POLICIES.md
-        # forbids.
-        echo "Running linter..."
-        golangci-lint run --config .golangci.yml ./...
-    else
-        # A new CACHEBUST on every run means the lint step is never
-        # served from cache (see Dockerfile.lint). The cacheonly output
-        # leaves no image behind.
-        docker build \
-            --progress=plain \
-            --build-arg CACHEBUST="$(date +%s)-$$" \
-            --output=type=cacheonly \
-            -f Dockerfile.lint .
-    fi
+    docker build --no-cache \
+        --target lint \
+        -t "$("$SCRIPT_DIR/projectname")-lint" .
 }
 
 main "$@"

script/setup

@@ -1,7 +1,6 @@
 #!/bin/sh
 # script/setup: set up the repo for development after a fresh clone:
-# installs dependencies (script/bootstrap) and the git pre-commit hook.
-# Add any repo-specific initialization (db init, .env template) here.
+# installs dependencies and the git pre-commit hook.
 set -eu
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"

script/test

@@ -1,27 +1,19 @@
 #!/bin/sh
-# script/test: run the test suite. CGO dependencies (pkg-config, vips,
-# libheif) come from nix-shell when not already available (e.g. inside
-# a Docker build or an existing nix-shell).
+# script/test: run the test suite. Testing is a phase of the Dockerfile
+# and this builds that phase alone, on the same terms as script/lint:
+# --target because a phase that is not the last stage is built only when
+# named, --no-cache because a cached test layer is a test that did not
+# run, and a tag so each build replaces the previous image.
 set -eu
 
-ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
-
-run_with_cgo_deps() {
-    if command -v pkg-config >/dev/null 2>&1; then
-        sh -c "$1"
-    else
-        nix-shell -p pkg-config vips libheif git --run "$1"
-    fi
-}
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
+ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
-    echo "Running tests..."
-    # Run without -v first for clean output on success; on failure rerun
-    # with -v for full diagnostics, then exit non-zero (REPO_POLICIES.md
-    # conditional-verbose-rerun pattern). The first run already proved the
-    # tests broken, so the build fails even if the rerun happens to pass.
-    run_with_cgo_deps "CGO_ENABLED=1 go test -timeout 30s -race -cover ./... || { echo '--- Rerunning with -v for details ---'; CGO_ENABLED=1 go test -timeout 30s -race -v ./...; exit 1; }"
+    docker build --no-cache \
+        --target test \
+        -t "$("$SCRIPT_DIR/projectname")-test" .
 }
 
 main "$@"