From f4ddb58ae1e10b30d9d3e47d5a8f031c67b2bd0c Mon Sep 17 00:00:00 2001 From: clawbot <35+clawbot@noreply.example.org> Date: Sun, 18 Oct 2026 19:25:33 +0200 Subject: [PATCH] Keep modules, lint cache and system packages in check builds (closes #109) Re-vendors REPO_POLICIES.md and script/cibuild, docker, lint and test from sneak/prompts at 0653579, on sneak's ruling in https://git.eeqj.de/sneak/prompts/issues/130. In the Dockerfile's lint, test and builder stages, the system-package install and the module download now come before ARG CACHEBUST, so Docker keeps those layers until the base image, the install line, go.mod or go.sum changes. golangci-lint run also mounts golangci-lint's cache. Every step that lints, tests or compiles still runs on every check build, and go test keeps -count=1 and -race. README and TODO.md say the same. Model: opus-5-5 --- Dockerfile | 32 +++++++++------ README.md | 23 +++++++---- REPO_POLICIES.md | 103 +++++++++++++++++++++++++++++++---------------- TODO.md | 21 ++++++++-- script/cibuild | 9 +++-- script/docker | 9 +++-- script/lint | 12 +++--- script/test | 11 ++--- 8 files changed, 144 insertions(+), 76 deletions(-) diff --git a/Dockerfile b/Dockerfile index 0722e19..551e25d 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,16 +1,23 @@ -# Every stage declares ARG CACHEBUST first: script/ passes a new value -# on every build, which reruns every RUN step after it. The steps that -# compile mount Go's build cache, which survives from build to build. +# In every stage ARG CACHEBUST comes right after the steps that install +# system packages and download Go's modules, or right after FROM in a +# stage with neither, and every step that lints, tests or compiles +# comes after it. script/ passes a new value on every build, which +# reruns every RUN step after it. Docker keeps the layers above it +# until the base image, their own lines or go.mod and go.sum change. +# The steps that compile mount Go's build cache, and golangci-lint run +# also mounts golangci-lint's; both survive from build to build. The +# test phase runs as nobody and so mounts Go's build cache at +# /tmp/.cache/go-build; its own comment says why. # Lint phase, built alone by script/lint. The tools are invoked directly # rather than through `make lint`, which runs docker itself and so cannot # run inside a build step. # golangci/golangci-lint:v2.14.0, 2026-10-07 FROM golangci/golangci-lint@sha256:ad862ba6b3798cbe0fd9fd7408d498fd74fbd2623a92406b2fd3898faf0bf98f AS lint -ARG CACHEBUST WORKDIR /src COPY go.mod go.sum ./ RUN go mod download +ARG CACHEBUST COPY . . # The gofmt half of `make fmt-check`. gofmt's output is assigned to a @@ -24,6 +31,7 @@ RUN files="$(gofmt -s -l .)" && \ # Validates .golangci.yml against the schema the pinned binary embeds. RUN golangci-lint config verify --config .golangci.yml RUN --mount=type=cache,target=/root/.cache/go-build \ + --mount=type=cache,target=/root/.cache/golangci-lint \ golangci-lint run --config .golangci.yml ./... # Test phase, built alone by script/test. -race needs cgo and so a C @@ -38,12 +46,12 @@ RUN --mount=type=cache,target=/root/.cache/go-build \ # nobody (65534) so the tests can write to it. # golang:1.25-trixie, 2026-10-04 FROM golang@sha256:2c4c60ef415fbfa5e90300722293bef36c5e63fae17570ce18f580af933dbd73 AS test -ARG CACHEBUST USER nobody ENV HOME=/tmp WORKDIR /src COPY go.mod go.sum ./ RUN go mod download +ARG CACHEBUST COPY . . RUN --mount=type=cache,target=/tmp/.cache/go-build,uid=65534,gid=65534 \ go test -count=1 -timeout 90s -race -cover ./... || \ @@ -51,19 +59,19 @@ RUN --mount=type=cache,target=/tmp/.cache/go-build,uid=65534,gid=65534 \ go test -count=1 -timeout 90s -race -v ./...; exit 1; } # Build stage. Nothing is wanted from either phase above; the copies are -# what make BuildKit build them first, so this stage cannot run unless -# lint and test passed. +# what make BuildKit build them first, so nothing after them can run +# unless lint and test passed. # golang:1.25-alpine, 2026-07-23 FROM golang@sha256:56961d79ea8129efddcc0b8643fd8a5416b4e6228cfd477e3fd61deb2672c587 AS builder -ARG CACHEBUST -COPY --from=lint /src/go.sum /dev/null -COPY --from=test /src/go.sum /dev/null RUN apk add --no-cache git make -# A tar-stream context keeps the sender's file owners, which git refuses. -RUN git config --system --add safe.directory /src WORKDIR /src COPY go.mod go.sum ./ RUN go mod download +ARG CACHEBUST +COPY --from=lint /src/go.sum /dev/null +COPY --from=test /src/go.sum /dev/null +# A tar-stream context keeps the sender's file owners, which git refuses. +RUN git config --system --add safe.directory /src COPY . . # The version stamped into the binary: the VERSION build argument when diff --git a/README.md b/README.md index acac419..4aaca1a 100644 --- a/README.md +++ b/README.md @@ -1125,13 +1125,22 @@ entrypoints are: - `script/install-precommit` — install the git pre-commit hook, as `.git/hooks/pre-commit`, that runs `script/precommit`. -Every `docker build` in `script/` passes a new `CACHEBUST` build argument, which -every stage of the `Dockerfile` declares first, so every `RUN` step runs again -each time. On an unchanged tree Docker would otherwise serve the gate steps from -its cache, and the build would pass having run no test and no linter. Go's build -cache is kept between builds on the steps that compile, so only what changed is -compiled again; the tests run with `-count=1`, so none reports a stored result. -Every run downloads the Go modules again and needs the network. +Every `docker build` in `script/` passes a new `CACHEBUST` build argument. In +every stage of the `Dockerfile`, `ARG CACHEBUST` comes right after the steps +that install system packages and download the Go modules, or right after `FROM` +in a stage with neither, and every step that lints, tests or compiles comes +after it, so every `RUN` step after it runs again each time. On an unchanged +tree Docker would otherwise serve the gate steps from its cache, and the build +would pass having run no test and no linter. The layers above that line stay in +Docker's build cache until the base image, their own lines, `go.mod` or `go.sum` +change, or until that cache is cleared; only then are the packages installed and +the modules downloaded again. Go's build cache is kept between builds on the +steps that compile, so only what changed is compiled again; the tests run with +`-count=1`, so none reports a stored result. `golangci-lint run` also keeps +golangci-lint's cache, and takes a package's findings from it only when the +package's files and those of the packages it imports, `go.mod`, the linters and +their settings in `.golangci.yml`, and the golangci-lint version are all +unchanged. ## Build diff --git a/REPO_POLICIES.md b/REPO_POLICIES.md index 5b24098..1067698 100644 --- a/REPO_POLICIES.md +++ b/REPO_POLICIES.md @@ -1,6 +1,6 @@ --- title: Repository Policies -last_modified: 2026-10-15 +last_modified: 2026-10-18 --- This document covers repository structure, tooling, and workflow standards. Code @@ -159,8 +159,11 @@ style conventions are in separate documents: one's findings, and a host-global lock in `$TMPDIR` makes concurrent runs exit non-zero with `parallel golangci-lint is running` — a status a caller cannot tell from real findings. Both have produced wrong verdicts in this - org, in both directions. A container has its own golangci-lint cache, its - own `TMPDIR` and a digest-pinned binary, so neither is reachable. + org, in both directions. A container has its own `TMPDIR`, so the lock is + out of reach. The lint phase does keep golangci-lint's cache between check + builds (below), but it lints every checkout at `/src`, and a finding is + taken from that cache only for the same files, settings and golangci-lint + version. - **Any build that runs checks is given a new `CACHEBUST` value.** Docker invalidates a `COPY` layer only when the copied content changes, so on an @@ -170,15 +173,21 @@ style conventions are in separate documents: id, so no two builds share a value, not even the three in one `script/cibuild`. `script/lint`, `script/test`, `script/cibuild` and `script/docker` are the four, and there is no fifth — `script/check` runs the - two gate phases and `script/fmt-check`, and builds no image of its own. Every - stage of the `Dockerfile` declares `ARG CACHEBUST` as its first line after - `FROM`, and a new value reruns every `RUN` step after that line; `COPY` steps - are compared by content and need nothing. A stage without the `ARG` line is - served from cache on an unchanged tree, so a repository re-vendors the scripts - and adds the `ARG` lines in one commit. The scripts do not pass `--no-cache`: - it reruns every step too, but it also empties every cache mount, and Go's - build cache, which the canonical Go `Dockerfile` below mounts so that compiled - packages survive between check builds, would start empty every time. A bare + two gate phases and `script/fmt-check`, and builds no image of its own. In + every stage of the `Dockerfile`, `ARG CACHEBUST` comes right after the steps + that install system packages and download Go's modules, or right after `FROM` + in a stage with neither, and every step that lints, tests or compiles comes + after it. A step that installs anything else as well, such as a + `script/bootstrap` that also installs node packages, comes after it too. A new + value reruns every `RUN` step after that line; `COPY` steps are compared by + content and need nothing. Docker keeps the layers above the line until the + base image, their own lines or the files they copy change. A stage without the + `ARG` line is served from cache on an unchanged tree, so a repository + re-vendors the scripts and adds the `ARG` lines in one commit. The scripts do + not pass `--no-cache`: it reruns every step too, but it also builds the layers + above the line again and empties every cache mount, so Go's build cache and + golangci-lint's, which the canonical Go `Dockerfile` below mounts so that they + survive between check builds, would start empty every time. A bare `docker build .` is not evidence that anything ran: a sub-second build reporting success is a cache hit, not a result. Never invalidate by pruning — `docker builder prune` and friends destroy a build cache shared with every @@ -194,19 +203,25 @@ style conventions are in separate documents: `Dockerfile`: ```dockerfile - # Every stage declares ARG CACHEBUST first: script/ passes a new value - # on every build, which reruns every RUN step after it. The steps that - # compile mount Go's build cache, which survives from build to build. + # In every stage ARG CACHEBUST comes right after the steps that install + # system packages and download Go's modules, or right after FROM in a + # stage with neither, and every step that lints, tests or compiles + # comes after it. script/ passes a new value on every build, which + # reruns every RUN step after it. Docker keeps the layers above it + # until the base image, their own lines or go.mod and go.sum change. + # The steps that compile mount Go's build cache, and golangci-lint run + # also mounts golangci-lint's; both survive from build to build. # Lint phase # golangci/golangci-lint:v2.x.x, YYYY-MM-DD FROM golangci/golangci-lint@sha256:... AS lint - ARG CACHEBUST WORKDIR /src COPY go.mod go.sum ./ RUN go mod download + ARG CACHEBUST COPY . . RUN --mount=type=cache,target=/root/.cache/go-build \ + --mount=type=cache,target=/root/.cache/golangci-lint \ golangci-lint run --config .golangci.yml ./... # Test phase. -race needs cgo and so a C compiler, which the Debian Go @@ -214,10 +229,10 @@ style conventions are in separate documents: # cache also holds test results, which go test would otherwise replay. # golang:1.x, YYYY-MM-DD FROM golang@sha256:... AS test - ARG CACHEBUST WORKDIR /src COPY go.mod go.sum ./ RUN go mod download + ARG CACHEBUST COPY . . RUN --mount=type=cache,target=/root/.cache/go-build \ go test -count=1 -timeout 90s -race -cover ./... || \ @@ -225,19 +240,19 @@ style conventions are in separate documents: go test -count=1 -timeout 90s -race -v ./...; exit 1; } # Build stage. Nothing is wanted from either phase above; the copies - # are what make BuildKit build them first, so this stage cannot run - # unless lint and test passed. + # are what make BuildKit build them first, so nothing after them can + # run unless lint and test passed. # golang:1.x-alpine, YYYY-MM-DD FROM golang@sha256:... AS builder - ARG CACHEBUST - COPY --from=lint /src/go.sum /dev/null - COPY --from=test /src/go.sum /dev/null RUN apk add --no-cache git - # A tar-stream context keeps the sender's file owners, which git refuses. - RUN git config --system --add safe.directory /src WORKDIR /src COPY go.mod go.sum ./ RUN go mod download + ARG CACHEBUST + COPY --from=lint /src/go.sum /dev/null + COPY --from=test /src/go.sum /dev/null + # A tar-stream context keeps the sender's file owners, which git refuses. + RUN git config --system --add safe.directory /src COPY . . # The VERSION build arg when one is given, otherwise @@ -274,16 +289,26 @@ style conventions are in separate documents: - Keep the runtime stage last, and if you add a stage after it, give it the same two copies. A plain `docker build .` builds the last stage's chain and nothing else. - - Only Go's build cache is mounted (`/root/.cache/go-build`, where Go keeps - it for root), and only on the steps that compile: `golangci-lint run`, - both `go test` runs and `go build`. It keeps compiled packages between - check builds, and Go reuses one only when all its inputs are unchanged, so - it saves the compile without skipping a check. Nothing else is kept: - golangci-lint's own cache would replay stored findings in place of a lint - run, and Go builds from whatever files a kept module cache holds without - checking them again (only `go mod verify` does), so a file changed there - would go unnoticed. Go's build cache also holds test results, which is why - both `go test` runs carry `-count=1`. + - Check builds keep these, and none of them can hand back a stale result: + - The layers above `ARG CACHEBUST`: the system packages and Go's + modules. Docker installs the packages again when the base image or the + install line changes, and downloads the modules again when `go.mod` or + `go.sum` changes. Go checks every module against `go.sum` as it + downloads it, and no later build can change a kept layer. The modules + are kept in a layer rather than a cache mount because a cache mount is + shared by every build on the host, and Go builds from whatever files + it holds without checking them again (only `go mod verify` does), so a + file changed there would go unnoticed. + - Go's build cache (`/root/.cache/go-build`, where Go keeps it for + root), mounted on the steps that compile: `golangci-lint run`, both + `go test` runs and `go build`. Go reuses a compiled package only when + all its inputs are unchanged. The cache also holds test results, which + is why both `go test` runs carry `-count=1`. + - golangci-lint's cache (`/root/.cache/golangci-lint`, where the pinned + image keeps it), mounted on `golangci-lint run`. golangci-lint reuses + a package's findings only when the package's files and those of every + package it imports, `go.mod`, the linters and their settings in + `.golangci.yml`, and the golangci-lint version are all unchanged. - If the project uses `//go:embed` directives that reference build artifacts (e.g. a web frontend compiled in a separate stage), the lint phase must create placeholder files so the embed directives resolve. Example: @@ -292,12 +317,20 @@ style conventions are in separate documents: in the lint phase. The `golangci/golangci-lint` image is Debian-based and has no `apk`, so install with `apt-get` under the Debian package name (`libvips-dev`, where alpine says `vips-dev`), and delete the package - lists in the same `RUN`, so the layer does not keep them: + lists in the same `RUN`, so the layer does not keep them. The test phase, + on the Debian Go image, installs the libraries its tests need the same + way. Either install goes right after `FROM`, above `ARG CACHEBUST`, so + Docker keeps it until the base image or the install line changes: ```dockerfile + FROM golangci/golangci-lint@sha256:... AS lint RUN apt-get update \ && apt-get install -y --no-install-recommends libvips-dev \ && rm -rf /var/lib/apt/lists/* + WORKDIR /src + COPY go.mod go.sum ./ + RUN go mod download + ARG CACHEBUST ``` - `.dockerignore` lets `.git` into the build context. It keeps out every git diff --git a/TODO.md b/TODO.md index 9096660..4dd4dff 100644 --- a/TODO.md +++ b/TODO.md @@ -29,6 +29,15 @@ # Completed Steps +- re-vendor `REPO_POLICIES.md` and the four scripts that pass `CACHEBUST` from + `sneak/prompts` `next` at `0653579`: in the `lint`, `test` and `builder` + stages of the `Dockerfile` the module download, and in `builder` the + system-package install, now come before `ARG CACHEBUST`, so Docker keeps them + until the base image, the install line, `go.mod` or `go.sum` changes, and + every step that lints, tests or compiles still comes after it; + `golangci-lint run` also keeps golangci-lint's cache. README says the same + (2026-10-18, https://git.eeqj.de/sneak/sfdupes/issues/109) + - releases until 1.0 are `v0.0.N` tags on `main`'s tip, so `go install sneak.berlin/go/sfdupes@latest` installs `main`'s tip once it has passed the build; README "Install" says so, says what `@main` and `v0.0.1` @@ -154,7 +163,11 @@ and the build stage installs `git` and `make` itself; a new push cancels the workflow's older run on the same branch, and a run stops after 20 minutes; `.claude/settings.json` is deleted (2026-10-15, - https://git.eeqj.de/sneak/sfdupes/issues/95) + https://git.eeqj.de/sneak/sfdupes/issues/95). Since + https://git.eeqj.de/sneak/sfdupes/issues/109 the module download in `lint`, + `test` and the build stage, and the install of `git` and `make` in the build + stage, come before `ARG CACHEBUST`, and Docker keeps them between builds; + every step that lints, tests or compiles still runs on every build - with `-x`, an operand under another operand is walked on its own instead of being dropped when a directory from it (from its directory, for a regular @@ -355,9 +368,9 @@ a `CHECK_EPOCH` build argument; since https://git.eeqj.de/sneak/sfdupes/issues/95 every `docker build` in `script/` passes a new `CACHEBUST` value instead, which every stage of the `Dockerfile` - declares first. Run as root, the tests fail - `TestScanHardlinkRunFailsTogether`, because root reads through the `chmod(0)` - the test relies on, so the `test` phase runs them as `nobody` + declares before every step that lints, tests or compiles. Run as root, the + tests fail `TestScanHardlinkRunFailsTogether`, because root reads through the + `chmod(0)` the test relies on, so the `test` phase runs them as `nobody` - check the installed golangci-lint version in `script/bootstrap` instead of only its presence (2026-08-09, branch `bootstrap-version-check`, closes https://git.eeqj.de/sneak/sfdupes/issues/24): the version lives only in diff --git a/script/cibuild b/script/cibuild index 66fcca0..2656771 100755 --- a/script/cibuild +++ b/script/cibuild @@ -2,11 +2,12 @@ # 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. -# A new CACHEBUST value reruns every RUN step, since a cached gate phase -# is a check that did not run; unlike --no-cache, it keeps Go's build cache. +# A new CACHEBUST value reruns every RUN step after the ARG CACHEBUST +# line, since a cached gate phase is a check that did not run; unlike +# --no-cache, it keeps the layers above that line and the cache mounts. # This relies on every stage of the Dockerfile declaring ARG CACHEBUST -# first; a stage without that line is served from cache on an unchanged -# tree, with no warning. +# before every step that lints, tests or compiles; a stage without that +# line is served from cache on an unchanged tree, with no warning. set -eu SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)" diff --git a/script/docker b/script/docker index 360037a..cc00d9c 100755 --- a/script/docker +++ b/script/docker @@ -1,11 +1,12 @@ #!/bin/sh # script/docker: build the Docker image tagged with the project name. # Identical in all repos; the tag comes from script/projectname. -# A new CACHEBUST value reruns every RUN step, since a cached gate phase -# is a check that did not run; unlike --no-cache, it keeps Go's build cache. +# A new CACHEBUST value reruns every RUN step after the ARG CACHEBUST +# line, since a cached gate phase is a check that did not run; unlike +# --no-cache, it keeps the layers above that line and the cache mounts. # This relies on every stage of the Dockerfile declaring ARG CACHEBUST -# first; a stage without that line is served from cache on an unchanged -# tree, with no warning. +# before every step that lints, tests or compiles; a stage without that +# line is served from cache on an unchanged tree, with no warning. set -eu SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)" diff --git a/script/lint b/script/lint index c4c459e..451a067 100755 --- a/script/lint +++ b/script/lint @@ -5,11 +5,13 @@ # make its answer untrustworthy. # # The phase is not the last stage in the file, so it is built only when -# --target names it. A new CACHEBUST value reruns every RUN step, since -# a cached lint layer is a lint that did not run; unlike --no-cache, it -# keeps Go's build cache. This relies on every stage of the Dockerfile -# declaring ARG CACHEBUST first; a stage without that line is served -# from cache on an unchanged tree, with no warning. +# --target names it. A new CACHEBUST value reruns every RUN step after +# the ARG CACHEBUST line, since a cached lint layer is a lint that did +# not run; unlike --no-cache, it keeps the layers above that line and +# the cache mounts. This relies on every stage of the Dockerfile +# declaring ARG CACHEBUST before every step that lints, tests or +# compiles; a stage without that line is served from cache on an +# unchanged tree, with no warning. # --output type=cacheonly writes no image, since nothing uses one. set -eu diff --git a/script/test b/script/test index a56c4a1..1622a11 100755 --- a/script/test +++ b/script/test @@ -3,11 +3,12 @@ # 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, and a new CACHEBUST value because a cached test layer is a test -# that did not run; unlike --no-cache, it keeps Go's build cache. This -# relies on every stage of the Dockerfile declaring ARG CACHEBUST first; -# a stage without that line is served from cache on an unchanged tree, -# with no warning. --output type=cacheonly writes no image, since -# nothing uses one. +# that did not run; unlike --no-cache, it keeps the layers above the ARG +# CACHEBUST line and the cache mounts. This relies on every stage of the +# Dockerfile declaring ARG CACHEBUST before every step that lints, tests +# or compiles; a stage without that line is served from cache on an +# unchanged tree, with no warning. --output type=cacheonly writes no +# image, since nothing uses one. set -eu SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"