From 17b6b8432250a6bd91401e76d4671a10376a6c95 Mon Sep 17 00:00:00 2001 From: clawbot <35+clawbot@noreply.example.org> Date: Tue, 6 Oct 2026 08:25:03 +0200 Subject: [PATCH] Bring the repo up to the standard layout (closes #1) Vendors .gitignore, .dockerignore, .editorconfig, REPO_POLICIES.md, script/cibuild, script/docker, script/lint, script/test and the CI workflow byte-identical from sneak/prompts commit cc440118c876; the two ignore files then add this repo's own build output, root-anchored so cmd/bsdaily/ stays in. The Dockerfile gains a lint phase on the golangci-lint image already pinned and a test phase on the Debian Go image with sqlite3 and zstd; the build stage copies a file from each, so a plain docker build cannot skip them. Nothing installs golangci-lint on the host. On apt, script/bootstrap refreshes the package lists once before its first install. .golangci.yml and the lint cleanup: https://git.eeqj.de/sneak/bsdaily/issues/6 Model: opus-5-5 --- .dockerignore | 79 +++++++ .editorconfig | 18 ++ .gitea/workflows/check.yml | 19 +- .gitignore | 58 +++++ Dockerfile | 51 +++-- Makefile | 1 - README.md | 29 ++- REPO_POLICIES.md | 455 ++++++++++++++++++++++++++++++------- TODO.md | 15 +- script/bootstrap | 17 +- script/cibuild | 26 ++- script/docker | 15 +- script/lint | 21 +- script/test | 23 +- 14 files changed, 668 insertions(+), 159 deletions(-) create mode 100644 .dockerignore create mode 100644 .editorconfig create mode 100644 .gitignore diff --git a/.dockerignore b/.dockerignore new file mode 100644 index 0000000..852aa9d --- /dev/null +++ b/.dockerignore @@ -0,0 +1,79 @@ +# .dockerignore does NOT use .gitignore semantics. Docker matches with +# moby/patternmatcher: filepath.Match plus `**`, so `*` does not cross +# `/` and an unprefixed pattern is anchored at the context root. Every +# depth-independent pattern therefore needs `**/`, or `config/.env` and +# `certs/server.key` still ship while this file reads as solved. Only +# genuinely root-anchored entries go unprefixed. Never transplant these +# into .gitignore, where `**/` is wrong. +# +# Matching is case-sensitive, so secrets use character ranges rather +# than an ALL-CAPS twin, which would still miss `Server.Key`. +# +# Extend with this repo's own host-built artifacts, written anchored: +# `/myapp`, never `**/myapp`, which also matches `cmd/myapp/` and +# deletes the package directory from the context. + +# .git is sent without its config. Without a VERSION build argument the +# stage that compiles runs `git describe --tags --always` on .git, which +# does not need .git/config; that file can hold a credential, such as a +# password in a remote URL or the token the CI checkout step stores there. +# Each submodule keeps a config with the same exposure in its git directory +# under .git/modules/, nested again for a submodule's own submodules, or in +# its own .git directory when it keeps one. +# KNOWN GAP: a submodule whose name has a `config` segment (`config`, +# `deploy/config`, `config/lib`) loses its whole git directory, because +# `**/.git/modules/**/config` also matches that segment's directory +# under .git/modules/. Go's version stamping then fails the build; +# nothing leaks. Name such a submodule without that segment: +# `git submodule add --name`. +**/.git/config +**/.git/modules/**/config + +# Agent scratch: one full checkout of the repo per in-flight agent. +# Anchored because it occurs once where agents run at the repo root. +# KNOWN GAP: a repo running agents in subdirectories still ships +# `services/api/.claude/` and must add its own anchored entry. +.claude + +# Environment files. `*.env` covers bare `.env` and the `prod.env` +# convention. Re-include a committed template with a negation if the +# build needs one: `!docs/example.env`. +**/*.[eE][nN][vV] +**/.[eE][nN][vV].* +**/.[eE][nN][vV][rR][cC] + +# Private keys and the bundles carrying them. Public certificates +# (*.crt, *.cer) are deliberately absent: they are legitimate inputs. +**/*.[pP][eE][mM] +**/*.[kK][eE][yY] +**/*.[pP]12 +**/*.[pP][fF][xX] +**/[iI][dD]_[rR][sS][aA] +**/[iI][dD]_[dD][sS][aA] +**/[iI][dD]_[eE][cC][dD][sS][aA] +**/[iI][dD]_[eE][cC][dD][sS][aA]_[sS][kK] +**/[iI][dD]_[eE][dD]25519 +**/[iI][dD]_[eE][dD]25519_[sS][kK] + +# Dependencies: restored inside the image, never copied in. +**/node_modules + +# OS metadata. +**/.DS_Store +**/Thumbs.db + +# Editor state: never a build input, and it churns COPY. +**/*.swp +**/*.swo +**/*~ +**/*.bak +**/.idea +**/.vscode +**/*.sublime-* + +# This repo's host-built artifacts: `make`, `go test -c` and +# `make test-coverage`. +/bsdaily +/*.test +/coverage.out +/coverage.html diff --git a/.editorconfig b/.editorconfig new file mode 100644 index 0000000..de84fae --- /dev/null +++ b/.editorconfig @@ -0,0 +1,18 @@ +root = true + +[*] +indent_style = space +indent_size = 4 +end_of_line = lf +charset = utf-8 +trim_trailing_whitespace = true +insert_final_newline = true + +[Makefile] +indent_style = tab + +[*.go] +indent_style = tab + +# This repository's own sections, such as one for another language it +# uses, go below this comment, and a re-vendor keeps them. diff --git a/.gitea/workflows/check.yml b/.gitea/workflows/check.yml index 0a914ad..ee73864 100644 --- a/.gitea/workflows/check.yml +++ b/.gitea/workflows/check.yml @@ -1,14 +1,9 @@ name: check -on: - push: - branches: [main] - pull_request: - branches: [main] +on: [push] jobs: - check: - runs-on: ubuntu-latest - steps: - # actions/checkout v4, 2024-09-16 - - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 - - name: Build and check - run: script/cibuild + check: + runs-on: ubuntu-latest + steps: + # actions/checkout v4.2.2, 2026-02-22 + - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 + - run: script/cibuild diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..6260843 --- /dev/null +++ b/.gitignore @@ -0,0 +1,58 @@ +# OS +.DS_Store +Thumbs.db + +# Editors +*.swp +*.swo +*~ +*.bak +.idea/ +.vscode/ +*.sublime-* + +# Agent scratch (worktrees of this repo, created and destroyed by +# in-flight tooling). Unanchored: .gitignore patterns already match at +# every depth, so no prefix is wanted here. This is not a .dockerignore +# entry and must not be given a `**/` prefix on the way into one. +.claude/ + +# Node +node_modules/ + +# Secrets. Unanchored like every entry above, so each matches at every +# depth. Matching is case-sensitive on Linux, so names use character +# ranges rather than a lowercase form that misses `Server.Key`. + +# Environment files. `*.env` covers bare `.env` and the `prod.env` +# convention. Only the templates `example.env` and `sample.env` are +# re-included below. A repository that commits any other template adds +# its own negation at the end of this file, for example `!.env.example`. +*.[eE][nN][vV] +.[eE][nN][vV].* +.[eE][nN][vV][rR][cC] +!example.env +!sample.env + +# Private keys and the bundles carrying them. +*.[pP][eE][mM] +*.[kK][eE][yY] +*.[pP]12 +*.[pP][fF][xX] +[iI][dD]_[rR][sS][aA] +[iI][dD]_[dD][sS][aA] +[iI][dD]_[eE][cC][dD][sS][aA] +[iI][dD]_[eE][cC][dD][sS][aA]_[sS][kK] +[iI][dD]_[eE][dD]25519 +[iI][dD]_[eE][dD]25519_[sS][kK] + +# This repository's own entries, such as its build outputs, go below +# this comment, and a re-vendor keeps them. Anchor a binary built at the +# root: `/myapp`, never `myapp`, which also ignores `cmd/myapp/`. + +# Go: logs, test binaries, coverage output, and the binary `make` builds. +*.log +*.test +*.out +/coverage.html +/bsdaily diff --git a/Dockerfile b/Dockerfile index 6104a62..85f283b 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,9 +1,9 @@ -# Lint stage -# golangci/golangci-lint:v2.12.2-alpine +# Lint phase. The linter is invoked directly rather than through `make +# lint` or `script/lint`, which are themselves a docker build and would +# recurse into a daemon that does not exist in a build step. +# golangci/golangci-lint:v2.12.2-alpine, 2026-06-28 FROM golangci/golangci-lint:v2.12.2-alpine@sha256:91b27804074a0bacea298707f016911e60cf0cdbc6c7bf5ccacb5f0606d18d60 AS lint -RUN apk add --no-cache make build-base - WORKDIR /src # Copy go mod files first for better layer caching @@ -13,22 +13,42 @@ RUN go mod download # Copy source code COPY . . -# Run formatting check and linter -RUN make fmt-check -RUN make lint +RUN golangci-lint run ./... -# Build stage -# golang:1.26.4-alpine +# Test phase, invoking `go test` directly for the same reason. -race +# needs cgo and so a C compiler, which the Debian Go image ships and the +# alpine one does not. The tool shells out to sqlite3, zstdmt and +# zstdcat, so tests that run it need them installed. +# golang:1.26.4-trixie, 2026-10-05 +FROM golang:1.26.4-trixie@sha256:68b7145ec43d1820b9a56704554b53d1520aa2a15cb5233e374188a31b2a1bce AS test + +RUN apt-get update \ + && apt-get install -y --no-install-recommends sqlite3 zstd \ + && rm -rf /var/lib/apt/lists/* + +WORKDIR /src + +COPY go.mod go.sum ./ +RUN go mod download + +COPY . . + +RUN go test -timeout 90s -race -cover ./... || \ + { echo "--- Rerunning with -v for details ---"; \ + go test -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. A plain `docker build .` builds only the +# last stage and what it depends on, so the runtime stage stays last. +# golang:1.26.4-alpine, 2026-06-28 FROM golang:1.26.4-alpine@sha256:3ad57304ad93bbec8548a0437ad9e06a455660655d9af011d58b993f6f615648 AS builder -# Depend on lint stage passing COPY --from=lint /src/go.sum /dev/null +COPY --from=test /src/go.sum /dev/null ARG VERSION=dev -# Install build deps plus the sqlite3 and zstd CLIs the tests/tool shell out to -RUN apk add --no-cache make build-base sqlite zstd - WORKDIR /src # Copy go mod files first for better layer caching @@ -38,14 +58,11 @@ RUN go mod download # Copy source code COPY . . -# Run tests -RUN make test - # Build (pure Go, no CGO required since we use modernc.org/sqlite) RUN CGO_ENABLED=0 go build -o /bsdaily ./cmd/bsdaily # Runtime stage -# alpine:3.21 +# alpine:3.21, 2026-06-28 FROM alpine:3.21@sha256:48b0309ca019d89d40f670aa1bc06e426dc0931948452e8491e3d65087abc07d # bsdaily shells out to sqlite3, zstdmt, zstdcat at runtime diff --git a/Makefile b/Makefile index 04ff721..47c8845 100644 --- a/Makefile +++ b/Makefile @@ -46,7 +46,6 @@ clean: # Install dependencies. deps: go mod download - go install github.com/golangci/golangci-lint/cmd/golangci-lint@latest # Run tests with coverage. test-coverage: diff --git a/README.md b/README.md index f8defea..3888c6e 100644 --- a/README.md +++ b/README.md @@ -53,27 +53,34 @@ standard: normalized scripts in `script/` are the entrypoints for the development workflow, and the Makefile targets are thin shims that call them. We provide: -- `script/bootstrap` — install all development dependencies (go, - golangci-lint, Go module download) +- `script/bootstrap` — install all development dependencies (go, Go + module download); the linter is not installed on the host - `script/setup` — make a fresh clone ready for development: runs `script/bootstrap`, then `script/install-precommit` - `script/projectname` — print the project name (used for the Docker - image tag) -- `script/test` — run the test suite (verbose rerun on failure) -- `script/lint` — run `golangci-lint run ./...` -- `script/fmt` — format all code (writes) -- `script/fmt-check` — check formatting (read-only) + image tags) +- `script/test` — build the Dockerfile's `test` phase, which runs the + test suite with `-race` (verbose rerun on failure) +- `script/lint` — build the Dockerfile's `lint` phase, which runs + `golangci-lint run ./...` +- `script/fmt` — format the Go code with `go fmt` (writes) +- `script/fmt-check` — check the Go formatting with `gofmt` (read-only) - `script/check` — run `script/test`, `script/lint`, and `script/fmt-check` - `script/docker` — build the Docker image tagged via + `script/projectname`; the build runs the `lint` and `test` phases + first +- `script/cibuild` — CI entrypoint: runs `script/bootstrap` and + `script/check`, then builds the Docker image tagged via `script/projectname` -- `script/cibuild` — CI entrypoint: `docker build .` (the Dockerfile - runs the checks) -- `script/precommit` — pre-commit gate: `go mod tidy` + `go fmt` (must - not change files), then `script/check` +- `script/precommit` — pre-commit gate: `go mod tidy` (must not change + `go.mod` or `go.sum`) and `go fmt`, then `script/check` - `script/install-precommit` — install the git pre-commit hook that runs `script/precommit` +Every Docker build in `script/` is uncached, so the `lint` and `test` +phases always run rather than being served from the build cache. + # Problem Statement A Bluesky firehose ingester writes every observed post (and associated diff --git a/REPO_POLICIES.md b/REPO_POLICIES.md index bc2f161..c72195c 100644 --- a/REPO_POLICIES.md +++ b/REPO_POLICIES.md @@ -1,6 +1,6 @@ --- title: Repository Policies -last_modified: 2026-07-06 +last_modified: 2026-10-06 --- This document covers repository structure, tooling, and workflow standards. Code @@ -60,17 +60,28 @@ style conventions are in separate documents: prerequisite since nvm requires bash. yarn is then pinned via `corepack prepare yarn@ --activate`. Never install "latest" or "lts"; always exact versions. `script/cibuild` runs the CI build: it changes to the - repo root and runs `docker build .`; the Gitea workflow calls it. Four further - scripts are our own extensions to the standard: `script/check` runs - `script/test`, `script/lint`, and `script/fmt-check`; `script/precommit` is - what the git pre-commit hook runs, and it calls `script/check`; - `script/install-precommit` installs the git pre-commit hook (the `make hooks` - target shims to it); and `script/projectname` (literally that filename) simply - outputs the project's name. Scripts that need the name call - `script/projectname` — e.g. `script/docker` assembles its image tag from it — - so those scripts stay byte-identical across all repos. Repo-type-specific - pre-commit extras (e.g. `go mod tidy` verification in Go repos) belong in - `script/precommit`, not in the hook itself. Model scripts are at + repo root, runs `script/bootstrap`, runs `script/check`, and builds the image + with the version; the Gitea workflow calls it. **`script/cibuild` runs + `script/bootstrap` first**, because the workflow checks out the repo and runs + nothing else, while `script/fmt-check` runs the formatter on the host: on a + pristine checkout with nothing installed the run dies there, after the + containerised gates have passed. **The bootstrap alone is not enough**: + `script/bootstrap` installs node and yarn under nvm and leaves neither on the + `PATH` of the shell that called it, so a bare `yarn` still exits 127. The host + entrypoints that need yarn — `script/fmt` and `script/fmt-check` — therefore + source nvm for the pinned node version before invoking it, exactly as + `script/bootstrap`'s own install step does. A runner carrying nothing but + docker and git then gets through `script/check`. Four further scripts are our + own extensions to the standard: `script/check` runs `script/test`, + `script/lint` and `script/fmt-check`; `script/precommit` is what the git + pre-commit hook runs, and it calls `script/check`; `script/install-precommit` + installs the git pre-commit hook (the `make hooks` target shims to it); and + `script/projectname` (literally that filename) simply outputs the project's + name. Scripts that need the name call `script/projectname` — e.g. + `script/docker` assembles its image tag from it — so those scripts stay + byte-identical across all repos. Repo-type-specific pre-commit extras (e.g. + `go mod tidy` verification in Go repos) belong in `script/precommit`, not in + the hook itself. Model scripts are at `https://git.eeqj.de/sneak/prompts/raw/branch/main/script/`. The README must document the provided scripts in an **Entrypoints** section (see the README requirements below). @@ -89,87 +100,201 @@ style conventions are in separate documents: contributor should be able to understand the entire development workflow by reading the Makefile. -- Every repo should have a `Dockerfile`. All Dockerfiles must run `make check` - as a build step so the build fails if the branch is not green. For non-server - repos, the Dockerfile should bring up a development environment and run - `make check`. For server repos, `make check` should run as an early build - stage before the final image is assembled. Dockerfiles install development - prerequisites by running `script/bootstrap` rather than duplicating installs - inline; COPY `script/` and the dependency manifests (`package.json` + - `yarn.lock`, `go.mod` + `go.sum`, etc.) before running it so the bootstrap - layer stays cached until dependencies change. +- Every repo should have a `Dockerfile`, and it carries the repo's gates: a + `lint` phase and a `test` phase, with the final stage depending on both so the + image cannot be built unless they pass. For non-server repos the final stage + brings up a development environment; for server repos it is the runtime image. + The gate phases and the build stage start from their pinned base images and + install what those images lack either inline, as the canonical Go `Dockerfile` + below does for `git`, or by running `script/bootstrap`, as the `prompts` + repo's own `Dockerfile` does for its yarn packages. The development + environment stage installs development prerequisites by running + `script/bootstrap` rather than duplicating its installs inline. A stage that + runs `script/bootstrap` COPYs `script/` and the dependency manifests + (`package.json` + `yarn.lock`, `go.mod` + `go.sum`, etc.) before running it. -- **Dockerfiles must use a separate lint stage for fail-fast feedback.** Go - repos use a multistage build where linting runs in an independent stage based - on the `golangci/golangci-lint` image (pinned by hash). This stage runs - `make fmt-check` and `make lint` before the full build begins. The build stage - then declares an explicit dependency on the lint stage via - `COPY --from=lint /src/go.sum /dev/null`, which forces BuildKit to complete - linting before proceeding to compilation and tests. This ensures lint failures - surface in seconds rather than minutes, without blocking on dependency - download or compilation in the build stage. +- **Linting and testing run in Docker, as phases of the `Dockerfile`.** There is + no separate lint file. `script/lint` and `script/test` each build one phase + and nothing else: - The standard pattern for a Go repo Dockerfile is: + ```sh + tag="$(script/projectname)" + docker build --no-cache --target lint -t "$tag-lint" . + docker build --no-cache --target test -t "$tag-test" . + ``` + + **A stage that is not the last one in the file is built only when the final + stage's chain depends on it, or when `--target` names it.** That is why the + two gates are always invoked by name here, and why the final stage carries a + `COPY --from=` of a harmless file from each of them: without that edge a + plain `docker build .` builds the last stage alone and exits 0 having linted + and tested nothing. + + **Every `docker build` in `script/` is tagged**, here and in + `script/cibuild` and `script/docker`. An untagged build leaves a dangling + image behind on every invocation, on every developer host and every CI + runner; a tagged one replaces the previous image. Each script assigns the + tag on its own line before the build, so `set -e` stops it where + `script/projectname` fails. + + Inside a phase the tool is invoked directly — `golangci-lint`, `go test`, + `eslint`, `prettier` — never through `make lint` or `script/test`, which are + themselves a `docker build` and would recurse into a daemon that does not + exist in a build step. Formatting is the exception and stays on the host: + `script/fmt` writes the working tree, and `script/fmt-check` is its + read-only twin. + + **No lint verdict may come from a host invocation of the linter.** On a + shared host golangci-lint reads a result cache keyed on file content rather + than location, so a second checkout of the same content is served the first + one's findings, and a host-global lock in `$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 cache, its own `TMPDIR` and + a digest-pinned binary, so neither is reachable. + +- **Any build that runs checks is built with `--no-cache`.** Docker invalidates + a `COPY` layer only when the copied content changes, so on an unchanged tree + the check `RUN` is served from cache, nothing executes, and the build still + exits 0. Every `docker build` in `script/` therefore passes `--no-cache`: + `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. 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 other build on the host. + When a check is added or changed, prove it works by planting a defect it must + catch and watching the run fail on it, then revert the defect. A green run + alone shows neither that the check ran nor that it covers what it should. + +- **The gate phases are separate stages, and the build stage depends on both.** + The lint phase is based on the `golangci/golangci-lint` image (pinned by + hash), so lint failures surface in seconds rather than after a full compile, + and the test phase is based on the Debian Go image. The canonical Go repo + `Dockerfile`: ```dockerfile - # Lint stage — fast feedback on formatting and lint issues + # Lint phase # golangci/golangci-lint:v2.x.x, YYYY-MM-DD FROM golangci/golangci-lint@sha256:... AS lint WORKDIR /src COPY go.mod go.sum ./ RUN go mod download COPY . . - RUN make fmt-check - RUN make lint + RUN golangci-lint run --config .golangci.yml ./... - # Build stage - # golang:1.x-alpine, YYYY-MM-DD - FROM golang@sha256:... AS builder + # Test phase. -race needs cgo and so a C compiler, which the Debian Go + # image ships and the alpine one does not. + # golang:1.x, YYYY-MM-DD + FROM golang@sha256:... AS test WORKDIR /src - - # Force BuildKit to run the lint stage before proceeding - COPY --from=lint /src/go.sum /dev/null - COPY go.mod go.sum ./ RUN go mod download COPY . . - RUN make test + RUN go test -timeout 90s -race -cover ./... || \ + { echo "--- Rerunning with -v for details ---"; \ + go test -timeout 90s -race -v ./...; exit 1; } - ARG VERSION=dev - RUN CGO_ENABLED=0 go build -trimpath \ - -ldflags="-s -w -X main.Version=${VERSION}" \ - -o /app ./cmd/app/ + # Build stage. Nothing is wanted from either phase above; the copies + # are what make BuildKit build them first, so this stage cannot run + # unless lint and test passed. + # golang:1.x-alpine, YYYY-MM-DD + FROM golang@sha256:... AS builder + COPY --from=lint /src/go.sum /dev/null + COPY --from=test /src/go.sum /dev/null + RUN apk add --no-cache git + # A tar-stream context keeps the sender's file owners, which git refuses. + RUN git config --system --add safe.directory /src + WORKDIR /src + COPY go.mod go.sum ./ + RUN go mod download + COPY . . - # Runtime stage + # The VERSION build arg when one is given, otherwise + # `git describe --tags --always` on the .git in the build context. With + # .git present, a version that is still empty, dev or unknown fails the + # build: git is missing or could not read the checkout. + ARG VERSION + RUN VERSION="${VERSION:-$(git describe --tags --always)}"; \ + if [ -e .git ]; then \ + case "$VERSION" in ""|dev|unknown) \ + echo "version is '$VERSION' although .git is present" >&2; \ + exit 1 ;; \ + esac; \ + fi; \ + CGO_ENABLED=0 go build -trimpath \ + -ldflags="-s -w -X main.Version=${VERSION}" \ + -o /app ./cmd/app/ + + # Runtime stage, and the last one FROM alpine@sha256:... COPY --from=builder /app /usr/local/bin/app ENTRYPOINT ["app"] ``` Key points: - - The lint stage uses the `golangci/golangci-lint` image directly (it - includes both Go and the linter), so there is no need to install the - linter separately. - - `COPY --from=lint /src/go.sum /dev/null` is a no-op file copy that creates - a stage dependency. BuildKit runs stages in parallel by default; without - this line, the build stage would not wait for lint to finish and a lint - failure might not fail the overall build. + - The lint phase uses the `golangci/golangci-lint` image directly (it has + both Go and the linter), so nothing needs installing. + - `COPY --from= /src/go.sum /dev/null` is a no-op copy whose only + purpose is the ordering edge. BuildKit runs stages in parallel by default, + and a stage nothing depends on is not built at all, so without these two + lines a red gate would not fail the build. + - 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. - If the project uses `//go:embed` directives that reference build artifacts - (e.g. a web frontend compiled in a separate stage), the lint stage must + (e.g. a web frontend compiled in a separate stage), the lint phase must create placeholder files so the embed directives resolve. Example: `RUN mkdir -p web/dist && touch web/dist/index.html web/dist/style.css`. - The lint stage should not depend on the actual build output — it exists to - fail fast. - - If the project requires CGO or system libraries for linting (e.g. - `vips-dev`), install them in the lint stage with `apk add`. - - The build stage runs `make test` after compilation setup. Tests run in the - build stage, not the lint stage, because they may require compiled - artifacts or heavier dependencies. + - If the project requires CGO or system libraries for linting, install them + 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: + + ```dockerfile + RUN apt-get update \ + && apt-get install -y --no-install-recommends libvips-dev \ + && rm -rf /var/lib/apt/lists/* + ``` + + - `.dockerignore` lets `.git` into the build context. It keeps out every git + `config` at any depth (`**/.git/config`, `**/.git/modules/**/config`): the + repository's own, each submodule's under `.git/modules/`, and that of a + submodule keeping its own `.git` directory. `git describe` does not need + them, and each can hold a credential: a password in a remote URL, or the + token the CI checkout step stores there. A submodule whose name has a + `config` segment (`config`, `deploy/config`, `config/lib`) loses its whole + git directory to `**/.git/modules/**/config`, and Go's version stamping + then fails the build: give it a name without that segment + (`git submodule add --name`). The stage that compiles has `git` (the + Debian Go image has it; an alpine one needs `apk add --no-cache git`) and + takes the version from the `VERSION` build argument when one is given, + otherwise from `git describe --tags --always`. That gives the tag on a + tagged commit; on a later commit, the tag, the number of commits since it + and the short commit (`v1.2.3-4-gabc1234`); and the short commit when no + tag is reachable. The stage that compiles also marks its working directory + safe for git (`git config --system --add safe.directory /src`): a context + sent as a tar stream keeps the sender's file owners, and git refuses a + checkout owned by another user, so the version would come out empty. + `ARG VERSION` has no default, and the build fails if the context carries + `.git` and the version still comes out empty, `dev` or `unknown`. A plain + `docker build .` with no build arguments must succeed; a Dockerfile that + refuses an empty build argument drops that refusal and keeps the argument. - Every repo should have a Gitea Actions workflow (`.gitea/workflows/`) that - runs `script/cibuild` (which runs `docker build .`) on push. Since the - Dockerfile already runs `make check`, a successful build implies all checks - pass. + runs `script/cibuild` on push, and checks out the repo as its only other step. + That script bootstraps, runs the gate phases, and then builds the image, so a + successful run means every check passed; a bare `docker build .` does not + carry the same guarantee, because its gate phases may come from the cache. The + image build is uncached and so runs the gate phases a second time. That is the + price of the rule above, and it is worth paying: the image that ships is built + from a run of its own gates rather than from a cache entry. A separate + workflow limited to `main` by a `branches` list under `on: push` cannot be + checked by review: to try a change to it, add the feature branch to that list + and push, then remove the branch from the list again before merging. Keep any + job in it that publishes behind `if: github.ref_name == 'main'`, so the run + from the feature branch publishes nothing. - Use platform-standard formatters: `black` for Python, `prettier` for JS/CSS/Markdown/HTML, `go fmt` for Go. Always use default configuration with @@ -189,14 +314,21 @@ style conventions are in separate documents: module under test to verify it compiles/parses. There is no excuse for `make test` to be a no-op. -- `make test` must complete in under 20 seconds. Add a 30-second timeout in the - Makefile. +- `make test` must complete in under 60 seconds. That is the hard cap, and a + suite that exceeds it fails. Under 20 seconds is the target. A suite between + 20 and 60 seconds is still green, but the overage must be filed as an + improvement bug against that repo. Add a 90-second timeout to the test + invocation (`go test -timeout 90s`). The backstop deliberately sits above the + hard cap so that it catches a genuinely hung test rather than a merely slow + one. -- **`make test` should use the conditional verbose rerun pattern.** Run tests - without `-v` (verbose) first. If tests fail, automatically rerun with `-v` to - show full output. This keeps CI logs and `docker build` output clean on - success (just package/suite summaries) while providing full diagnostic detail - on failure (every test case, every assertion). The general shell pattern: +- **The test command should use the conditional verbose rerun pattern.** Run + tests without `-v` (verbose) first. If tests fail, automatically rerun with + `-v` to show full output. This keeps CI logs and `docker build` output clean + on success (just package/suite summaries) while providing full diagnostic + detail on failure (every test case, every assertion). The command lives in the + `test` phase of the `Dockerfile`, since `script/test` builds that phase; the + Makefile form below is the same pattern for any repo-local invocation: ```makefile test: @@ -209,11 +341,26 @@ style conventions are in separate documents: ```makefile test: - @go test -timeout 30s -race -cover ./... || \ + @go test -count=1 -timeout 90s -race -cover ./... || \ { echo "--- Rerunning with -v for details ---"; \ - go test -timeout 30s -race -v ./...; exit 1; } + go test -count=1 -timeout 90s -race -v ./...; exit 1; } ``` + `-count=1` is required on both invocations: it defeats Go's test _result_ + cache, so neither run can report a stored pass in place of running the + tests. It leaves the build cache alone, so it costs the runtime of the suite + and no recompilation. + + That cache is Go's own, separate from Docker's layer cache. Go stores a + passing result in its cache directory (`GOCACHE`), and when the same tests + run again on unchanged code it prints that result, marked `(cached)`, + without running them. That matters on a developer's machine, where this + target runs and the directory lasts from one run to the next. The `test` + phase of the `Dockerfile` needs no `-count=1`: its base image holds no + result for this repo's tests and nothing before its `go test` step runs a + test, so there is nothing to replay. `--no-cache` (above) is what makes that + step run on an unchanged tree. + Python example: ```makefile @@ -239,10 +386,89 @@ style conventions are in separate documents: must be in `.gitignore`. No exceptions. - `.gitignore` should be comprehensive from the start: OS files (`.DS_Store`), - editor files (`.swp`, `*~`), language build artifacts, and `node_modules/`. - Fetch the standard `.gitignore` from + editor files (`.swp`, `*~`), in-repo agent scratch directories (`.claude/`), + `node_modules/`, and the repo's own build outputs. Fetch the standard + `.gitignore` from `https://git.eeqj.de/sneak/prompts/raw/branch/main/.gitignore` when setting up - a new repo. + a new repo. A repo's `.gitignore` is the standard file followed by the repo's + own entries, such as its binaries; a re-vendor replaces the standard part and + keeps those entries. These patterns are written to `.gitignore`'s own + semantics, in which an unanchored pattern already matches at every depth; they + are not a `.dockerignore` and must not be transplanted into one unmodified. + +- **`.dockerignore` does not use `.gitignore` semantics, and copying patterns + across unmodified leaves secrets in the build context.** Docker matches with + `moby/patternmatcher`: `filepath.Match` semantics plus a `**` extension, so + `*` does not cross `/` and a pattern without a leading `**/` is anchored at + the build-context root. A `.dockerignore` listing `.env`, `*.pem` and `*.key` + therefore excludes only the copies at the repository root, while `config/.env` + and `certs/server.key` still reach the context and can land in an image layer + — which is more dangerous than a short file with no secret patterns at all, + because it reads as solved and stops anyone looking. Give every + depth-independent pattern the `**/` prefix and leave only genuinely + root-anchored entries unprefixed: `.claude`, and the repo's own host-built + binary, written `/myapp` and never `**/myapp`, which would also match + `cmd/myapp/` and delete the package directory from the context. Matching is + case-sensitive, and an ALL-CAPS twin per pattern still misses `Server.Key`, so + secret names use character ranges — `**/*.[kK][eE][yY]`, `**/*.[pP][eE][mM]`, + and likewise for `.envrc` and the extensionless SSH keys. Where such a pattern + also catches something the build needs, re-include it with a negation + (`!docs/example.env`); deleting the pattern reopens the exposure for every + other file it covers. Fetch the standard `.dockerignore` from + `https://git.eeqj.de/sneak/prompts/raw/branch/main/.dockerignore` and extend + it with the repo's own artifacts. + +- **In-repo agent scratch belongs in both files, written to each file's own + semantics.** `.claude/` holds one worktree per in-flight agent — an entire + additional checkout of the repo — so under `COPY . .` the build context + inflates by a multiple of the repo and another session's unreviewed work can + be copied into an image layer. In `.gitignore` the entry is `.claude/`, + unanchored. In `.dockerignore` it is `.claude`, anchored and with **no** `**/` + prefix, because the prefixed form would also delete any nested directory of + that name from the build. Anchoring carries a known gap that the canonical + `.dockerignore` states in its own comment, since consuming repos receive the + file and not the tracker: the directory is created in the agent's working + directory, so a repo running agents in subdirectories still ships + `services/api/.claude/` and must add its own anchored entry there. + +- **A plain `docker build .` of a clone stamps the version that + `git describe --tags --always` gives**, derived from the `.git` in the build + context as the canonical `Dockerfile` above shows. Without its failure check, + a missing `git` or an unreadable checkout would leave `-X main.Version=` empty + and the build would still exit 0. `script/docker` and `script/cibuild` pass + the version they compute on the host; it takes precedence. They do this + byte-identically across repos: + + ```sh + # The version and the tag each get their own line: a failing command + # substitution inside an argument does not trip `set -e`, so the inline + # form degrades to an empty constant. + version="$(git describe --tags --always --dirty 2>/dev/null || true)" + [ -n "$version" ] || version="unknown" + tag="$(script/projectname)" + docker build --no-cache \ + --build-arg VERSION="$version" \ + -t "$tag" . + ``` + + `--always` makes an untagged repo yield an abbreviated commit hash rather + than failing, and the `[ -n "$version" ]` line is the single place the + fallback is applied — a live check that fires on a build from an export with + no `.git` and on a repository with no commits yet. Do not fold it into the + substitution as `|| echo unknown`, which makes the guard unreachable. The + Dockerfile's side is `ARG VERSION` in the stage that compiles, declared + there because `ARG` is stage-scoped; passing `VERSION` to a repo whose + Dockerfile declares no such `ARG` is ignored and costs nothing, which is why + the scripts stay byte-identical. One consequence for CI: the standard + checkout action clones shallow and fetches no tags, so a repo that embeds a + tag-derived version must set `fetch-depth: 0` on its checkout step. + +- **Verify `.dockerignore` by enumerating the image, not by reading the + patterns.** Plant files at the root _and_ at least two directories deep, build + a probe image that does `COPY . .`, and list what actually landed + (`docker run --rm --entrypoint find IMAGE /app`). The `transferring context` + size is not a substitute: a nested secret is a few bytes, and BuildKit + transfers only the delta from the previous build. - **No build artifacts in version control.** Code-derived data (compiled bundles, minified output, generated assets) must never be committed to the @@ -258,9 +484,56 @@ style conventions are in separate documents: - Make all changes on a feature branch. You can do whatever you want on a feature branch. -- `.golangci.yml` is standardized and must _NEVER_ be modified by an agent, only - manually by the user. Fetch from - `https://git.eeqj.de/sneak/prompts/raw/branch/main/.golangci.yml`. +- `.golangci.yml` is standardized. The vendored copy in a consuming repo must + _NEVER_ be modified by an agent: fetch it from + `https://git.eeqj.de/sneak/prompts/raw/branch/main/.golangci.yml` and keep it + byte-identical, so that no repo can quietly loosen its own linting. Linter + configuration changes are made to the canonical copy in the `prompts` repo and + reach consuming repos by re-vendoring; an agent may open a PR against + canonical, which only the user merges. One list is exempt from byte-identity, + because it cannot be written once for every repo: the `deny` list of the + `test-support` depguard rule, where a repo names its own test-support packages + by full import path. A repo adds entries there and changes nothing else, and a + re-vendor carries its entries forward. The canonical golangci-lint version is + v2.14.0 (released 2026-09-24), pinned as the digest of the lint phase's base + image + (`golangci/golangci-lint@sha256:ad862ba6b3798cbe0fd9fd7408d498fd74fbd2623a92406b2fd3898faf0bf98f`, + which reports `2.14.0 built with go1.27.0 from 114493f9`). A module's `go` + directive must not name a newer Go minor version than the one golangci-lint + was built with, or golangci-lint refuses to lint it: this release lints + `go 1.27.1` but not `go 1.28`. That digest is the only pin, since no repo + installs golangci-lint on the host. A repo sets the lint phase digest to the + one named here and re-vendors `.golangci.yml` in the same commit, whichever of + the two prompted the change: the canonical copy can name linters that an older + golangci-lint rejects, and a newer golangci-lint can add linters that + `default: all` switches on until the canonical copy disables them. + +- **`script/bootstrap` installs a pinned tool by comparing versions, never by + testing presence.** An `if ! command -v ; then install; fi` guard tests + `PATH` only, so on an already-provisioned machine the pin is inert and a + version bump is a silent no-op — while the Dockerfile, installing into a clean + image, gets the pinned version, so a local `make check` and `make docker` can + disagree about what the tool even is. The canonical form: + - compares the installed version against the pin over the **whole** version + token; a parser that stops at the first `-` reports `2.12.2` for a host + running `2.12.2-rc1` and skips the install; + - treats absent, non-zero, empty or unrecognised `--version` output as a + mismatch, so the failure direction is a redundant install and never a + skipped one; + - after installing, re-resolves the binary the way callers do — `hash -r`, + then through `PATH`, not through the directory the installer wrote to — + and fails naming the resolved path, since an install that a shadowing + binary hides succeeds while changing nothing any caller sees; + - is actually called, and prints the version on both success paths: a + function defined and never invoked has the same exit status and the same + empty output as one that worked. + + Keep it POSIX sh: no arrays, no `[[`, no `grep -P`. + + A Go tool a repo needs on the host is installed with `go install` pinned to + a commit hash (`go install @`). It is never tracked as + a `go.mod` tool dependency or through a `tools.go` file, either of which + pulls the tool's own dependencies into the repo's `go.mod` and `go.sum`. - When pinning images or packages by hash, add a comment above the reference with the version and date (YYYY-MM-DD). @@ -371,15 +644,21 @@ style conventions are in separate documents: Never edit existing migrations after release. - All repos should have an `.editorconfig` enforcing the project's indentation - settings. + settings: the standard file from + `https://git.eeqj.de/sneak/prompts/raw/branch/main/.editorconfig`, which sets + tabs for `Makefile` and Go files, followed by the repo's own sections, such as + one for another language it uses. A re-vendor replaces the standard part and + keeps those sections. - Avoid putting files in the repo root unless necessary. Root should contain - only project-level config files (`README.md`, `Makefile`, `Dockerfile`, - `LICENSE`, `.gitignore`, `.editorconfig`, `REPO_POLICIES.md`, and - language-specific config). Everything else goes in a subdirectory. Canonical - subdirectory names: + only project-level config files (`README.md`, `AGENTS.md`, `Makefile`, + `Dockerfile`, `LICENSE`, `.gitignore`, `.editorconfig`, `REPO_POLICIES.md`, + and language-specific config). Everything else goes in a subdirectory. + Canonical subdirectory names: - `bin/` — executable scripts and tools - - `cmd/` — Go command entrypoints + - `cmd/` — Go command entrypoints; thin only: one `main.go` per binary whose + body is a single call into `internal/` or `pkg/`, no project logic in + `cmd/` - `configs/` — configuration templates and examples - `deploy/` — deployment manifests (k8s, compose, terraform) - `docs/` — documentation and markdown (README.md stays in root) @@ -406,3 +685,7 @@ style conventions are in separate documents: - Go: `go.mod`, `go.sum`, `.golangci.yml` - JS: `package.json`, `yarn.lock`, `.prettierrc`, `.prettierignore` - Python: `pyproject.toml` + +- Guidance for coding agents lives in one `AGENTS.md` at the repository root. It + is never committed under a file or directory named after one agent tool, such + as `CLAUDE.md` or `.claude/`, and never split into separate memory files. diff --git a/TODO.md b/TODO.md index 611a0b9..92ae9e3 100644 --- a/TODO.md +++ b/TODO.md @@ -14,12 +14,17 @@ pre-1.0 # Next Step -Bring the repo into policy compliance in one commit: add .gitignore, -.dockerignore, .editorconfig, and .golangci.yml. Verify `make check` stays -green with the new lint config. +Add the canonical `.golangci.yml`, move the lint phase to golangci-lint +v2.14.0 in the same commit, and fix the findings it surfaces +(https://git.eeqj.de/sneak/bsdaily/issues/6). # Completed Steps +- 2026-10-05: Brought the repo up to the standard layout: canonical + `.gitignore`, `.dockerignore` and `.editorconfig`; `lint` and `test` + phases in the `Dockerfile`, built by `script/lint` and `script/test`; + canonical `script/cibuild`, `script/docker` and CI workflow; no linter + installed on the host; re-vendored `REPO_POLICIES.md`. - 2026-07-07 Adopted scripts-to-rule-them-all: `script/` entrypoints, Makefile shims, README Entrypoints section - 2026-06-28: Fixed errcheck lint failures; added compilation smoke test; @@ -36,8 +41,8 @@ green with the new lint config. # Future Steps -- Add .gitignore, .dockerignore, .editorconfig, .golangci.yml (the Next - Step). +- Format Markdown with prettier in `script/fmt` and `script/fmt-check` + (https://git.eeqj.de/sneak/bsdaily/issues/7). - Expand tests beyond the compilation smoke test: unit tests for the extraction, verification, and atomic-publish paths. - Cut a first SemVer release once compliance and test coverage land. diff --git a/script/bootstrap b/script/bootstrap index 3a156e5..4dcdcd7 100755 --- a/script/bootstrap +++ b/script/bootstrap @@ -10,6 +10,7 @@ ROOT="$(cd "$(dirname "$0")/.." && pwd -P)" PKGMGR="" SUDO="" +APT_UPDATED="" detect_pkgmgr() { [ -n "$PKGMGR" ] && return 0 @@ -38,7 +39,14 @@ pkg_install() { detect_pkgmgr case "$PKGMGR" in nix) nix-env -iA "nixpkgs.$1" ;; - apt) $SUDO env DEBIAN_FRONTEND=noninteractive apt-get install -y "$2" ;; + apt) + # Package lists may be empty (fresh images); refresh once per run. + if [ -z "$APT_UPDATED" ]; then + $SUDO env DEBIAN_FRONTEND=noninteractive apt-get update + APT_UPDATED=1 + fi + $SUDO env DEBIAN_FRONTEND=noninteractive apt-get install -y "$2" + ;; brew) brew install "$3" ;; apk) apk add --no-cache "$4" ;; esac @@ -58,13 +66,6 @@ main() { # Go toolchain if missing go; then pkg_install go golang go go; fi - # golangci-lint: packaged in nix, brew, and apk. There is no apt - # package; on apt systems install it manually from a hash-verified - # GitHub release archive (never curl | sh). - if missing golangci-lint; then - pkg_install golangci-lint golangci-lint golangci-lint golangci-lint - fi - go mod download echo "bootstrap complete" diff --git a/script/cibuild b/script/cibuild index 3da5857..f00646a 100755 --- a/script/cibuild +++ b/script/cibuild @@ -1,14 +1,30 @@ #!/bin/sh -# script/cibuild: run the CI build. The Dockerfile runs script/check -# (via make check), so a successful build implies all checks pass. -# Generic: needs no adaptation. The Gitea workflow runs this on push. +# script/cibuild: run the CI build. It bootstraps first: a CI runner +# checks out and runs this and nothing else, and script/fmt-check runs +# the formatter on the host, which a pristine checkout cannot do. +# --no-cache for the same reason as script/docker: the gate phases the +# final stage depends on are RUN steps, and a cached one is a check that +# did not run. set -eu -ROOT="$(cd "$(dirname "$0")/.." && pwd -P)" +SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)" +ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)" main() { cd "$ROOT" - docker build . + "$SCRIPT_DIR/bootstrap" + "$SCRIPT_DIR/check" + # The version and the tag each get their own line: a failing + # command substitution inside an argument does not trip `set -e`, + # so the inline form degrades silently to an empty constant. The + # VERSION build argument takes precedence over the version a build + # stage derives from the .git in the context. + version="$(git describe --tags --always --dirty 2>/dev/null || true)" + [ -n "$version" ] || version="unknown" + tag="$("$SCRIPT_DIR/projectname")" + docker build --no-cache \ + --build-arg VERSION="$version" \ + -t "$tag" . } main "$@" diff --git a/script/docker b/script/docker index 2884e41..5b7dda8 100755 --- a/script/docker +++ b/script/docker @@ -1,7 +1,8 @@ #!/bin/sh # script/docker: build the Docker image tagged with the project name. # Identical in all repos; the tag comes from script/projectname. -# Generic: needs no adaptation. +# --no-cache because the gate phases the final stage depends on are RUN +# steps, and a cached one is a check that did not run. set -eu SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)" @@ -9,7 +10,17 @@ ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)" main() { cd "$ROOT" - docker build -t "$("$SCRIPT_DIR/projectname")" . + # The version and the tag each get their own line: a failing + # command substitution inside an argument does not trip `set -e`, + # so the inline form degrades silently to an empty constant. The + # VERSION build argument takes precedence over the version a build + # stage derives from the .git in the context. + version="$(git describe --tags --always --dirty 2>/dev/null || true)" + [ -n "$version" ] || version="unknown" + tag="$("$SCRIPT_DIR/projectname")" + docker build --no-cache \ + --build-arg VERSION="$version" \ + -t "$tag" . } main "$@" diff --git a/script/lint b/script/lint index 9b57aea..634d4a2 100755 --- a/script/lint +++ b/script/lint @@ -1,12 +1,27 @@ #!/bin/sh -# script/lint: run the linter. +# script/lint: run the linter. Linting is a phase of the Dockerfile and +# this builds that phase alone; the linter is never installed or run on +# a developer host, where a shared result cache and a host-global lock +# make its answer untrustworthy. +# +# The phase is not the last stage in the file, so it is built only when +# --target names it. --no-cache because a cached lint layer is a lint +# that did not run. The tag makes each build replace the previous image +# instead of leaving a dangling one behind. set -eu -ROOT="$(cd "$(dirname "$0")/.." && pwd -P)" +SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)" +ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)" main() { cd "$ROOT" - golangci-lint run ./... + # The tag gets its own line: a failing command substitution inside + # an argument does not trip `set -e`, so the inline form degrades + # silently to an empty constant. + tag="$("$SCRIPT_DIR/projectname")" + docker build --no-cache \ + --target lint \ + -t "$tag-lint" . } main "$@" diff --git a/script/test b/script/test index f1a8a6a..38fa1b3 100755 --- a/script/test +++ b/script/test @@ -1,18 +1,23 @@ #!/bin/sh -# script/test: run the test suite. Quiet on success; on failure, rerun -# verbosely for full diagnostic output (the exit 1 ensures the rerun -# never turns a failure into a pass). +# 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 "$0")/.." && pwd -P)" +SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)" +ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)" main() { cd "$ROOT" - go test -race -timeout 30s ./... || { - echo "--- Rerunning with -v for details ---" - go test -race -timeout 30s -v ./... - exit 1 - } + # The tag gets its own line: a failing command substitution inside + # an argument does not trip `set -e`, so the inline form degrades + # silently to an empty constant. + tag="$("$SCRIPT_DIR/projectname")" + docker build --no-cache \ + --target test \ + -t "$tag-test" . } main "$@"