rig/test/cli.sh

229 lines
14 KiB
Bash
Raw Normal View History

#!/usr/bin/env bash
# Dependency-free CLI assertions. Run: bash test/cli.sh
# Deliberately no `set -e` — the harness asserts on failing commands.
set -u
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
PASS=0 FAIL=0
# check <desc> <want_exit> <want_substr> <cmd...>
# Runs cmd, asserts exit code and (if non-empty) that combined output
# contains want_substr.
check() {
local desc="$1" want="$2" substr="$3"; shift 3
local out rc
out="$("$@" 2>&1)"; rc=$?
if [ "$rc" -ne "$want" ]; then
echo "FAIL: $desc — exit $rc, wanted $want"
printf '%s\n' "$out" | sed 's/^/ /'
FAIL=$((FAIL + 1)); return
fi
if [ -n "$substr" ] && ! printf '%s' "$out" | grep -qF -e "$substr"; then
echo "FAIL: $desc — output missing '$substr'"
printf '%s\n' "$out" | sed 's/^/ /'
FAIL=$((FAIL + 1)); return
fi
echo "ok: $desc"; PASS=$((PASS + 1))
}
check "no args shows usage, exit 2" 2 "usage:" "$ROOT/bin/rig"
check "--help exits 0" 0 "usage:" "$ROOT/bin/rig" --help
check "help exits 0" 0 "usage:" "$ROOT/bin/rig" help
check "unknown command exits 2" 2 "unknown command" "$ROOT/bin/rig" frobnicate
check "bare coolify shows usage, exit 2" 2 "usage:" "$ROOT/bin/rig" coolify
check "bootstrap: role required, exit 2" 2 "role required" "$ROOT/commands/bootstrap.sh"
check "bootstrap: --help exits 0" 0 "usage:" "$ROOT/commands/bootstrap.sh" --help
check "bootstrap: unknown role exits 2" 2 "unknown role" "$ROOT/commands/bootstrap.sh" potato
check "bootstrap: unknown flag exits 2" 2 "unknown flag" "$ROOT/commands/bootstrap.sh" workload --nope
check "bootstrap: hostname needs value" 2 "needs a value" "$ROOT/commands/bootstrap.sh" workload --hostname
check "bootstrap: runner refuses tag:server" 2 "must not advertise tag:server" "$ROOT/commands/bootstrap.sh" runner --ts-tag tag:server
if [ "$(id -u)" -ne 0 ]; then
check "bootstrap: refuses non-root" 1 "must run as root" env TS_AUTHKEY=x "$ROOT/commands/bootstrap.sh" workload
check "bootstrap: runner role parses, refuses non-root" 1 "must run as root" env TS_AUTHKEY=x "$ROOT/commands/bootstrap.sh" runner
else
echo "skip: bootstrap non-root refusals (running as root)"
fi
check "coolify: version required, exit 2" 2 "--version" "$ROOT/commands/coolify-install.sh"
check "coolify: --help exits 0" 0 "usage:" "$ROOT/commands/coolify-install.sh" --help
check "coolify: version needs value" 2 "needs a value" "$ROOT/commands/coolify-install.sh" --version
check "coolify: unknown flag exits 2" 2 "unknown flag" "$ROOT/commands/coolify-install.sh" --nope
if [ "$(id -u)" -ne 0 ]; then
check "coolify: refuses non-root" 1 "must run as root" "$ROOT/commands/coolify-install.sh" --version 4.1.2
else
echo "skip: coolify non-root refusal (running as root)"
fi
feat(coolify): install the control-plane dump as a systemd timer The Coolify control-plane database holds the GitHub App private key, every registered server's SSH key, and every environment value for every environment it manages. Backing it up was a manual runbook step, and the dump script lived in cast — the off-box tool, whose src never references it. It runs on the box, as root, under a scheduler: that is rig's job description. It matters beyond tidiness. The dump is forensics, not a restore path — a lost control plane is rebuilt fresh and reconciled from the manifest. So there will be a next control-plane box, and as a runbook step it was born un-backed-up, depending on someone remembering mid-incident. Now it is backed up from birth. rig installs the machinery and templates /etc/coolify-dump.env empty at 0600, never reading it back — no credential passes through rig. The script's own guards make an unfilled file fail the unit loudly rather than ship plaintext. systemd timer over cron: EnvironmentFile is the right idiom for 0600 secrets, failures surface in systemctl status instead of being mailed into the void, and Persistent=true catches a run missed while the box was down. Two hazards the cast script missed, carried into the unit: - aws-cli >= 2.23 enables default upload checksums that S3-compatible backends reject; Debian 13 ships 2.23.6, so the unit defaults both checksum knobs to when_required. - A failed pg_dump piped into age still yields a valid, tiny, encrypted file that uploads cleanly every night and looks exactly like a working backup. The script now refuses to upload an empty artifact. Closes #8 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-12 19:14:07 +00:00
check "bare coolify backup shows usage, exit 2" 2 "usage:" "$ROOT/bin/rig" coolify backup
check "coolify backup: bad subcommand exits 2" 2 "usage:" "$ROOT/bin/rig" coolify backup frobnicate
check "coolify backup: --help exits 0" 0 "usage:" "$ROOT/commands/coolify-backup-install.sh" --help
check "coolify backup: schedule needs value" 2 "needs a value" "$ROOT/commands/coolify-backup-install.sh" --schedule
check "coolify backup: pg-container needs value" 2 "needs a value" "$ROOT/commands/coolify-backup-install.sh" --pg-container
check "coolify backup: unknown flag exits 2" 2 "unknown flag" "$ROOT/commands/coolify-backup-install.sh" --nope
if [ "$(id -u)" -ne 0 ]; then
check "coolify backup: refuses non-root" 1 "must run as root" "$ROOT/commands/coolify-backup-install.sh"
else
echo "skip: coolify backup non-root refusal (running as root)"
fi
feat(db): bring ad-hoc dump/restore on-box as `rig db` Add `rig db dump <container> [outfile]` and `rig db restore <artifact> <container> [db] [--yes]` — imperative on-box PostgreSQL tooling, the interactive counterpart to the scheduled, declarative `coolify backup install`. Key decisions: - Dumps carry `--clean --if-exists --no-owner --no-acl`. `--no-owner --no-acl` is mandatory for cross-instance restores: the target's superuser differs (Coolify randomizes it), so a plain dump aborts under ON_ERROR_STOP=1 on the first GRANT/ALTER OWNER for a missing role. - $POSTGRES_USER/$POSTGRES_DB are read INSIDE the container (single-quoted `sh -c`), never hardcoded to `postgres` on the host. - restore connects as the container's own superuser and runs with ON_ERROR_STOP=1; the optional [db] arg targets a NAMED database in a shared container, passed in via a container env var rather than string splicing. - restore overwrites the target, so it prompts y/N; --yes/--force is the automation bypass. Artifact existence/non-emptiness is checked before the confirm gate and before anything touches the DB. - dump uses pipefail + a sibling temp promoted only on success, and refuses to keep an empty artifact — a failed pg_dump must never leave a plausible-looking .gz behind. Args are validated before the root check (testable without root); guards are root, Debian-family warn, docker, and gzip/gunzip. Adds CLI tests and a `### rig db` README section. Closes #15 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-17 15:16:35 +00:00
# --- rig db (ad-hoc dump/restore) -------------------------------------------
check "bare db shows usage, exit 2" 2 "usage:" "$ROOT/bin/rig" db
check "db --help exits 0" 0 "usage:" "$ROOT/bin/rig" db --help
check "db bad subcommand exits 2" 2 "usage:" "$ROOT/bin/rig" db frobnicate
check "db dump: --help exits 0" 0 "usage:" "$ROOT/commands/db.sh" dump --help
check "db dump: container required, exit 2" 2 "needs a container" "$ROOT/commands/db.sh" dump
check "db dump: unknown flag exits 2" 2 "unknown flag" "$ROOT/commands/db.sh" dump --nope
check "db restore: artifact required, exit 2" 2 "needs an artifact" "$ROOT/commands/db.sh" restore
check "db restore: container required, exit 2" 2 "needs a target container" \
"$ROOT/commands/db.sh" restore /tmp/whatever.sql.gz
check "db restore: unknown flag exits 2" 2 "unknown flag" "$ROOT/commands/db.sh" restore --nope
# Artifact existence is checked BEFORE docker/root, so a fat-fingered path fails
# clearly and cheaply — and is testable here without root or a live container.
check "db restore: missing artifact fails before the docker/root path" \
1 "artifact not found" "$ROOT/commands/db.sh" restore /no/such/artifact.sql.gz somecontainer --yes
# The two DB invariants live as embedded command strings (single-quoted sh -c),
# not an extractable heredoc, so guard them directly: dropping --no-owner/--no-acl
# breaks every cross-instance restore, and hardcoding a role instead of the
# container's own $POSTGRES_USER/$POSTGRES_DB is wrong on Coolify's randomized
# superuser. ON_ERROR_STOP=1 is what makes a bad restore fail instead of limp.
check "db dump embeds --no-owner --no-acl" 0 "" \
grep -qF -- "--no-owner --no-acl" "$ROOT/commands/db.sh"
# The $POSTGRES_USER below is a LITERAL we grep for in db.sh (it must read the
# container's env, not the host's) — single quotes are the point here.
# shellcheck disable=SC2016
check "db dump reads the container's own \$POSTGRES_USER/\$POSTGRES_DB" 0 "" \
grep -qF 'pg_dump -U "$POSTGRES_USER"' "$ROOT/commands/db.sh"
# shellcheck disable=SC2016
check "db restore connects as the container's own \$POSTGRES_USER" 0 "" \
grep -qF 'psql -U "$POSTGRES_USER"' "$ROOT/commands/db.sh"
check "db restore uses ON_ERROR_STOP=1" 0 "" \
grep -qF "ON_ERROR_STOP=1" "$ROOT/commands/db.sh"
if [ "$(id -u)" -ne 0 ]; then
# Valid args, so validation passes and we reach the root guard.
check "db dump: refuses non-root" 1 "must run as root" "$ROOT/commands/db.sh" dump somecontainer
# Restore needs a real, non-empty artifact to get PAST the artifact check and
# reach the root guard; --yes skips the confirm prompt so the check is exit-clean.
DB_ART="$(mktemp)"; printf 'SELECT 1;\n' > "$DB_ART"
check "db restore: refuses non-root" 1 "must run as root" \
"$ROOT/commands/db.sh" restore "$DB_ART" somecontainer --yes
rm -f "$DB_ART"
else
echo "skip: db non-root refusals (running as root)"
fi
check "bare runner shows usage, exit 2" 2 "usage:" "$ROOT/bin/rig" runner
check "runner: --help exits 0" 0 "usage:" "$ROOT/commands/runner-install.sh" --help
check "runner: repo required, exit 2" 2 "--repo" "$ROOT/commands/runner-install.sh" --version 2.335.1
check "runner: version needs value" 2 "needs a value" "$ROOT/commands/runner-install.sh" --repo acme/widgets --version
check "runner: repo needs value" 2 "needs a value" "$ROOT/commands/runner-install.sh" --repo
check "runner: rejects bad repo slug" 2 "owner/repo" "$ROOT/commands/runner-install.sh" --repo not-a-slug --version 2.335.1
check "runner: refuses --user root" 2 "must not be root" "$ROOT/commands/runner-install.sh" --repo acme/widgets --version 2.335.1 --user root
check "runner: unknown flag exits 2" 2 "unknown flag" "$ROOT/commands/runner-install.sh" --nope
if [ "$(id -u)" -ne 0 ]; then
check "runner: refuses non-root" 1 "must run as root" env RUNNER_TOKEN=x "$ROOT/commands/runner-install.sh" --repo acme/widgets --version 2.335.1
else
echo "skip: runner non-root refusal (running as root)"
fi
check "runner: bad subcommand exits 2" 2 "usage:" "$ROOT/bin/rig" runner frobnicate
fix(runner): install refuses a box registered to another repo `rig runner install --repo <B>` on a box already registered to repo A treated the mere existence of .runner as "already registered", skipped configure, restarted the service still pointed at A, and reported success. --repo was accepted, validated, and then ignored — leaving B with zero runners and its `runs-on` jobs queued against one that will never come. This is the natural next command after a partial `repoint`, and the failure is worse than a no-op: moving a runner between repos is a trust-boundary act, so quietly putting it back on the old one defeats the point of the move. Gate install on the repo .runner actually names. Convergence — the property worth keeping — is untouched: re-running against the repo the box is already on still skips registration, never prompts for a token, and exits 0. Skipping when the repo *differs* was never convergence, only a silently ignored argument, so it now fails and names both repos, pointing at `runner repoint` (move) or `runner remove` (start over). An unreadable .runner is refused too — it is no licence to assume a match. The .runner reader that `status` and `repoint` each carried is lifted into commands/lib/runner-config.sh, which now also holds the guard. Its json_field no longer dies bare under `set -o pipefail` when a key is missing, which is what `status`'s own ${REPO_URL:-unknown} fallback always assumed. Tests: the guard is exercised against a fixture .runner (refuses another repo naming both, points at repoint, no-ops on the same repo, passes an unregistered box, refuses an unreadable one) plus an ordering assertion that it precedes svc.sh start — reaching it through the CLI would need root and a really-registered runner, which the dependency-free harness cannot fabricate. All three mutants (guard deleted, guard comparing nothing, guard moved below the service start) go red. Closes #13
2026-07-13 14:57:28 +00:00
# --- runner install: --repo must agree with what the box is already on -------
# The bug: `install --repo B` on a box registered to repo A skipped configure,
# restarted the service on A, and reported success — --repo accepted, validated,
# then ignored. The guard is exercised here through the shared lib, against a
# fixture .runner: reaching it via the CLI needs root AND a really-registered
# runner, neither of which this harness can fabricate.
guard() { # guard <runner_dir> <owner/repo>
bash -c 'set -euo pipefail
. "$1/commands/lib/runner-config.sh"
assert_runner_repo "$2" "$3"' _ "$ROOT" "$1" "$2"
}
REG_DIR="$(mktemp -d)" # a box registered to acme/alpha
EMPTY_DIR="$(mktemp -d)" # a box with no runner at all
printf '%s\n' '{"agentId":7,"agentName":"ci-box","gitHubUrl":"https://github.com/acme/alpha","workFolder":"_work"}' \
> "$REG_DIR/.runner"
check "runner install: refuses a repo the box is not registered to" \
1 "already registered to https://github.com/acme/alpha" guard "$REG_DIR" acme/beta
check "runner install: the refusal names the repo that was asked for" \
1 "not https://github.com/acme/beta" guard "$REG_DIR" acme/beta
check "runner install: the refusal points at repoint" \
1 "rig runner repoint --repo acme/beta" guard "$REG_DIR" acme/beta
# Convergence is the property worth keeping: same repo stays a clean no-op.
check "runner install: the repo it is already on is a no-op" \
0 "" guard "$REG_DIR" acme/alpha
check "runner install: an unregistered box passes the guard" \
0 "" guard "$EMPTY_DIR" acme/beta
# A .runner rig cannot read is not a licence to assume it matches.
printf '%s\n' '{"agentName":"ci-box"}' > "$REG_DIR/.runner"
check "runner install: refuses an unreadable registration" \
1 "names no repository" guard "$REG_DIR" acme/alpha
rm -rf "$REG_DIR" "$EMPTY_DIR"
# The guard is only worth something if it runs BEFORE the box is touched: the
# token prompt, the download, configure and svc.sh start all come after it.
# Ordering is the whole fix, so assert it rather than trust it.
# Matches the CALL, not the word: the comment above it mentions assert_runner_repo
# too, and a plain grep would keep finding that after the call itself was deleted.
# The defaults fail closed, so a guard that is gone cannot read as one that merely
# sits early in the file.
guard_at="$(grep -nE '^[[:space:]]*assert_runner_repo ' "$ROOT/commands/runner-install.sh" | head -n1 | cut -d: -f1)"
start_at="$(grep -n 'svc.sh start' "$ROOT/commands/runner-install.sh" | head -n1 | cut -d: -f1)"
check "runner install: the repo guard precedes svc.sh start" \
0 "" test "${guard_at:-999999}" -lt "${start_at:-0}"
check "runner status: --help exits 0" 0 "usage:" "$ROOT/commands/runner-status.sh" --help
check "runner status: user needs value" 2 "needs a value" "$ROOT/commands/runner-status.sh" --user
check "runner status: refuses --user root" 2 "must not be root" "$ROOT/commands/runner-status.sh" --user root
check "runner status: unknown flag exits 2" 2 "unknown flag" "$ROOT/commands/runner-status.sh" --nope
check "runner remove: --help exits 0" 0 "usage:" "$ROOT/commands/runner-remove.sh" --help
check "runner remove: user needs value" 2 "needs a value" "$ROOT/commands/runner-remove.sh" --user
check "runner remove: refuses --user root" 2 "must not be root" "$ROOT/commands/runner-remove.sh" --user root
check "runner remove: unknown flag exits 2" 2 "unknown flag" "$ROOT/commands/runner-remove.sh" --nope
check "runner repoint: --help exits 0" 0 "usage:" "$ROOT/commands/runner-repoint.sh" --help
check "runner repoint: repo required" 2 "--repo" "$ROOT/commands/runner-repoint.sh"
check "runner repoint: repo needs value" 2 "needs a value" "$ROOT/commands/runner-repoint.sh" --repo
check "runner repoint: rejects bad slug" 2 "owner/repo" "$ROOT/commands/runner-repoint.sh" --repo not-a-slug
check "runner repoint: labels need value" 2 "needs a value" "$ROOT/commands/runner-repoint.sh" --repo acme/widgets --labels
check "runner repoint: refuses --user root" 2 "must not be root" "$ROOT/commands/runner-repoint.sh" --repo acme/widgets --user root
check "runner repoint: unknown flag exits 2" 2 "unknown flag" "$ROOT/commands/runner-repoint.sh" --nope
if [ "$(id -u)" -ne 0 ]; then
check "runner status: refuses non-root" 1 "must run as root" "$ROOT/commands/runner-status.sh"
check "runner remove: refuses non-root" 1 "must run as root" \
env RUNNER_REMOVE_TOKEN=x "$ROOT/commands/runner-remove.sh"
# --local too: the token-free path must still not be runnable by the runner user.
check "runner remove: --local refuses non-root" 1 "must run as root" \
"$ROOT/commands/runner-remove.sh" --local
check "runner repoint: refuses non-root" 1 "must run as root" \
env RUNNER_REMOVE_TOKEN=x RUNNER_TOKEN=y "$ROOT/commands/runner-repoint.sh" --repo acme/widgets
else
echo "skip: runner status/remove/repoint non-root refusals (running as root)"
fi
fix(coolify): validate the dump bindings, and stop printing $EDITOR Both found by the first run on a real control-plane box — neither was reachable by the argument-parsing tests. $EDITOR is unset on a freshly-bootstrapped server, which is precisely rig's target environment. The printed next-step `$EDITOR /etc/coolify-dump.env` expanded to nothing, so bash tried to EXECUTE the 0600 bindings file and said "Permission denied" — an error that reads like a filesystem problem and is not one. Print `nano`. A bare bucket name in S3_BUCKET reads to `aws` as a LOCAL path, so the upload died with "Invalid argument type" and a usage dump — after pg_dump had run and age had encrypted 14MB, with nothing in the error pointing at the actual mistake. The script now validates the bindings up front: S3_BUCKET must be an s3:// URI, S3_ENDPOINT must carry a scheme. Both fail with the value quoted and the reason stated, before a database is read. Note what still cannot be validated, and now says so in the script: age's X25519 header does not reveal its recipient, so a valid-but-WRONG key (staging's instead of prod's) yields a flawless backup nobody can open. Only decrypting an artifact proves the recipient. The printed next-steps now walk through that read-back explicitly, from a machine holding the private key — never the box. The dump script ships as an embedded heredoc, so a typo in it would first surface at 04:00 on a live control plane. test/cli.sh now extracts it and asserts it is valid bash and that both new guards fire. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-12 19:55:39 +00:00
# The dump script ships to control-plane boxes as an embedded heredoc. A syntax
# error in it would be invisible here and would first surface at 04:00 on a live
# control plane. Extract it and syntax-check what actually gets written.
DUMP_TMP="$(mktemp)"
sed -n "/<<'DUMP_SCRIPT'/,/^DUMP_SCRIPT\$/p" "$ROOT/commands/coolify-backup-install.sh" \
| sed '1d;$d' > "$DUMP_TMP"
check "embedded dump script extracted (guards the sed above)" 0 "" grep -q "pg_dump" "$DUMP_TMP"
check "embedded dump script is valid bash" 0 "" bash -n "$DUMP_TMP"
check "embedded dump script rejects a bare bucket name" 1 "must be an s3:// URI" \
env AGE_RECIPIENT=age1x S3_BUCKET=my-bucket S3_ENDPOINT=https://s3.example.com bash "$DUMP_TMP"
check "embedded dump script rejects a schemeless endpoint" 1 "needs a scheme" \
env AGE_RECIPIENT=age1x S3_BUCKET=s3://b/k S3_ENDPOINT=s3.example.com bash "$DUMP_TMP"
rm -f "$DUMP_TMP"
# Regression: /etc/os-release defines VERSION (e.g. "13 (trixie)" on Debian);
# sourcing it in the main shell clobbers a script's $VERSION and splices the
# OS string into download URLs. It must only ever be sourced in a subshell.
check "no main-shell os-release sourcing" 1 "" \
grep -rnE '^[[:space:]]*\.[[:space:]]+/etc/os-release' "$ROOT/commands"
echo "---"
echo "$PASS passed, $FAIL failed"
[ "$FAIL" -eq 0 ]