holocron/tests/test-check-rtk-prefix.sh

#!/usr/bin/env bash
set -euo pipefail

# Tests for scripts/check-rtk-prefix.sh — ADR-0023 clause 1.
#
# Case 1 is the one that earns the rest: it runs the gate against the corpus as
# it stood BEFORE the #113 sweep, and asserts it fails there. A gate that only
# passes on the already-fixed tree proves nothing about whether it would have
# caught the drift it was written for.
#
# Pinned to a commit SHA, not the `main` ref: `main` is the moving integration
# branch, and the #113 fix (ed8c99e) landed back on it, so querying live
# `main` for the "pre-sweep" corpus stopped reproducing the drift the moment
# that fix merged — the case silently started asserting the opposite of what
# it says. 598a7c3 is the last commit where gitea-issues/SKILL.md still had
# the bare `git remote get-url origin` call ed8c99e fixed.
#
# Everything after that is synthetic. The false-NEGATIVE cases (a bare command
# the gate must catch) and the false-POSITIVE cases (correct content the gate
# must leave alone) carry equal weight: this hook's failure mode is not missing
# a violation, it is firing on deliberately-bare clause-2 and clause-3 content
# until someone adds it to SKIP.

REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
SCRIPT="$REPO_ROOT/scripts/check-rtk-prefix.sh"
PASS=0
FAIL=0

pass() { echo "  PASS: $1"; PASS=$((PASS + 1)); }
fail() { echo "  FAIL: $1"; FAIL=$((FAIL + 1)); }

if ! command -v python3 >/dev/null 2>&1; then
  echo "SKIP: python3 is not installed — the script under test fails closed on it, so every case here would only re-assert the missing-dependency guard"
  exit 77
fi

RUN_TMP="$(mktemp -d)"
trap 'rm -rf "$RUN_TMP"' EXIT

# Writes $2 to a .md file and asserts the gate's verdict. $1 is "clean" or
# "dirty"; $3 is the case description.
expect() {
  local want="$1" body="$2" desc="$3"
  local f="$RUN_TMP/case.md"
  printf '%s\n' "$body" > "$f"
  local rc=0
  bash "$SCRIPT" "$f" > "$RUN_TMP/out" 2>&1 || rc=$?
  if [[ "$want" == "dirty" && $rc -eq 0 ]]; then
    fail "$desc — expected a violation, exited 0"
  elif [[ "$want" == "clean" && $rc -ne 0 ]]; then
    fail "$desc — expected no violation, exited $rc"
    sed 's/^/    /' "$RUN_TMP/out"
  else
    pass "$desc"
  fi
}

echo "--- the pre-#113 corpus trips the gate ---"

# The commit set is derived from git, not hardcoded, at this fixed SHA: the
# point is "the drift this gate exists for", and a hardcoded path list goes
# stale the moment a file is renamed. The SHA itself is deliberately hardcoded
# — see the header comment for why it must NOT be a moving ref like `main`.
PRE_SWEEP_REF="598a7c326a4bbfa4a39007eb95d944c4150686e8"
if ! git -C "$REPO_ROOT" rev-parse --verify -q "$PRE_SWEEP_REF" >/dev/null; then
  echo "SKIP: pre-sweep commit $PRE_SWEEP_REF not reachable locally (shallow clone?) — the historical-corpus case cannot be reconstructed"
  exit 77
fi

PRE="$RUN_TMP/pre"
# A read loop, not the bash-4 array builtin: tests/test-vale-wrap.sh scans every
# script under tests/ for bash-4-only constructs, because these run on macOS's
# bash 3.2. Same reason for the `[@]+` guards on every array expansion below.
PRE_FILES=()
PRE_PATHS=()
while IFS= read -r PRE_REL; do
  PRE_FILES+=("$PRE_REL")
  PRE_PATHS+=("$PRE/$PRE_REL")
done < <(
  git -C "$REPO_ROOT" ls-tree -r --name-only "$PRE_SWEEP_REF" -- 'plugins' \
    | grep -E '^plugins/[^/]+/\.apm/(skills/.*\.md|agents/.*\.agent\.md)$' \
    | grep -v '/README\.md$'
)
if [[ ${#PRE_FILES[@]} -eq 0 ]]; then
  fail "no plugin skill/agent files found at $PRE_SWEEP_REF — the historical case checked nothing"
else
  for f in ${PRE_FILES[@]+"${PRE_FILES[@]}"}; do
    mkdir -p "$PRE/$(dirname "$f")"
    git -C "$REPO_ROOT" show "$PRE_SWEEP_REF:$f" > "$PRE/$f"
  done
  if bash "$SCRIPT" ${PRE_PATHS[@]+"${PRE_PATHS[@]}"} > "$RUN_TMP/pre.out" 2>&1; then
    fail "the pre-sweep corpus passed — the gate would not have caught the #113 drift"
  else
    hits="$(grep -c '^ADR-0023: ' "$RUN_TMP/pre.out" || true)"
    if [[ "$hits" -lt 20 ]]; then
      fail "the pre-sweep corpus produced only $hits findings — too few to be the known drift"
    elif ! grep -q 'gitea-issues/SKILL.md.*git remote get-url origin' "$RUN_TMP/pre.out"; then
      fail "the pre-sweep corpus failed, but not on the known gitea drift"
      sed 's/^/    /' "$RUN_TMP/pre.out" | head -5
    else
      pass "the pre-sweep corpus fails with $hits findings, including the gitea sweep gap"
    fi
  fi
fi

echo ""
echo "--- shell fences: what must fail ---"

expect dirty '```bash
git commit -m "x"
```' "a bare git command in a bash fence"

expect dirty '```sh
rtk git add -u && git commit -m "x"
```' "a bare git after && on a line that starts with rtk git"

expect dirty '```bash
SKIP=check-yaml git commit -m "x"
```' "a bare git behind an environment-variable prefix"

expect dirty '```bash
url=$(git config remote.origin.url)
```' "a bare git inside a command substitution"

expect dirty '```console
$ git status
```' "a bare git behind a copied shell prompt"

echo ""
echo "--- shell fences: what must NOT fail ---"

expect clean '```bash
rtk git commit -m "x"
rtk git push
```' "prefixed commands"

expect clean '```bash
git stash list   # bare per ADR-0023: rtk prints "No stashes" where git prints nothing
```' "a bare command carrying the ADR-0023 opt-out marker"

expect clean '```text
git worktree list --porcelain -z
```' "a non-shell fence (text) is out of scope"

expect clean '```yaml
entry: git
```' "a yaml fence is out of scope"

expect clean '```bash
# never reach for git commit --no-verify here
rtk git commit
```' "a bare git inside a shell comment"

expect clean 'Run `git switch <branch>` — no wait, this is prose, not a fence.' \
  "a bare git in a prose line outside any fence"

echo ""
echo "--- dispatch tables ---"

expect dirty '| Operation | Run |
|---|---|
| List | `git worktree list -v` |' "a bare command opening a Run cell"

expect clean '| Operation | Run |
|---|---|
| List | `rtk git worktree list -v` |' "a prefixed command in a Run cell"

expect clean '| Operation | Run |
|---|---|
| List | `git worktree list -v` — bare per ADR-0023 |' \
  "a bare Run cell carrying the opt-out marker"

# The clause-2 shapes that made an every-span check unusable. Both are real rows
# from git-worktrees/SKILL.md.
expect clean '| Operation | Run |
|---|---|
| Track | `rtk git worktree add --track -b <b> <p> <r>/<b>` — always correct. `git worktree add <p> <b>` expands to exactly this |' \
  "a referential bare mention AFTER the instructed command in a Run cell"

expect clean '| Operation | Run |
|---|---|
| **Never** `git worktree add <p> <r>/<b>` | That ref resolves, so `git push` needs an explicit refspec |' \
  "an anti-pattern row whose Run cell opens with prose"

expect clean '| Flag | Meaning |
|---|---|
| `-L` | as in `git log -L` |' "a table with no Run column is out of scope"

echo ""
echo "--- degenerate inputs ---"

expect clean '' "an empty file"

expect clean '```bash
rtk git status' "an unterminated fence does not crash the parser"

if bash "$SCRIPT" > "$RUN_TMP/noargs.out" 2>&1; then
  pass "no filenames exits 0 rather than erroring"
else
  fail "no filenames should exit 0 — pre-commit calls hooks with an empty file list"
fi

if bash "$SCRIPT" "$RUN_TMP/does-not-exist.md" > "$RUN_TMP/missing.out" 2>&1; then
  fail "an unreadable file exited 0 — unreadable must be an error, never a silent pass"
elif ! grep -q 'could not read file' "$RUN_TMP/missing.out"; then
  fail "an unreadable file failed for the wrong reason"
  sed 's/^/    /' "$RUN_TMP/missing.out"
else
  pass "an unreadable file exits 1 and says so"
fi

echo ""
echo "--- the live corpus is clean ---"

LIVE=()
while IFS= read -r LIVE_REL; do
  LIVE+=("$LIVE_REL")
done < <(
  git -C "$REPO_ROOT" ls-files -- 'plugins' \
    | grep -E '^plugins/[^/]+/\.apm/(skills/.*\.md|agents/.*\.agent\.md)$' \
    | grep -v '/README\.md$'
)
if [[ ${#LIVE[@]} -eq 0 ]]; then
  fail "no plugin skill/agent files matched the hook's files: pattern"
elif (cd "$REPO_ROOT" && bash "$SCRIPT" ${LIVE[@]+"${LIVE[@]}"} > "$RUN_TMP/live.out" 2>&1); then
  pass "the ${#LIVE[@]} in-scope corpus files pass"
else
  fail "the live corpus has ADR-0023 clause-1 violations"
  sed 's/^/    /' "$RUN_TMP/live.out"
fi

echo ""
echo "Results: $PASS passed, $FAIL failed"
[[ $FAIL -eq 0 ]]