#!/bin/sh
# Tests for the agents/ directory the plugin ships, and doctor's shadow check.
#
# skills#51: pr-gatekeeper blocked dispatch#75 five times, every block a real
# escape verified by execution — and the agent definition lived only at
# ~/.claude/agents/pr-gatekeeper.md on one host. Unversioned, unreviewable, one
# rm from gone. Doctrine now depends on it (local-dev AGENT.md rule 8), so the
# file has to be in the repo.
#
# These assertions observe FILE CONTENT and doctor's OUTPUT. They cannot and do
# not claim the agent reviews well — naming them otherwise would be the exact
# defect rule 9 exists for.

set -u

ROOT=$(CDPATH= cd -- "$(dirname -- "$0")/.." && pwd)
AGENT="$ROOT/agents/pr-gatekeeper.md"
DOCTOR="$ROOT/bin/doctor"

pass=0
fail=0
WORK=${TMPDIR:-/tmp}/agents_test.$$

ok()  { pass=$((pass + 1)); printf 'ok: %s\n' "$1"; }
no()  { fail=$((fail + 1)); printf 'FAIL: %s\n' "$1"; }

# --- the file is in the repo ------------------------------------------------

if [ -f "$AGENT" ]; then
  ok 'agents/pr-gatekeeper.md exists in the checkout'
else
  no 'agents/pr-gatekeeper.md exists in the checkout'
  printf '\n%s passed, %s failed\n' "$pass" "$fail"
  exit 1
fi

# --- frontmatter is present and well-formed ---------------------------------

head -1 "$AGENT" | grep -q '^---$' \
  && ok 'the file opens with a frontmatter fence' \
  || no 'the file opens with a frontmatter fence'

for field in name description tools; do
  if sed -n '2,/^---$/p' "$AGENT" | grep -q "^$field:"; then
    ok "frontmatter declares $field"
  else
    no "frontmatter declares $field"
  fi
done

fm_name=$(sed -n '2,/^---$/p' "$AGENT" | sed -n 's/^name: *//p' | head -1)
if [ "$fm_name" = "pr-gatekeeper" ]; then
  ok 'the frontmatter name equals the filename stem'
else
  no "the frontmatter name equals the filename stem (got '$fm_name')"
fi

# --- the practices that actually found the defects --------------------------
#
# Each string below is traceable to a specific round of dispatch#75 or to the
# incident the agent itself caused. A grep is a weak check — it proves the
# phrase is present, not that the procedure is followed — so the test is named
# for the phrase, not for the behaviour.

check_phrase() {
  if grep -qi -- "$1" "$AGENT"; then
    ok "the file names: $2"
  else
    no "the file names: $2"
  fi
}

check_phrase 'verify by execution'        'verify by execution, not by reading the implementation'
check_phrase 'flip'                       'flip-testing'
check_phrase 'read the survivors'         'read the survivors of a differential'
check_phrase 'exit code'                  'grade a linter on its exit code'
check_phrase 'never the buffer'           'a probe prints a count, never the buffer'
check_phrase 'claims more than'           'a test name must not claim more than it proves'

# --- doctor flags a host-local copy that shadows the shipped one ------------

setup() {
  rm -rf "$WORK"
  mkdir -p "$WORK/home/.claude/agents" "$WORK/ck/skills/x" "$WORK/ck/agents"
  printf 'x\n' > "$WORK/ck/skills/x/SKILL.md"
  printf -- '---\nname: pr-gatekeeper\n---\n' > "$WORK/ck/agents/pr-gatekeeper.md"
}

setup
printf -- '---\nname: pr-gatekeeper\n---\n' > "$WORK/home/.claude/agents/pr-gatekeeper.md"
out=$(HOME="$WORK/home" DOCTOR_CHECKOUT="$WORK/ck" sh "$DOCTOR" 2>&1)
if printf '%s' "$out" | grep -q 'pr-gatekeeper'; then
  ok 'doctor reports a host-local agent that shadows a shipped one'
else
  no "doctor reports a host-local agent that shadows a shipped one (got: $out)"
fi

setup
out=$(HOME="$WORK/home" DOCTOR_CHECKOUT="$WORK/ck" sh "$DOCTOR" 2>&1)
if printf '%s' "$out" | grep -q 'pr-gatekeeper'; then
  no "doctor is silent when no host-local copy exists (got: $out)"
else
  ok 'doctor is silent when no host-local copy exists'
fi

rm -rf "$WORK"
printf '\n%s passed, %s failed\n' "$pass" "$fail"
[ "$fail" -eq 0 ]