repo-mailbox/scripts/state-line-guard-selftest.sh

#!/bin/bash
# state-line-guard-selftest.sh - proves hooks/scripts/pre-state-line-guard.mjs
# actually PREVENTS a Write/Edit that would push a STATE.md past the
# documented ~60-line convention (global CLAUDE.md), and leaves everything
# else alone. ASCII only, bash 3.2 safe.
#
# PreToolUse, not PostToolUse: the org-ops work order (20260814T144553Z) asked
# for PostToolUse, but PostToolUse fires AFTER the tool already ran and cannot
# undo the write (confirmed against the official hooks docs, 2026-08-14).
# PreToolUse is the only event that can deny before the file lands. Blocking
# convention (stderr + exit 2) matches llm-security's pre-write-pathguard.mjs,
# the only other PreToolUse Write/Edit guard in this marketplace.
set -u
export LC_ALL=C

DIR="$(cd "$(dirname "$0")" && pwd)"
HOOK="$DIR/../hooks/scripts/pre-state-line-guard.mjs"
TMPDIR="$(mktemp -d)"
trap 'rm -rf "$TMPDIR"' EXIT

PASS=0; FAIL=0
check() { if [ "$2" -eq 0 ]; then PASS=$((PASS+1)); echo "  ok   - $1"; else FAIL=$((FAIL+1)); echo "  FAIL - $1"; fi; }

# run_hook <json-file> -- sets HOOK_EXIT, HOOK_STDERR
run_hook() {
  HOOK_STDERR="$(node "$HOOK" <"$1" 2>&1 1>/dev/null)"
  HOOK_EXIT=$?
}

# payload <node-script-writing-JSON-to-stdout> -- returns path to a tmp file
payload() {
  f="$TMPDIR/payload_$$_$RANDOM.json"
  node -e "$1" >"$f"
  printf '%s' "$f"
}

echo "state-line-guard-selftest"

# --- 1. Write: line-count boundary ------------------------------------------

P="$(payload '
const content = "x\n".repeat(60);
process.stdout.write(JSON.stringify({
  tool_name: "Write",
  tool_input: { file_path: "/tmp/wherever/STATE.md", content }
}));
')"
run_hook "$P"
[ "$HOOK_EXIT" -eq 0 ]; check "Write: exactly 60 lines allows" $?

P="$(payload '
const content = "x\n".repeat(61);
process.stdout.write(JSON.stringify({
  tool_name: "Write",
  tool_input: { file_path: "/tmp/wherever/STATE.md", content }
}));
')"
run_hook "$P"
[ "$HOOK_EXIT" -eq 2 ]; check "Write: 61 lines denies (exit 2)" $?
printf '%s' "$HOOK_STDERR" | grep -q "61"; check "Write: denial message names the projected count" $?
printf '%s' "$HOOK_STDERR" | grep -q "60"; check "Write: denial message names the max" $?

# --- 2. Write: only STATE.md is guarded -------------------------------------

P="$(payload '
const content = "x\n".repeat(500);
process.stdout.write(JSON.stringify({
  tool_name: "Write",
  tool_input: { file_path: "/tmp/wherever/NOTES.md", content }
}));
')"
run_hook "$P"
[ "$HOOK_EXIT" -eq 0 ]; check "Write: non-STATE.md file allows regardless of size" $?

P="$(payload '
const content = "x\n".repeat(500);
process.stdout.write(JSON.stringify({
  tool_name: "Write",
  tool_input: { file_path: "/some/deep/plugin/subdir/STATE.md", content }
}));
')"
run_hook "$P"
[ "$HOOK_EXIT" -eq 2 ]; check "Write: STATE.md matched by basename at any depth" $?

# --- 3. Only Write/Edit are guarded ------------------------------------------

P="$(payload '
const content = "x\n".repeat(500);
process.stdout.write(JSON.stringify({
  tool_name: "Read",
  tool_input: { file_path: "/tmp/wherever/STATE.md", content }
}));
')"
run_hook "$P"
[ "$HOOK_EXIT" -eq 0 ]; check "Read: never guarded, regardless of content field" $?

# --- 4. Malformed / partial input never crashes the hook --------------------

P="$TMPDIR/malformed.json"
printf 'not json at all {' >"$P"
run_hook "$P"
[ "$HOOK_EXIT" -eq 0 ]; check "malformed JSON on stdin fails open" $?

P="$(payload '
process.stdout.write(JSON.stringify({ tool_name: "Write", tool_input: {} }));
')"
run_hook "$P"
[ "$HOOK_EXIT" -eq 0 ]; check "Write with no file_path fails open" $?

P="$(payload '
process.stdout.write(JSON.stringify({
  tool_name: "Write",
  tool_input: { file_path: "/tmp/wherever/STATE.md" }
}));
')"
run_hook "$P"
[ "$HOOK_EXIT" -eq 0 ]; check "Write with no content field fails open" $?

# --- 5. Edit: projects the post-edit file, not the diff ---------------------

FIXTURE="$TMPDIR/a"
mkdir -p "$FIXTURE"
node -e '
const fs = require("fs");
fs.writeFileSync(process.argv[1], "x\n".repeat(55));
' "$FIXTURE/STATE.md"

# 55 lines, replace one "x\n" occurrence with 6 "y\n" lines: net +5 -> 60, allow
P="$(payload "
process.stdout.write(JSON.stringify({
  tool_name: 'Edit',
  tool_input: {
    file_path: '$FIXTURE/STATE.md',
    old_string: 'x\\n',
    new_string: 'y\\n'.repeat(6)
  }
}));
")"
run_hook "$P"
[ "$HOOK_EXIT" -eq 0 ]; check "Edit: projected 60 lines allows" $?

# same fixture, net +6 -> 61, deny
P="$(payload "
process.stdout.write(JSON.stringify({
  tool_name: 'Edit',
  tool_input: {
    file_path: '$FIXTURE/STATE.md',
    old_string: 'x\\n',
    new_string: 'y\\n'.repeat(7)
  }
}));
")"
run_hook "$P"
[ "$HOOK_EXIT" -eq 2 ]; check "Edit: projected 61 lines denies" $?
printf '%s' "$HOOK_STDERR" | grep -q "61"; check "Edit: denial message names the projected count" $?

# --- 6. Edit: replace_all is honored, not just the first occurrence --------

FIXTURE2="$TMPDIR/b"
mkdir -p "$FIXTURE2"
node -e '
const fs = require("fs");
fs.writeFileSync(process.argv[1], "a\n".repeat(50) + "b\n".repeat(5));
' "$FIXTURE2/STATE.md"

# 55 lines total. replace_all doubles each of the 50 "a\n" occurrences
# (a\n -> a\na\n): net +50 -> 105 lines. A hook that only replaced the FIRST
# occurrence would project 56 lines and wrongly allow this.
P="$(payload "
process.stdout.write(JSON.stringify({
  tool_name: 'Edit',
  tool_input: {
    file_path: '$FIXTURE2/STATE.md',
    old_string: 'a\\n',
    new_string: 'a\\na\\n',
    replace_all: true
  }
}));
")"
run_hook "$P"
[ "$HOOK_EXIT" -eq 2 ]; check "Edit: replace_all counts every occurrence, not just the first" $?

# --- 7. Edit: cases the hook must leave to the real tool --------------------

P="$(payload "
process.stdout.write(JSON.stringify({
  tool_name: 'Edit',
  tool_input: {
    file_path: '$FIXTURE/STATE.md',
    old_string: 'this string is not in the fixture',
    new_string: 'y\\n'.repeat(500)
  }
}));
")"
run_hook "$P"
[ "$HOOK_EXIT" -eq 0 ]; check "Edit: old_string not found in file fails open" $?

P="$(payload "
process.stdout.write(JSON.stringify({
  tool_name: 'Edit',
  tool_input: {
    file_path: '$TMPDIR/does-not-exist/STATE.md',
    old_string: 'x',
    new_string: 'y\\n'.repeat(500)
  }
}));
")"
run_hook "$P"
[ "$HOOK_EXIT" -eq 0 ]; check "Edit: nonexistent file fails open" $?

echo ""
echo "state-line-guard-selftest: $PASS passed, $FAIL failed"
[ "$FAIL" -eq 0 ] || exit 1
exit 0