#!/usr/bin/env node
// Hook: pre-bash-executor.mjs
// Event: PreToolUse (Bash)
// Purpose: Block or warn about destructive shell commands, and ask a person
//   before merge into main, push, tag/release and destructive git (P12).
//   Wired universally (every Voyage session, not just execution) by deliberate
//   decision -- these are session-agnostic safety rails (rm -rf /, fork bombs,
//   ...). The CC if: path-scoping mechanism now works, but narrowing to
//   execute-only would only weaken protection with no offsetting benefit. See
//   cc-upgrade matrix CC-15/F2.
//
// Precondition: Voyage's guards are deterministic only when no installed mod
//   handles `tool.check`. A mod that does answers after the PreToolUse hooks
//   and can replace their answer (code.claude.com/docs/en/permissions section Extend
//   permissions with hooks). A hook cannot see whether such a mod is installed.
//
// Protocol:
//   - Read JSON from stdin: { tool_name, tool_input, cwd }
//   - tool_input.command — the shell command string
//   - BLOCK (exit 2): catastrophic/irreversible operations
//   - ASK   (exit 0, JSON permissionDecision "ask"): merge into main, push,
//     tag/release, destructive git (hooks/lib/git-approval.mjs). The prompt is
//     labelled [plugin:voyage] and also appears in auto mode (hooks reference
//     section PreToolUse decision control). Advisories are added to the prompt.
//     In the permission mode that shows no prompts, every call it would ask
//     about is BLOCKED instead: there is no one to ask (operator, 2026-10-09).
//   - WARN  (exit 0): risky but recoverable operations — advisory to stderr
//   - Allow (exit 0): everything else
//
// Based on llm-security's pre-bash-destructive.mjs with executor-specific additions.
// Command reading lives in hooks/lib/bash-view.mjs (shared with the hook that
// logs approvals).

import { readFileSync } from 'node:fs';

// The guard's own modules are loaded so that a broken install cannot crash
// the hook: a crash (exit 1) is a non-blocking error to Claude Code, which
// would let every command through. A module that will not load makes the
// guard ask about every command instead, and refuse it where no one can be asked.
let lib;
let loadError = null;
try {
  const [view, approval, record] = await Promise.all([
    import('../lib/bash-view.mjs'),
    import('../lib/git-approval.mjs'),
    import('../lib/approval-record.mjs'),
  ]);
  lib = { ...view, ...approval, ...record };
} catch (e) {
  loadError = e;
}

// ---------------------------------------------------------------------------
// BLOCK rules — exit 2, command is not executed.
// ---------------------------------------------------------------------------
const BLOCK_RULES = [
  {
    name: 'Filesystem root/home destruction (rm -rf /)',
    // Matches rm with both -r and -f flags targeting /, ~, or $HOME.
    // Uses (?:\s|$) instead of \b because / and ~ are non-word chars.
    pattern: /\brm\s+(?:-[a-zA-Z]*f[a-zA-Z]*\s+|--force\s+)*-[a-zA-Z]*r[a-zA-Z]*\s+(?:\/|~|\$HOME)(?:\s|$)/,
    description:
      '`rm -rf /`, `rm -rf ~`, and `rm -rf $HOME` would destroy the filesystem ' +
      'or home directory. Unconditionally blocked.',
  },
  {
    name: 'World-writable chmod (chmod 777)',
    pattern: /\bchmod\s+(?:-[a-zA-Z]+\s+)*777\b/,
    description:
      '`chmod 777` grants full read/write/execute to all users. ' +
      'Use minimal permissions (e.g. 644, 755).',
  },
  {
    name: 'Pipe-to-shell (curl|bash, wget|sh)',
    pattern: /(?:curl|wget)\b[^|]*\|\s*(?:bash|sh|zsh|ksh|dash)\b/,
    description:
      'Piping remote content into a shell allows arbitrary remote code execution. ' +
      'Download first, review, then execute.',
  },
  {
    name: 'Fork bomb',
    pattern: /:\(\)\s*\{\s*:\s*\|\s*:&\s*\}\s*;?\s*:/,
    description: 'Fork bomb — exhausts system process resources. Blocked.',
  },
  {
    name: 'Filesystem format (mkfs)',
    pattern: /\bmkfs(?:\.[a-z0-9]+)?\s/,
    description: '`mkfs` formats a filesystem, destroying all data. Blocked.',
  },
  {
    name: 'Raw disk overwrite via dd',
    pattern: /\bdd\b[^&|;]*\bof=\/dev\/(?:sd|nvme|hd|vd|xvd|mmcblk)[a-z0-9]*/,
    description: '`dd` writing to a raw block device destroys disk data. Blocked.',
  },
  {
    name: 'Direct device write (> /dev/sd*)',
    pattern: />\s*\/dev\/(?:sd|nvme|hd|vd|xvd|mmcblk)[a-z0-9]*/,
    description: 'Shell redirection to a block device destroys disk data. Blocked.',
  },
  {
    name: 'eval with variable/command expansion',
    pattern: /\beval\s+(?:`|\$[\({]|"[^"]*\$)/,
    description:
      '`eval` with variable or command substitution is a code injection vector. ' +
      'Refactor to use explicit commands.',
  },
  // --- Executor-specific additions ---
  {
    name: 'System shutdown/reboot',
    // Anchored to command position — start of string/line, or after a
    // separator (`;`, `|`, `&`, `&&`), with optional `sudo` and an optional
    // absolute path. An unanchored \b match blocked the bare word anywhere,
    // including quoted grep patterns, heredoc data, and commit messages.
    //
    // Runs against commandView, not the whitespace-collapsed string: collapsing
    // \s+ to ' ' would erase the newline separator before the pattern ever saw
    // it, and quoted spans must read as data, not as command position.
    commandView: true,
    pattern: /(?:^|[\n;|&])\s*(?:sudo\s+(?:-[a-zA-Z]+\s+)*)?(?:[\w./-]*\/)?(?:shutdown|reboot|halt|poweroff)\b/,
    description: 'System shutdown/reboot commands are blocked during execution.',
  },
  {
    name: 'Cron persistence',
    pattern: /\bcrontab\b|>\s*\/etc\/cron/,
    description:
      'Writing to crontab or /etc/cron* creates persistent scheduled tasks. ' +
      'Blocked during execution.',
  },
  {
    name: 'Base64-encoded execution',
    pattern: /\bbase64\b[^|]*\|\s*(?:bash|sh|zsh)\b/,
    description: 'Base64-decoded content piped to shell is obfuscated code execution. Blocked.',
  },
  {
    name: 'Kill all processes (kill -9 -1)',
    pattern: /\b(?:kill|pkill)\s+-9\s+-1\b/,
    description: 'Killing all user processes with signal 9. Blocked.',
  },
  {
    name: 'History destruction',
    pattern: /\bhistory\s+-c\b|>\s*~\/\.bash_history\b|>\s*~\/\.zsh_history\b/,
    description: 'Clearing shell history or truncating history files. Blocked.',
  },
];

// ---------------------------------------------------------------------------
// WARN rules — exit 0 with advisory message on stderr.
// ---------------------------------------------------------------------------
const WARN_RULES = [
  {
    name: 'Force push (git push --force)',
    pattern: /\bgit\s+push\b[^|&;]*(?:--force|-f)\b/,
    description:
      'WARNING: `git push --force` rewrites remote history. Prefer `--force-with-lease`.',
  },
  {
    name: 'Hard reset (git reset --hard)',
    pattern: /\bgit\s+reset\s+--hard\b/,
    description:
      'WARNING: `git reset --hard` permanently discards uncommitted changes.',
  },
  {
    name: 'Recursive remove (rm -rf, non-root)',
    pattern: /\brm\s+(?:-[a-zA-Z]*f[a-zA-Z]*\s+|--force\s+)*-[a-zA-Z]*r[a-zA-Z]*\s+/,
    description:
      'WARNING: `rm -rf` permanently deletes files. Verify the target path.',
  },
  {
    name: 'Docker system prune',
    pattern: /\bdocker\s+system\s+prune\b/,
    description:
      'WARNING: `docker system prune` removes all stopped containers and unused images.',
  },
  {
    name: 'npm publish',
    pattern: /\bnpm\s+publish\b/,
    description:
      'WARNING: `npm publish` releases a package to the public registry.',
  },
  {
    name: 'DROP TABLE or DROP DATABASE (SQL)',
    pattern: /\bDROP\s+(?:TABLE|DATABASE|SCHEMA)\b/i,
    description:
      'WARNING: SQL DROP permanently deletes database objects.',
  },
  {
    name: 'DELETE without WHERE (SQL)',
    pattern: /\bDELETE\s+FROM\s+\w+(?:\s*;|\s*$)/i,
    description:
      'WARNING: DELETE FROM without WHERE deletes all rows.',
  },
  // --- Executor-specific additions ---
  {
    name: 'Dependency installation during execution',
    pattern: /\b(?:npm\s+install\s+--save|pip3?\s+install\s+(?!-e\s+\.)|cargo\s+add)\b/,
    description:
      'WARNING: Installing dependencies during plan execution is unusual. ' +
      'Verify this is intentional.',
  },
];

// ---------------------------------------------------------------------------
// Main
// ---------------------------------------------------------------------------
let input;
try {
  const raw = readFileSync(0, 'utf-8');
  input = JSON.parse(raw);
} catch {
  // Cannot parse stdin — fail open.
  process.exit(0);
}

const command = input?.tool_input?.command;

if (!command || typeof command !== 'string') {
  process.exit(0);
}

// In the permission mode where Claude Code shows no prompts, an "ask" reaches
// no one and the call runs unattended (see the refusals below).
const NO_PROMPT_MODE = 'bypassPermissions';
const noOneToAsk = input.permission_mode === NO_PROMPT_MODE;

// The one refusal text for "no one to ask", with the way forward (release
// review of 6.3.0, round 7: it was written out twice).
function refuseUnattended(what, commandLine, way) {
  process.stderr.write(
    `[voyage] BLOCKED: ${what} with no one to ask\n` + commandLine +
    '  This session runs in the permission mode where Claude Code asks nothing, so the guard cannot ask a person. ' +
    `Way forward: ${way}\n`
  );
  process.exit(2);
}

if (loadError) {
  // A guard that cannot read its rules asks about every command; where no one
  // can be asked it refuses instead (release review of 6.3.0, 2026-10-10).
  if (noOneToAsk) {
    refuseUnattended(`Voyage's Bash guard could not load its rules (${loadError.message})`, '',
      'reinstall Voyage to restore the guard, or run the command yourself.');
  }
  process.stdout.write(JSON.stringify({
    hookSpecificOutput: {
      hookEventName: 'PreToolUse',
      permissionDecision: 'ask',
      permissionDecisionReason:
        `Voyage's Bash guard could not load its rules (${loadError.message}), so this command was not checked. ` +
        'Way forward: approve only a command you have read yourself; reinstall Voyage to restore the guard.',
    },
  }));
  process.exit(0);
}
const { normalizeBashExpansion, normalizeCommand, commandPositionView, classifyGitApproval, askReason, writeApprovalRecord } = lib;

// Strip bash evasion, then normalize whitespace
const deobfuscated = normalizeBashExpansion(command);
const normalized = normalizeCommand(deobfuscated);
const commandView = commandPositionView(deobfuscated.replace(/\x1B\[[0-9;]*m/g, ''));

// BEGIN args-heredoc-closed-early
// The commands hand $ARGUMENTS to lib/parsers/arg-parser.mjs (--stdin) through
// a quoted heredoc closed by VOYAGE_ARGS_EOF_7F3C9E. A typed line equal to that
// delimiter would close the heredoc there, and the shell would run every line
// after it as a command (fix round 4.5b, R6). This check reads the raw
// command: `normalized` and `commandView` collapse lines and drop heredoc
// bodies (hooks/lib/bash-view.mjs). A command that never names the delimiter
// skips the whole check.
// Every opener in the command is read in two ways, and the command is blocked
// when either reading blocks it (the union):
//   1. A regex finds <<D, <<'D', <<"D" and <<\D, with an optional - and
//      spaces (fix round 4.5b and its part 2).
//   2. A shell reading (fix round 4.5b, part 3) starts at every < in the
//      text, wherever it stands; like the regex, it does not lex the command
//      around it. A backslash directly followed by a line break is a
//      continuation: removed, not quoting. The word after << (and an optional
//      -, spaces and tabs) is read as the shell reads it: a backslash makes
//      the next character literal and quotes the word; '...', "...", $'...'
//      and $"..." quote it, so a partly quoted word such as
//      <<"VOYAGE"_ARGS_EOF_7F3C9E counts. The word ends at unquoted
//      whitespace (a line break included),
//      at one of ; & | ( ) < > or at the end of the text. Its body lines are
//      the raw lines after the line on which the word ends: continuations
//      change only how the word is read, never the line count.
// bash reads a heredoc body only from the lines after the opener's line, so
// an opener with no non-blank line after it (a one-line grep or commit
// message that only mentions it) has no body: nothing can close early and an
// unquoted opener has nothing to expand, so it is skipped. An opener with a
// non-blank line after it is blocked unless it is quoted (its body is not
// expanded) and exactly one line, trimmed, equals the delimiter with every
// line after that one empty (the regex reading counts every line of the
// command, the shell reading the body lines).
// A word the guard cannot read is treated as unquoted, whatever its letters:
// a quote with no partner anywhere in the rest of the text (the word is cut
// there, so its line is the quote's line), any backslash inside "...",
// $"..." or $'...' (no escape there is decoded), a backslash at the end of
// the text, a - reached only after a continuation (bash reads <<-, zsh
// reads the - as part of the word), and a continuation between a $ and the
// quote it opens. The word is compared with the delimiter after trim(), the
// same trim the body lines get, so a CR (a CRLF line), VT, FF or other
// character trim() strips around the word does not hide it.
// After a quoted opener that passes, a later opener is skipped only when its
// word is cut by an unpaired quote and is readable otherwise: the shell meets
// the same unpaired quote, stops with a parse error and runs nothing after it,
// so a typed argument such as fix "<<" handling passes. Every other later
// opener is checked, because the accepted opener may sit inside a string and
// must not hide a real opener after it.
// The shell reading fails closed: an error in it blocks (exit 2), because an
// exit 1 is a non-blocking error and the command would run.
const ARGS_DELIM = 'VOYAGE_ARGS_EOF_7F3C9E';

function blockArgs(unquoted, unreadable) {
  const why = unquoted
    ? `The heredoc that hands the arguments to the arg parser opens ${ARGS_DELIM} unquoted, so the shell would expand its body. ` +
      `Way forward: open it as <<'${ARGS_DELIM}'.`
    : `The arguments hold a line equal to the heredoc's closing line ${ARGS_DELIM}, or text follows that closing line, ` +
      'so the shell would run what follows as commands. Way forward: take that line out of the arguments and run the command again.';
  const unread = unreadable ? " The guard could not read the opener's word, so it treats it as unquoted." : '';
  process.stderr.write(
    '[voyage] BLOCKED: args-heredoc-closed-early\n' +
    `  Command: ${normalized.slice(0, 200)}${normalized.length > 200 ? '...' : ''}\n` +
    `  ${why}${unread}\n`
  );
  process.exit(2);
}

// Each heredoc operator in `text`, in text order, as the shell reads its word:
// { index (the operator's first <), end, word, quoted, unreadable, cutOnly }.
function argsShellOpeners(text) {
  const n = text.length;
  // The index after any run of continuations that starts at k.
  const skip = (k) => {
    while (text[k] === '\\' && text[k + 1] === '\n') k += 2;
    return k;
  };
  const openers = [];
  let i = text.indexOf('<');
  while (i !== -1) {
    let next = i + 1;
    let k = skip(i + 1);
    if (text[k] === '<') {
      const second = k;
      // The scan resumes right after the second <, never at the word's end,
      // so a quoted word that spans lines cannot hide a < inside it.
      next = second + 1;
      k = skip(second + 1);
      if (text[k] === '<') {
        next = k + 1; // a here-string: move past it
      } else {
        let unreadable = false;
        if (text[k] === '-') {
          // After a continuation, bash reads <<- and zsh reads - as the word.
          if (k !== second + 1) unreadable = true;
          k = skip(k + 1);
        }
        while (k < n) {
          if (text[k] === ' ' || text[k] === '\t') k += 1;
          else if (text[k] === '\\' && text[k + 1] === '\n') k += 2;
          else break;
        }
        const start = k;
        let word = '';
        let quoted = false;
        let cut = -1;
        while (k < n) {
          const c = text[k];
          if (c === ' ' || c === '\t' || c === '\n' || ';&|()<>'.includes(c)) break;
          if (c === '\\') {
            if (text[k + 1] === '\n') { k += 2; continue; }
            if (k + 1 >= n) { unreadable = true; k += 1; break; }
            word += text[k + 1];
            quoted = true;
            k += 2;
            continue;
          }
          // A $ opens $'...' or $"..." also across continuations; a
          // continuation between the $ and the quote makes the word unreadable.
          const q1 = c === '$' ? skip(k + 1) : k + 1;
          const dollar = c === '$' && (text[q1] === "'" || text[q1] === '"');
          if (dollar && q1 !== k + 1) unreadable = true;
          if (c === "'" || c === '"' || dollar) {
            const open = dollar ? q1 : k;
            const q = text[open];
            const close = text.indexOf(q, open + 1);
            if (close === -1) { cut = open; break; }
            const inner = text.slice(open + 1, close);
            if ((q === '"' || dollar) && inner.includes('\\')) unreadable = true;
            word += inner;
            quoted = true;
            k = close + 1;
            continue;
          }
          word += c;
          k += 1;
        }
        const isCut = cut !== -1;
        if (k > start || unreadable || isCut) {
          openers.push({
            index: i,
            end: isCut ? cut : k,
            word,
            quoted,
            unreadable: unreadable || isCut,
            cutOnly: isCut && !unreadable,
          });
        }
      }
    }
    i = text.indexOf('<', next);
  }
  return openers;
}

if (command.includes(ARGS_DELIM)) {
  const argsOpeners = command.matchAll(new RegExp(`<<-?\\s*(['"\\\\]?)${ARGS_DELIM}(['"]?)`, 'g'));
  const argsLines = command.split('\n');
  const argsClosing = argsLines.flatMap((l, i) => (l.trim() === ARGS_DELIM ? [i] : []));
  const closesOnceAtEnd = argsClosing.length === 1 &&
    argsLines.slice(argsClosing[0] + 1).every((line) => line.trim() === '');
  for (const argsOpener of argsOpeners) {
    // Some line after the opener's line is non-blank (\s is the set trim() strips).
    const hasBody = /\n\s*\S/.test(command.slice(argsOpener.index));
    if (!hasBody) continue;
    const [, open, close] = argsOpener;
    const quoted = open === '\\' ? close === '' : open !== '' && close === open;
    if (!quoted || !closesOnceAtEnd) blockArgs(!quoted, false);
  }
  // The shell reading. The loop records the first failing verdict; an error
  // anywhere in it blocks.
  let argsVerdict = null;
  try {
    let bodyFrom = Infinity;
    for (const o of argsShellOpeners(command)) {
      if (o.index >= bodyFrom && o.cutOnly) continue;
      // The word is compared trimmed, as the body lines are: a word of D plus
      // characters trim() strips (a CR from a CRLF line, a VT, an FF, a
      // no-break space) is closed by a line equal to it, which trims to D.
      if (o.word.trim() !== ARGS_DELIM && !o.unreadable) continue;
      const nl = command.indexOf('\n', o.end);
      if (nl === -1) continue;
      // The raw lines after the line on which the word ends.
      const body = argsLines.slice(command.slice(0, nl).split('\n').length);
      if (!body.some((line) => line.trim() !== '')) continue;
      const isQuoted = o.quoted && !o.unreadable;
      const closing = body.flatMap((l, i) => (l.trim() === ARGS_DELIM ? [i] : []));
      if (isQuoted && closing.length === 1 && body.slice(closing[0] + 1).every((line) => line.trim() === '')) {
        if (bodyFrom === Infinity) bodyFrom = nl + 1;
        continue;
      }
      argsVerdict = [!isQuoted, o.unreadable];
      break;
    }
  } catch {
    blockArgs(true, true);
  }
  if (argsVerdict) blockArgs(argsVerdict[0], argsVerdict[1]);
}
// END args-heredoc-closed-early

// Check BLOCK rules first
for (const rule of BLOCK_RULES) {
  if (rule.pattern.test(rule.commandView ? commandView : normalized)) {
    process.stderr.write(
      `[voyage] BLOCKED: ${rule.name}\n` +
      `  Command: ${normalized.slice(0, 200)}${normalized.length > 200 ? '...' : ''}\n` +
      `  ${rule.description}\n`
    );
    process.exit(2);
  }
}

// Check WARN rules (advisory — still exit 0)
const warnings = [];
for (const rule of WARN_RULES) {
  if (rule.pattern.test(normalized)) {
    warnings.push(`  [WARN] ${rule.name}: ${rule.description}`);
  }
}

if (warnings.length > 0) {
  process.stderr.write(
    `[voyage] SECURITY ADVISORY: Potentially risky command.\n` +
    `  Command: ${normalized.slice(0, 200)}${normalized.length > 200 ? '...' : ''}\n` +
    warnings.join('\n') + '\n'
  );
}

// P12: ask a person before merge into main, push, tag/release, destructive git.
// A classifier error must not turn into a silent allow of a push: ask instead.
let approvals;
try {
  approvals = classifyGitApproval(command, { cwd: input.cwd });
} catch (e) {
  approvals = [{ name: `a command the approval guard could not read (${e.message})`, kind: null, way: 'approve only if you have read the command yourself.' }];
}

// In the permission mode where Claude Code shows no prompts, an "ask" reaches
// no one and the call runs unattended. Everything this guard would ask about -
// merge into main, push, tag/release, destructive git, and a command it could
// not read - is refused there instead, with the way forward (operator
// decisions 2026-10-09: first merge and push, then the other two classes).
// /trekexecute relies on this: its main-merge gate is a lock, and this guard's
// question is the one question.
if (noOneToAsk && approvals.length > 0) {
  refuseUnattended(approvals.map((m) => m.name).join(', '),
    `  Command: ${normalized.slice(0, 200)}${normalized.length > 200 ? '...' : ''}\n`,
    'run the command yourself, or switch to a mode that asks, then retry.');
}

if (approvals.length > 0) {
  // What the person is asked is what post-approval-log.mjs logs once the call ran.
  const loggable = approvals.filter((m) => m.kind).map(({ kind, name, subject }) => ({ kind, name, subject }));
  const recorded = writeApprovalRecord(input.session_id, input.tool_use_id, {
    command,
    permission_mode: input.permission_mode ?? null,
    matches: loggable,
    asked_at: new Date().toISOString(),
  });
  // Say it now if this approval cannot reach the log afterwards.
  const unlogged = loggable.length > 0 && !recorded
    ? ' Note: this approval will not be logged (Voyage could not record the question).' : '';
  const advisory = (warnings.length > 0 ? ` Advisory: ${warnings.map((w) => w.trim()).join(' ')}` : '') + unlogged;
  process.stdout.write(JSON.stringify({
    hookSpecificOutput: {
      hookEventName: 'PreToolUse',
      permissionDecision: 'ask',
      permissionDecisionReason: askReason(approvals) + advisory,
    },
  }));
}

process.exit(0);