voyage/lib/validators/query-privacy-gate.mjs

// lib/validators/query-privacy-gate.mjs
// Inspect an outbound research query before it leaves the machine. Called
// only from the new high-effort steps (Phase 4.5 dimension discovery + the
// bounded Phase 5 loop turns) — the existing single-pass Phase 5 path is
// unchanged (Step 6, plan-v2).
//
// Two-tier, same shape as lib/exporters/endpoint-validator.mjs's SSRF gate:
//   - WARN tier  — absolute filesystem paths, repo-internal identifiers.
//     Operator-overridable via `strict: false` / `--soft` (matches
//     lib/validators/research-validator.mjs's strict/soft convention), and
//     fully bypassable via the VOYAGE_QUERY_PRIVACY_ALLOW=1 opt-in.
//   - HARD-BLOCK tier — secret-shaped tokens. NEVER overridable by strict,
//     --soft, or the opt-in env var — mirrors endpoint-validator.mjs's
//     HARD_BLOCKED_HOSTS, where an opt-in widens the warn tier but never
//     unlocks the permanently-blocked one.
//
// CLI shim:
//   node lib/validators/query-privacy-gate.mjs [--soft] "<query text>"
//   → JSON {valid, errors, warnings}; exit 0 valid, 1 invalid.

import { issue } from '../util/result.mjs';

// WARN tier — absolute filesystem paths (leaks local directory layout).
export const ABSOLUTE_PATH_PATTERNS = Object.freeze([
  /\/Users\/[^\s"'`]+/,
  /\/home\/[^\s"'`]+/,
  /[A-Za-z]:\\[^\s"'`]+/,
  /\$\{?HOME\}?\/[^\s"'`]+/,
]);

// WARN tier — repo-internal identifiers that don't need to leave the
// machine in a generic research query.
export const REPO_IDENTIFIER_PATTERNS = Object.freeze([
  /git\.fromaitochitta\.com[^\s"'`]*/,
  /\bktg-plugin-marketplace\b/,
  /\bplugins\/cache\/[^\s"'`]+/,
]);

// HARD-BLOCK tier — secret-shaped strings. Never operator-overridable.
//
// Token bodies that contain `-` or `_` break a plain `[A-Za-z0-9]{n,}` run, so
// each such format needs its own pattern rather than relying on run length:
// an Anthropic Console key runs out after `api03` (3 alphanumerics), and a
// fine-grained GitHub PAT after its 22-character segment. Patterns whose body
// class includes `-`/`_` carry no trailing `\b`, which would not fire on a
// non-word final character.
export const SECRET_SHAPED_PATTERNS = Object.freeze([
  /\bsk-[A-Za-z0-9]{20,}\b/, // OpenAI-style API key (sk-<48>)
  /\bsk-ant-[a-z0-9]+-[A-Za-z0-9_-]{20,}/, // Anthropic Console key (sk-ant-api03-/-oat01- + ~95 base64url)
  /\bAKIA[0-9A-Z]{16}\b/, // AWS access key ID
  /\bgh[pousr]_[A-Za-z0-9]{36,}\b/, // GitHub classic PAT / OAuth / user / server / refresh token
  /\bgithub_pat_[A-Za-z0-9_]{20,}/, // GitHub fine-grained PAT (github_pat_<22>_<59>)
  /\bxox[baprs]-[A-Za-z0-9-]{10,}\b/, // Slack token
  /-----BEGIN [A-Z ]*PRIVATE KEY-----/, // PEM private key block
]);

function findMatch(patterns, text) {
  for (const re of patterns) {
    const m = re.exec(text);
    if (m) return m[0];
  }
  return null;
}

/**
 * @param {string} text
 * @param {{strict?: boolean, env?: object}} [opts]
 * @returns {{valid: boolean, errors: import('../util/result.mjs').Issue[], warnings: import('../util/result.mjs').Issue[]}}
 */
export function validateOutboundQuery(text, opts = {}) {
  const strict = opts.strict !== false;
  const env = opts.env || process.env;
  // Bypasses the WARN tier entirely — never affects the hard-block tier below.
  const allowWarnTier = env.VOYAGE_QUERY_PRIVACY_ALLOW === '1';

  if (typeof text !== 'string' || text.length === 0) {
    return { valid: false, errors: [issue('PRIVACY_EMPTY_QUERY', 'Outbound query must be a non-empty string')], warnings: [] };
  }

  const errors = [];
  const warnings = [];

  // Hard-block tier — checked unconditionally; no opt-in reaches this branch.
  const secretMatch = findMatch(SECRET_SHAPED_PATTERNS, text);
  if (secretMatch) {
    errors.push(issue('PRIVACY_SECRET_SHAPED', `Outbound query contains a secret-shaped token: ${secretMatch}`));
  }

  if (!allowWarnTier) {
    const pathMatch = findMatch(ABSOLUTE_PATH_PATTERNS, text);
    if (pathMatch) {
      const issueObj = issue('PRIVACY_ABSOLUTE_PATH', `Outbound query contains an absolute filesystem path: ${pathMatch}`);
      if (strict) errors.push(issueObj); else warnings.push(issueObj);
    }

    const repoMatch = findMatch(REPO_IDENTIFIER_PATTERNS, text);
    if (repoMatch) {
      const issueObj = issue('PRIVACY_REPO_IDENTIFIER', `Outbound query contains a repo-internal identifier: ${repoMatch}`);
      if (strict) errors.push(issueObj); else warnings.push(issueObj);
    }
  }

  return { valid: errors.length === 0, errors, warnings };
}

// ---- CLI shim ----------------------------------------------------------------

if (import.meta.url === `file://${process.argv[1]}`) {
  const args = process.argv.slice(2);
  const strict = !args.includes('--soft');
  const text = args.find(a => !a.startsWith('--'));
  if (text === undefined) {
    process.stderr.write('Usage: query-privacy-gate.mjs [--soft] "<query text>"\n');
    process.exit(2);
  }
  const r = validateOutboundQuery(text, { strict });
  process.stdout.write(JSON.stringify(r) + '\n');
  process.exit(r.valid ? 0 : 1);
}