lakehouse/mcp-server/phase_1_6_gate_4.test.ts

// Phase 1.6 Gate 4 absence test.
//
// Spec: docs/PHASE_1_6_BIPA_GATES.md §1 Gate 4 — Engineering acceptance:
//   "Unit test asserts no protected-attribute inference functions exist
//    in search.html or any mcp-server module"
//
// What this guards: the FEMALE_NAMES / NAMES_HISPANIC / SURNAMES_* lookup
// tables and the genderFor() / guessEthnicityFromFirstName() / etc.
// inference functions removed 2026-05-03. Re-introduction would re-open
// (1) Title VII / IL Human Rights Act discriminatory-feature risk and
// (2) BIPA's broad-reading "biometric information derived from a biometric
// identifier" pattern when combined with deepface output.
//
// Strategy: walk every .html / .ts / .tsx / .js / .mjs file under
// mcp-server/ and grep-assert that none of them DEFINE the forbidden
// symbols. We deliberately allow the symbol NAMES to appear inside
// comments — search.html has a removal note that names them so future
// readers know what was excised — but we forbid actual definition
// patterns (var / const / let / function / class member / object literal).

import { test, expect } from "bun:test";
import { readdirSync, statSync, readFileSync } from "node:fs";
import { join } from "node:path";

const FORBIDDEN_DATA_TABLES = [
  // First-name lookup tables
  "FEMALE_NAMES",
  "MALE_NAMES",
  "NAMES_HISPANIC",
  "NAMES_BLACK",
  "NAMES_SOUTH_ASIAN",
  "NAMES_EAST_ASIAN",
  "NAMES_MIDDLE_EASTERN",
  // Surname lookup tables
  "SURNAMES_HISPANIC",
  "SURNAMES_BLACK",
  "SURNAMES_SOUTH_ASIAN",
  "SURNAMES_EAST_ASIAN",
  "SURNAMES_MIDDLE_EASTERN",
];

const FORBIDDEN_FUNCTIONS = [
  "guessGenderFromFirstName",
  "guessEthnicityFromName",
  "guessEthnicityFromFirstName",
  "genderFor",
];

function* walkSource(dir: string): Generator<string> {
  for (const entry of readdirSync(dir)) {
    if (entry === "node_modules" || entry === "dist" || entry.startsWith(".")) continue;
    const path = join(dir, entry);
    const stat = statSync(path);
    if (stat.isDirectory()) {
      yield* walkSource(path);
    } else if (/\.(html|ts|tsx|js|mjs)$/.test(entry)) {
      // Don't grep this test file itself — it lists the forbidden tokens
      // by name as match targets, not as definitions.
      if (path.endsWith("phase_1_6_gate_4.test.ts")) continue;
      yield path;
    }
  }
}

// definitionPatternsFor: returns regexes that match common DEFINITION
// forms in JS/TS/HTML embedded scripts. A bare reference inside a
// comment is intentionally NOT matched.
//
// 2026-05-03 opus scrum WARN (gate_4_test:60) added object-literal +
// class-field patterns: a developer wrapping the lookup tables in
// `const tables = { FEMALE_NAMES: [...] }` or a TypeScript class
// field `FEMALE_NAMES: string[] = [...]` would have bypassed the
// original 4 patterns silently.
function definitionPatternsFor(symbol: string): RegExp[] {
  return [
    // var / const / let SYMBOL =
    new RegExp(`\\b(?:var|const|let)\\s+${symbol}\\b\\s*=`),
    // function SYMBOL(
    new RegExp(`\\bfunction\\s+${symbol}\\s*\\(`),
    // SYMBOL = function(  OR  SYMBOL = (...) =>
    new RegExp(`\\b${symbol}\\s*=\\s*(?:function\\s*\\(|\\([^)]*\\)\\s*=>|async\\s*(?:\\(|function))`),
    // class method: SYMBOL(...) {
    new RegExp(`^\\s*${symbol}\\s*\\([^)]*\\)\\s*\\{`, "m"),
    // object-literal property assigned to an array OR object value:
    //   { SYMBOL: [...]  }  or  SYMBOL: {...}  or  SYMBOL: new Set(...)
    new RegExp(`(?:^|[,{])\\s*${symbol}\\s*:\\s*(?:\\[|\\{|new\\s+(?:Set|Map|Array)\\b)`, "m"),
    // TypeScript / class field with type annotation. The boundary
    // before SYMBOL is start-of-line OR `{`/`;`/`}` so single-line
    // class bodies (`class L { public NAMES_X: string[] = []; }`)
    // are caught alongside multi-line ones.
    new RegExp(`(?:^|[{};])\\s*(?:public|private|protected|readonly|static\\s+)*\\s*${symbol}\\s*:\\s*[^=;{]+=\\s*[\\[\\{]`, "m"),
  ];
}

function findOffenders(filePath: string, text: string): string[] {
  const out: string[] = [];
  for (const sym of [...FORBIDDEN_DATA_TABLES, ...FORBIDDEN_FUNCTIONS]) {
    for (const pattern of definitionPatternsFor(sym)) {
      if (pattern.test(text)) {
        out.push(`${filePath}: definition of ${sym} (matched ${pattern})`);
      }
    }
  }
  return out;
}

test("Gate 4: no protected-attribute inference DEFINITIONS in mcp-server", () => {
  const root = import.meta.dir;
  const offenders: string[] = [];
  for (const path of walkSource(root)) {
    const text = readFileSync(path, "utf8");
    offenders.push(...findOffenders(path, text));
  }
  if (offenders.length > 0) {
    throw new Error(
      `Phase 1.6 Gate 4 violation — protected-attribute inference symbols defined in mcp-server:\n` +
        offenders.map((o) => `  - ${o}`).join("\n"),
    );
  }
  expect(offenders.length).toBe(0);
});

// Sanity: confirm the test actually walks files (otherwise the absence
// assertion is vacuously true). If mcp-server ever lost its source
// tree, this would catch it.
test("Gate 4: walker actually finds source files to scan", () => {
  const root = import.meta.dir;
  let count = 0;
  for (const _ of walkSource(root)) count++;
  expect(count).toBeGreaterThan(5); // mcp-server has more than 5 source files
});

// Defense in depth: the regex itself must catch a synthetic positive.
// If the definition pattern ever stops matching real code, the absence
// test would silently pass on actual reintroductions.
test("Gate 4: regex catches a synthetic positive (defense in depth)", () => {
  const synthetic =
    `var NAMES_HISPANIC = ["Maria"];\n` +
    `function guessEthnicityFromFirstName(name) { return "?"; }\n`;
  const offenders = findOffenders("synthetic_test_input", synthetic);
  expect(offenders.length).toBeGreaterThanOrEqual(2);
  expect(offenders.some((o) => o.includes("NAMES_HISPANIC"))).toBe(true);
  expect(offenders.some((o) => o.includes("guessEthnicityFromFirstName"))).toBe(true);
});

// 2026-05-03 opus scrum WARN regression: the bypass forms a developer
// might use to wrap the lookup tables without tripping the original
// four patterns. All of these MUST trip a definition regex.
test("Gate 4: object-literal and class-field bypasses are caught", () => {
  const bypassForms = [
    // Inline object-literal property → array
    `const tables = { FEMALE_NAMES: ["Maria"] };`,
    // Object property → Set/Map constructor
    `const lookups = { NAMES_BLACK: new Set(["X"]) };`,
    // Multi-line object literal
    `const all = {\n  NAMES_HISPANIC: [...],\n};`,
    // TypeScript class field with type annotation + initializer
    `class Lookup {\n  SURNAMES_BLACK: string[] = ["X"];\n}`,
    // TypeScript public field
    `class L { public NAMES_EAST_ASIAN: string[] = []; }`,
  ];
  for (const synthetic of bypassForms) {
    const offenders = findOffenders("bypass_synthetic", synthetic);
    if (offenders.length === 0) {
      throw new Error(
        `Gate 4 bypass not caught — pattern would slip past:\n  ${synthetic}`,
      );
    }
  }
});