gstack/bin/gstack-redact

#!/usr/bin/env bun
/**
 * gstack-redact — scan text for secrets/PII/legal content via the shared engine.
 *
 * Skill-facing CLI over lib/redact-engine.ts. Reads from stdin (default) or
 * --from-file, scans, and prints findings as JSON (--json) or a human table.
 *
 * Exit codes (consumed by skill bash to gate dispatch/file/edit/commit):
 *   0  clean (no HIGH, no MEDIUM)
 *   2  MEDIUM present (no HIGH) — skill runs the per-finding AskUserQuestion
 *   3  HIGH present            — skill blocks
 *
 * WARN findings (tool-fence-degraded credentials) never change the exit code.
 *
 * Flags:
 *   --json                       Emit JSON {findings, counts, repoVisibility, oversize}
 *   --repo-visibility V          public | private | unknown (default unknown=public-strict wording)
 *   --from-file PATH             Read input from PATH instead of stdin
 *   --allowlist PATH             Newline-delimited exact spans to suppress
 *   --self-email EMAIL           Suppress this email (the invoking user's own)
 *   --repo-public-emails PATH    Newline-delimited repo-public emails to suppress
 *   --auto-redact IDS            Comma-separated finding ids to auto-redact;
 *                                prints the redacted body to stdout + diff to stderr.
 *   --max-bytes N                Override the fail-closed size cap (default 1 MiB).
 *
 * Security note: this is a GUARDRAIL, not airtight enforcement. A determined
 * user can always bypass it (direct gh/git). It catches accidents.
 */
import * as fs from "fs";
import * as path from "path";
import { spawnSync } from "child_process";
import {
  scan,
  applyRedactions,
  exitCodeFor,
  type RepoVisibility,
  type ScanOptions,
  type Finding,
} from "../lib/redact-engine";
import { mkdirpSync } from "../lib/fs-utils";

const MAX_STDIN_BYTES = 16 * 1024 * 1024; // hard ceiling before the engine cap

// ── pre-push hook install/uninstall (chains any existing hook) ────────────────

const MANAGED_MARKER = "# gstack-redact pre-push (managed)";

function hooksPath(): string {
  const r = spawnSync("git", ["rev-parse", "--git-path", "hooks"], { encoding: "utf8" });
  if (r.status !== 0) {
    process.stderr.write("gstack-redact: not in a git repo\n");
    process.exit(1);
  }
  return r.stdout.trim();
}

function installPrepushHook(): void {
  const dir = hooksPath();
  // mkdirpSync, not bare mkdirSync: bun on Windows throws EEXIST from a
  // recursive mkdir when .git/hooks already exists (#2635).
  mkdirpSync(dir);
  const hookPath = path.join(dir, "pre-push");
  const prepushBin = path.join(import.meta.dir, "gstack-redact-prepush");

  // If a non-managed hook exists, preserve it as pre-push.local and chain it.
  if (fs.existsSync(hookPath)) {
    const existing = fs.readFileSync(hookPath, "utf8");
    if (existing.includes(MANAGED_MARKER)) {
      process.stdout.write("gstack-redact: pre-push hook already installed.\n");
      return;
    }
    const localPath = path.join(dir, "pre-push.local");
    fs.renameSync(hookPath, localPath);
    fs.chmodSync(localPath, 0o755);
    process.stdout.write("gstack-redact: preserved existing hook as pre-push.local (chained).\n");
  }

  // stdin is single-consume: capture it once, feed both the chained hook and ours.
  // The `printf x` sentinel preserves the trailing newline that `$(cat)` strips.
  // Without it, a chained shell pre-push.local built on `while read` silently
  // drops the final (often only) ref line and exits 0 — the guard reports
  // success having scanned nothing, i.e. it fails OPEN.
  const wrapper = `#!/usr/bin/env bash
${MANAGED_MARKER}
set -euo pipefail
_input="$(cat; printf x)"
_input="\${_input%x}"
_local="$(git rev-parse --git-path hooks/pre-push.local)"
if [ -x "$_local" ]; then
  printf '%s' "$_input" | "$_local" "$@" || exit $?
fi
printf '%s' "$_input" | bun "${prepushBin}" "$@"
`;
  fs.writeFileSync(hookPath, wrapper, { mode: 0o755 });
  fs.chmodSync(hookPath, 0o755);
  process.stdout.write(`gstack-redact: installed pre-push hook at ${hookPath}\n`);
}

function uninstallPrepushHook(): void {
  const dir = hooksPath();
  const hookPath = path.join(dir, "pre-push");
  const localPath = path.join(dir, "pre-push.local");
  if (!fs.existsSync(hookPath) || !fs.readFileSync(hookPath, "utf8").includes(MANAGED_MARKER)) {
    process.stdout.write("gstack-redact: no managed pre-push hook to remove.\n");
    return;
  }
  if (fs.existsSync(localPath)) {
    fs.renameSync(localPath, hookPath); // restore the chained original
    process.stdout.write("gstack-redact: removed managed hook, restored pre-push.local.\n");
  } else {
    fs.unlinkSync(hookPath);
    process.stdout.write("gstack-redact: removed managed pre-push hook.\n");
  }
}

function arg(name: string): string | undefined {
  const i = process.argv.indexOf(name);
  return i >= 0 ? process.argv[i + 1] : undefined;
}
function flag(name: string): boolean {
  return process.argv.includes(name);
}

function readInput(): string {
  const file = arg("--from-file");
  if (file) {
    const st = fs.statSync(file);
    if (st.size > MAX_STDIN_BYTES) {
      // Don't even read it — fail closed at the CLI boundary.
      process.stderr.write(`gstack-redact: input file too large (${st.size} bytes)\n`);
      process.exit(3);
    }
    return fs.readFileSync(file, "utf8");
  }
  // stdin
  const chunks: Buffer[] = [];
  let total = 0;
  const fd = 0;
  const buf = Buffer.alloc(65536);
  while (true) {
    let n = 0;
    try {
      n = fs.readSync(fd, buf, 0, buf.length, null);
    } catch (e: any) {
      if (e.code === "EAGAIN") continue;
      if (e.code === "EOF") break;
      throw e;
    }
    if (n === 0) break;
    total += n;
    if (total > MAX_STDIN_BYTES) {
      process.stderr.write("gstack-redact: stdin too large\n");
      process.exit(3);
    }
    chunks.push(Buffer.from(buf.subarray(0, n)));
  }
  return Buffer.concat(chunks).toString("utf8");
}

function readLines(path: string | undefined): string[] | undefined {
  if (!path || !fs.existsSync(path)) return undefined;
  return fs
    .readFileSync(path, "utf8")
    .split("\n")
    .map((l) => l.trim())
    .filter(Boolean);
}

function buildOpts(): ScanOptions {
  const vis = (arg("--repo-visibility") as RepoVisibility) || "unknown";
  const maxBytes = arg("--max-bytes");
  // #1824: validate the RAW string, not the parse result. parseInt("123abc")
  // is 123 and parseInt("foo") is NaN — both silently corrupt the fail-closed
  // oversize guard. Require a clean positive integer or reject before scanning.
  let maxBytesOpt: number | undefined;
  if (maxBytes !== undefined) {
    if (!/^\d+$/.test(maxBytes) || Number(maxBytes) <= 0) {
      process.stderr.write(
        `gstack-redact: --max-bytes must be a positive integer (got "${maxBytes}")\n`,
      );
      process.exit(1);
    }
    maxBytesOpt = Number(maxBytes);
  }
  return {
    repoVisibility: ["public", "private", "unknown"].includes(vis) ? vis : "unknown",
    allowlist: readLines(arg("--allowlist")),
    selfEmail: arg("--self-email"),
    repoPublicEmails: readLines(arg("--repo-public-emails")),
    ...(maxBytesOpt !== undefined ? { maxBytes: maxBytesOpt } : {}),
  };
}

function humanTable(findings: Finding[]): string {
  if (!findings.length) return "  (no findings)";
  const rows = findings.map(
    (f) =>
      `  ${f.severity.padEnd(6)} ${f.id.padEnd(24)} ${String(f.line).padStart(4)}:${String(
        f.col,
      ).padEnd(3)} ${f.preview}`,
  );
  return rows.join("\n");
}

/**
 * Usage. Exits 0 when asked for (--help), 1 when the invocation was wrong.
 *
 * Deliberately NOT 2 or 3: those mean MEDIUM and HIGH findings, and callers
 * gate dispatch on them (see the exit-code table at the top). A usage error
 * that exited 2 would be read as "medium findings — prompt the user".
 */
function printUsage(code: number): never {
  const out = code === 0 ? process.stdout : process.stderr;
  out.write(
    "gstack-redact — scan text for secrets/PII/legal content.\n" +
      "\n" +
      "Reads the text to scan from STDIN, or from --from-file PATH. It is a\n" +
      "filter: with nothing piped in it has nothing to scan.\n" +
      "\n" +
      "  git diff | gstack-redact --repo-visibility private\n" +
      "  gstack-redact --from-file notes.md --json\n" +
      "\n" +
      "Subcommands:\n" +
      "  install-prepush-hook     install the managed git pre-push credential guard\n" +
      "  uninstall-prepush-hook   remove it\n" +
      "\n" +
      "Flags: --json --repo-visibility V --from-file PATH --allowlist PATH\n" +
      "       --self-email EMAIL --repo-public-emails PATH --auto-redact IDS\n" +
      "       --max-bytes N\n" +
      "\n" +
      "Exit: 0 clean · 1 usage error · 2 MEDIUM present · 3 HIGH present\n",
  );
  process.exit(code);
}

function main() {
  // Subcommands (positional, not flags).
  const sub = process.argv[2];
  if (sub === "install-prepush-hook") return installPrepushHook();
  if (sub === "uninstall-prepush-hook") return uninstallPrepushHook();
  if (sub === "--help" || sub === "-h" || sub === "help") return printUsage(0);

  // An unrecognized POSITIONAL is a typo, not input. This used to fall through
  // to the stdin scan, which on empty stdin prints "(no findings)" and exits 0
  // — so `install-prepush-hooks` (plural) installed nothing and still looked
  // like success, leaving the credential guard absent while the operator
  // believed it was armed. A guard that no-ops must never exit 0.
  //
  // "scan" is exempt: the human output header reads "gstack-redact scan —
  // repo …", so people reasonably type it. It stays an alias for the default.
  // Flags start with "-" and are parsed further down, so only bare words land
  // here.
  if (sub !== undefined && sub !== "scan" && !sub.startsWith("-")) {
    process.stderr.write(`gstack-redact: unknown subcommand "${sub}"\n\n`);
    return printUsage(1);
  }

  const opts = buildOpts();

  // Nothing piped in and no --from-file: readInput() below blocks on
  // readSync(fd 0) until EOF, which on an interactive terminal never comes.
  // That prints nothing at all and is indistinguishable from a crash or a
  // slow scan. Show usage instead of hanging silently.
  if (!arg("--from-file") && process.stdin.isTTY) return printUsage(1);

  const input = readInput();

  // Auto-redact mode: print redacted body to stdout, diff to stderr, exit 0.
  const autoIds = arg("--auto-redact");
  if (autoIds) {
    const { body, diff, skipped } = applyRedactions(input, autoIds.split(","), opts);
    process.stdout.write(body);
    if (diff) process.stderr.write(diff + "\n");
    if (skipped.length) {
      process.stderr.write(
        `\ngstack-redact: ${skipped.length} finding(s) could not be auto-redacted (structural) — edit manually:\n` +
          skipped.map((f) => `  ${f.id} @ ${f.line}:${f.col}`).join("\n") +
          "\n",
      );
    }
    process.exit(0);
  }

  const result = scan(input, opts);
  const code = exitCodeFor(result);

  if (flag("--json")) {
    process.stdout.write(JSON.stringify(result, null, 2) + "\n");
  } else {
    const vis = result.repoVisibility.toUpperCase();
    process.stdout.write(`gstack-redact scan — repo ${vis}\n`);
    if (result.oversize) {
      process.stdout.write("  BLOCKED — input too large to scan safely (fail-closed)\n");
    } else {
      process.stdout.write(humanTable(result.findings) + "\n");
      const { HIGH, MEDIUM, LOW, WARN } = result.counts;
      process.stdout.write(`  HIGH=${HIGH} MEDIUM=${MEDIUM} LOW=${LOW} WARN=${WARN}\n`);
    }
  }
  process.exit(code);
}

main();