gstack/bin/gstack-redact-prepush

#!/usr/bin/env bun
/**
 * gstack-redact-prepush — git pre-push hook that scans the diff being pushed for
 * HIGH-severity credentials and blocks the push on a hit.
 *
 * THIS IS A GUARDRAIL, NOT ENFORCEMENT. `git push --no-verify` bypasses it, as
 * does `GSTACK_REDACT_PREPUSH=skip`. It catches accidental credential pushes,
 * the most common real-world leak. It does NOT scan history, binary/LFS/submodule
 * files, or non-added lines. History scanning is /cso's job.
 *
 * Git pre-push interface: refs are read from STDIN, one per line:
 *   <local ref> <local sha> <remote ref> <remote sha>
 * We scan the ADDED lines of <remote sha>..<local sha> per ref (what's being
 * pushed). Special cases:
 *   - remote sha all-zeroes  → new branch: diff against merge-base with the
 *     remote's default branch (fallback: scan all commits unique to local ref).
 *   - local sha all-zeroes   → branch delete: nothing to scan, skip.
 *   - force-push             → remote..local still gives the net new content.
 *
 * Behavior:
 *   - HIGH finding in added lines → print + exit 1 (block), for public AND private.
 *   - MEDIUM → warn (non-blocking), one line per finding naming its rule,
 *     file line and fix, never the matched value. LOW/WARN → silent.
 *   - `pii.email` skips the pusher's own address, `gstack.redact.allowEmail`
 *     entries, and addresses already in the destination's commit metadata
 *     (see emailScanOptions).
 *   - `.gstack-redact-allowlist`, read from each pushed commit (never the
 *     working tree), lists exact matched spans reviewed as benign, one per
 *     line, `#` comments. Only a finding whose matched text equals an entry is
 *     suppressed; every push that carries entries lists what they suppressed.
 *   - GSTACK_REDACT_PREPUSH=skip → log + exit 0 (escape valve).
 *
 * Installed/uninstalled via `gstack-redact install-prepush-hook` (see the
 * gstack-redact CLI), which chains any pre-existing hook.
 */
import { spawnSync } from "child_process";
import * as fs from "fs";
import * as path from "path";
import { normalizeWithMap, scan, type Finding, type ScanOptions } from "../lib/redact-engine";
import { mkdirpSync } from "../lib/fs-utils";
import { resolveStateRoot } from "../lib/state-root";

const ZERO = /^0+$/;
let emptyTree: string | undefined;
function emptyTreeOid(): string {
  if (emptyTree) return emptyTree;
  const oid = gitStrict(["hash-object", "-w", "-t", "tree", "--stdin"]).trim();
  if (!/^(?:[0-9a-f]{40}|[0-9a-f]{64})$/.test(oid)) throw new Error("git could not resolve the empty tree");
  emptyTree = oid;
  return oid;
}

/**
 * Permissive git for legitimately-fallible PROBES (symbolic-ref, rev-parse,
 * merge-base) where a non-zero exit is normal control flow. The DIFF call
 * must NOT use this — see gitStrict (#1946 fail-closed).
 */
function git(args: string[]): string {
  const r = spawnSync("git", args, { encoding: "utf8", maxBuffer: 64 * 1024 * 1024 });
  return r.status === 0 ? (r.stdout ?? "") : "";
}

/**
 * Fail-closed git for the diff that decides whether the push is scanned
 * (#1946). status !== 0 covers repo errors; status === null covers a killed
 * process AND maxBuffer overflow — the oversized-diff case is exactly where
 * a large secret-bearing blob is most likely, so "couldn't read the diff"
 * must block, not silently allow.
 */
function gitStrict(args: string[]): string {
  const r = spawnSync("git", args, { encoding: "utf8", maxBuffer: 64 * 1024 * 1024 });
  // status !== 0 covers BOTH a non-zero exit AND null (process killed by a
  // signal or maxBuffer overflow — null !== 0 is true).
  if (r.status !== 0) {
    throw new Error(
      `git ${args[0]} failed (status=${r.status ?? "killed/overflow"}): ${(r.stderr ?? "").slice(0, 300)}`,
    );
  }
  return r.stdout ?? "";
}

/** True when the object exists in the local odb (cat-file -e signals via exit code). */
function objectExists(sha: string): boolean {
  const r = spawnSync("git", ["cat-file", "-e", sha], { encoding: "utf8" });
  return r.status === 0;
}

/**
 * The remote-tracking exclusion used when narrowing to "commits new to the
 * remote" (#2592 catch-up merges, #2573 rebased force-pushes).
 *
 * Narrowed to the PUSH TARGET's namespace (S1): a bare `--remotes` excludes
 * commits reachable from ANY remote-tracking ref, so a secret that had only
 * ever been fetched from (or pushed to) a private/local-path remote was never
 * scanned when later pushed to a PUBLIC remote — "already left this machine"
 * is not "already reached THIS remote". Git hands pre-push the push remote's
 * name as $1 (and its URL as $2); the installed hook wrapper forwards "$@".
 * A URL push has no tracking namespace, even if origin happens to contain
 * the same commits. Direct invocations without Git's argv keep the historical
 * all-remotes behavior for compatibility.
 */
type PushTarget = { kind: "remote"; name: string } | { kind: "url" } | { kind: "unknown" };
let cachedPushTarget: PushTarget | undefined;
function pushTarget(): PushTarget {
  if (cachedPushTarget) return cachedPushTarget;
  const name = process.argv[2];
  const url = process.argv[3];
  if (!name && !url) return cachedPushTarget = { kind: "unknown" };
  if (!name || !url) return cachedPushTarget = { kind: "url" };
  const remotes = git(["remote"]).split("\n");
  if (!remotes.includes(name)) return cachedPushTarget = { kind: "url" };
  const pushUrls = git(["remote", "get-url", "--push", "--all", name]).trim().split("\n");
  const fetchUrls = git(["remote", "get-url", "--all", name]).trim().split("\n");
  return cachedPushTarget = pushUrls.includes(url) && fetchUrls[0] === url
    ? { kind: "remote", name }
    : { kind: "url" };
}

function remotesExclusionArgs(): string[] {
  const target = pushTarget();
  if (target.kind === "remote") return [`--remotes=${target.name}/*`];
  return target.kind === "unknown" ? ["--remotes"] : [];
}

function defaultRemoteBranch(): string | null {
  const target = pushTarget();
  if (target.kind === "url") return null;
  const remote = target.kind === "remote" ? target.name : "origin";
  const sym = git(["symbolic-ref", `refs/remotes/${remote}/HEAD`]).trim();
  if (sym.startsWith(`refs/remotes/${remote}/`) && git(["rev-parse", "--verify", `${sym}^{commit}`]).trim()) return sym;
  for (const b of [`${remote}/main`, `${remote}/master`]) {
    const qualified = `refs/remotes/${b}`;
    if (git(["rev-parse", "--verify", `${qualified}^{commit}`]).trim()) return qualified;
  }
  return null;
}

/**
 * Base commit for a new remote ref, ordered from most precise to most
 * conservative. Returns null when nothing can anchor the range.
 */
function unknownRemoteTipBase(localSha: string): string | null {
  // 1. The common case: a merge-base with the remote's default branch.
  const defaultBranch = defaultRemoteBranch();
  const base = defaultBranch ? git(["merge-base", localSha, defaultBranch]).trim() : "";
  if (base) return base;

  // 2. No merge-base. The target's default branch may be unavailable
  //    (named trunk/develop, remote/HEAD unset), or history may be disjoint.
  //    Anything reachable from localSha but from NO remote-tracking
  //    branch is what this push actually adds; the parent of its oldest commit
  //    is the real base.
  //
  //    Without this we drop straight to EMPTY_TREE and re-scan content that is
  //    already on the remote. That is not merely wasteful, it is wrong in two
  //    ways: a secret pushed long ago gets re-reported as if THIS push
  //    introduced it (telling the operator to rotate a key over someone else's
  //    old commit), and on any real repository the input overshoots the
  //    engine's byte cap, so `engine.input_too_large` blocks having scanned
  //    NOTHING — "scans more, never less" inverted into "scans nothing".
  //
  //    The exclusion is scoped to the PUSH TARGET's tracking refs (see
  //    remotesExclusionArgs): content on some OTHER remote has left this machine,
  //    but it has not reached the remote being pushed to — a secret that only
  //    ever hit a private remote must still be scanned on its way to a public
  //    one (S1).
  const exclusions = remotesExclusionArgs();
  const newCommits = git(["rev-list", "--reverse", localSha, ...(exclusions.length ? ["--not", ...exclusions] : [])]).trim();
  if (newCommits) {
    const oldest = newCommits.split("\n")[0];
    const parent = git(["rev-parse", "--verify", `${oldest}^`]).trim();
    if (parent) return parent;
    // Oldest new commit is a root commit: there is no parent to anchor on.
  }

  // 3. Nothing to anchor on — a genuinely fresh repository with no remote refs.
  //    Every commit IS new content, so scanning it all is the correct answer.
  return null;
}

/**
 * The commits this push actually adds — reachable from localSha and from NO
 * remote-tracking ref.
 *
 * ⚠ WHY THIS EXISTS RATHER THAN A TWO-DOT RANGE.
 *
 * `remoteSha..localSha` is "everything new on this branch", which is NOT the
 * same as "everything new to the remote". Merge origin/main into a feature
 * branch and every commit main gained since the branch's last push becomes an
 * added line — content that is already published, already scanned, and not
 * this push's doing.
 *
 * Two things follow, and both were observed:
 *
 *   · FALSE HIGH FINDINGS. A placeholder connection string in a test fixture,
 *     already merged to main by someone else, blocked an unrelated push as
 *     `db.url_with_password` — telling the operator to rotate a credential
 *     over a fixture they had never touched. A
 *     guard that cries wolf on catch-up merges is a guard people learn to
 *     bypass reflexively — which is exactly how a real secret gets through.
 *   · OVERSIZED SCANS. The comment on SCAN_CHUNK_BYTES below records a
 *     1,146,782-byte diff from "a feature branch catching up to a busy main"
 *     blowing the engine's 1 MiB cap. Same root cause, treated there as a size
 *     problem and solved by slicing. Narrowing the range fixes the size too.
 *
 * A two-dot range cannot express this: after merging main, neither the remote
 * tip nor the merge-base with main is an ancestor of the other, so no single
 * base excludes both. `rev-list --not --remotes=<push-remote>/*` is the
 * operation that does, and this file already reasons that way in
 * `unknownRemoteTipBase` step 2. The exclusion is scoped to the push target's
 * tracking namespace (see remotesExclusionArgs): the upstream commits a catch-up
 * merge brings in came from the SAME remote being pushed to, so scoping keeps
 * the #2592 fix intact while a secret known only to some OTHER (private)
 * remote is still scanned on its way to this one (S1).
 *
 * Each commit is diffed alone. `--cc` on a merge shows only the conflict
 * RESOLUTION — content that exists in no parent — so a secret introduced while
 * resolving a merge is still caught, while an ordinary merge contributes
 * nothing. Returns null when the notion does not apply, so callers fall back.
 */
function addedLinesFromNewCommits(localSha: string, remoteSha: string): AddedFile[] | null {
  // remoteSha is what git TELLS us the remote has, and it is authoritative in a
  // way `--remotes` is not: remote-tracking refs can be absent (a fresh clone
  // that never fetched, a push to a remote with no tracking ref) or stale. Drop
  // it and a repo with no tracking refs excludes NOTHING — every commit ever
  // made reads as "new", which re-introduces the false positives from the other
  // direction. So it stays the base; `--remotes` only ADDS exclusions on top.
  if (ZERO.test(remoteSha) || !objectExists(remoteSha)) return null;

  const narrowed = git(["rev-list", localSha, "--not", remoteSha, ...remotesExclusionArgs()]).trim();
  if (!narrowed) return null;

  // If excluding remote-tracking refs changes nothing, this push has no
  // catch-up commits and the plain range already describes it exactly. Defer to
  // it. That is not just an optimization: it keeps every push that ISN'T a
  // catch-up merge on the original gitStrict diff path, so the fail-closed
  // guarantee (#1946) and its regression test keep exercising the code they
  // were written for. A narrowing that silently retired that test would be a
  // worse trade than the false positives it set out to fix.
  const plain = git(["rev-list", `${remoteSha}..${localSha}`]).trim();
  const asSet = (s: string) => s.split("\n").filter(Boolean).sort().join("\n");
  if (asSet(narrowed) === asSet(plain)) return null;

  const shas = narrowed.split("\n").filter(Boolean);
  // A rewrite of long history should fall back rather than shell out per commit.
  if (shas.length > 500) return null;
  const out: AddedFile[] = [];
  for (const sha of shas) {
    // gitStrict: a failed diff must never read as "nothing added" (#1946).
    // Collected per commit so a finding names the commit whose file line it is.
    out.push(...collectAddedLines(gitStrict([
      "show", "--unified=0", "--no-color", "--no-ext-diff", "--no-textconv",
      "--src-prefix=a/", "--dst-prefix=b/", "--cc", "--format=", sha,
    ]), sha));
  }
  return out;
}

/**
 * Added lines grouped by the file they were added to (`+++ b/` path; empty
 * when unknown). `lines[i]` is the file line number of the i-th line of
 * `text`, read from the hunk headers; `commit` is set when the lines came from
 * one commit's diff rather than the net diff of the pushed range.
 */
interface AddedFile { file: string; text: string; lines: number[]; commit?: string }

/** Return the added lines for a ref update being pushed. */
function addedLinesFor(localSha: string, remoteSha: string): AddedFile[] {
  // Preferred ONLY when this push carries catch-up commits: scanning them again
  // is the bug. Every other shape falls through to the range logic below.
  const fromNew = addedLinesFromNewCommits(localSha, remoteSha);
  if (fromNew !== null) return fromNew;

  let range: string;
  if (ZERO.test(remoteSha) || !objectExists(remoteSha)) {
    const base = ZERO.test(remoteSha) ? unknownRemoteTipBase(localSha) : null;
    range = base ? `${base}..${localSha}` : `${emptyTreeOid()}..${localSha}`;
  } else {
    // Existing branch (incl. force-push): net new content remote..local.
    range = `${remoteSha}..${localSha}`;
  }
  // -U0: only changed lines; we keep lines starting with '+' (added), drop the
  // +++ file header. Unified diff added lines start with a single '+'.
  // Strict (#1946): a failed diff used to return "" and the push sailed
  // through unscanned — fail open on the exact path the guard exists for.
  //
  // --no-ext-diff: a user's `diff.external` driver replaces the entire diff
  // with its own output — with one set, `git diff` emits zero '+' lines, so an
  // unhardened scanner reads an empty diff and exits 0 on a push full of
  // secrets. Reachable from ordinary user config, not hypothetical. (#2498)
  // --no-textconv: a .gitattributes textconv driver can likewise rewrite
  // content before we ever see it. (#2498)
  const diff = gitStrict([
    "diff", "--unified=0", "--no-color", "--no-ext-diff", "--no-textconv",
    "--src-prefix=a/", "--dst-prefix=b/", range,
  ]);
  return collectAddedLines(diff);
}

/**
 * Added-line text from a unified diff. Shared by both range strategies so the
 * hunk-aware header handling below cannot drift between them.
 */
function collectAddedLines(diff: string, commit?: string): AddedFile[] {
  const added: AddedFile[] = [];
  // Hunk-aware header skip (#2498): `+++ ` is only a FILE HEADER outside a
  // hunk. Inside a hunk, an added content line whose text begins with "++"
  // renders as "+++<content>" — the old blanket startsWith("+++") skip
  // silently dropped exactly those lines from the scan.
  let inHunk = false;
  let file = "";
  let fileLines: string[] = [];
  let lineNumbers: number[] = [];
  // File line tracking from hunk headers. A combined (--cc) header has one
  // more `@` than it has parents, and each body line one prefix column per
  // parent; a line belongs to the resulting file unless a column says `-`.
  let parents = 1;
  let nextLine = 0;
  const flush = () => {
    const lines = releaseVersionExempt(file, fileLines);
    if (lines.length) added.push({ file, text: lines.join("\n"), lines: lineNumbers, ...(commit ? { commit } : {}) });
    fileLines = [];
    lineNumbers = [];
  };
  for (const line of diff.split("\n")) {
    // `diff --` rather than `diff --git`: a merge scanned with --cc emits
    // `diff --cc <path>`, so a --git-only reset left inHunk true across file
    // boundaries and read the next file's `+++ b/...` header as content. Only
    // noise (it over-scans, never under-scans), but the boundary is real.
    if (line.startsWith("diff --")) { flush(); file = ""; inHunk = false; continue; }
    if (line.startsWith("@@")) {
      inHunk = true;
      parents = (/^@+/.exec(line)?.[0].length ?? 2) - 1;
      nextLine = Number(/ \+(\d+)(?:,\d+)? @+/.exec(line)?.[1] ?? 0);
      continue;
    }
    if (!inHunk && line.startsWith("+++ ")) { file = line.startsWith("+++ b/") ? line.slice(6) : ""; continue; }
    if (!inHunk && (line.startsWith("+++") || line.startsWith("---"))) continue;
    const inResult = inHunk && !line.startsWith("\\") && !line.slice(0, parents).includes("-");
    const lineNumber = inResult ? nextLine++ : 0;
    if (line.startsWith("+")) {
      // A combined (--cc) body line carries one prefix column per parent.
      fileLines.push(line.slice(inHunk ? parents : 1));
      lineNumbers.push(lineNumber);
    }
  }
  flush();
  return added;
}

const VERSION_FILE_CONTENT = /^\d+(?:\.\d+)+$/;
const CHANGELOG_RELEASE_VERSION = /^(#{1,6}[\t ]*\[?v?)\d+(?:\.\d+){3}(?=[\]\t ]|$)/;

/**
 * #2856: a 4-part release version (MAJOR.MINOR.PATCH.MICRO) is shaped exactly like a
 * public IPv4 address, so /ship's own VERSION bump and CHANGELOG heading
 * raised pii.ip_public on every release. Exempt only those two release
 * artifacts, decided from the pushed diff alone (works in shallow clones):
 * a root VERSION whose entire added content is one version string, and the
 * version token of a root CHANGELOG.md release heading (the rest of the
 * heading is still scanned). Every other file — and any other position in
 * these two — is scanned unchanged; the engine's global allowlist is untouched.
 */
function releaseVersionExempt(file: string, lines: string[]): string[] {
  if (file === "VERSION" && lines.length === 1 && VERSION_FILE_CONTENT.test(lines[0].trim())) return [];
  if (file === "CHANGELOG.md") return lines.map((l) => l.replace(CHANGELOG_RELEASE_VERSION, "$1VERSION"));
  return lines;
}

/**
 * Byte budget per scan() call. Kept comfortably under redact-engine's
 * DEFAULT_MAX_BYTES (1 MiB) so a slice never trips its oversize guard.
 */
const SCAN_CHUNK_BYTES = 768 * 1024;
const SCAN_OVERLAP_CHARS = 16 * 1024;
const MAX_SCAN_BYTES = 1024 * 1024;

/**
 * Scan complete-line core slices with bounded left and right context. Admit
 * only findings whose original captured start lies inside that core.
 *
 * Why: the engine refuses input over its byte cap and fails closed, which is
 * right for one scan() call but wrong as a push policy — a feature branch
 * catching up to a busy main legitimately produces more added lines than the
 * cap (1,146,782 bytes against the 1 MiB default in the push that prompted
 * this, and only ~7% of that was the lockfile). The push then blocked on
 * `engine.input_too_large` — a size error naming no credential — which trains
 * people to reach for --no-verify, defeating the guardrail far more thoroughly
 * than a large diff does.
 *
 * A match may need context on either adjacent line (`nearWindow` reaches 300
 * normalized characters). The full core lines keep opaque spans intact; the
 * engine's normalization map selects context in normalized units without
 * changing the raw input. A partial context may create an artificial boundary,
 * but its findings are never admitted as core findings.
 *
 * Fail-closed is preserved: a SINGLE line over the budget is still passed to
 * the engine intact, so a genuinely unscannable blob (minified bundle,
 * embedded base64) trips input_too_large and blocks exactly as before.
 *
 * The engine reports line/col relative to each slice; an admitted finding's
 * `line` is rewritten to its 1-based line within `added`, which the caller
 * maps to the file line. Do not lift this into the engine, where callers rely
 * on absolute line numbers.
 */
function scanAddedLines(added: string, opts: Parameters<typeof scan>[1]): Finding[] {
  const findings: Finding[] = [];
  const cores: Array<{ start: number; end: number }> = [];
  const lines = added.split("\n");
  let start = 0;
  let end = 0;
  let bytes = 0;
  for (let i = 0; i < lines.length; i++) {
    const line = lines[i];
    const newline = i < lines.length - 1 ? 1 : 0;
    const lineBytes = Buffer.byteLength(line, "utf8") + newline;
    if (bytes && bytes + lineBytes > SCAN_CHUNK_BYTES) {
      cores.push({ start, end });
      start = end;
      bytes = 0;
    }
    end += line.length + newline;
    bytes += lineBytes;
    if (lineBytes > SCAN_CHUNK_BYTES) {
      cores.push({ start, end });
      start = end;
      bytes = 0;
    }
  }
  if (bytes) cores.push({ start, end });

  const contextStart = (boundary: number): number => {
    if (!boundary) return 0;
    let length = Math.min(boundary, SCAN_OVERLAP_CHARS * 2);
    while (true) {
      const from = boundary - length;
      const raw = added.slice(from, boundary);
      if (Buffer.byteLength(raw, "utf8") > MAX_SCAN_BYTES) return from;
      const { normalized, map } = normalizeWithMap(raw);
      if (!from || normalized.length > SCAN_OVERLAP_CHARS) {
        return from + (map[Math.max(0, normalized.length - SCAN_OVERLAP_CHARS - 1)] ?? 0);
      }
      length = Math.min(boundary, length * 2);
    }
  };

  const contextEnd = (boundary: number): number => {
    if (boundary === added.length) return boundary;
    let length = Math.min(added.length - boundary, SCAN_OVERLAP_CHARS * 2);
    while (true) {
      const to = boundary + length;
      const raw = added.slice(boundary, to);
      if (Buffer.byteLength(raw, "utf8") > MAX_SCAN_BYTES) return to;
      const { normalized, map } = normalizeWithMap(raw);
      if (to === added.length || normalized.length > SCAN_OVERLAP_CHARS) {
        return boundary + (map[Math.min(normalized.length, SCAN_OVERLAP_CHARS + 1)] ?? length);
      }
      length = Math.min(added.length - boundary, length * 2);
    }
  };

  const addedLineStarts = [0];
  for (let i = 0; i < added.length; i++) if (added[i] === "\n") addedLineStarts.push(i + 1);
  const lineAt = (offset: number): number => {
    let lo = 0;
    let hi = addedLineStarts.length - 1;
    while (lo < hi) {
      const mid = (lo + hi + 1) >> 1;
      if (addedLineStarts[mid] <= offset) lo = mid;
      else hi = mid - 1;
    }
    return lo + 1;
  };

  for (const core of cores) {
    const left = contextStart(core.start);
    const text = added.slice(left, contextEnd(core.end));
    const result = scan(text, opts);
    if (result.oversize) {
      findings.push(...result.findings);
      return findings;
    }
    const starts = [0];
    for (let i = 0; i < text.length; i++) if (text[i] === "\n") starts.push(i + 1);
    for (const finding of result.findings) {
      const offset = starts[finding.line - 1] + finding.col - 1 + left;
      if (offset >= core.start && offset < core.end) findings.push({ ...finding, line: lineAt(offset) });
    }
  }

  return findings;
}

function logSkip(reason: string): void {
  try {
    const home = resolveStateRoot();
    const dir = path.join(home, "security");
    // mkdirpSync, not bare mkdirSync: bun-on-Windows EEXIST (#2635). This site
    // is try-wrapped by the caller, so the old failure was a silent skip-log
    // loss rather than a crash — the fix makes the log survive, not un-crash.
    mkdirpSync(dir);
    fs.appendFileSync(
      path.join(dir, "prepush-skip.jsonl"),
      JSON.stringify({ ts: new Date().toISOString(), reason }) + "\n",
    );
  } catch {
    // best-effort; never block a push because logging failed
  }
}

const HISTORY_MAX_COMMITS = 50_000;
const HISTORY_TIMEOUT_MS = 5_000;

function configValues(args: string[]): string[] {
  return git(["config", ...args]).split("\n").map((v) => v.trim()).filter(Boolean);
}

/**
 * Addresses `pii.email` treats as not a new leak (#3060): the pusher's own
 * (`git config user.email`), the ones listed in `gstack.redact.allowEmail`,
 * and the author and committer addresses (raw and mailmapped) the destination
 * will hold after this push. That last set is the history of every pushed tip
 * (pushed commits become public with the push, third-party authors included),
 * of each remote tip being replaced, and, for a ref whose remote tip is new or
 * unknown, the push remote's own tracking refs. A URL or unknown destination
 * never borrows a remote's tracking refs; another remote's history never counts.
 *
 * Each input fails on its own and a failure omits only that input, which is
 * the behavior before these exemptions existed. The history read is bounded:
 * past the commit cap it uses the newest authors it read; an error or the
 * timeout passes no history, and the reason is returned so the report can say
 * suppression was limited.
 */
function emailScanOptions(historyRevs: string[], trackingRemote: string | null): {
  options: Pick<ScanOptions, "selfEmail" | "repoPublicEmails">;
  limited?: string;
} {
  const selfEmail = configValues(["--get", "user.email"])[0];
  const allowed = configValues(["--get-all", "gstack.redact.allowEmail"]);
  const r = spawnSync("git", [
    "log", "--no-show-signature", "--no-color", `--max-count=${HISTORY_MAX_COMMITS}`, "--format=%ae%n%aE%n%ce%n%cE",
    ...historyRevs, ...(trackingRemote ? [`--remotes=${trackingRemote}/*`] : []), "--",
  ], { encoding: "utf8", maxBuffer: 64 * 1024 * 1024, timeout: HISTORY_TIMEOUT_MS, killSignal: "SIGKILL" });
  const timedOut = (r.error as NodeJS.ErrnoException | undefined)?.code === "ETIMEDOUT";
  const history = r.status === 0 && !r.error
    ? (r.stdout ?? "").split("\n").map((e) => e.trim()).filter((e) => e.includes("@"))
    : null;
  return {
    options: {
      ...(selfEmail ? { selfEmail } : {}),
      repoPublicEmails: [...new Set([...(history ?? []), ...allowed])],
    },
    ...(history ? {} : { limited: timedOut ? `reading commit history took over ${HISTORY_TIMEOUT_MS / 1000} s` : "reading commit history failed" }),
  };
}

const ALLOWLIST_PATH = ".gstack-redact-allowlist";
const ALLOWLIST_MAX_BYTES = 64 * 1024;

/**
 * Entries of the allowlist committed in `sha`. Read from the pushed commit so
 * a suppression exists only as a reviewable commit. Absent, unreadable or
 * oversized means no entries: the file can record a reviewed exception, never
 * loosen the scan by accident.
 */
function committedAllowlist(sha: string): string[] {
  const spec = `${sha}:${ALLOWLIST_PATH}`;
  const size = Number(git(["cat-file", "-s", spec]).trim());
  if (!size) return [];
  if (size > ALLOWLIST_MAX_BYTES) {
    process.stderr.write(
      `gstack-redact-prepush: ${ALLOWLIST_PATH} in ${sha.slice(0, 12)} is over ${ALLOWLIST_MAX_BYTES} bytes; ignoring it.\n`,
    );
    return [];
  }
  return git(["cat-file", "blob", spec]).split("\n")
    .map((l) => l.trim())
    .filter((l) => l && !l.startsWith("#"));
}

/** File line (and commit) of a finding. Never the matched value. */
function findingWhere(f: Finding, part: AddedFile): string {
  const line = part.lines[f.line - 1];
  return `${part.file || "(unknown file)"}${line ? `:${line}` : ""}` +
    (part.commit ? ` in commit ${part.commit.slice(0, 12)}` : "");
}

/** One MEDIUM report line: rule id, file line (and commit), and the fix. Never the matched value. */
function mediumLine(f: Finding, part: AddedFile): string {
  const where = findingWhere(f, part);
  const fix = f.id === "pii.email"
    ? "remove the address, or allow it: git config --add gstack.redact.allowEmail <address>"
    : "remove the value before it becomes public";
  return `  MEDIUM  ${f.id}  ${where}  fix: ${fix}\n`;
}

function main() {
  if ((process.env.GSTACK_REDACT_PREPUSH || "").toLowerCase() === "skip") {
    logSkip(process.env.GSTACK_REDACT_PREPUSH_REASON || "env-skip");
    process.stderr.write("gstack-redact-prepush: skipped via GSTACK_REDACT_PREPUSH=skip\n");
    process.exit(0);
  }

  const stdin = fs.readFileSync(0, "utf8");
  const refs = stdin
    .split("\n")
    .map((l) => l.trim())
    .filter(Boolean)
    .map((l) => l.split(/\s+/));

  const parts: Array<{ part: AddedFile; allowlist: string[] }> = [];
  const allowEntries = new Set<string>();
  const historyRevs = new Set<string>();
  let trackingRemote: string | null = null;

  for (const fields of refs) {
    // Fail CLOSED on a ref line we cannot parse (#2498): git hands pre-push
    // exactly "<local ref> <local sha> <remote ref> <remote sha>" — anything
    // else means we cannot tell WHAT is being pushed, and silently skipping
    // it would leave that ref unscanned.
    const [, localSha, , remoteSha] = fields;
    const shaShaped = (s: string | undefined) => !!s && /^[0-9a-f]{40,64}$/i.test(s);
    if (fields.length !== 4 || !shaShaped(localSha) || !shaShaped(remoteSha)) {
      process.stderr.write(
        "\n⛔ gstack-redact-prepush BLOCKED the push — could not parse a pre-push ref line, " +
          "so its content cannot be scanned.\n" +
          `  line: ${JSON.stringify(fields.join(" "))}\n` +
          "Bypass if you're sure: GSTACK_REDACT_PREPUSH=skip git push   (or git push --no-verify)\n",
      );
      process.exit(1);
    }
    if (ZERO.test(localSha!)) continue; // branch delete → nothing pushed
    let added: AddedFile[];
    try {
      added = addedLinesFor(localSha, remoteSha || "0");
    } catch (err) {
      // Fail CLOSED (#1946): if we can't compute the pushed diff we can't
      // scan it, and unscanned-but-allowed is the failure mode this hook
      // exists to prevent.
      process.stderr.write(
        "\n⛔ gstack-redact-prepush BLOCKED the push — could not compute the pushed diff, " +
          "so it cannot be scanned for credentials.\n" +
          `  (${err instanceof Error ? err.message.split("\n")[0] : String(err)})\n` +
          "Bypass if you're sure: GSTACK_REDACT_PREPUSH=skip git push   (or git push --no-verify)\n",
      );
      process.exit(1);
    }
    const allowlist = committedAllowlist(localSha);
    for (const entry of allowlist) allowEntries.add(entry);
    for (const part of added) if (part.text.trim()) parts.push({ part, allowlist });
    historyRevs.add(localSha);
    if (!ZERO.test(remoteSha) && objectExists(remoteSha)) historyRevs.add(remoteSha);
    else {
      const target = pushTarget();
      if (target.kind === "remote") trackingRemote = target.name;
    }
  }

  const allHigh: Finding[] = [];
  const mediums: string[] = [];
  let emailMedium = false;
  const emails = parts.length ? emailScanOptions([...historyRevs], trackingRemote) : { options: {} };
  // Visibility doesn't change HIGH behavior; pass private so nothing is treated
  // as public-strict (HIGH blocks regardless either way).
  // Sliced (see scanAddedLines) so a large-but-legitimate diff is actually
  // scanned rather than blocked unscanned on the engine's size cap.
  // Scanned per file so a pattern can use the file's type (#3048).
  // An allowlisted span is found by scanning with and without the entries,
  // so the report names exactly what they suppressed.
  const allowed: string[] = [];
  const findingKey = (f: Finding) => `${f.id}:${f.line}:${f.col}`;
  for (const { part, allowlist } of parts) {
    const opts = { repoVisibility: "private" as const, ...emails.options, ...(part.file ? { sourcePath: part.file } : {}) };
    const findings = scanAddedLines(part.text, opts);
    const kept = allowlist.length
      ? new Set(scanAddedLines(part.text, { ...opts, allowlist }).map(findingKey))
      : null;
    for (const f of findings) {
      if (kept && !kept.has(findingKey(f))) {
        if (f.severity === "HIGH" || f.severity === "MEDIUM") allowed.push(`  ${f.severity}  ${f.id}  ${findingWhere(f, part)}\n`);
        continue;
      }
      if (f.severity === "HIGH") allHigh.push(f);
      else if (f.severity === "MEDIUM") {
        mediums.push(mediumLine(f, part));
        if (f.id === "pii.email") emailMedium = true;
      }
    }
  }

  if (allowEntries.size > 0) {
    process.stderr.write(
      `gstack-redact-prepush: ${ALLOWLIST_PATH} (${allowEntries.size} entr${allowEntries.size === 1 ? "y" : "ies"}) ` +
        `suppressed ${allowed.length} finding(s) in this push${allowed.length ? ":" : "."}\n`,
    );
    for (const line of allowed) process.stderr.write(line);
  }

  if (mediums.length > 0) {
    process.stderr.write(
      `gstack-redact-prepush: ${mediums.length} MEDIUM finding(s) in pushed diff (PII/internal). ` +
        "Not blocking. Review before this becomes public.\n",
    );
    for (const line of mediums) process.stderr.write(line);
    if (emailMedium && "limited" in emails && emails.limited) {
      process.stderr.write(
        `gstack-redact-prepush: existing-email suppression was limited for this push (${emails.limited}), ` +
          "so an address already in the history may be listed above.\n",
      );
    }
  }

  if (allHigh.length > 0) {
    // A scan that could not RUN is not a scan that FOUND something. Reporting
    // "credential(s) in the pushed diff — rotate the credential" for an
    // `engine.*` finding tells the operator to rotate a secret that was never
    // detected, on a diff that was never read. Blocking is still right (fail
    // closed), but the reason must be the true one: a guardrail that cries wolf
    // is a guardrail that gets bypassed by reflex, which is worse than none.
    // The computed range can be much larger than the visible tip diff, and a
    // single over-cap line is deliberately withheld rather than partly scanned.
    const unscanned = allHigh.filter((f) => f.id.startsWith("engine."));
    const secrets = allHigh.filter((f) => !f.id.startsWith("engine."));

    if (secrets.length > 0) {
      process.stderr.write(
        "\n⛔ gstack-redact-prepush BLOCKED the push — credential(s) in the pushed diff:\n\n",
      );
      for (const f of secrets) {
        process.stderr.write(`  HIGH  ${f.id}  ${f.preview}\n`);
      }
      process.stderr.write(
        "\nRotate the credential (a pushed secret is compromised) and remove it from the diff.\n" +
          `If the value is a known-benign sample, commit its exact matched text as a line of ${ALLOWLIST_PATH}\n` +
          "at the repo root instead of reshaping code to dodge the pattern; every push lists what that file suppresses.\n",
      );
    }

    if (unscanned.length > 0) {
      process.stderr.write(
        "\n⛔ gstack-redact-prepush BLOCKED the push — the diff could NOT be scanned.\n" +
          "   No credential was found; none was looked for. Blocking fail-closed.\n\n",
      );
      for (const f of unscanned) {
        process.stderr.write(`  ${f.id}: ${f.description}\n`);
      }
      process.stderr.write(
        "\nA long line, large first push, or unavailable remote tip may exceed the\n" +
          "per-slice safety cap. Check the destination and range; scan the diff yourself\n" +
          "before bypassing: `git diff <base>..HEAD | grep -inE \'password|secret|token|api.?key\'`.\n",
      );
    }

    process.stderr.write(
      "This is a guardrail: `git push --no-verify` or `GSTACK_REDACT_PREPUSH=skip git push` bypass it.\n",
    );
    process.exit(1);
  }

  process.exit(0);
}

main();