gstack/lib/ship-policy.ts

/**
 * ship-policy — the machine-readable repo ship policy (plan C1):
 * `.gstack/ship-policy.json`, read from the committed base-branch copy
 * (`origin/<base>`) so a PR cannot smuggle a command into its own gate.
 *
 * File presence never authorizes execution: `release_tool` runs only under
 * `/ship` or `--allow-repo-commands` (bin/gstack-restamp enforces that; this
 * module only names the commands a policy declares). Every repo-controlled
 * path (`stamp_paths`, `release_outputs`, `changelog`, `mirror`) is
 * containment-checked here: no absolute paths, no `..`, globs confined to the
 * repository, regex size caps, and symlink-escape checks when a glob is
 * resolved against a tree. Docs: docs/ship-policy.md. Callers: bin/gstack-
 * ship-policy, lib/restamp.ts, lib/tree-receipt.ts, lib/ship-receipt.ts.
 */
import { spawnSync } from 'node:child_process';
import * as fs from 'node:fs';
import * as path from 'node:path';
import { RESULT_CODES, type ResultCodeName } from './result-codes';

export const SHIP_POLICY_PATH = '.gstack/ship-policy.json';
export const SHIP_POLICY_SCHEMA = 'https://github.com/garrytan/gstack/docs/ship-policy.md#schema-v1';

export type BumpPolicy = 'patch' | 'ask';
export type QueueMode = 'claim-at-open' | 'stamp-at-merge';
export type HistoryPolicy = 'merge-only' | 'squash-ok';

export interface ShipPolicy {
  $schema?: string;
  /** `patch` skips the MINOR/MAJOR prompts in /ship Step 12; `ask` keeps them. */
  bump: BumpPolicy;
  /** `stamp-at-merge`: no claim at PR open; stamp when the PR is next. `claim-at-open` is today's queue. */
  queue_mode: QueueMode;
  /** The repo's own release tool (for example `bun run release:restamp`); run only under /ship or --allow-repo-commands. */
  release_tool: string | null;
  /** Globs the release tool may write beyond the stamp files; any other output is a refusal. */
  release_outputs: string[];
  /** Globs where `(was X)`, `since: X` and `vX` mentions are rewritten on a restamp. */
  stamp_paths: string[];
  /** The CHANGELOG re-headed on a restamp; null for repos without one. */
  changelog: string | null;
  /** Path of a paired repo to restamp identically (tier 2). */
  mirror: string | null;
  /** `merge-only` refuses a squash or rebase plan in /ship. */
  history: HistoryPolicy;
  /** Each must be an ancestor of HEAD before push (`gstack-evidence ancestor`). */
  preregistration_shas: string[];
  /** Evidence labels that consume VERSION or generated bytes and always rerun on the stamped tree. */
  stamp_sensitive_gates: string[];
  /** Consumed by the plan reviews (D1). */
  pr_count: { default_pr_count: number; split_requires_owner: boolean };
  /** Maintainer logins for contributor-PR mode (E3); empty means "use push permission". */
  maintainers: string[];
}

export const DEFAULT_POLICY: ShipPolicy = {
  bump: 'ask',
  queue_mode: 'claim-at-open',
  release_tool: null,
  release_outputs: [],
  stamp_paths: [],
  changelog: 'CHANGELOG.md',
  mirror: null,
  history: 'squash-ok',
  preregistration_shas: [],
  stamp_sensitive_gates: [],
  pr_count: { default_pr_count: 1, split_requires_owner: true },
  maintainers: [],
};

export type PolicyKey = Exclude<keyof ShipPolicy, '$schema'>;
export const POLICY_KEYS = Object.keys(DEFAULT_POLICY) as PolicyKey[];

/** What each key means, printed by `init --explain` (JSON carries no comments). */
export const POLICY_EXPLANATIONS: Record<PolicyKey, string> = {
  bump: 'patch | ask. `patch` skips the MINOR/MAJOR prompt in /ship Step 12.',
  queue_mode: 'claim-at-open | stamp-at-merge. stamp-at-merge stamps when the PR is next (`gstack-restamp --next`), from the base branch version at that moment.',
  release_tool: 'The repo’s own release command, run in an isolated staging worktree with an enumerated allowed-output set. Never runs without /ship or --allow-repo-commands.',
  release_outputs: 'Globs the release tool may write beyond the version files, lockfiles, CHANGELOG and stamp_paths. Any other output refuses the restamp.',
  stamp_paths: 'Globs (repo-relative, no `..`) where exact `(was X)`, `since: X` and `vX` mentions of the old version are rewritten.',
  changelog: 'CHANGELOG path re-headed on a restamp (the PR’s `[Unreleased]` or old-version section moves to the top under the new version). null to skip.',
  mirror: 'Relative path of a paired repo to restamp identically; writes are confined to it. null to skip.',
  history: 'merge-only | squash-ok. merge-only makes /ship refuse a squash or rebase plan.',
  preregistration_shas: 'Commits that must be ancestors of HEAD before push (preregistered evals); checked by `gstack-evidence ancestor`.',
  stamp_sensitive_gates: 'Evidence labels (gstack-evidence --label) that read VERSION or generated bytes; the tree receipt never marks them reusable.',
  pr_count: '{ default_pr_count, split_requires_owner }: the PR-count row in plan reviews.',
  maintainers: 'GitHub logins treated as maintainers by /review contributor mode; empty uses repository push permission.',
};

export interface PolicyError { code: ResultCodeName; path: string; message: string }

const MAX_LIST = 64;
const MAX_PATTERN = 256;
const MAX_REGEX = 512;
const MAX_COMMAND = 512;
const SHA_RE = /^[0-9a-f]{7,64}$/;

function hasDotDot(p: string): boolean {
  return p.split(/[\\/]+/).some(seg => seg === '..');
}

/** A repo-relative path or glob: no absolute paths, drive letters, `..` segments, NULs or control bytes. */
export function containedRelative(p: string): string | null {
  if (typeof p !== 'string' || p.length === 0) return 'must be a non-empty string';
  if (p.length > MAX_PATTERN) return `longer than ${MAX_PATTERN} characters`;
  if (/[\0\r\n]/.test(p)) return 'contains a control character';
  if (path.isAbsolute(p) || /^[A-Za-z]:[\\/]/.test(p) || p.startsWith('\\\\')) return 'must be repo-relative, not absolute';
  if (p.startsWith('~')) return 'must not start with ~';
  if (hasDotDot(p)) return 'must not contain a `..` segment';
  return null;
}

/** Glob → anchored RegExp. `**` spans directories, `*` and `?` stay inside one segment. Size-capped. */
export function globToRegExp(glob: string): RegExp {
  let out = '^';
  for (let i = 0; i < glob.length; i++) {
    const ch = glob[i]!;
    if (ch === '*') {
      if (glob[i + 1] === '*') {
        i += 1;
        if (glob[i + 1] === '/') { i += 1; out += '(?:.*/)?'; } else out += '.*';
      } else out += '[^/]*';
    } else if (ch === '?') out += '[^/]';
    else out += ch.replace(/[.+^${}()|[\]\\]/g, '\\$&');
  }
  out += '$';
  if (out.length > MAX_REGEX) throw new Error(`pattern expands past ${MAX_REGEX} characters`);
  return new RegExp(out);
}

export function matchesAny(globs: readonly string[], rel: string): boolean {
  const norm = rel.replace(/\\/g, '/').replace(/^\.\//, '');
  return globs.some(g => globToRegExp(g).test(norm));
}

function listErrors(key: string, value: unknown, out: PolicyError[], check: (item: string) => string | null): void {
  if (!Array.isArray(value)) { out.push({ code: 'POLICY_INVALID', path: key, message: 'must be an array of strings' }); return; }
  if (value.length > MAX_LIST) out.push({ code: 'POLICY_CONTAINMENT', path: key, message: `more than ${MAX_LIST} entries` });
  value.forEach((item, i) => {
    if (typeof item !== 'string') { out.push({ code: 'POLICY_INVALID', path: `${key}[${i}]`, message: 'must be a string' }); return; }
    const why = check(item);
    if (why) out.push({ code: 'POLICY_CONTAINMENT', path: `${key}[${i}]`, message: `${JSON.stringify(item)} ${why}` });
  });
}

function globError(g: string): string | null {
  const why = containedRelative(g);
  if (why) return why;
  try { globToRegExp(g); } catch (e: any) { return e.message; }
  return null;
}

/** Schema and containment check of a parsed policy object. Unknown keys are errors (a typo must not silently mean "default"). */
export function validatePolicy(raw: unknown): PolicyError[] {
  const errors: PolicyError[] = [];
  if (!raw || typeof raw !== 'object' || Array.isArray(raw)) return [{ code: 'POLICY_INVALID', path: '', message: 'policy must be a JSON object' }];
  const obj = raw as Record<string, unknown>;
  for (const key of Object.keys(obj)) {
    if (key !== '$schema' && !POLICY_KEYS.includes(key as PolicyKey)) errors.push({ code: 'POLICY_INVALID', path: key, message: `unknown key; valid keys: ${POLICY_KEYS.join(', ')}` });
  }
  const oneOf = (key: string, values: readonly string[]) => {
    if (key in obj && !values.includes(obj[key] as string)) errors.push({ code: 'POLICY_INVALID', path: key, message: `must be one of ${values.join(' | ')}, got ${JSON.stringify(obj[key])}` });
  };
  oneOf('bump', ['patch', 'ask']);
  oneOf('queue_mode', ['claim-at-open', 'stamp-at-merge']);
  oneOf('history', ['merge-only', 'squash-ok']);
  if ('release_tool' in obj && obj.release_tool !== null) {
    const t = obj.release_tool;
    if (typeof t !== 'string' || !t.trim()) errors.push({ code: 'POLICY_INVALID', path: 'release_tool', message: 'must be a non-empty string or null' });
    else if (t.length > MAX_COMMAND) errors.push({ code: 'POLICY_CONTAINMENT', path: 'release_tool', message: `longer than ${MAX_COMMAND} characters` });
    else if (/[\0\r\n]/.test(t)) errors.push({ code: 'POLICY_CONTAINMENT', path: 'release_tool', message: 'contains a newline or NUL' });
  }
  if ('release_outputs' in obj) listErrors('release_outputs', obj.release_outputs, errors, globError);
  if ('stamp_paths' in obj) listErrors('stamp_paths', obj.stamp_paths, errors, globError);
  for (const key of ['changelog', 'mirror'] as const) {
    if (!(key in obj) || obj[key] === null) continue;
    if (typeof obj[key] !== 'string') { errors.push({ code: 'POLICY_INVALID', path: key, message: 'must be a string or null' }); continue; }
    const p = obj[key] as string;
    const why = key === 'mirror' ? mirrorPathError(p) : containedRelative(p);
    if (why) errors.push({ code: 'POLICY_CONTAINMENT', path: key, message: `${JSON.stringify(p)} ${why}` });
  }
  if ('preregistration_shas' in obj) listErrors('preregistration_shas', obj.preregistration_shas, errors, s => (SHA_RE.test(s) ? null : 'is not a 7-64 character hex commit id'));
  if ('stamp_sensitive_gates' in obj) listErrors('stamp_sensitive_gates', obj.stamp_sensitive_gates, errors, s => (/^[A-Za-z0-9_.:-]{1,64}$/.test(s) ? null : 'is not an evidence label ([A-Za-z0-9_.:-]{1,64})'));
  if ('maintainers' in obj) listErrors('maintainers', obj.maintainers, errors, s => (/^[A-Za-z0-9-]{1,39}$/.test(s) ? null : 'is not a GitHub login'));
  if ('pr_count' in obj) {
    const pc = obj.pr_count as Record<string, unknown> | null;
    if (!pc || typeof pc !== 'object' || Array.isArray(pc)) errors.push({ code: 'POLICY_INVALID', path: 'pr_count', message: 'must be { default_pr_count, split_requires_owner }' });
    else {
      if (!Number.isInteger(pc.default_pr_count) || (pc.default_pr_count as number) < 1) errors.push({ code: 'POLICY_INVALID', path: 'pr_count.default_pr_count', message: 'must be an integer >= 1' });
      if (typeof pc.split_requires_owner !== 'boolean') errors.push({ code: 'POLICY_INVALID', path: 'pr_count.split_requires_owner', message: 'must be a boolean' });
      for (const k of Object.keys(pc)) if (!['default_pr_count', 'split_requires_owner'].includes(k)) errors.push({ code: 'POLICY_INVALID', path: `pr_count.${k}`, message: 'unknown key' });
    }
  }
  return errors;
}

/**
 * A mirror is a sibling checkout, so leading `..` segments are allowed; an
 * interior `..`, an absolute path or the repo itself (`.`) are not.
 */
function mirrorPathError(p: string): string | null {
  if (!p || p.length > MAX_PATTERN) return 'must be a non-empty relative path';
  if (/[\0\r\n]/.test(p)) return 'contains a control character';
  if (path.isAbsolute(p) || /^[A-Za-z]:[\\/]/.test(p)) return 'must be relative to the repository root';
  const segs = p.split(/[\\/]+/).filter(s => s && s !== '.');
  if (segs.length === 0) return 'must not be the repository itself';
  let i = 0;
  while (i < segs.length && segs[i] === '..') i += 1;
  if (segs.slice(i).includes('..')) return 'must not contain an interior `..` segment';
  if (i === segs.length) return 'must name a directory, not only parents';
  return null;
}

/** Merge a parsed file over the defaults, recording per-key provenance. */
export function mergePolicy(raw: Record<string, unknown> | null, sourceLabel: string): { policy: ShipPolicy; values: Record<string, string> } {
  const policy: ShipPolicy = JSON.parse(JSON.stringify(DEFAULT_POLICY));
  const values: Record<string, string> = {};
  for (const key of POLICY_KEYS) {
    if (raw && key in raw) { (policy as any)[key] = raw[key]; values[key] = sourceLabel; }
    else values[key] = 'default';
  }
  if (raw && typeof raw.$schema === 'string') policy.$schema = raw.$schema;
  return { policy, values };
}

export interface PolicySource { kind: 'base' | 'head' | 'none'; ref: string | null; sha: string | null; label: string }
export interface LoadedPolicy {
  policy: ShipPolicy;
  present: boolean;
  source: PolicySource;
  errors: PolicyError[];
  values: Record<string, string>;
}
export type PolicyLoad = LoadedPolicy | { unavailable: true; base: string; detail: string };

function git(repoRoot: string, args: string[]): { ok: boolean; out: string; err: string } {
  const r = spawnSync('git', args, { cwd: repoRoot, encoding: 'utf8', timeout: 30_000 });
  return { ok: r.status === 0, out: (r.stdout ?? '').trim(), err: (r.stderr ?? '').trim() };
}

/** `--base` when given, else origin/HEAD's branch, else `main`. */
export function resolveBaseBranch(repoRoot: string, explicit?: string): string {
  if (explicit && explicit.trim()) return explicit.trim().replace(/^origin\//, '');
  const r = git(repoRoot, ['symbolic-ref', '--quiet', '--short', 'refs/remotes/origin/HEAD']);
  if (r.ok && r.out) return r.out.replace(/^origin\//, '');
  return 'main';
}

function finish(rawText: string | null, source: PolicySource): LoadedPolicy {
  if (rawText === null) return { policy: mergePolicy(null, source.label).policy, present: false, source, errors: [], values: mergePolicy(null, source.label).values };
  let raw: unknown;
  try { raw = JSON.parse(rawText); }
  catch (e: any) { return { policy: JSON.parse(JSON.stringify(DEFAULT_POLICY)), present: true, source, errors: [{ code: 'POLICY_INVALID', path: SHIP_POLICY_PATH, message: `not valid JSON: ${e.message}` }], values: {} }; }
  const errors = validatePolicy(raw);
  const merged = mergePolicy(errors.length ? null : (raw as Record<string, unknown>), source.label);
  return { policy: merged.policy, present: true, source, errors, values: merged.values };
}

/**
 * The reviewed policy: `.gstack/ship-policy.json` as committed on
 * `origin/<base>`. An unresolvable base is `unavailable` (POLICY_SOURCE_
 * UNAVAILABLE); the caller must never fall back to the working tree silently.
 */
export function loadPolicyFromBase(repoRoot: string, base: string): PolicyLoad {
  const ref = `origin/${base.replace(/^origin\//, '')}`;
  const sha = git(repoRoot, ['rev-parse', '--verify', '--quiet', `${ref}^{commit}`]);
  if (!sha.ok || !sha.out) return { unavailable: true, base: base.replace(/^origin\//, ''), detail: `${ref} is not a resolvable commit` };
  const source: PolicySource = { kind: 'base', ref, sha: sha.out, label: `${ref}@${sha.out.slice(0, 12)}:${SHIP_POLICY_PATH}` };
  const exists = git(repoRoot, ['cat-file', '-e', `${sha.out}:${SHIP_POLICY_PATH}`]);
  if (!exists.ok) return finish(null, { ...source, kind: 'none', label: `${ref}@${sha.out.slice(0, 12)} (no ${SHIP_POLICY_PATH})` });
  const show = git(repoRoot, ['show', `${sha.out}:${SHIP_POLICY_PATH}`]);
  return finish(show.ok ? show.out : null, source);
}

/** The working-tree policy: unreviewed, labeled so in every receipt. */
export function loadPolicyFromHead(repoRoot: string): LoadedPolicy {
  const file = path.join(repoRoot, SHIP_POLICY_PATH);
  const source: PolicySource = { kind: 'head', ref: null, sha: null, label: `head (unreviewed) ${SHIP_POLICY_PATH}` };
  if (!fs.existsSync(file)) return finish(null, { ...source, kind: 'none', label: `head (no ${SHIP_POLICY_PATH})` });
  return finish(fs.readFileSync(file, 'utf8'), source);
}

/** The one POLICY_SOURCE_UNAVAILABLE line, with the base branch substituted into the fix clause. */
export function policyUnavailableLine(context: string, base: string, detail: string): string {
  const row = RESULT_CODES.POLICY_SOURCE_UNAVAILABLE;
  return `${context}: ${row.summary} (${detail}); fix: ${row.fix.replace('<base>', base)} (POLICY_SOURCE_UNAVAILABLE)`;
}

export function isUnavailable(load: PolicyLoad): load is { unavailable: true; base: string; detail: string } {
  return (load as any).unavailable === true;
}

/** Commands a policy declares; their presence never authorizes execution. */
export function declaredCommands(policy: ShipPolicy): Array<{ key: string; command: string; cwd: string }> {
  const out: Array<{ key: string; command: string; cwd: string }> = [];
  if (policy.release_tool) out.push({ key: 'release_tool', command: policy.release_tool, cwd: '.' });
  if (policy.release_tool && policy.mirror) out.push({ key: 'mirror.release_tool', command: policy.release_tool, cwd: policy.mirror });
  return out;
}

/** The example `init` writes: every key at its default plus `$schema`. */
export function examplePolicyJson(overrides: Partial<ShipPolicy> = {}): string {
  const body: Record<string, unknown> = { $schema: SHIP_POLICY_SCHEMA };
  for (const key of POLICY_KEYS) body[key] = key in overrides ? (overrides as any)[key] : (DEFAULT_POLICY as any)[key];
  return JSON.stringify(body, null, 2) + '\n';
}

export function explainPolicy(): string {
  return POLICY_KEYS.map(key => `${key}: ${POLICY_EXPLANATIONS[key]} default: ${JSON.stringify((DEFAULT_POLICY as any)[key])}`).join('\n') + '\n';
}

/** `key=value  (source)` lines plus the `policy:` provenance line, as show-effective prints them. */
export function renderEffective(load: LoadedPolicy, opts: { base?: string } = {}): string {
  const lines = [`policy: ${load.source.kind === 'base' ? 'base' : load.source.kind === 'head' ? 'head (unreviewed)' : 'none (defaults)'} ${load.source.label}`];
  for (const key of POLICY_KEYS) lines.push(`${key}=${JSON.stringify((load.policy as any)[key])}  (${load.values[key] ?? 'default'})`);
  return lines.join('\n') + '\n' + shipConsequences(load.policy, opts.base ?? '<base>').map(l => `ship: ${l}`).join('\n') + '\n';
}

/** What `/ship` does differently under this policy: the workflow prose the skill prints instead of carrying (docs/ship-policy.md#ship). */
export function shipConsequences(policy: ShipPolicy, base: string): string[] {
  const out: string[] = [];
  if (policy.history === 'merge-only') out.push('history merge-only: never rebase, squash or force-push this branch; `gstack-ship-policy check-history --plan <merge|squash|rebase>` refuses a rewrite plan (HISTORY_POLICY_VIOLATION)');
  if (policy.queue_mode === 'stamp-at-merge') {
    out.push(`queue_mode stamp-at-merge: Step 12 items 1-4 are replaced by \`gstack-restamp --next --base ${base} --pr <pr-number> --expect-base <base-sha>\` when this PR is next in the queue (\`--after <predecessor-pr>\` gates ahead in a throwaway worktree when it is not); follow its next: line; claims are ignored`);
    out.push('gate-ahead: with .gstack/tmp/gate-ahead.json present, Step 16 reuses only the lanes `gstack-tree-receipt --from .gstack/tmp/gate-ahead.json --predecessor-pr <pr> --bundle <bundle> --json > .gstack/tmp/tree-receipt.json` marks reusable; stamp-sensitive and not-eligible lanes run live; `--force-gate <reason>` is the coordinator\'s call');
  } else out.push('queue_mode claim-at-open: Step 12 runs as written (claims through gstack-next-version)');
  out.push(policy.bump === 'patch' ? 'bump patch: Step 12 never asks for MINOR or MAJOR; PATCH or MICRO by size' : 'bump ask: Step 12 asks for MINOR and MAJOR as written');
  if (policy.preregistration_shas.length) out.push(`preregistration: \`gstack-evidence ancestor --from-policy --base ${base}\` must print only ANCESTOR: ok before push; the ship receipt records the result`);
  if (policy.release_tool) out.push(`release_tool: \`${policy.release_tool}\` runs only inside gstack-restamp (staging worktree, outputs confined to release_outputs)`);
  return out;
}

/**
 * Files under `globs` inside a committed tree, as `git ls-tree` lists them.
 * Symlinks (mode 120000) never match: a stamp write through a link would
 * escape the tree the glob confines it to.
 */
export function listTreeFiles(repoRoot: string, treeish: string): Array<{ path: string; mode: string }> {
  const r = git(repoRoot, ['ls-tree', '-r', '-z', treeish]);
  if (!r.ok) return [];
  return r.out.split('\0').filter(Boolean).map(line => {
    const [meta, p] = line.split('\t');
    return { path: p ?? '', mode: meta?.split(' ')[0] ?? '' };
  }).filter(e => e.path);
}

export function stampFilesInTree(repoRoot: string, treeish: string, globs: readonly string[]): string[] {
  if (globs.length === 0) return [];
  return listTreeFiles(repoRoot, treeish).filter(e => e.mode !== '120000' && matchesAny(globs, e.path)).map(e => e.path);
}

/**
 * A working-tree path a stamp may write: inside `root` after realpath (a
 * symlink out of the repository is refused even when the glob matched).
 */
export function assertInsideRoot(root: string, rel: string): string | null {
  const realRoot = fs.realpathSync(root);
  const abs = path.resolve(realRoot, rel);
  if (abs !== realRoot && !abs.startsWith(realRoot + path.sep)) return `${rel} resolves outside ${root}`;
  let probe = abs;
  while (!fs.existsSync(probe)) {
    const parent = path.dirname(probe);
    if (parent === probe) break;
    probe = parent;
  }
  let real: string;
  try { real = fs.realpathSync(probe); } catch { return null; }
  if (real !== realRoot && !real.startsWith(realRoot + path.sep)) return `${rel} resolves through a symlink to outside ${root}`;
  return null;
}