gstack/bin/gstack-gbrain-repo-policy

#!/usr/bin/env bash
# gstack-gbrain-repo-policy — per-remote trust tier for gbrain repo ingest.
#
# Usage:
#   gstack-gbrain-repo-policy get [<remote-url>]
#     Print the tier for the given remote, or the current repo's origin
#     if no URL is passed. Exits 0 with one of: read-write, read-only,
#     deny, unset.
#
#   gstack-gbrain-repo-policy get --batch
#     Read remote URLs from stdin (one per line); print one tier per line
#     in input order: read-write, read-only, deny, or none (no entry / no
#     store). A corrupt store is a hard error (exit 2), NEVER quarantined:
#     batch callers are unattended ingest gates that must fail closed
#     rather than bypass a set policy.
#
#   gstack-gbrain-repo-policy set <remote-url> <read-write|read-only|deny>
#     Persist a tier for the given remote. Exits 0 on success.
#
#   gstack-gbrain-repo-policy list
#     Print every entry as "<key>\t<tier>", sorted by key.
#
#   gstack-gbrain-repo-policy normalize <url>
#     Print the normalized (canonical) key for a given remote URL.
#     Use this when other skills or tests need the same collapsing logic.
#
#   gstack-gbrain-repo-policy --help
#
# Storage:
#   ~/.gstack/gbrain-repo-policy.json, mode 0600.
#
# File format:
#   {
#     "_schema_version": 2,
#     "github.com/foo/bar": "read-write",
#     "github.com/baz/qux": "deny"
#   }
#
# Tier semantics:
#   read-write — agent may search AND write new pages from this repo.
#   read-only  — agent may search but NEVER write pages from this repo.
#                (Enforced at the caller level; this binary just stores the
#                decision.)
#   deny       — no gbrain interaction at all.
#
# Legacy migration:
#   On any read of a file missing `_schema_version` (or with version < 2),
#   legacy `allow` values are atomically rewritten to `read-write`, and
#   `_schema_version: 2` is added. Log line emitted on stderr when the
#   migration actually changes anything. Idempotent: running twice is safe.
#
# Env:
#   GSTACK_HOME — override ~/.gstack state directory (aligns with other
#                 gstack-* bins; used heavily in tests).
set -euo pipefail

STATE_DIR="${GSTACK_HOME:-$HOME/.gstack}"
POLICY_FILE="$STATE_DIR/gbrain-repo-policy.json"
SCHEMA_VERSION=2

die() { echo "gstack-gbrain-repo-policy: $*" >&2; exit 2; }

require_jq() {
  if ! command -v jq >/dev/null 2>&1; then
    die "jq is required. Install with: brew install jq"
  fi
}

# normalize <url> — canonical form: lowercase host + path, no protocol,
# no userinfo, no trailing .git or /. SSH shorthand (git@host:path) collapses
# to the same key as https://host/path.
normalize() {
  local url="$1"
  [ -z "$url" ] && { echo ""; return 0; }
  # Strip protocol://
  url="${url#*://}"
  # Strip userinfo (git@, user:password@, etc.) — everything up to and
  # including the first @ iff an @ appears before the first / or :.
  case "$url" in
    *@*)
      local before_at="${url%%@*}"
      case "$before_at" in
        */*|*:*) : ;;  # @ is in the path, not userinfo — leave it
        *) url="${url#*@}" ;;
      esac
      ;;
  esac
  # SSH shorthand: github.com:foo/bar → github.com/foo/bar. Only when the
  # hostname-part (before first /) contains a colon. sed is clearer than
  # bash's `${var/:/\/}` which has tricky escaping.
  local head="${url%%/*}"
  case "$head" in
    *:*) url=$(printf '%s' "$url" | sed 's|:|/|') ;;
  esac
  # Lowercase BEFORE the suffix strips so a `.GIT` suffix still strips —
  # parity with lib/gstack-memory-helpers' canonicalizeRemote, which strips
  # `.git` case-insensitively. GitHub and most hosts are case-insensitive on
  # paths anyway; collapsing avoids duplicate entries for "Foo/Bar" vs
  # "foo/bar". (Parity is pinned by test/gbrain-repo-policy-client.test.ts:
  # a key set through THIS normalize must be found via the canonicalized form
  # memory-ingest passes to `get --batch`.)
  url=$(printf '%s' "$url" | tr '[:upper:]' '[:lower:]')
  # Strip trailing slash(es) FIRST, so ".git/" still loses its suffix (same
  # order as canonicalizeRemote — slash-first, then .git, then re-strip).
  while [ "${url%/}" != "$url" ]; do url="${url%/}"; done
  # Strip trailing .git
  url="${url%.git}"
  # Re-strip trailing slash(es): a path remote ending in a `.git` directory
  # component ("/repo/.git") exposes a new trailing slash once .git is gone.
  while [ "${url%/}" != "$url" ]; do url="${url%/}"; done
  printf '%s\n' "$url"
}

# ensure_file — create the policy file if missing, migrate if legacy.
# Emits the migration log line on stderr exactly once per run when a
# migration actually rewrites values.
ensure_file() {
  require_jq
  mkdir -p "$STATE_DIR"

  if [ ! -f "$POLICY_FILE" ]; then
    # Fresh file — just the schema version, no entries.
    local tmp
    tmp=$(mktemp "$POLICY_FILE.tmp.XXXXXX")
    printf '{"_schema_version":%d}\n' "$SCHEMA_VERSION" > "$tmp"
    mv "$tmp" "$POLICY_FILE"
    chmod 0600 "$POLICY_FILE"
    return 0
  fi

  # File exists — validate, migrate if needed.
  local raw
  if ! raw=$(cat "$POLICY_FILE" 2>/dev/null); then
    die "Cannot read $POLICY_FILE"
  fi

  # Corrupt JSON → quarantine and start fresh.
  if ! echo "$raw" | jq empty 2>/dev/null; then
    local ts
    ts=$(date +%Y%m%d-%H%M%S)
    local quarantine="$POLICY_FILE.corrupt-$ts"
    mv "$POLICY_FILE" "$quarantine"
    echo "gstack-gbrain-repo-policy: corrupt policy file quarantined to $quarantine; starting fresh" >&2
    local tmp
    tmp=$(mktemp "$POLICY_FILE.tmp.XXXXXX")
    printf '{"_schema_version":%d}\n' "$SCHEMA_VERSION" > "$tmp"
    mv "$tmp" "$POLICY_FILE"
    chmod 0600 "$POLICY_FILE"
    return 0
  fi

  # Check schema version.
  local version
  version=$(echo "$raw" | jq -r '._schema_version // 0')
  if [ "$version" -ge "$SCHEMA_VERSION" ]; then
    return 0
  fi

  # Migrate: rename `allow` → `read-write`, add _schema_version.
  local allow_count migrated
  allow_count=$(echo "$raw" | jq '[to_entries[] | select(.key != "_schema_version" and .value == "allow")] | length')
  migrated=$(echo "$raw" | jq --argjson v "$SCHEMA_VERSION" '
    (to_entries | map(
      if .key == "_schema_version" then empty
      elif .value == "allow" then .value = "read-write"
      else .
      end
    ) | from_entries) + {_schema_version: $v}
  ')
  local tmp
  tmp=$(mktemp "$POLICY_FILE.tmp.XXXXXX")
  printf '%s\n' "$migrated" > "$tmp"
  mv "$tmp" "$POLICY_FILE"
  chmod 0600 "$POLICY_FILE"
  if [ "$allow_count" -gt 0 ]; then
    echo "[gstack-gbrain-repo-policy] Migrated $allow_count legacy allow entries to read-write" >&2
  fi
}

# get --batch — bulk lookup for ingest gates. One URL per stdin line, one
# tier per stdout line, input order preserved. Reuses normalize() (the same
# code path single `get` uses) per line. Prints `none` where single `get`
# prints `unset` — batch consumers (lib/gbrain-repo-policy-client.ts) speak
# the RepoPolicyTierValue vocabulary directly.
#
# Corruption polarity differs from single `get` ON PURPOSE: interactive
# `get` quarantines a corrupt store and starts fresh because /setup-gbrain
# re-asks the user; a batch caller is an unattended ingest gate with nobody
# to re-ask, so silently quarantining would BYPASS a set deny policy. Batch
# fails hard (exit 2) instead and names the recovery path.
cmd_get_batch() {
  require_jq
  if [ ! -f "$POLICY_FILE" ]; then
    # No store = no policy was ever set. Every URL is `none`; don't create
    # the file just for a read (matches cmd_list).
    while IFS= read -r url || [ -n "$url" ]; do
      printf 'none\n'
    done
    return 0
  fi
  if ! jq empty "$POLICY_FILE" 2>/dev/null; then
    die "policy store $POLICY_FILE is corrupt (invalid JSON) — refusing batch read. Inspect with: gstack-gbrain-repo-policy list; re-run /setup-gbrain to rebuild the store."
  fi
  # Valid JSON from here, so ensure_file only performs the legacy
  # allow → read-write migration (never the quarantine branch).
  ensure_file
  local url key
  while IFS= read -r url || [ -n "$url" ]; do
    key=$(normalize "$url")
    if [ -z "$key" ]; then
      printf 'none\n'
      continue
    fi
    jq -r --arg key "$key" '.[$key] // "none"' "$POLICY_FILE"
  done
}

cmd_get() {
  local url="${1:-}"
  if [ "$url" = "--batch" ]; then
    cmd_get_batch
    return 0
  fi
  if [ -z "$url" ]; then
    url=$(git remote get-url origin 2>/dev/null || true)
    if [ -z "$url" ]; then
      echo "unset"
      return 0
    fi
  fi
  local key
  key=$(normalize "$url")
  if [ -z "$key" ]; then
    echo "unset"
    return 0
  fi
  ensure_file
  jq -r --arg key "$key" '.[$key] // "unset"' "$POLICY_FILE"
}

cmd_set() {
  local url="${1:-}"
  local tier="${2:-}"
  [ -z "$url" ] && die "usage: set <remote-url> <tier>"
  [ -z "$tier" ] && die "usage: set <remote-url> <tier>"
  case "$tier" in
    read-write|read-only|deny) ;;
    *) die "invalid tier '$tier' (must be one of: read-write, read-only, deny)" ;;
  esac
  local key
  key=$(normalize "$url")
  [ -z "$key" ] && die "cannot normalize remote URL: $url"
  ensure_file
  local tmp
  tmp=$(mktemp "$POLICY_FILE.tmp.XXXXXX")
  jq --arg key "$key" --arg tier "$tier" '.[$key] = $tier' "$POLICY_FILE" > "$tmp"
  mv "$tmp" "$POLICY_FILE"
  chmod 0600 "$POLICY_FILE"
  echo "Set $key → $tier"
}

cmd_list() {
  if [ ! -f "$POLICY_FILE" ]; then
    # Nothing to list; don't create the file just for a read.
    return 0
  fi
  ensure_file
  jq -r 'to_entries[] | select(.key != "_schema_version") | "\(.key)\t\(.value)"' "$POLICY_FILE" | sort
}

cmd_normalize() {
  local url="${1:-}"
  [ -z "$url" ] && die "usage: normalize <url>"
  normalize "$url"
}

case "${1:-}" in
  get) shift; cmd_get "$@" ;;
  set) shift; cmd_set "$@" ;;
  list) shift; cmd_list "$@" ;;
  normalize) shift; cmd_normalize "$@" ;;
  --help|-h|help) sed -n '2,54p' "$0" | sed 's/^# \{0,1\}//' ;;
  "") die "usage: gstack-gbrain-repo-policy {get|set|list|normalize|--help}" ;;
  *) die "unknown subcommand: $1" ;;
esac