gstack/bin/gstack-gbrain-source-wireup

#!/usr/bin/env bash
# gstack-gbrain-source-wireup — register the gstack brain repo as a gbrain
# federated source via `git worktree`, run an initial sync, hook into
# subsequent skill-end syncs.
#
# Replaces the v1.12.2.0 dead `consumers.json + ingest_url + /ingest-repo`
# wireup which depended on a gbrain HTTP endpoint that never shipped.
#
# Usage:
#   gstack-gbrain-source-wireup [--strict] [--source-id <id>] [--no-pull]
#                               [--database-url <url>]
#   gstack-gbrain-source-wireup --uninstall [--source-id <id>]
#                               [--database-url <url>]
#   gstack-gbrain-source-wireup --probe
#   gstack-gbrain-source-wireup --advance-only   # daily unattended worktree advance (#2516)
#   gstack-gbrain-source-wireup --help
#
# Exit codes:
#   0 — success, OR benign skip without --strict
#   1 — hard failure (gbrain or git op errored on a real call)
#   2 — missing prereqs (no gbrain >= 0.18.0, no .git or remote-file)
#   3 — source-id derivation failed in --uninstall, no fallback worked
#
# Env:
#   GSTACK_HOME — override ~/.gstack (test harness)
#   GSTACK_BRAIN_WORKTREE — override worktree path (default ~/.gstack-brain-worktree)
#   GSTACK_BRAIN_SOURCE_ID — id override; --source-id flag takes precedence
#   GSTACK_BRAIN_NO_SYNC — skip the gbrain sync step (tests; helper still
#                          ensures source registration)
#
# Defense against external rewrites of ~/.gbrain/config.json:
# At helper startup we capture the database URL ONCE — from --database-url,
# from GBRAIN_DATABASE_URL/DATABASE_URL env, or from ~/.gbrain/config.json —
# and export it as GBRAIN_DATABASE_URL for every child `gbrain` invocation.
# That env var overrides whatever's in config.json (per gbrain's loadConfig
# at src/core/config.ts:53), so a process that flips config.json mid-sync
# can't redirect us at a different brain mid-stream.
#
# Depends on: jq (transitive via gstack-gbrain-detect).

set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
CONFIG_BIN="$SCRIPT_DIR/gstack-config"

GSTACK_HOME="${GSTACK_HOME:-$HOME/.gstack}"
WORKTREE="${GSTACK_BRAIN_WORKTREE:-$HOME/.gstack-brain-worktree}"
# v1.27.0.0+ canonical name; brain-remote is the legacy fallback during migration.
if [ -f "$HOME/.gstack-artifacts-remote.txt" ]; then
  REMOTE_FILE="$HOME/.gstack-artifacts-remote.txt"
else
  REMOTE_FILE="$HOME/.gstack-brain-remote.txt"
fi
PLIST_PATH="$HOME/Library/LaunchAgents/com.gstack.brain-sync.plist"
GBRAIN_CONFIG="$HOME/.gbrain/config.json"

# ---- arg parse ----
MODE="wireup"
STRICT=0
NO_PULL=0
SOURCE_ID=""
DATABASE_URL_ARG=""

while [ $# -gt 0 ]; do
  case "$1" in
    --uninstall)     MODE="uninstall"; shift ;;
    --probe)         MODE="probe"; shift ;;
    --advance-only)  MODE="advance-only"; shift ;;
    --strict)        STRICT=1; shift ;;
    --no-pull)       NO_PULL=1; shift ;;
    --source-id)     SOURCE_ID="$2"; shift 2 ;;
    --database-url)  DATABASE_URL_ARG="$2"; shift 2 ;;
    --help|-h)       sed -n '2,40p' "$0" | sed 's/^# \{0,1\}//'; exit 0 ;;
    *)               echo "Unknown flag: $1" >&2; exit 1 ;;
  esac
done

# ---- lock the database URL at startup ----
# Precedence: --database-url flag > existing GBRAIN_DATABASE_URL/DATABASE_URL
# env > read once from ~/.gbrain/config.json. Whichever wins gets exported as
# GBRAIN_DATABASE_URL so every child `gbrain` invocation uses THAT brain even
# if config.json is rewritten by another process during the wireup.
_locked_url=""
if [ -n "$DATABASE_URL_ARG" ]; then
  _locked_url="$DATABASE_URL_ARG"
elif [ -n "${GBRAIN_DATABASE_URL:-}" ]; then
  _locked_url="$GBRAIN_DATABASE_URL"
elif [ -n "${DATABASE_URL:-}" ]; then
  _locked_url="$DATABASE_URL"
elif [ -f "$GBRAIN_CONFIG" ]; then
  # Python heredoc reads config.json. On JSON parse failure or any IO error,
  # we WARN (not silently swallow) so the user knows the URL lock fell back
  # to gbrain's own loadConfig (which would still read this same file).
  _py_err=$(mktemp -t wireup-pyerr 2>/dev/null || mktemp /tmp/wireup-pyerr.XXXXXX)
  _locked_url=$(GBRAIN_CONFIG_PATH="$GBRAIN_CONFIG" python3 -c '
import json, os, sys
try:
    c = json.load(open(os.environ["GBRAIN_CONFIG_PATH"]))
    print(c.get("database_url",""))
except FileNotFoundError:
    sys.exit(0)
except Exception as e:
    print(f"config.json parse error: {e}", file=sys.stderr)
    sys.exit(1)
' </dev/null 2>"$_py_err") || warn "could not read $GBRAIN_CONFIG ($(cat "$_py_err" 2>/dev/null)); URL not locked"
  rm -f "$_py_err" 2>/dev/null
fi
if [ -n "$_locked_url" ]; then
  export GBRAIN_DATABASE_URL="$_locked_url"
fi

prefix() { sed 's/^/gstack-gbrain-source-wireup: /' >&2; }
warn()   { echo "$*" | prefix; }
# die <message> [exit_code]: warn with just the message, exit with code (default 1).
die()    { warn "$1"; exit "${2:-1}"; }

# Refuse to rm anything outside $HOME/. Defends against GSTACK_BRAIN_WORKTREE=/
# or empty-string overrides that would otherwise have line 169 / 161 nuke the
# user's home or root.
safe_rm_worktree() {
  local target="$1"
  case "$target" in
    "" | "/" | "/Users" | "/Users/" | "$HOME" | "$HOME/" )
      die "refusing to rm dangerous path: $target" 1 ;;
  esac
  case "$target" in
    "$HOME"/*) rm -rf "$target" ;;
    *) die "refusing to rm path outside \$HOME: $target" 1 ;;
  esac
}

# ---- source-id derivation (D6 multi-fallback) ----
derive_source_id() {
  if [ -n "$SOURCE_ID" ]; then
    echo "$SOURCE_ID"; return 0
  fi
  if [ -n "${GSTACK_BRAIN_SOURCE_ID:-}" ]; then
    echo "$GSTACK_BRAIN_SOURCE_ID"; return 0
  fi
  local remote_url=""
  remote_url=$(git -C "$GSTACK_HOME" remote get-url origin 2>/dev/null) || true
  if [ -z "$remote_url" ] && [ -f "$REMOTE_FILE" ]; then
    remote_url=$(head -1 "$REMOTE_FILE" 2>/dev/null | tr -d '[:space:]')
  fi
  [ -z "$remote_url" ] && return 3
  basename "$remote_url" .git \
    | tr '[:upper:]' '[:lower:]' \
    | tr -c 'a-z0-9-' '-' \
    | sed 's/--*/-/g; s/^-//; s/-$//' \
    | cut -c1-32
}

# ---- gbrain version gate ----
gbrain_version_ok() {
  if ! command -v gbrain >/dev/null 2>&1; then
    return 1
  fi
  local v
  v=$(gbrain --version 2>/dev/null | awk '{print $2}')
  [ -z "$v" ] && return 1
  # 0.18.0 minimum (gbrain sources shipped here). Put the floor first in stdin
  # so equal or greater $v sorts to position 2 — head -1 == "0.18.0" iff $v >= floor.
  [ "$(printf '0.18.0\n%s\n' "$v" | sort -V | head -1)" = "0.18.0" ]
}

# ---- worktree management ----
# A worktree is always created `--detach`ed at $GSTACK_HOME's HEAD. Detached
# because a branch (main) can only be checked out in ONE worktree, and the
# parent at $GSTACK_HOME already has it. To advance, we re-checkout the
# parent's current HEAD into the detached worktree.
_worktree_add_detached() {
  local sha
  sha=$(git -C "$GSTACK_HOME" rev-parse HEAD 2>/dev/null) || return 1
  git -C "$GSTACK_HOME" worktree prune 2>/dev/null || true
  # Surface git errors via prefix so users see WHY the add failed (disk, perms, etc).
  git -C "$GSTACK_HOME" worktree add --detach "$WORKTREE" "$sha" 2>&1 | prefix
  return "${PIPESTATUS[0]}"
}

ensure_worktree() {
  if [ ! -d "$GSTACK_HOME/.git" ]; then
    return 2
  fi
  if [ -d "$WORKTREE/.git" ] || [ -f "$WORKTREE/.git" ]; then
    # already exists; advance the detached HEAD to parent's current HEAD
    if [ "$NO_PULL" = "0" ]; then
      local sha
      sha=$(git -C "$GSTACK_HOME" rev-parse HEAD 2>/dev/null) || return 1
      # Surface checkout errors via prefix so users see WHY the advance failed
      # (uncommitted changes in the detached worktree, ref ambiguity, etc).
      ( cd "$WORKTREE" && git checkout --detach "$sha" 2>&1 | prefix; exit "${PIPESTATUS[0]}" ) || {
        warn "worktree at $WORKTREE could not advance to $sha; resetting via remove + re-add"
        git -C "$GSTACK_HOME" worktree remove --force "$WORKTREE" 2>/dev/null || safe_rm_worktree "$WORKTREE"
        _worktree_add_detached || return 1
      }
    fi
    return 0
  fi
  # Stray non-git dir? Remove first.
  [ -e "$WORKTREE" ] && safe_rm_worktree "$WORKTREE"
  _worktree_add_detached || return 1
}

# ---- gbrain sources operations ----
# Returns 0 if source with id exists at expected path. 1 if exists but path differs. 2 if absent.
# Hard-fails (exits non-zero via die) if jq is missing — without jq we cannot
# distinguish "absent" from "missing-tool" and would falsely re-add an existing
# source. jq is documented as a dependency of gstack-gbrain-detect (transitive)
# but adversarial review flagged the silent-fall-through path; this probe makes
# the failure mode loud.
check_source_state() {
  local id="$1"
  if ! command -v jq >/dev/null 2>&1; then
    die "jq required for source state detection. Install jq (brew install jq) and re-run." 1
  fi
  local existing_path
  existing_path=$(gbrain sources list --json 2>/dev/null \
    | jq -r --arg id "$id" '.sources[] | select(.id==$id) | .local_path' 2>/dev/null \
    | tr -d '[:space:]') || existing_path=""
  if [ -z "$existing_path" ]; then
    return 2
  fi
  if [ "$existing_path" = "$WORKTREE" ]; then
    return 0
  fi
  return 1
}

# ---- modes ----
do_probe() {
  local id worktree_status="absent" gbrain_status="missing" source_status="absent"
  id=$(derive_source_id 2>/dev/null) || id="(unknown)"
  # Use explicit if-block so [ -d ] || [ -f ] doesn't get short-circuited by &&
  # precedence (the `||` and `&&` chain has trap behavior in bash test syntax).
  if [ -d "$WORKTREE/.git" ] || [ -f "$WORKTREE/.git" ]; then
    worktree_status="present"
  fi
  if gbrain_version_ok; then
    gbrain_status="ok ($(gbrain --version 2>/dev/null | awk '{print $2}'))"
    # Capture check_source_state's return code explicitly. Relying on $? after
    # an `if`-elif chain is fragile under set -e and undefined under some shells.
    set +e
    check_source_state "$id"
    local css_rc=$?
    set -e
    case "$css_rc" in
      0) source_status="registered ($WORKTREE)" ;;
      1) source_status="registered (different path)" ;;
    esac
  fi
  echo "source_id=$id"
  echo "worktree=$WORKTREE"
  echo "worktree_status=$worktree_status"
  echo "gbrain=$gbrain_status"
  echo "source_status=$source_status"
}

do_wireup() {
  local id
  id=$(derive_source_id) || die "cannot derive source id (no .git, no remote-file, no --source-id)" 2

  if ! gbrain_version_ok; then
    if [ "$STRICT" = "1" ]; then
      die "gbrain not installed or < 0.18.0; install/upgrade gbrain and re-run" 2
    fi
    warn "gbrain not installed or < 0.18.0; skipping wireup (benign skip)"
    exit 0
  fi

  # Capture ensure_worktree's return code explicitly. `$?` after `||` reflects
  # the LAST command in the function under set -e, which is unreliable when the
  # function has multiple internal exit paths.
  set +e
  ensure_worktree
  ew_rc=$?
  set -e
  case "$ew_rc" in
    0) : ;;  # success
    2)
      [ "$STRICT" = "1" ] && die "no $GSTACK_HOME/.git; run /setup-gbrain Step 7 (gstack-brain-init) first" 2
      warn "no $GSTACK_HOME/.git; skipping (benign skip)"
      exit 0
      ;;
    *) die "git worktree creation failed at $WORKTREE" 1 ;;
  esac

  # Source registration: probe state, then act.
  set +e
  check_source_state "$id"
  local sstate=$?
  set -e
  case "$sstate" in
    0) : ;;  # already correctly registered
    1)
      # Multi-Mac case: if the existing path also looks like another machine's
      # brain-worktree (same basename, different parent), don't ping-pong the
      # registration. Just sync from our local worktree — gbrain stores pages
      # by content, not by local_path. The metadata is informational only.
      local existing_path
      existing_path=$(gbrain sources list --json 2>/dev/null \
        | jq -r --arg id "$id" '.sources[] | select(.id==$id) | .local_path' 2>/dev/null \
        | tr -d '[:space:]') || existing_path=""
      if [ "$(basename "$existing_path")" = "$(basename "$WORKTREE")" ] \
         && [ "$existing_path" != "$WORKTREE" ]; then
        warn "source $id is registered at $existing_path (likely another machine's local copy of the same brain repo). Skipping re-registration; will sync from local worktree."
      else
        warn "source $id registered with different path; recreating (gbrain has no 'sources update')"
        gbrain sources remove "$id" --yes 2>&1 | prefix || die "gbrain sources remove failed" 1
        gbrain sources add "$id" --path "$WORKTREE" --federated 2>&1 | prefix \
          || die "gbrain sources add failed" 1
      fi
      ;;
    2)
      gbrain sources add "$id" --path "$WORKTREE" --federated 2>&1 | prefix \
        || die "gbrain sources add failed" 1
      ;;
  esac

  # ZeroEntropy sunset advisory (#2365): the provider shuts down Sept 4, 2026,
  # after which brains on gbrain's zeroentropyai recipe stop embedding new
  # pages silently. Detection is a fail-open grep of gbrain's config — any
  # missing/unreadable/other-provider config stays silent (grep -qs), never
  # blocking a working setup.
  if grep -qsi 'zeroentropyai' "$GBRAIN_CONFIG" 2>/dev/null; then
    warn "gbrain config appears to use the ZeroEntropy embedding recipe. ZeroEntropy sunsets on September 4, 2026 — after that, new pages stop embedding silently. Migration options: https://github.com/garrytan/gstack/issues/2365"
  fi

  if [ "${GSTACK_BRAIN_NO_SYNC:-0}" = "1" ]; then
    echo "source_id=$id"
    echo "worktree=$WORKTREE"
    echo "pages_synced=skipped"
    exit 0
  fi

  # #2662: `sync --repo <path>` resolves against the brain's DEFAULT source and
  # can silently repoint that source's local_path anchor at our worktree while
  # the source registered above gets nothing. Target the registered source by
  # id. `--source` support is probed first (the documented floor is gbrain >=
  # 0.18.0 and nothing proves the flag exists there): an older gbrain keeps the
  # wrong-but-working --repo call with an upgrade warning, never a hard failure.
  local sync_out sync_redacted
  local -a sync_cmd
  if gbrain sync --help 2>/dev/null | grep -q -- '--source'; then
    sync_cmd=(gbrain sync --source "$id")
  else
    warn "this gbrain's sync lacks --source; falling back to 'sync --repo' (upgrade gbrain so the sync targets source $id directly — #2662)"
    sync_cmd=(gbrain sync --repo "$WORKTREE")
  fi
  sync_out=$("${sync_cmd[@]}" 2>&1) || {
    # Redact any postgres:// URLs from the error message in case gbrain logged
    # a connection error containing the full DSN with password. The user sees
    # "***REDACTED***" instead of credentials in their stderr or any log.
    sync_redacted=$(echo "$sync_out" | tail -10 | sed -E 's#postgres(ql)?://[^[:space:]]+#postgres://***REDACTED***#g')
    die "gbrain sync failed (last 10 lines, secrets redacted): $sync_redacted" 1
  }
  echo "$sync_out" | tail -3 | prefix

  echo "source_id=$id"
  echo "worktree=$WORKTREE"
  echo "pages_synced=$(echo "$sync_out" | grep -oE '[0-9]+ pages? imported' | head -1 || echo 'incremental')"
}

do_advance_only() {
  # Daily unattended advance (#2516): the brain worktree gbrain indexes only
  # moved when setup-gbrain / sync-gbrain / brain-restore ran, so brains
  # silently served stale code. This mode is git-only (no gbrain prereqs) and
  # SAFE for a cron cadence: it refuses dirty worktrees and NEVER runs
  # ensure_worktree's force-remove recovery — an unattended path must not be
  # able to delete local worktree changes. All git ops are pinned to
  # $GSTACK_HOME / $WORKTREE, never cwd-derived.
  [ -d "$GSTACK_HOME/.git" ] || { warn "advance-only: no artifacts repo at $GSTACK_HOME; nothing to advance"; exit 0; }
  if [ ! -d "$WORKTREE/.git" ] && [ ! -f "$WORKTREE/.git" ]; then
    warn "advance-only: no managed worktree at $WORKTREE (run the setup-gbrain wireup first)"
    exit 0
  fi
  # Managed-marker check: refuse anything that is not a worktree OF the
  # artifacts repo — a misconfigured GSTACK_BRAIN_WORKTREE pointing at a user
  # repo must never be advanced/detached.
  local gitdir home_git
  gitdir=$(git -C "$WORKTREE" rev-parse --absolute-git-dir 2>/dev/null || echo "")
  # Physical path for the comparison: rev-parse returns resolved paths, while
  # $GSTACK_HOME may reach the same place through a symlink (macOS /var/folders).
  home_git=$(cd "$GSTACK_HOME/.git" 2>/dev/null && pwd -P || echo "$GSTACK_HOME/.git")
  case "$gitdir" in
    "$home_git/worktrees/"*) : ;;
    *) warn "advance-only: $WORKTREE is not a worktree of $GSTACK_HOME (gitdir: ${gitdir:-unreadable}); refusing"; exit 0 ;;
  esac
  if [ -n "$(git -C "$WORKTREE" status --porcelain 2>/dev/null)" ]; then
    warn "advance-only: worktree at $WORKTREE has local changes; refusing to advance them away"
    exit 0
  fi
  local sha cur
  sha=$(git -C "$GSTACK_HOME" rev-parse HEAD 2>/dev/null) || { warn "advance-only: cannot read parent HEAD"; exit 0; }
  cur=$(git -C "$WORKTREE" rev-parse HEAD 2>/dev/null || echo "")
  if [ "$cur" = "$sha" ]; then
    echo "advance-only: up-to-date at $sha"
    return 0
  fi
  if ( cd "$WORKTREE" && git checkout --detach "$sha" 2>&1 | prefix; exit "${PIPESTATUS[0]}" ); then
    echo "advance-only: advanced $WORKTREE to $sha"
  else
    warn "advance-only: could not advance $WORKTREE to $sha; NOT force-resetting on the unattended path. Run gstack-gbrain-source-wireup to repair."
    exit 1
  fi
}

do_uninstall() {
  local id
  id=$(derive_source_id) || die "cannot derive source id; pass --source-id <id> explicitly" 3

  if command -v gbrain >/dev/null 2>&1; then
    gbrain sources remove "$id" --yes 2>&1 | prefix || warn "gbrain sources remove failed (continuing)"
  fi

  if [ -d "$WORKTREE/.git" ] || [ -f "$WORKTREE/.git" ]; then
    git -C "$GSTACK_HOME" worktree remove --force "$WORKTREE" 2>/dev/null \
      || safe_rm_worktree "$WORKTREE"
  fi

  # Cron-stub: future launchd plist (not created today; safety net for D9 future).
  rm -f "$PLIST_PATH" 2>/dev/null || true

  echo "uninstalled source=$id worktree=$WORKTREE"
}

case "$MODE" in
  probe)        do_probe ;;
  wireup)       do_wireup ;;
  uninstall)    do_uninstall ;;
  advance-only) do_advance_only ;;
esac