gstack/bin/gstack-brain-sync

#!/usr/bin/env bash
# gstack-brain-sync — drain queue, commit allowlisted paths, push to remote.
#
# Usage:
#   gstack-brain-sync --once           drain queue, commit, push (default)
#   gstack-brain-sync --status         print sync health as JSON
#   gstack-brain-sync --skip-file <p>  add <p> to ~/.gstack/.brain-skip.txt
#   gstack-brain-sync --drop-queue --yes   clear queue without committing
#   gstack-brain-sync --discover-new   scan allowlist dirs, enqueue changed files
#
# Invoked by the preamble at skill START and END boundaries. No persistent
# daemon. Typical run <1s when queue empty; ~200-800ms with network push.
#
# Singleton enforcement: flock on ~/.gstack/.brain-sync.lock. Concurrent
# invocations queue and serialize.
#
# Env:
#   GSTACK_HOME — override ~/.gstack (aligns with writers).

set -uo pipefail

GSTACK_HOME="${GSTACK_HOME:-$HOME/.gstack}"
QUEUE="$GSTACK_HOME/.brain-queue.jsonl"
ALLOWLIST="$GSTACK_HOME/.brain-allowlist"
PRIVACY_MAP="$GSTACK_HOME/.brain-privacy-map.json"
SKIP_FILE="$GSTACK_HOME/.brain-skip.txt"
STATUS_FILE="$GSTACK_HOME/.brain-sync-status.json"
LAST_PUSH_FILE="$GSTACK_HOME/.brain-last-push"
LOCK_FILE="$GSTACK_HOME/.brain-sync.lock"
DISCOVER_CURSOR="$GSTACK_HOME/.brain-discover-cursor"

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

# Remote-specific hint for auth errors (branch on origin URL).
remote_auth_hint() {
  local url
  url=$(git -C "$GSTACK_HOME" remote get-url origin 2>/dev/null || echo "")
  case "$url" in
    *github.com*|*@github.*) echo "run: gh auth status (and gh auth refresh if needed)" ;;
    *gitlab*) echo "run: glab auth status" ;;
    *) echo "check 'git remote -v' and your credentials" ;;
  esac
}

write_status() {
  # args: status_code message [extra_json_blob]
  local code="$1"
  local msg="$2"
  local extra="${3:-{\}}"
  local ts
  ts=$(date -u +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || echo "")
  python3 - "$STATUS_FILE" "$code" "$msg" "$ts" "$extra" <<'PYEOF' 2>/dev/null || true
import json, sys
path, code, msg, ts, extra = sys.argv[1:6]
try:
    extra_obj = json.loads(extra) if extra else {}
except Exception:
    extra_obj = {}
data = {"status": code, "message": msg, "ts": ts, **extra_obj}
with open(path, "w") as f:
    json.dump(data, f)
    f.write("\n")
PYEOF
}

# Read config; return 0 if sync active, 1 otherwise.
sync_active() {
  if [ ! -d "$GSTACK_HOME/.git" ]; then
    return 1
  fi
  local mode
  mode=$("$CONFIG_BIN" get artifacts_sync_mode 2>/dev/null || echo off)
  [ "$mode" = "off" ] && return 1
  return 0
}

# Secret regex families — stdin scan. Exits 0 clean, 1 if hit.
# Echoes the matching pattern family name on hit. Uses python3 -c (not
# heredoc) so sys.stdin stays available for the diff content.
secret_scan_stdin() {
  python3 -c "
import sys, re
patterns = [
    ('aws-access-key', re.compile(r'AKIA[0-9A-Z]{16}')),
    ('github-token', re.compile(r'\\b(gh[pousr]_[A-Za-z0-9]{20,}|github_pat_[A-Za-z0-9_]{20,})')),
    ('openai-key', re.compile(r'\\bsk-[A-Za-z0-9_-]{20,}')),
    ('pem-block', re.compile(r'-----BEGIN [A-Z ]{3,}-----')),
    ('jwt', re.compile(r'\\beyJ[A-Za-z0-9_-]{10,}\\.[A-Za-z0-9_-]{10,}\\.[A-Za-z0-9_-]{10,}\\b')),
    ('bearer-token-json',
     # JSON-embedded auth headers. The optional Bearer/Basic/Token prefix
     # matters: real auth values include a literal space after the scheme
     # name, but the value charset below does not include spaces, so
     # without the optional prefix every Bearer token in a JSON blob slips
     # past the scanner.
     re.compile(r'\"(authorization|api[_-]?key|apikey|token|secret|password)\"\\s*:\\s*\"(Bearer |Basic |Token )?[A-Za-z0-9_./+=-]{16,}\"',
                re.IGNORECASE)),
]
text = sys.stdin.read()
for name, rx in patterns:
    m = rx.search(text)
    if m:
        snippet = m.group(0)
        if len(snippet) > 30:
            snippet = snippet[:30] + '...'
        print(name + ':' + snippet)
        sys.exit(1)
sys.exit(0)
"
}

# Compute matched allowlisted, privacy-filtered path set from queue.
# Output: newline-delimited relative paths that should be staged.
compute_paths_to_stage() {
  local mode="$1"
  python3 - "$GSTACK_HOME" "$QUEUE" "$ALLOWLIST" "$PRIVACY_MAP" "$SKIP_FILE" "$mode" <<'PYEOF'
import sys, json, os, fnmatch, glob

gstack_home, queue, allowlist_path, privacy_path, skip_path, mode = sys.argv[1:7]

def load_lines(path):
    try:
        with open(path) as f:
            return [l.strip() for l in f if l.strip() and not l.lstrip().startswith("#")]
    except FileNotFoundError:
        return []

def load_privacy_map(path):
    try:
        with open(path) as f:
            data = json.load(f)
        # Expected: [{"pattern": "glob", "class": "artifact" | "behavioral"}]
        return data if isinstance(data, list) else []
    except (FileNotFoundError, json.JSONDecodeError):
        return []

allowlist_globs = load_lines(allowlist_path)
privacy_map = load_privacy_map(privacy_path)
# Normalize skip entries to the POSIX form queued paths use, so a backslash
# entry in .brain-skip.txt still matches on Windows. The drain is the safety
# boundary that actually stages files, so it must normalize identically to
# discover_new — otherwise an explicitly-skipped file gets committed.
skip_lines = {s.replace(os.sep, "/") for s in load_lines(skip_path)}

# Read queue; collect unique file paths.
queue_paths = set()
try:
    with open(queue) as f:
        for line in f:
            line = line.strip()
            if not line:
                continue
            try:
                obj = json.loads(line)
                p = obj.get("file")
                if isinstance(p, str):
                    queue_paths.add(p)
            except json.JSONDecodeError:
                continue
except FileNotFoundError:
    pass

def path_matches_any(path, globs):
    for pattern in globs:
        if fnmatch.fnmatchcase(path, pattern):
            return True
    return False

def privacy_class(path, mapping):
    for entry in mapping:
        pat = entry.get("pattern")
        if pat and fnmatch.fnmatchcase(path, pat):
            return entry.get("class", "artifact")
    # Default class when no pattern matches: artifact (safe default).
    return "artifact"

# mode filter: 'off' → nothing; 'artifacts-only' → only artifact class;
# 'full' → both classes.
def mode_allows(cls, mode):
    if mode == "off":
        return False
    if mode == "artifacts-only":
        return cls == "artifact"
    return True  # full

final = []
for p in sorted(queue_paths):
    if p in skip_lines:
        continue
    # Must be under GSTACK_HOME root. Reject absolute + reject ../ escape.
    if p.startswith("/") or ".." in p.split("/"):
        continue
    # Must match at least one allowlist glob.
    if not path_matches_any(p, allowlist_globs):
        continue
    # Must survive privacy mode filter.
    cls = privacy_class(p, privacy_map)
    if not mode_allows(cls, mode):
        continue
    # Must exist on disk — can't stage what isn't there.
    if not os.path.exists(os.path.join(gstack_home, p)):
        continue
    final.append(p)

for p in final:
    print(p)
PYEOF
}

subcmd_once() {
  if ! sync_active; then
    # Silent no-op when feature not initialized / disabled.
    exit 0
  fi

  # Singleton lock via atomic mkdir. `flock(1)` isn't on macOS by default;
  # `mkdir` is atomic on every POSIX filesystem. If another --once is already
  # running, skip (don't wait) — the next skill boundary will catch up.
  local lock_dir="${LOCK_FILE}.d"
  if ! mkdir "$lock_dir" 2>/dev/null; then
    # Is the lock stale? Check the pidfile inside. If process is dead, clear it.
    if [ -f "$lock_dir/pid" ]; then
      local lock_pid
      lock_pid=$(cat "$lock_dir/pid" 2>/dev/null || echo "")
      if [ -n "$lock_pid" ] && ! kill -0 "$lock_pid" 2>/dev/null; then
        # Stale lock — clear and retry once.
        rm -rf "$lock_dir" 2>/dev/null || true
        if ! mkdir "$lock_dir" 2>/dev/null; then
          exit 0
        fi
      else
        # Lock is held by a live process.
        exit 0
      fi
    else
      # Lock dir without pidfile — treat as held; don't touch.
      exit 0
    fi
  fi
  echo "$$" > "$lock_dir/pid" 2>/dev/null || true

  local mode
  mode=$("$CONFIG_BIN" get artifacts_sync_mode 2>/dev/null || echo off)

  local paths_file
  paths_file=$(mktemp /tmp/brain-sync-paths.XXXXXX) || { rm -rf "$lock_dir" 2>/dev/null; write_status "error" "mktemp failed"; exit 1; }
  # Single trap covers both: lock cleanup AND tempfile cleanup.
  trap 'rm -f "$paths_file" 2>/dev/null; rm -rf "$lock_dir" 2>/dev/null || true' EXIT INT TERM

  compute_paths_to_stage "$mode" > "$paths_file"
  if [ ! -s "$paths_file" ]; then
    # Nothing to stage. Clear any stale queue entries and exit.
    : > "$QUEUE"
    write_status "idle" "no allowlisted changes in queue"
    exit 0
  fi

  # Stage with git add -f (forces past .gitignore=*) explicit paths only.
  while IFS= read -r p; do
    p="${p%$'\r'}"   # Windows: compute_paths_to_stage's python print() emits CRLF;
                     # a trailing CR makes the pathspec match nothing (silent no-stage).
    [ -z "$p" ] && continue
    git -C "$GSTACK_HOME" add -f -- "$p" 2>/dev/null || true
  done < "$paths_file"

  # Secret-scan staged diff.
  local scan_out
  scan_out=$(git -C "$GSTACK_HOME" diff --cached 2>/dev/null | secret_scan_stdin || true)
  if [ -n "$scan_out" ]; then
    # Hit — unstage, preserve queue, write loud status.
    git -C "$GSTACK_HOME" reset HEAD -- . >/dev/null 2>&1 || true
    local hint
    hint="secret pattern detected ($scan_out). Remediation: review the staged file, then run: gstack-brain-sync --skip-file <path> OR edit the content."
    write_status "blocked" "$hint"
    echo "BRAIN_SYNC: blocked: $scan_out" >&2
    exit 0
  fi

  # Commit with template message.
  local n ts
  n=$(wc -l < "$paths_file" | tr -d ' ')
  ts=$(date -u +%Y-%m-%dT%H:%M:%SZ)
  local msg="sync: $n file(s) | $ts"
  git -C "$GSTACK_HOME" -c user.email="gstack@localhost" -c user.name="gstack-brain-sync" \
    commit -q -m "$msg" 2>/dev/null || {
      # Nothing to commit (e.g. all files already committed).
      : > "$QUEUE"
      write_status "idle" "queue drained but no new changes to commit"
      exit 0
    }

  # Push. On reject, fetch + merge (merge driver handles JSONL) + retry once.
  local push_err
  push_err=$(git -C "$GSTACK_HOME" push origin HEAD 2>&1 >/dev/null) || {
    # Check if this is an auth error first — no point retrying.
    if echo "$push_err" | grep -qiE "auth|permission|403|401|forbidden"; then
      local hint
      hint=$(remote_auth_hint)
      write_status "push_failed" "push failed: auth error. fix: $hint"
      echo "BRAIN_SYNC: push failed: auth. fix: $hint" >&2
      # Queue cleared because the commit exists locally; next push will send it.
      : > "$QUEUE"
      exit 0
    fi

    # Try a fetch-and-merge + retry.
    if git -C "$GSTACK_HOME" fetch origin 2>/dev/null; then
      local branch
      branch=$(git -C "$GSTACK_HOME" rev-parse --abbrev-ref HEAD 2>/dev/null || echo main)
      if git -C "$GSTACK_HOME" merge --no-edit "origin/$branch" >/dev/null 2>&1; then
        if git -C "$GSTACK_HOME" push origin HEAD 2>/dev/null; then
          : > "$QUEUE"
          date -u +%Y-%m-%dT%H:%M:%SZ > "$LAST_PUSH_FILE"
          write_status "ok" "pushed $n file(s) after rebase"
          exit 0
        fi
      fi
    fi
    write_status "push_failed" "push failed: $(printf '%s' "$push_err" | head -1)"
    : > "$QUEUE"
    exit 0
  }

  # Success: clear queue, update last-push.
  : > "$QUEUE"
  date -u +%Y-%m-%dT%H:%M:%SZ > "$LAST_PUSH_FILE"
  write_status "ok" "pushed $n file(s)"
  exit 0
}

subcmd_status() {
  if [ -f "$STATUS_FILE" ]; then
    cat "$STATUS_FILE"
  else
    echo '{"status":"unknown","message":"no status file yet"}'
  fi
  # Supplemental info (not in status file).
  local queue_depth=0
  [ -f "$QUEUE" ] && queue_depth=$(wc -l < "$QUEUE" | tr -d ' ')
  local last_push="never"
  [ -f "$LAST_PUSH_FILE" ] && last_push=$(cat "$LAST_PUSH_FILE" 2>/dev/null || echo never)
  local mode
  mode=$("$CONFIG_BIN" get artifacts_sync_mode 2>/dev/null || echo off)
  printf '{"queue_depth":%s,"last_push":"%s","mode":"%s"}\n' "$queue_depth" "$last_push" "$mode"
}

subcmd_skip_file() {
  local path="${1:-}"
  if [ -z "$path" ]; then
    echo "Usage: gstack-brain-sync --skip-file <path>" >&2
    exit 1
  fi
  mkdir -p "$GSTACK_HOME"
  # Avoid duplicate entries.
  if [ -f "$SKIP_FILE" ] && grep -Fxq "$path" "$SKIP_FILE"; then
    echo "already in skip list: $path"
    exit 0
  fi
  echo "$path" >> "$SKIP_FILE"
  echo "added to skip list: $path"
  echo "(future writers will not enqueue this path; existing queue entries ignored on next --once)"
}

subcmd_drop_queue() {
  local force="${1:-}"
  if [ "$force" != "--yes" ]; then
    echo "Refusing: --drop-queue discards pending syncs. Pass --yes to confirm." >&2
    exit 1
  fi
  if [ ! -f "$QUEUE" ]; then
    echo "queue already empty"
    exit 0
  fi
  local n
  n=$(wc -l < "$QUEUE" | tr -d ' ')
  : > "$QUEUE"
  echo "dropped $n queue entries"
}

subcmd_discover_new() {
  if ! sync_active; then
    exit 0
  fi
  # Walk allowlist globs; enqueue any file where mtime+size differs from cursor.
  python3 - "$GSTACK_HOME" "$ALLOWLIST" "$DISCOVER_CURSOR" <<'PYEOF' 2>/dev/null || true
import sys, os, json, fnmatch
from datetime import datetime, timezone

gstack_home, allowlist_path, cursor_path = sys.argv[1:4]
queue_path = os.path.join(gstack_home, ".brain-queue.jsonl")
skip_path = os.path.join(gstack_home, ".brain-skip.txt")

def load_lines(path):
    try:
        with open(path) as f:
            return [l.strip() for l in f if l.strip() and not l.lstrip().startswith("#")]
    except FileNotFoundError:
        return []

def load_cursor(path):
    try:
        with open(path) as f:
            return json.load(f)
    except (FileNotFoundError, json.JSONDecodeError):
        return {}

def save_cursor(path, data):
    try:
        with open(path, "w") as f:
            json.dump(data, f)
    except OSError:
        pass

allowlist = load_lines(allowlist_path)
# Normalize skip entries to the same POSIX form as `rel` below, so a
# backslash entry in .brain-skip.txt still matches a normalized path on Windows.
skip = {s.replace(os.sep, "/") for s in load_lines(skip_path)}
cursor = load_cursor(cursor_path)
new_cursor = dict(cursor)
to_enqueue = []

# Walk all files under gstack_home, match against allowlist.
for root, dirs, files in os.walk(gstack_home):
    # Skip .git and .brain-* state files.
    if ".git" in root.split(os.sep):
        continue
    for name in files:
        full = os.path.join(root, name)
        # Repo paths are POSIX-relative. os.path.relpath yields backslash
        # separators on Windows, which never match the forward-slash allowlist
        # globs (e.g. "projects/*/learnings.jsonl"), so discovery silently
        # enqueued nothing under projects/ on Windows. Normalize to "/".
        rel = os.path.relpath(full, gstack_home).replace(os.sep, "/")
        if rel.startswith(".brain-"):
            continue
        if not any(fnmatch.fnmatchcase(rel, pat) for pat in allowlist):
            continue
        if rel in skip:
            continue
        try:
            st = os.stat(full)
            key = f"{int(st.st_mtime)}:{st.st_size}"
        except OSError:
            continue
        if cursor.get(rel) != key:
            to_enqueue.append((rel, key))

# Append to the queue directly. The previous implementation shelled out to
# gstack-brain-enqueue once per file, but Windows Python cannot exec a
# bash-shebang script (the spawn fails with a fork error), so discovery
# enqueued nothing on Windows even after the path-match fix above.
# Writing the queue line here is platform-agnostic; the drain step
# (compute_paths_to_stage) still re-applies the skip-list + privacy filters.
if to_enqueue:
    ts = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
    try:
        # One atomic append per record (O_APPEND, each line < PIPE_BUF), matching
        # gstack-brain-enqueue's concurrency contract so a writer-shim append
        # running in parallel can't interleave mid-record. Buffered text writes
        # don't guarantee that. Compact separators match the shim's JSON shape.
        fd = os.open(queue_path, os.O_WRONLY | os.O_CREAT | os.O_APPEND, 0o644)
        try:
            for rel, key in to_enqueue:
                rec = json.dumps({"file": rel, "ts": ts}, separators=(",", ":"))
                os.write(fd, (rec + "\n").encode("utf-8"))
        finally:
            os.close(fd)
    except OSError:
        # Queue write failed (disk full, AV file lock). Leave the cursor
        # unadvanced so these files are retried on the next discover instead of
        # being silently recorded as synced (which loses the change until the
        # file next changes).
        to_enqueue = []
    # Advance the cursor only for records actually written.
    for rel, key in to_enqueue:
        new_cursor[rel] = key

save_cursor(cursor_path, new_cursor)
PYEOF
}

# -------- dispatch --------
case "${1:-}" in
  --once|"") subcmd_once ;;
  --status) subcmd_status ;;
  --skip-file) shift; subcmd_skip_file "${1:-}" ;;
  --drop-queue) shift; subcmd_drop_queue "${1:-}" ;;
  --discover-new) subcmd_discover_new ;;
  --help|-h)
    sed -n '2,18p' "$0" | sed 's/^# \{0,1\}//'
    ;;
  *)
    echo "Unknown subcommand: $1" >&2
    echo "Run: gstack-brain-sync --help" >&2
    exit 1
    ;;
esac