gstack/bin/gstack-artifacts-init

#!/usr/bin/env bash
# gstack-artifacts-init — set up ~/.gstack/ as a git repo synced to a private
# git host (GitHub or GitLab) so a remote gbrain can ingest your artifacts
# (CEO plans, designs, /investigate reports) as a federated source.
#
# Replaces gstack-brain-init in v1.27.0.0 (per D4 hard-delete; no compat
# shim). Existing users are migrated by gstack-upgrade/migrations/v1.27.0.0.sh.
#
# Usage:
#   gstack-artifacts-init [--remote <url>] [--host github|gitlab|manual]
#                         [--url-form-supported true|false]
#
# Interactive by default. Pass --remote to skip the host prompt.
#
# Idempotent: safe to re-run. If ~/.gstack/.git already exists AND points at
# the same remote, reconfigures drivers/hooks/attributes without clobbering
# history. If it points at a DIFFERENT remote, refuses.
#
# What it does:
#   1. git init ~/.gstack/  (or verify existing repo points at the right remote)
#   2. Write .gitignore = "*"  (ignore everything; allowlist is explicit)
#   3. Write .brain-allowlist  (canonical paths to sync)
#   4. Write .brain-privacy-map.json  (paths → privacy class)
#   5. Write .gitattributes  (register JSONL + union merge drivers)
#   6. git config  merge.jsonl-append.driver + merge.union.driver
#   7. Install .git/hooks/pre-commit  (defense-in-depth secret scan)
#   8. Provider-aware repo create (gh / glab) OR manual URL paste
#   9. Initial commit + push
#   10. Write ~/.gstack-artifacts-remote.txt  (HTTPS URL — canonical form)
#   11. Print "Send this to your brain admin" hookup command
#
# Env:
#   GSTACK_HOME — override ~/.gstack
#   USER — fallback for repo naming if $USER is unset

set -euo pipefail

GSTACK_HOME="${GSTACK_HOME:-$HOME/.gstack}"
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
URL_BIN="$SCRIPT_DIR/gstack-artifacts-url"
REMOTE_FILE="$HOME/.gstack-artifacts-remote.txt"

REMOTE_URL=""
HOST_PREF=""
URL_FORM_SUPPORTED="false"
while [ $# -gt 0 ]; do
  case "$1" in
    --remote) REMOTE_URL="$2"; shift 2 ;;
    --host) HOST_PREF="$2"; shift 2 ;;
    --url-form-supported) URL_FORM_SUPPORTED="$2"; shift 2 ;;
    --help|-h) sed -n '2,32p' "$0" | sed 's/^# \{0,1\}//'; exit 0 ;;
    *) echo "Unknown flag: $1" >&2; exit 1 ;;
  esac
done

# ---- preconditions ----
mkdir -p "$GSTACK_HOME"

EXISTING_REMOTE=""
if [ -d "$GSTACK_HOME/.git" ]; then
  EXISTING_REMOTE=$(git -C "$GSTACK_HOME" remote get-url origin 2>/dev/null || echo "")
  if [ -n "$EXISTING_REMOTE" ] && [ -n "$REMOTE_URL" ]; then
    # Compare at the canonical level. The stored remote is SSH (for git push),
    # the input is usually HTTPS — same logical repo, different surface form.
    EXISTING_HTTPS=$("$URL_BIN" --to https "$EXISTING_REMOTE" 2>/dev/null || echo "$EXISTING_REMOTE")
    INPUT_HTTPS=$("$URL_BIN" --to https "$REMOTE_URL" 2>/dev/null || echo "$REMOTE_URL")
    if [ "$EXISTING_HTTPS" != "$INPUT_HTTPS" ]; then
      cat >&2 <<EOF
gstack-artifacts-init: ~/.gstack/ is already a git repo pointing at:
  $EXISTING_REMOTE  (canonical: $EXISTING_HTTPS)

You asked to init with:
  $REMOTE_URL  (canonical: $INPUT_HTTPS)

Refusing to overwrite. To switch remotes, edit manually:
  git -C ~/.gstack remote set-url origin <url>
EOF
      exit 1
    fi
  fi
fi

# ---- detect available providers ----
gh_ok=false
glab_ok=false
if command -v gh >/dev/null 2>&1 && gh auth status >/dev/null 2>&1; then gh_ok=true; fi
if command -v glab >/dev/null 2>&1 && glab auth status >/dev/null 2>&1; then glab_ok=true; fi

# ---- choose remote URL ----
if [ -z "$REMOTE_URL" ] && [ -n "$EXISTING_REMOTE" ]; then
  REMOTE_URL="$EXISTING_REMOTE"
  echo "Using existing remote: $REMOTE_URL"
fi

REPO_NAME="gstack-artifacts-${USER:-$(whoami)}"
DESCRIPTION="gstack artifacts (CEO plans, designs, reports) — synced from ~/.gstack/projects/"

# Decide host preference if not pinned by --host.
if [ -z "$REMOTE_URL" ] && [ -z "$HOST_PREF" ]; then
  if $gh_ok && $glab_ok; then
    cat >&2 <<EOF

gstack-artifacts-init: which git host?
  1) GitHub      (gh CLI authenticated)
  2) GitLab      (glab CLI authenticated)
  3) Other / paste a private git URL

EOF
    printf "Choice [1]: " >&2
    read -r CH || CH=""
    case "$CH" in
      ""|1) HOST_PREF="github" ;;
      2) HOST_PREF="gitlab" ;;
      3) HOST_PREF="manual" ;;
      *) echo "Invalid choice: $CH" >&2; exit 1 ;;
    esac
  elif $gh_ok; then
    HOST_PREF="github"
    echo "Using GitHub (gh CLI authenticated; glab not available)" >&2
  elif $glab_ok; then
    HOST_PREF="gitlab"
    echo "Using GitLab (glab CLI authenticated; gh not available)" >&2
  else
    HOST_PREF="manual"
    echo "(Neither gh nor glab CLI authenticated — falling through to manual URL)" >&2
  fi
fi

# ---- create repo on chosen host ----
if [ -z "$REMOTE_URL" ]; then
  case "$HOST_PREF" in
    github)
      echo "Creating GitHub repo: $REPO_NAME ..."
      if ! gh repo create "$REPO_NAME" --private --description "$DESCRIPTION" 2>/dev/null; then
        # Maybe already exists; try to fetch its URL.
        REMOTE_URL=$(gh repo view "$REPO_NAME" --json url -q .url 2>/dev/null || echo "")
        if [ -z "$REMOTE_URL" ]; then
          echo "Failed to create or find '$REPO_NAME'. Try --remote <url>." >&2
          exit 1
        fi
        echo "Repo already exists; using $REMOTE_URL"
      else
        REMOTE_URL=$(gh repo view "$REPO_NAME" --json url -q .url 2>/dev/null || echo "")
      fi
      ;;
    gitlab)
      echo "Creating GitLab repo: $REPO_NAME ..."
      if ! glab repo create "$REPO_NAME" --private --description "$DESCRIPTION" 2>/dev/null; then
        REMOTE_URL=$(glab repo view "$REPO_NAME" -F json 2>/dev/null | jq -r '.web_url // empty' 2>/dev/null || echo "")
        if [ -z "$REMOTE_URL" ]; then
          echo "Failed to create or find '$REPO_NAME'. Try --remote <url>." >&2
          exit 1
        fi
        echo "Repo already exists; using $REMOTE_URL"
      else
        REMOTE_URL=$(glab repo view "$REPO_NAME" -F json 2>/dev/null | jq -r '.web_url // empty' 2>/dev/null || echo "")
      fi
      ;;
    manual)
      echo "(provide a private git URL)"
      printf "Paste an HTTPS git URL (e.g. https://github.com/you/gstack-artifacts.git): " >&2
      read -r REMOTE_URL || REMOTE_URL=""
      if [ -z "$REMOTE_URL" ]; then
        echo "No URL provided. Aborting." >&2
        exit 1
      fi
      ;;
    *) echo "Unknown --host: $HOST_PREF (expected github|gitlab|manual)" >&2; exit 1 ;;
  esac
fi

# ---- canonicalize to HTTPS form ----
# We store HTTPS in ~/.gstack-artifacts-remote.txt (codex Finding #10:
# canonical form, derive SSH at push time via gstack-artifacts-url --to ssh).
# Unrecognized forms (local bare paths, file:// URLs, self-hosted gitea, etc.)
# pass through verbatim so unusual remotes still work.
CANONICAL_HTTPS=$("$URL_BIN" --to https "$REMOTE_URL" 2>/dev/null || echo "")
if [ -z "$CANONICAL_HTTPS" ]; then
  CANONICAL_HTTPS="$REMOTE_URL"
fi

# Use SSH for git push (more reliable for repeated pushes than HTTPS+token).
# Fall back to the canonical input if derivation fails.
PUSH_URL=$("$URL_BIN" --to ssh "$CANONICAL_HTTPS" 2>/dev/null || echo "$CANONICAL_HTTPS")

# ---- verify push URL is reachable ----
echo "Verifying remote connectivity: $PUSH_URL"
if ! git ls-remote "$PUSH_URL" >/dev/null 2>&1; then
  cat >&2 <<EOF
Remote not reachable via SSH: $PUSH_URL
This could mean:
  - Wrong URL
  - SSH key not added to your git host (GitHub: gh ssh-key list; GitLab: glab ssh-key list)
  - Network issue
Fix and re-run gstack-artifacts-init.
EOF
  exit 1
fi

# ---- git init ----
if [ ! -d "$GSTACK_HOME/.git" ]; then
  git -C "$GSTACK_HOME" init -q -b main 2>/dev/null || git -C "$GSTACK_HOME" init -q
  git -C "$GSTACK_HOME" branch -M main 2>/dev/null || true
fi

if [ -z "$(git -C "$GSTACK_HOME" remote 2>/dev/null)" ]; then
  git -C "$GSTACK_HOME" remote add origin "$PUSH_URL"
else
  git -C "$GSTACK_HOME" remote set-url origin "$PUSH_URL"
fi

# ---- write canonical files (idempotent) ----
cat > "$GSTACK_HOME/.gitignore" <<'EOF'
# gstack-artifacts sync: ignore-everything base. Paths are included explicitly via
# .brain-allowlist and `git add -f` from gstack-brain-sync. Do not edit.
*
EOF

cat > "$GSTACK_HOME/.brain-allowlist" <<'EOF'
# Canonical allowlist of paths that gstack-brain-sync will publish.
# One glob per line. Anything not matching stays local.
# Do not edit directly; managed by gstack-artifacts-init. User additions go
# below the marker and survive re-init.
projects/*/learnings.jsonl
projects/*/*-reviews.jsonl
projects/*/ceo-plans/*.md
projects/*/ceo-plans/*/*.md
projects/*/designs/*.md
projects/*/designs/*/*.md
# Project-root design / test-plan artifacts written by /office-hours,
# /plan-eng-review, and /autoplan. The skills emit
# `{user}-{branch}-design-{datetime}.md`,
# `{user}-{branch}-test-plan-{datetime}.md`, and
# `{user}-{branch}-eng-review-test-plan-{datetime}.md` at the project
# root (not under designs/), so the existing `designs/*.md` patterns
# miss them. Without these the cross-machine pull on machine B gets
# the referencing CEO plan but not the underlying design / test plan
# (#1452).
projects/*/*-design-*.md
projects/*/*-test-plan-*.md
projects/*/*-eng-review-test-plan-*.md
projects/*/timeline.jsonl
retros/*.md
developer-profile.json
builder-journey.md
builder-profile.jsonl
# Transcripts staged in remote-http MCP mode (per plan D11 split-engine).
# gstack-memory-ingest persists per-run dirs here when local gbrain import
# is skipped; brain admin pulls + indexes into the remote brain.
transcripts/run-*/*.md
transcripts/run-*/**/*.md
# NOT synced (machine-local UX state):
#   projects/*/question-preferences.json (per-machine UX preferences)
#   projects/*/question-log.jsonl (audit/derivation log stays with preferences)
#   projects/*/question-events.jsonl (same)
# ---- USER ADDITIONS BELOW ---- (survives re-init; above is managed)
EOF

cat > "$GSTACK_HOME/.brain-privacy-map.json" <<'EOF'
[
  {"pattern": "projects/*/learnings.jsonl", "class": "artifact"},
  {"pattern": "projects/*/*-reviews.jsonl", "class": "artifact"},
  {"pattern": "projects/*/ceo-plans/*.md", "class": "artifact"},
  {"pattern": "projects/*/ceo-plans/*/*.md", "class": "artifact"},
  {"pattern": "projects/*/designs/*.md", "class": "artifact"},
  {"pattern": "projects/*/designs/*/*.md", "class": "artifact"},
  {"pattern": "projects/*/*-design-*.md", "class": "artifact"},
  {"pattern": "projects/*/*-test-plan-*.md", "class": "artifact"},
  {"pattern": "projects/*/*-eng-review-test-plan-*.md", "class": "artifact"},
  {"pattern": "retros/*.md", "class": "artifact"},
  {"pattern": "builder-journey.md", "class": "artifact"},
  {"pattern": "projects/*/timeline.jsonl", "class": "behavioral"},
  {"pattern": "developer-profile.json", "class": "behavioral"},
  {"pattern": "builder-profile.jsonl", "class": "behavioral"},
  {"pattern": "transcripts/run-*/*.md", "class": "behavioral"},
  {"pattern": "transcripts/run-*/**/*.md", "class": "behavioral"}
]
EOF

cat > "$GSTACK_HOME/.gitattributes" <<'EOF'
# gstack-artifacts: merge drivers for cross-machine sync conflicts.
*.jsonl merge=jsonl-append
retros/*.md merge=union
projects/*/designs/**/*.md merge=union
projects/*/ceo-plans/**/*.md merge=union
projects/*/*-design-*.md merge=union
projects/*/*-test-plan-*.md merge=union
EOF

# ---- register merge drivers in local git config ----
git -C "$GSTACK_HOME" config merge.jsonl-append.driver "$SCRIPT_DIR/gstack-jsonl-merge %O %A %B"
git -C "$GSTACK_HOME" config merge.jsonl-append.name "gstack JSONL append-only merger"
git -C "$GSTACK_HOME" config merge.union.driver "cat %A %B > %A.merged && mv %A.merged %A"
git -C "$GSTACK_HOME" config merge.union.name "union concat"

# ---- install pre-commit hook (defense-in-depth) ----
HOOK="$GSTACK_HOME/.git/hooks/pre-commit"
mkdir -p "$(dirname "$HOOK")"
cat > "$HOOK" <<'HOOK_EOF'
#!/usr/bin/env bash
# gstack-artifacts pre-commit hook — secret-scan defense-in-depth.
# The primary scanner runs inside gstack-brain-sync BEFORE staging. This hook
# catches any manual `git commit` a user might accidentally run against the
# artifacts repo.
set -uo pipefail

python3 -c "
import sys, re, subprocess
try:
    out = subprocess.check_output(['git', 'diff', '--cached'], stderr=subprocess.DEVNULL).decode('utf-8', 'replace')
except Exception:
    sys.exit(0)

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',
     re.compile(r'\"(authorization|api[_-]?key|apikey|token|secret|password)\"\s*:\s*\"[A-Za-z0-9_./+=-]{16,}\"',
                re.IGNORECASE)),
]
for name, rx in patterns:
    if rx.search(out):
        sys.stderr.write(f'gstack-artifacts pre-commit: refusing commit — {name} detected in staged diff.\n')
        sys.stderr.write('Either edit the offending file, or if intentional, run:\n')
        sys.stderr.write('  gstack-brain-sync --skip-file <path>  (to permanently exclude)\n')
        sys.exit(1)
sys.exit(0)
"
HOOK_EOF
chmod +x "$HOOK"

# ---- initial commit (idempotent) ----
cd "$GSTACK_HOME"
git add -f .gitignore .brain-allowlist .brain-privacy-map.json .gitattributes
if git rev-parse HEAD >/dev/null 2>&1; then
  if ! git diff --cached --quiet 2>/dev/null; then
    git -c user.email="gstack@localhost" -c user.name="gstack-artifacts-init" \
        commit -q -m "chore: gstack-artifacts-init (refresh sync config)"
  fi
else
  git -c user.email="gstack@localhost" -c user.name="gstack-artifacts-init" \
      commit -q -m "chore: gstack-artifacts-init"
fi

# ---- initial push ----
if ! git push -q -u origin main 2>/dev/null; then
  CURRENT_BRANCH=$(git rev-parse --abbrev-ref HEAD)
  if git fetch origin 2>/dev/null && git pull --ff-only origin "$CURRENT_BRANCH" 2>/dev/null; then
    git push -q -u origin "$CURRENT_BRANCH" || {
      echo "Push to $PUSH_URL failed. The remote may have divergent content." >&2
      echo "Try: cd ~/.gstack && git pull --rebase origin $CURRENT_BRANCH && git push origin $CURRENT_BRANCH" >&2
      exit 1
    }
  else
    echo "Push to $PUSH_URL failed and fetch/merge didn't help." >&2
    echo "Manual recovery: cd ~/.gstack && git status, then push once conflicts are resolved." >&2
    exit 1
  fi
fi

# ---- write the remote-url helper file (HTTPS canonical) ----
echo "$CANONICAL_HTTPS" > "$REMOTE_FILE"
chmod 600 "$REMOTE_FILE"

# ---- print brain-admin hookup command (always print, never auto-execute;
#      codex Finding #3) ----
SOURCE_ID="gstack-artifacts-${USER:-$(whoami)}"
cat <<EOF

gstack-artifacts-init complete.
Repo:    $GSTACK_HOME (git)
Remote:  $CANONICAL_HTTPS  (canonical form, in ~/.gstack-artifacts-remote.txt)
Push:    $PUSH_URL  (derived SSH form for git push)

EOF

cat <<EOF
─────────────────────────────────────────────────────────────────────────
  Send this to your brain admin (the person who runs your gbrain server)
─────────────────────────────────────────────────────────────────────────
EOF

if [ "$URL_FORM_SUPPORTED" = "true" ]; then
  cat <<EOF
On the brain host, run:

  gbrain sources add $SOURCE_ID --url $CANONICAL_HTTPS --federated

EOF
else
  cat <<EOF
On the brain host (gbrain v0.26.x doesn't accept URLs directly yet), run:

  git clone $CANONICAL_HTTPS ~/$SOURCE_ID
  gbrain sources add $SOURCE_ID --path ~/$SOURCE_ID --federated

When gbrain ships --url support, this becomes a one-liner:
  gbrain sources add $SOURCE_ID --url $CANONICAL_HTTPS --federated

EOF
fi

cat <<EOF
After that, your CEO plans / designs / reports become searchable via
'gbrain search' from any machine pointing at this brain.
─────────────────────────────────────────────────────────────────────────

New machine? Put a copy of $REMOTE_FILE in that machine's home directory,
then run: gstack-artifacts-init  (it'll detect the remote and re-init).
EOF