gstack/bin/gstack-community-backup

#!/usr/bin/env bash
# gstack-community-backup — sync local state to Supabase for cloud backup
#
# Backs up: config, analytics summary, retro history.
# Requires community tier + valid auth token.
# Rate limited to once per 30 minutes.
#
# Env overrides (for testing):
#   GSTACK_STATE_DIR           — override ~/.gstack state directory
#   GSTACK_DIR                 — override auto-detected gstack root
set -uo pipefail

GSTACK_DIR="${GSTACK_DIR:-$(cd "$(dirname "$0")/.." && pwd)}"
STATE_DIR="${GSTACK_STATE_DIR:-$HOME/.gstack}"
ANALYTICS_DIR="$STATE_DIR/analytics"
JSONL_FILE="$ANALYTICS_DIR/skill-usage.jsonl"
BACKUP_RATE_FILE="$ANALYTICS_DIR/.last-backup-time"
CONFIG_CMD="$GSTACK_DIR/bin/gstack-config"
AUTH_REFRESH="$GSTACK_DIR/bin/gstack-auth-refresh"

# Source Supabase config
if [ -f "$GSTACK_DIR/supabase/config.sh" ]; then
  . "$GSTACK_DIR/supabase/config.sh"
fi
ENDPOINT="${GSTACK_TELEMETRY_ENDPOINT:-}"
ANON_KEY="${GSTACK_SUPABASE_ANON_KEY:-}"

# ─── Pre-checks ─────────────────────────────────────────────
# Must be community tier
TIER="$("$CONFIG_CMD" get telemetry 2>/dev/null || true)"
[ "$TIER" != "community" ] && exit 0

# Must have auth
"$AUTH_REFRESH" --check 2>/dev/null || exit 0

# Must have endpoint
[ -z "$ENDPOINT" ] && exit 0

# Rate limit: once per 30 minutes
if [ -f "$BACKUP_RATE_FILE" ]; then
  STALE=$(find "$BACKUP_RATE_FILE" -mmin +30 2>/dev/null || true)
  [ -z "$STALE" ] && exit 0
fi

# ─── Get auth token ─────────────────────────────────────────
ACCESS_TOKEN="$("$AUTH_REFRESH" 2>/dev/null || true)"
[ -z "$ACCESS_TOKEN" ] && exit 0

# Read user info from auth file
AUTH_JSON="$(cat "$STATE_DIR/auth-token.json" 2>/dev/null || echo "{}")"
USER_ID="$(echo "$AUTH_JSON" | grep -o '"user_id":"[^"]*"' | head -1 | sed 's/"user_id":"//;s/"//')"
EMAIL="$(echo "$AUTH_JSON" | grep -o '"email":"[^"]*"' | head -1 | sed 's/"email":"//;s/"//')"

[ -z "$USER_ID" ] && exit 0

# ─── Build config snapshot ───────────────────────────────────
CONFIG_SNAPSHOT="{}"
if [ -f "$STATE_DIR/config.yaml" ]; then
  # Convert YAML-like config to JSON
  CONFIG_SNAPSHOT="{"
  FIRST=true
  while IFS=': ' read -r KEY VALUE; do
    [ -z "$KEY" ] && continue
    [ -z "$VALUE" ] && continue
    if [ "$FIRST" = "true" ]; then FIRST=false; else CONFIG_SNAPSHOT="$CONFIG_SNAPSHOT,"; fi
    CONFIG_SNAPSHOT="$CONFIG_SNAPSHOT\"$KEY\":\"$VALUE\""
  done < "$STATE_DIR/config.yaml"
  CONFIG_SNAPSHOT="$CONFIG_SNAPSHOT}"
fi

# ─── Build analytics summary ────────────────────────────────
# Per-skill aggregates + last 100 events (not raw JSONL)
ANALYTICS_SNAPSHOT="{\"skills\":{},\"recent_events\":[]}"
if [ -f "$JSONL_FILE" ]; then
  # Count per-skill totals
  SKILL_COUNTS="$(grep -o '"skill":"[^"]*"' "$JSONL_FILE" 2>/dev/null | awk -F'"' '{print $4}' | sort | uniq -c | sort -rn | head -20)"

  SKILLS_JSON="{"
  FIRST=true
  while read -r COUNT SKILL; do
    [ -z "$SKILL" ] && continue
    if [ "$FIRST" = "true" ]; then FIRST=false; else SKILLS_JSON="$SKILLS_JSON,"; fi
    SKILLS_JSON="$SKILLS_JSON\"$SKILL\":{\"total_runs\":$COUNT}"
  done <<< "$SKILL_COUNTS"
  SKILLS_JSON="$SKILLS_JSON}"

  # Last 100 events (strip local-only fields)
  RECENT="$(tail -100 "$JSONL_FILE" 2>/dev/null | sed \
    -e 's/,"_repo_slug":"[^"]*"//g' \
    -e 's/,"_branch":"[^"]*"//g' | tr '\n' ',' | sed 's/,$//')"

  ANALYTICS_SNAPSHOT="{\"skills\":${SKILLS_JSON},\"recent_events\":[${RECENT}]}"
fi

# ─── Build retro history snapshot ────────────────────────────
RETRO_SNAPSHOT="[]"
# Look for retro files in common locations
RETRO_FILES=""
if [ -d "$STATE_DIR" ]; then
  RETRO_FILES="$(find "$STATE_DIR" -name "retro-*.json" -o -name "retro_*.json" 2>/dev/null | head -20 || true)"
fi

if [ -n "$RETRO_FILES" ]; then
  RETRO_SNAPSHOT="["
  FIRST=true
  while IFS= read -r RFILE; do
    [ -f "$RFILE" ] || continue
    CONTENT="$(cat "$RFILE" 2>/dev/null || true)"
    [ -z "$CONTENT" ] && continue
    if [ "$FIRST" = "true" ]; then FIRST=false; else RETRO_SNAPSHOT="$RETRO_SNAPSHOT,"; fi
    RETRO_SNAPSHOT="$RETRO_SNAPSHOT$CONTENT"
  done <<< "$RETRO_FILES"
  RETRO_SNAPSHOT="$RETRO_SNAPSHOT]"
fi

# ─── Upsert to installations table ──────────────────────────
GSTACK_VERSION="$(cat "$GSTACK_DIR/VERSION" 2>/dev/null | tr -d '[:space:]' || echo "unknown")"
OS="$(uname -s | tr '[:upper:]' '[:lower:]')"
NOW_ISO="$(date -u +%Y-%m-%dT%H:%M:%SZ)"

# Escape JSON strings that might contain special characters
# Config and retro snapshots are already JSON, analytics too
PAYLOAD="{
  \"installation_id\": \"${USER_ID}\",
  \"user_id\": \"${USER_ID}\",
  \"email\": \"${EMAIL}\",
  \"gstack_version\": \"${GSTACK_VERSION}\",
  \"os\": \"${OS}\",
  \"config_snapshot\": ${CONFIG_SNAPSHOT},
  \"analytics_snapshot\": ${ANALYTICS_SNAPSHOT},
  \"retro_history\": ${RETRO_SNAPSHOT},
  \"last_backup_at\": \"${NOW_ISO}\",
  \"last_seen\": \"${NOW_ISO}\"
}"

# Upsert (POST with Prefer: resolution=merge-duplicates)
HTTP_CODE="$(curl -s -o /dev/null -w '%{http_code}' --max-time 15 \
  -X POST "${ENDPOINT}/installations" \
  -H "Content-Type: application/json" \
  -H "apikey: ${ANON_KEY}" \
  -H "Authorization: Bearer ${ACCESS_TOKEN}" \
  -H "Prefer: resolution=merge-duplicates,return=minimal" \
  -d "$PAYLOAD" 2>/dev/null || echo "000")"

# Update rate limit marker on success
case "$HTTP_CODE" in
  2*) touch "$BACKUP_RATE_FILE" 2>/dev/null || true ;;
esac

exit 0