#!/usr/bin/env bash
# gstack-telemetry-sync — sync local JSONL events to Supabase
#
# Fire-and-forget, backgrounded, rate-limited to once per 5 minutes.
# Strips local-only fields before sending. Respects privacy tiers.
#
# Env overrides (for testing):
#   GSTACK_STATE_DIR           — override ~/.gstack state directory
#   GSTACK_DIR                 — override auto-detected gstack root
#   GSTACK_TELEMETRY_ENDPOINT  — override Supabase endpoint URL
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="$ANALYTICS_DIR/skill-usage.jsonl"
CURSOR_FILE="$ANALYTICS_DIR/.last-sync-line"
RATE_FILE="$ANALYTICS_DIR/.last-sync-time"
CONFIG_CMD="$GSTACK_DIR/bin/gstack-config"

# Source Supabase config if not overridden by env
if [ -z "${GSTACK_TELEMETRY_ENDPOINT:-}" ] && [ -f "$GSTACK_DIR/supabase/config.sh" ]; then
  . "$GSTACK_DIR/supabase/config.sh"
fi
ENDPOINT="${GSTACK_TELEMETRY_ENDPOINT:-}"
ANON_KEY="${GSTACK_SUPABASE_ANON_KEY:-}"

# ─── Pre-checks ──────────────────────────────────────────────
# No endpoint configured yet → exit silently
[ -z "$ENDPOINT" ] && exit 0

# No JSONL file → nothing to sync
[ -f "$JSONL_FILE" ] || exit 0

# Rate limit: once per 5 minutes
if [ -f "$RATE_FILE" ]; then
  STALE=$(find "$RATE_FILE" -mmin +5 2>/dev/null || true)
  [ -z "$STALE" ] && exit 0
fi

# ─── Read tier ───────────────────────────────────────────────
TIER="$("$CONFIG_CMD" get telemetry 2>/dev/null || true)"
TIER="${TIER:-off}"
[ "$TIER" = "off" ] && exit 0

# ─── Read cursor ─────────────────────────────────────────────
CURSOR=0
if [ -f "$CURSOR_FILE" ]; then
  CURSOR="$(cat "$CURSOR_FILE" 2>/dev/null | tr -d ' \n\r\t')"
  # Validate: must be a non-negative integer
  case "$CURSOR" in *[!0-9]*) CURSOR=0 ;; esac
fi

# Safety: if cursor exceeds file length, reset
TOTAL_LINES="$(wc -l < "$JSONL_FILE" | tr -d ' \n\r\t')"
if [ "$CURSOR" -gt "$TOTAL_LINES" ] 2>/dev/null; then
  CURSOR=0
fi

# Nothing new to sync
[ "$CURSOR" -ge "$TOTAL_LINES" ] 2>/dev/null && exit 0

# ─── Read unsent lines ───────────────────────────────────────
SKIP=$(( CURSOR + 1 ))
UNSENT="$(tail -n "+$SKIP" "$JSONL_FILE" 2>/dev/null || true)"
[ -z "$UNSENT" ] && exit 0

# ─── Strip local-only fields and build batch ─────────────────
BATCH="["
FIRST=true
COUNT=0

while IFS= read -r LINE; do
  # Skip empty or malformed lines
  [ -z "$LINE" ] && continue
  echo "$LINE" | grep -q '^{' || continue

  # Strip local-only fields + map JSONL field names to Postgres column names
  CLEAN="$(echo "$LINE" | sed \
    -e 's/,"_repo_slug":"[^"]*"//g' \
    -e 's/,"_branch":"[^"]*"//g' \
    -e 's/"v":/"schema_version":/g' \
    -e 's/"ts":/"event_timestamp":/g' \
    -e 's/"sessions":/"concurrent_sessions":/g' \
    -e 's/,"repo":"[^"]*"//g')"

  # If anonymous tier, strip installation_id
  if [ "$TIER" = "anonymous" ]; then
    CLEAN="$(echo "$CLEAN" | sed 's/,"installation_id":"[^"]*"//g; s/,"installation_id":null//g')"
  fi

  if [ "$FIRST" = "true" ]; then
    FIRST=false
  else
    BATCH="$BATCH,"
  fi
  BATCH="$BATCH$CLEAN"
  COUNT=$(( COUNT + 1 ))

  # Batch size limit
  [ "$COUNT" -ge 100 ] && break
done <<< "$UNSENT"

BATCH="$BATCH]"

# Nothing to send after filtering
[ "$COUNT" -eq 0 ] && exit 0

# ─── POST to Supabase ────────────────────────────────────────
HTTP_CODE="$(curl -s -o /dev/null -w '%{http_code}' --max-time 10 \
  -X POST "${ENDPOINT}/telemetry_events" \
  -H "Content-Type: application/json" \
  -H "apikey: ${ANON_KEY}" \
  -H "Authorization: Bearer ${ANON_KEY}" \
  -H "Prefer: return=minimal" \
  -d "$BATCH" 2>/dev/null || echo "000")"

# ─── Update cursor on success (2xx) ─────────────────────────
case "$HTTP_CODE" in
  2*) NEW_CURSOR=$(( CURSOR + COUNT ))
      echo "$NEW_CURSOR" > "$CURSOR_FILE" 2>/dev/null || true ;;
esac

# Update rate limit marker
touch "$RATE_FILE" 2>/dev/null || true

exit 0