gstack/bin/gstack-telemetry-log

#!/usr/bin/env bash
# gstack-telemetry-log — append a telemetry event to local JSONL
#
# Data flow:
#   preamble (start) ──▶ .pending marker
#   preamble (epilogue) ──▶ gstack-telemetry-log ──▶ skill-usage.jsonl
#                                                 └──▶ gstack-telemetry-sync (bg)
#
# Usage:
#   gstack-telemetry-log --skill qa --duration 142 --outcome success \
#     --used-browse true --session-id "12345-1710756600"
#
# Env overrides (for testing):
#   GSTACK_STATE_DIR  — override ~/.gstack state directory
#   GSTACK_DIR        — override auto-detected gstack root
#
# NOTE: Uses set -uo pipefail (no -e) — telemetry must never exit non-zero
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="$ANALYTICS_DIR/skill-usage.jsonl"
PENDING_DIR="$ANALYTICS_DIR"  # .pending-* files live here
CONFIG_CMD="$GSTACK_DIR/bin/gstack-config"
VERSION_FILE="$GSTACK_DIR/VERSION"

# ─── Parse flags ─────────────────────────────────────────────
SKILL=""
DURATION=""
OUTCOME="unknown"
USED_BROWSE="false"
SESSION_ID=""
ERROR_CLASS=""
ERROR_MESSAGE=""
FAILED_STEP=""
EVENT_TYPE="skill_run"
SOURCE=""

while [ $# -gt 0 ]; do
  case "$1" in
    --skill)         SKILL="$2"; shift 2 ;;
    --duration)      DURATION="$2"; shift 2 ;;
    --outcome)       OUTCOME="$2"; shift 2 ;;
    --used-browse)   USED_BROWSE="$2"; shift 2 ;;
    --session-id)    SESSION_ID="$2"; shift 2 ;;
    --error-class)   ERROR_CLASS="$2"; shift 2 ;;
    --error-message) ERROR_MESSAGE="$2"; shift 2 ;;
    --failed-step)   FAILED_STEP="$2"; shift 2 ;;
    --event-type)    EVENT_TYPE="$2"; shift 2 ;;
    --source)        SOURCE="$2"; shift 2 ;;
    *) shift ;;
  esac
done

# Source: flag > env > default 'live'
SOURCE="${SOURCE:-${GSTACK_TELEMETRY_SOURCE:-live}}"

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

# Validate tier
case "$TIER" in
  off|anonymous|community) ;;
  *) TIER="off" ;;  # invalid value → default to off
esac

if [ "$TIER" = "off" ]; then
  # Still clear pending markers for this session even if telemetry is off
  [ -n "$SESSION_ID" ] && rm -f "$PENDING_DIR/.pending-$SESSION_ID" 2>/dev/null || true
  exit 0
fi

# ─── Finalize stale .pending markers ────────────────────────
# Each session gets its own .pending-$SESSION_ID file to avoid races
# between concurrent sessions. Finalize any that don't match our session.
for PFILE in "$PENDING_DIR"/.pending-*; do
  [ -f "$PFILE" ] || continue
  # Skip our own session's marker (it's still in-flight)
  PFILE_BASE="$(basename "$PFILE")"
  PFILE_SID="${PFILE_BASE#.pending-}"
  [ "$PFILE_SID" = "$SESSION_ID" ] && continue

  PENDING_DATA="$(cat "$PFILE" 2>/dev/null || true)"
  rm -f "$PFILE" 2>/dev/null || true
  if [ -n "$PENDING_DATA" ]; then
    # Extract fields from pending marker using grep -o + awk
    P_SKILL="$(echo "$PENDING_DATA" | grep -o '"skill":"[^"]*"' | head -1 | awk -F'"' '{print $4}')"
    P_TS="$(echo "$PENDING_DATA" | grep -o '"ts":"[^"]*"' | head -1 | awk -F'"' '{print $4}')"
    P_SID="$(echo "$PENDING_DATA" | grep -o '"session_id":"[^"]*"' | head -1 | awk -F'"' '{print $4}')"
    P_VER="$(echo "$PENDING_DATA" | grep -o '"gstack_version":"[^"]*"' | head -1 | awk -F'"' '{print $4}')"
    P_OS="$(uname -s | tr '[:upper:]' '[:lower:]')"
    P_ARCH="$(uname -m)"

    # Write the stale event as outcome: unknown
    mkdir -p "$ANALYTICS_DIR"
    printf '{"v":1,"ts":"%s","event_type":"skill_run","skill":"%s","session_id":"%s","gstack_version":"%s","os":"%s","arch":"%s","duration_s":null,"outcome":"unknown","error_class":null,"used_browse":false,"sessions":1}\n' \
      "$P_TS" "$P_SKILL" "$P_SID" "$P_VER" "$P_OS" "$P_ARCH" >> "$JSONL_FILE" 2>/dev/null || true
  fi
done

# Clear our own session's pending marker (we're about to log the real event)
[ -n "$SESSION_ID" ] && rm -f "$PENDING_DIR/.pending-$SESSION_ID" 2>/dev/null || true

# ─── Collect metadata ────────────────────────────────────────
TS="$(date -u +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || date -u +%Y-%m-%dT%H:%M:%S 2>/dev/null || echo "")"
GSTACK_VERSION="$(cat "$VERSION_FILE" 2>/dev/null | tr -d '[:space:]' || echo "unknown")"
OS="$(uname -s | tr '[:upper:]' '[:lower:]')"
ARCH="$(uname -m)"
SESSIONS="1"
if [ -d "$STATE_DIR/sessions" ]; then
  _SC="$(find "$STATE_DIR/sessions" -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' \n\r\t')"
  [ -n "$_SC" ] && [ "$_SC" -gt 0 ] 2>/dev/null && SESSIONS="$_SC"
fi

# Generate installation_id for community tier
# Uses a random UUID stored locally — not derived from hostname/user so it
# can't be guessed or correlated by someone who knows your machine identity.
INSTALL_ID=""
if [ "$TIER" = "community" ]; then
  ID_FILE="$HOME/.gstack/installation-id"
  if [ -f "$ID_FILE" ]; then
    INSTALL_ID="$(cat "$ID_FILE" 2>/dev/null)"
  fi
  if [ -z "$INSTALL_ID" ]; then
    # Generate a random UUID v4
    if command -v uuidgen >/dev/null 2>&1; then
      INSTALL_ID="$(uuidgen | tr '[:upper:]' '[:lower:]')"
    elif [ -r /proc/sys/kernel/random/uuid ]; then
      INSTALL_ID="$(cat /proc/sys/kernel/random/uuid)"
    else
      # Fallback: random hex from /dev/urandom
      INSTALL_ID="$(od -An -tx1 -N16 /dev/urandom 2>/dev/null | tr -d ' \n')"
    fi
    if [ -n "$INSTALL_ID" ]; then
      mkdir -p "$(dirname "$ID_FILE")" 2>/dev/null
      printf '%s' "$INSTALL_ID" > "$ID_FILE" 2>/dev/null
    fi
  fi
fi

# Local-only fields (never sent remotely)
REPO_SLUG=""
BRANCH=""
if command -v git >/dev/null 2>&1; then
  REPO_SLUG="$(git remote get-url origin 2>/dev/null | sed 's|.*[:/]\([^/]*/[^/]*\)\.git$|\1|;s|.*[:/]\([^/]*/[^/]*\)$|\1|' | tr '/' '-' 2>/dev/null || true)"
  BRANCH="$(git rev-parse --abbrev-ref HEAD 2>/dev/null || true)"
fi

# ─── Construct and append JSON ───────────────────────────────
mkdir -p "$ANALYTICS_DIR"

# Sanitize string fields for JSON safety (strip quotes, backslashes, control chars)
json_safe() { printf '%s' "$1" | tr -d '"\\\n\r\t' | head -c 200; }
SKILL="$(json_safe "$SKILL")"
OUTCOME="$(json_safe "$OUTCOME")"
SESSION_ID="$(json_safe "$SESSION_ID")"
SOURCE="$(json_safe "$SOURCE")"
EVENT_TYPE="$(json_safe "$EVENT_TYPE")"
REPO_SLUG="$(json_safe "$REPO_SLUG")"
BRANCH="$(json_safe "$BRANCH")"

# Escape null fields — sanitize ERROR_CLASS and FAILED_STEP via json_safe()
ERR_FIELD="null"
[ -n "$ERROR_CLASS" ] && ERR_FIELD="\"$(json_safe "$ERROR_CLASS")\""

ERR_MSG_FIELD="null"
[ -n "$ERROR_MESSAGE" ] && ERR_MSG_FIELD="\"$(printf '%s' "$ERROR_MESSAGE" | head -c 200 | sed -e 's/\\/\\\\/g' -e 's/"/\\"/g' -e 's/	/\\t/g' | tr '\n\r' '  ')\""

STEP_FIELD="null"
[ -n "$FAILED_STEP" ] && STEP_FIELD="\"$(json_safe "$FAILED_STEP")\""

# Cap unreasonable durations
if [ -n "$DURATION" ] && [ "$DURATION" -gt 86400 ] 2>/dev/null; then
  DURATION=""  # null if > 24h
fi
if [ -n "$DURATION" ] && [ "$DURATION" -lt 0 ] 2>/dev/null; then
  DURATION=""  # null if negative
fi

DUR_FIELD="null"
[ -n "$DURATION" ] && DUR_FIELD="$DURATION"

INSTALL_FIELD="null"
[ -n "$INSTALL_ID" ] && INSTALL_FIELD="\"$INSTALL_ID\""

BROWSE_BOOL="false"
[ "$USED_BROWSE" = "true" ] && BROWSE_BOOL="true"

printf '{"v":1,"ts":"%s","event_type":"%s","skill":"%s","session_id":"%s","gstack_version":"%s","os":"%s","arch":"%s","duration_s":%s,"outcome":"%s","error_class":%s,"error_message":%s,"failed_step":%s,"used_browse":%s,"sessions":%s,"installation_id":%s,"source":"%s","_repo_slug":"%s","_branch":"%s"}\n' \
  "$TS" "$EVENT_TYPE" "$SKILL" "$SESSION_ID" "$GSTACK_VERSION" "$OS" "$ARCH" \
  "$DUR_FIELD" "$OUTCOME" "$ERR_FIELD" "$ERR_MSG_FIELD" "$STEP_FIELD" \
  "$BROWSE_BOOL" "${SESSIONS:-1}" \
  "$INSTALL_FIELD" "$SOURCE" "$REPO_SLUG" "$BRANCH" >> "$JSONL_FILE" 2>/dev/null || true

# ─── Trigger sync if tier is not off ─────────────────────────
SYNC_CMD="$GSTACK_DIR/bin/gstack-telemetry-sync"
if [ -x "$SYNC_CMD" ]; then
  "$SYNC_CMD" 2>/dev/null &
fi

exit 0