feat: richer error telemetry — error_message + failed_step fields

Adds error_message (max 200 chars, e.g. "bun test: 3 tests failed")
and failed_step (e.g. "run_tests", "create_pr") to telemetry events.
Schema, ingest function, and local logger all updated. Makes crash
reports actionable instead of just "timeout — 252 occurrences".

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-03-20 08:20:44 -07:00
parent d87e8fb7ef
commit 1584deaca8
3 changed files with 29 additions and 10 deletions

View File

@@ -32,17 +32,21 @@ OUTCOME="unknown"
USED_BROWSE="false"
SESSION_ID=""
ERROR_CLASS=""
ERROR_MESSAGE=""
FAILED_STEP=""
EVENT_TYPE="skill_run"
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 ;;
--event-type) EVENT_TYPE="$2"; shift 2 ;;
--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="$2"; shift 2 ;;
*) shift ;;
esac
done
@@ -135,6 +139,12 @@ mkdir -p "$ANALYTICS_DIR"
ERR_FIELD="null"
[ -n "$ERROR_CLASS" ] && ERR_FIELD="\"$ERROR_CLASS\""
ERR_MSG_FIELD="null"
[ -n "$ERROR_MESSAGE" ] && ERR_MSG_FIELD="\"$(echo "$ERROR_MESSAGE" | head -c 200 | sed 's/"/\\"/g')\""
STEP_FIELD="null"
[ -n "$FAILED_STEP" ] && STEP_FIELD="\"$(echo "$FAILED_STEP" | head -c 30)\""
DUR_FIELD="null"
[ -n "$DURATION" ] && DUR_FIELD="$DURATION"
@@ -144,9 +154,10 @@ INSTALL_FIELD="null"
BROWSE_BOOL="false"
[ "$USED_BROWSE" = "true" ] && BROWSE_BOOL="true"
printf '{"v":1,"ts":"%s","event_type":"%s","skill":"%s","session_id":"%s","gstack_version":"%s","os":"%s","arch":"%s","duration_s":%s,"outcome":"%s","error_class":%s,"used_browse":%s,"sessions":%s,"installation_id":%s,"_repo_slug":"%s","_branch":"%s"}\n' \
printf '{"v":1,"ts":"%s","event_type":"%s","skill":"%s","session_id":"%s","gstack_version":"%s","os":"%s","arch":"%s","duration_s":%s,"outcome":"%s","error_class":%s,"error_message":%s,"failed_step":%s,"used_browse":%s,"sessions":%s,"installation_id":%s,"_repo_slug":"%s","_branch":"%s"}\n' \
"$TS" "$EVENT_TYPE" "$SKILL" "$SESSION_ID" "$GSTACK_VERSION" "$OS" "$ARCH" \
"$DUR_FIELD" "$OUTCOME" "$ERR_FIELD" "$BROWSE_BOOL" "${SESSIONS:-1}" \
"$DUR_FIELD" "$OUTCOME" "$ERR_FIELD" "$ERR_MSG_FIELD" "$STEP_FIELD" \
"$BROWSE_BOOL" "${SESSIONS:-1}" \
"$INSTALL_FIELD" "$REPO_SLUG" "$BRANCH" >> "$JSONL_FILE" 2>/dev/null || true
# ─── Trigger sync if tier is not off ─────────────────────────