#!/usr/bin/env bash
# Explain + delete spurious LiteLLM failure logs from restart disconnects
set -euo pipefail
ssh -o BatchMode=yes eventhub-ift bash -s <<'REMOTE'
set -euo pipefail
cd /opt/ai-router-stack
set -a; source .env; set +a
PG=$(docker ps -q -f name=ai-router_postgres | head -1)
USER="${POSTGRES_USER:-litellm}"
DB="${POSTGRES_DB:-litellm}"

echo "== Error message sample =="
docker exec -e PGPASSWORD="$POSTGRES_PASSWORD" "$PG" \
  psql -U "$USER" -d "$DB" -t -A -c "
SELECT left(metadata->'error_information'->>'error_message', 200)
FROM \"LiteLLM_SpendLogs\"
WHERE status='failure'
LIMIT 3;
"

echo "== Delete empty-model restart failures =="
docker exec -e PGPASSWORD="$POSTGRES_PASSWORD" "$PG" \
  psql -U "$USER" -d "$DB" -c "
DELETE FROM \"LiteLLM_SpendLogs\"
WHERE status = 'failure'
  AND (model IS NULL OR model = '')
  AND (call_type IS NULL OR call_type = '');
"

echo "== Remaining =="
docker exec -e PGPASSWORD="$POSTGRES_PASSWORD" "$PG" \
  psql -U "$USER" -d "$DB" -c "
SELECT status, count(*) FROM \"LiteLLM_SpendLogs\" GROUP BY 1;
"
echo CLEANED_SPURIOUS_FAILS_OK
REMOTE