#!/usr/bin/env bash
# Loads data/memory.md and data/claude-legacy-memory.md into the
# memory-retrieval knowledgebase (POST /ingest).
#
# ponytail: one chunk per non-empty, non-heading line — both source files are
# already one fact/paragraph per line (no hard-wrapping), so this needs no
# real chunking logic. Re-run after editing either file; there's no dedup,
# PGVector always inserts — clear the collection first if you need a clean
# reload.
set -euo pipefail
cd "$(dirname "$0")/.."

[ -f .env ] && set -a && . ./.env && set +a

: "${MEMORY_RETRIEVAL_API_KEY:?Set MEMORY_RETRIEVAL_API_KEY in .env first}"
MEMORY_RETRIEVAL_URL="${MEMORY_RETRIEVAL_URL:-http://localhost:8000}"

ingest_file() {
  local file="$1" section=""
  local chunks="[]"
  while IFS= read -r line; do
    case "$line" in
      "#"*) section="${line#\# }"; section="${section#\#\# }"; continue ;;
      ""|"---") continue ;;
    esac
    chunks=$(jq --arg content "$line" --arg source "$file" --arg section "$section" \
      '. += [{"content": $content, "metadata": {"source": $source, "section": $section}}]' <<<"$chunks")
  done < "$file"

  echo "Ingesting $(jq 'length' <<<"$chunks") chunks from $file..."
  curl -sf -X POST "${MEMORY_RETRIEVAL_URL}/ingest" \
    -H "Authorization: Bearer ${MEMORY_RETRIEVAL_API_KEY}" \
    -H "Content-Type: application/json" \
    -d "{\"chunks\": ${chunks}}" > /dev/null
}

ingest_file data/memory.md
ingest_file data/claude-legacy-memory.md
echo "Done."