#!/usr/bin/env bash
# Run the 12 staffer-demo scenarios (4 personas × 3 contracts) with
# cloud T3 enabled. After each run, KB indexes the outcome and
# recomputes that staffer's competence_score. By the end, the top
# staffer's playbooks will be surfacing first in neighbor retrieval.

set -e
cd "$(dirname "$0")/.."

export OLLAMA_CLOUD_KEY="$(python3 -c "import json; print(json.load(open('/root/llm_team_config.json'))['providers']['ollama_cloud']['api_key'])" 2>/dev/null || echo '')"

MANIFEST="tests/multi-agent/scenarios/staffer_demo/manifest.json"
if [ ! -f "$MANIFEST" ]; then
  echo "✗ no manifest — run: bun tests/multi-agent/gen_staffer_demo.ts"
  exit 1
fi

START_TS=$(date -Iseconds)
LOG_DIR="/tmp/lakehouse_staffer_demo_$(date +%s)"
mkdir -p "$LOG_DIR"
echo "▶ Staffer demo start: $START_TS, logs → $LOG_DIR"

python3 -c "
import json
m = json.load(open('$MANIFEST'))
for s in m['scenarios']:
    print(s['file'], '|', s['staffer'], '|', s['contract'])
" | while IFS='|' read -r SCEN STAFFER CONTRACT; do
  SCEN=$(echo "$SCEN" | xargs)
  STAFFER=$(echo "$STAFFER" | xargs)
  CONTRACT=$(echo "$CONTRACT" | xargs)
  SPEC="tests/multi-agent/scenarios/staffer_demo/$SCEN"
  BASE=$(basename "$SPEC" .json)
  LOG="$LOG_DIR/${BASE}.log"
  echo "  ▶ $STAFFER × $CONTRACT"
  LH_OVERVIEW_CLOUD=1 bun tests/multi-agent/scenario.ts "$SPEC" > "$LOG" 2>&1 || true
  OK=$(grep -oP '\d+/\d+ events succeeded' "$LOG" | tail -1 || echo "no-result")
  RESCUES=$(grep -c "cloud rescue requested" "$LOG" || true)
  RESCUE_OK=$(grep -c "retry outcome: ✓" "$LOG" || true)
  SIG=$(grep -oP 'KB indexed: sig=\K[a-f0-9]+' "$LOG" | tail -1 || echo "-")
  echo "    → $OK; rescues=$RESCUES (${RESCUE_OK} succeeded); sig=$SIG"
done

echo "▶ Staffer demo done: $(date -Iseconds)"
echo "▶ Staffer competence leaderboard:"
python3 scripts/kb_staffer_report.py 2>/dev/null || echo "(run scripts/kb_staffer_report.py after batch completes)"