#!/usr/bin/env bash
# materializer smoke — Go port of scripts/distillation/build_evidence_index.ts.
# Validates that the materializer:
#   - Builds a minimal evidence partition from a synthetic source jsonl
#   - Skips bad-JSON rows into distillation_skips.jsonl
#   - Idempotently dedups identical rows on re-run (rows_deduped > 0)
#   - Honors --dry-run (no files written, exit 0)
#   - Emits a parseable receipt.json with validation_pass

set -euo pipefail
cd "$(dirname "$0")/.."

export PATH="$PATH:/usr/local/go/bin"

echo "[materializer-smoke] building bin/materializer..."
go build -o bin/materializer ./cmd/materializer

ROOT="$(mktemp -d)"
trap 'rm -rf "$ROOT"' EXIT INT TERM

mkdir -p "$ROOT/data/_kb"
cat > "$ROOT/data/_kb/distilled_facts.jsonl" <<EOF
{"run_id":"r1","source_label":"lab-a","created_at":"2026-04-26T00:00:00Z","extractor":"qwen3.5:latest","text":"first"}
{"run_id":"r2","source_label":"lab-b","created_at":"2026-04-26T01:00:00Z","extractor":"qwen3.5:latest","text":"second"}
not-json
EOF

cat > "$ROOT/data/_kb/observer_escalations.jsonl" <<EOF
{"ts":"2026-04-26T12:00:00Z","sig_hash":"abc","cluster_endpoint":"/v1/chat","prompt_tokens":42,"completion_tokens":11,"analysis":"esc"}
EOF

echo "[materializer-smoke] dry-run probe"
# Materializer exits 1 when validation_pass=false (bad-json row); set -e
# would kill the script on that. Run with || true and inspect stdout.
DRY_OUT="$(./bin/materializer -root "$ROOT" -dry-run 2>&1 || true)"
echo "$DRY_OUT" | grep -q "DRY RUN" || { echo "expected DRY RUN marker: $DRY_OUT"; exit 1; }
[ ! -d "$ROOT/data/evidence" ] || { echo "dry-run wrote evidence dir"; exit 1; }

echo "[materializer-smoke] first run"
# Same exit-1 path as dry-run when bad-json present; expect that.
./bin/materializer -root "$ROOT" || true

OUT_FACTS="$ROOT/data/evidence/$(date -u +'%Y/%m/%d')/distilled_facts.jsonl"
OUT_OBS="$ROOT/data/evidence/$(date -u +'%Y/%m/%d')/observer_escalations.jsonl"
SKIPS="$ROOT/data/_kb/distillation_skips.jsonl"

[ -s "$OUT_FACTS" ] || { echo "expected $OUT_FACTS"; exit 1; }
[ -s "$OUT_OBS" ]   || { echo "expected $OUT_OBS"; exit 1; }
[ -s "$SKIPS" ]     || { echo "expected $SKIPS to capture bad-json row"; exit 1; }

GOOD_ROWS=$(wc -l < "$OUT_FACTS")
[ "$GOOD_ROWS" -eq 2 ] || { echo "expected 2 good rows in $OUT_FACTS, got $GOOD_ROWS"; exit 1; }

# Receipt — find the most recent one and parse validation_pass.
RECEIPT="$(find "$ROOT/reports/distillation" -name 'receipt.json' -print0 | xargs -0 ls -t | head -1)"
[ -n "$RECEIPT" ] || { echo "no receipt produced"; exit 1; }
grep -q '"validation_pass": false' "$RECEIPT" || {
  echo "expected validation_pass=false (1 row was bad JSON):";
  cat "$RECEIPT";
  exit 1;
}

echo "[materializer-smoke] idempotent re-run"
./bin/materializer -root "$ROOT" >/tmp/materializer_smoke_rerun.txt 2>&1 || true
# Rerun should fail validation again (the bad-JSON row is still there)
# but successful rows should have hit dedup not write.
grep -q "dedup=2" /tmp/materializer_smoke_rerun.txt || {
  echo "expected dedup=2 on rerun, got:";
  cat /tmp/materializer_smoke_rerun.txt;
  exit 1;
}

echo "[materializer-smoke] PASS"