#!/usr/bin/env bash
# lance smoke — gates the 5 /vectors/lance/* HTTP routes (search, doc,
# index, append, migrate). Only the read paths are exercised here so a
# CI run doesn't mutate state. Migrate + index + append have shape
# probes (request bodies are well-formed) but ride the not-found path
# that the 2026-05-02 audit added.
#
# Targets the live gateway at $LH_GATEWAY (default :3100). Uses an
# existing on-disk Lance dataset — `workers_500k_v1` — so no
# migration setup is needed. If the dataset is missing the smoke
# fails loudly with a clear message.
#
# Surfaced 2026-05-02: the lance crates had zero tests + no smoke;
# substrate change to lance_backend.rs would silently break the live
# surface. This smoke is the regression gate.
#
# Usage:
#   ./scripts/lance_smoke.sh
#   LH_GATEWAY=http://127.0.0.1:3100 ./scripts/lance_smoke.sh

set -euo pipefail

GATEWAY="${LH_GATEWAY:-http://127.0.0.1:3100}"
DATASET="${LH_LANCE_DATASET:-workers_500k_v1}"
PREFIX="$GATEWAY/vectors/lance"
PASS=0; FAIL=0
PROBE() { local label="$1"; shift; "$@" && { echo "  ✓ $label"; PASS=$((PASS+1)); } || { echo "  ✗ $label"; FAIL=$((FAIL+1)); }; }

echo "[lance-smoke] gateway=$GATEWAY dataset=$DATASET"

# ── 0. Gateway alive ─────────────────────────────────────────────
PROBE "gateway /v1/health responds" \
  bash -c "curl -sf -m 3 $GATEWAY/v1/health -o /dev/null"

# ── 1. Search returns IVF_PQ results on existing dataset ────────
RESP=$(curl -sS -m 30 -X POST "$PREFIX/search/$DATASET" \
  -H 'Content-Type: application/json' \
  -d '{"query":"forklift operator","top_k":3}' 2>/dev/null || echo '{}')
PROBE "search/$DATASET returns top-3 lance_ivf_pq results" \
  bash -c "echo '$RESP' | jq -e '.method == \"lance_ivf_pq\" and (.results | length) == 3' >/dev/null"

# Capture one doc_id from those results so the next probe has something real to fetch.
DOC_ID=$(echo "$RESP" | jq -r '.results[0].doc_id // ""')

# ── 2. get_doc by id returns the row ────────────────────────────
PROBE "doc/$DATASET/<known-id> returns full row" \
  bash -c "[ -n '$DOC_ID' ] && curl -sf -m 5 '$PREFIX/doc/$DATASET/$DOC_ID' | jq -e '.row.doc_id == \"$DOC_ID\"' >/dev/null"

# ── 3. get_doc with bogus id returns 404 (not 500) ──────────────
STATUS=$(curl -sS -m 5 -o /tmp/lance_smoke_404.json -w '%{http_code}' \
  "$PREFIX/doc/$DATASET/W500K-NOT-A-REAL-ID-00000")
PROBE "doc/$DATASET/<missing-id> → 404" \
  test "$STATUS" = "404"

# ── 4. search on missing dataset returns 404 + sanitized message ─
STATUS=$(curl -sS -m 5 -o /tmp/lance_smoke_500.json -w '%{http_code}' \
  -X POST "$PREFIX/search/no-such-dataset-${RANDOM}" \
  -H 'Content-Type: application/json' \
  -d '{"query":"x","top_k":1}')
BODY=$(cat /tmp/lance_smoke_500.json)
PROBE "search/<missing> → 404 (was 500 pre-2026-05-02)" \
  test "$STATUS" = "404"
# The sanitizer fix specifically: no /home/ or /root/.cargo/ in body.
PROBE "search/<missing> body sanitized — no filesystem leak" \
  bash -c "echo '$BODY' | grep -qvE '/home/|/root/\.cargo/'"

# ── 5. build_index on missing dataset also sanitized ────────────
STATUS=$(curl -sS -m 5 -o /tmp/lance_smoke_idx.json -w '%{http_code}' \
  -X POST "$PREFIX/index/no-such-dataset-${RANDOM}" \
  -H 'Content-Type: application/json' \
  -d '{}')
BODY=$(cat /tmp/lance_smoke_idx.json)
PROBE "index/<missing> body sanitized" \
  bash -c "echo '$BODY' | grep -qvE '/home/|/root/\.cargo/'"

# ── 6. append validates input shape (rejects empty rows array) ──
STATUS=$(curl -sS -m 5 -o /dev/null -w '%{http_code}' \
  -X POST "$PREFIX/append/$DATASET" \
  -H 'Content-Type: application/json' \
  -d '{"rows":[]}')
PROBE "append with empty rows[] → 400" \
  test "$STATUS" = "400"

# ── 7. migrate route is reachable (POST without body returns a real error, not 404) ──
STATUS=$(curl -sS -m 5 -o /dev/null -w '%{http_code}' \
  -X POST "$PREFIX/migrate/probe-not-real-${RANDOM}?bucket=primary" 2>/dev/null)
# Should be 4xx (bad request shape), NOT 404 (route registered) and NOT 200.
PROBE "migrate route registered (non-404, non-200 on empty body)" \
  bash -c "[ '$STATUS' != '404' ] && [ '$STATUS' != '200' ]"

echo "[lance-smoke] $PASS PASS / $FAIL FAIL"
[ "$FAIL" -eq 0 ]