golangLAKEHOUSE/scripts/g1_smoke.sh

#!/usr/bin/env bash
# G1 smoke — vectord (HNSW vector search). All assertions go
# through gateway :3110, none direct to vectord :3215.
#
# Validates:
#   - POST /v1/vectors/index → 201, params echoed back
#   - POST /v1/vectors/index/{name}/add (batch of 200) → 200, length=200
#   - POST /v1/vectors/index/{name}/search → top-K with the inserted
#     vector at distance≈0 (recall=1 for the inserted vector itself)
#   - Dim mismatch on Add → 400
#   - Search on missing index → 404
#   - Duplicate Create → 409
#   - DELETE then Search → 404
#
# Requires vectord + gateway. Other backing services aren't needed.
#
# Usage: ./scripts/g1_smoke.sh

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

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

echo "[g1-smoke] building vectord + gateway..."
go build -o bin/ ./cmd/vectord ./cmd/gateway

pkill -f "bin/vectord|bin/gateway" 2>/dev/null || true
sleep 0.3

PIDS=()
TMP="$(mktemp -d)"
cleanup() {
  echo "[g1-smoke] cleanup"
  for p in "${PIDS[@]}"; do [ -n "$p" ] && kill "$p" 2>/dev/null || true; done
  rm -rf "$TMP"
}
trap cleanup EXIT INT TERM

poll_health() {
  local port="$1" deadline=$(($(date +%s) + 5))
  while [ "$(date +%s)" -lt "$deadline" ]; do
    if curl -sS --max-time 1 "http://127.0.0.1:$port/health" >/dev/null 2>&1; then return 0; fi
    sleep 0.05
  done
  return 1
}

echo "[g1-smoke] launching vectord → gateway..."
./bin/vectord -config scripts/g1_smoke.toml > /tmp/vectord.log 2>&1 &
PIDS+=($!)
poll_health 3215 || { echo "vectord failed"; tail /tmp/vectord.log; exit 1; }
./bin/gateway -config scripts/g1_smoke.toml > /tmp/gateway.log 2>&1 &
PIDS+=($!)
poll_health 3110 || { echo "gateway failed"; tail /tmp/gateway.log; exit 1; }

FAILED=0
NAME="g1_workers"
DIM=8

echo "[g1-smoke] /v1/vectors/index — create dim=$DIM:"
HTTP="$(curl -sS -o "$TMP/create.out" -w '%{http_code}' -X POST http://127.0.0.1:3110/v1/vectors/index \
  -H 'Content-Type: application/json' \
  -d "{\"name\":\"$NAME\",\"dimension\":$DIM,\"distance\":\"cosine\"}")"
if [ "$HTTP" = "201" ]; then
  echo "  ✓ create → 201"
else
  echo "  ✗ create → $HTTP body=$(cat "$TMP/create.out")"; FAILED=1
fi

echo "[g1-smoke] duplicate create → 409:"
HTTP="$(curl -sS -o /dev/null -w '%{http_code}' -X POST http://127.0.0.1:3110/v1/vectors/index \
  -H 'Content-Type: application/json' \
  -d "{\"name\":\"$NAME\",\"dimension\":$DIM}")"
if [ "$HTTP" = "409" ]; then
  echo "  ✓ duplicate → 409"
else
  echo "  ✗ duplicate → $HTTP"; FAILED=1
fi

echo "[g1-smoke] add batch of 200 vectors:"
# Build a batch payload with 200 items. ID encodes index; vector
# is a deterministic spread so we can assert recall on a known id.
python3 - <<EOF > "$TMP/batch.json"
import json
items = []
for i in range(200):
    # Each vector is unit-norm-ish with one dominant axis cycling
    # through DIM dims, and a UNIQUE perturbation derived from i itself
    # (no modulo — would create collisions when 200/DIM rolls over).
    v = [0.0] * $DIM
    v[i % $DIM] = 1.0
    v[(i+1) % $DIM] = i * 0.0001  # unique per i
    items.append({"id": f"w-{i:03d}", "vector": v, "metadata": {"row": i}})
print(json.dumps({"items": items}))
EOF
ADD_RESP="$(curl -sS -X POST "http://127.0.0.1:3110/v1/vectors/index/$NAME/add" \
  -H 'Content-Type: application/json' \
  -d @"$TMP/batch.json")"
LEN="$(echo "$ADD_RESP" | jq -r '.length')"
ADDED="$(echo "$ADD_RESP" | jq -r '.added')"
if [ "$LEN" = "200" ] && [ "$ADDED" = "200" ]; then
  echo "  ✓ added=200, length=200"
else
  echo "  ✗ add → $ADD_RESP"; FAILED=1
fi

echo "[g1-smoke] search for inserted vector w-042 → recall:"
# Build the same vector w-042 was inserted with.
python3 - <<EOF > "$TMP/q.json"
import json
i = 42
v = [0.0] * $DIM
v[i % $DIM] = 1.0
v[(i+1) % $DIM] = i * 0.0001  # match the unique-per-i perturbation
print(json.dumps({"vector": v, "k": 3}))
EOF
SEARCH_RESP="$(curl -sS -X POST "http://127.0.0.1:3110/v1/vectors/index/$NAME/search" \
  -H 'Content-Type: application/json' \
  -d @"$TMP/q.json")"
TOP_ID="$(echo "$SEARCH_RESP" | jq -r '.results[0].id')"
TOP_DIST="$(echo "$SEARCH_RESP" | jq -r '.results[0].distance')"
TOP_META="$(echo "$SEARCH_RESP" | jq -c '.results[0].metadata')"
RC="$(echo "$SEARCH_RESP" | jq -r '.results | length')"
# Distance should be ~0 (cosine of identical unit vectors). Allow 1e-4.
DIST_OK="$(python3 -c "import sys; sys.exit(0 if abs($TOP_DIST) < 1e-4 else 1)" && echo y || echo n)"
if [ "$TOP_ID" = "w-042" ] && [ "$DIST_OK" = "y" ] && [ "$RC" = "3" ] && [ "$TOP_META" = '{"row":42}' ]; then
  echo "  ✓ top hit = w-042 (dist=$TOP_DIST), 3 results, metadata round-tripped"
else
  echo "  ✗ search → top_id=$TOP_ID dist=$TOP_DIST rc=$RC meta=$TOP_META"
  echo "    full: $SEARCH_RESP"
  FAILED=1
fi

echo "[g1-smoke] dim mismatch on add → 400:"
HTTP="$(curl -sS -o /dev/null -w '%{http_code}' -X POST "http://127.0.0.1:3110/v1/vectors/index/$NAME/add" \
  -H 'Content-Type: application/json' \
  -d '{"items":[{"id":"bad","vector":[1,2,3]}]}')"
if [ "$HTTP" = "400" ]; then
  echo "  ✓ dim mismatch → 400"
else
  echo "  ✗ dim mismatch → $HTTP"; FAILED=1
fi

echo "[g1-smoke] search on missing index → 404:"
HTTP="$(curl -sS -o /dev/null -w '%{http_code}' -X POST "http://127.0.0.1:3110/v1/vectors/index/no_such/search" \
  -H 'Content-Type: application/json' \
  -d "{\"vector\":[1,0,0,0,0,0,0,0],\"k\":1}")"
if [ "$HTTP" = "404" ]; then
  echo "  ✓ unknown index → 404"
else
  echo "  ✗ unknown index → $HTTP"; FAILED=1
fi

echo "[g1-smoke] DELETE then GET → 404:"
curl -sS -o /dev/null -X DELETE "http://127.0.0.1:3110/v1/vectors/index/$NAME"
HTTP="$(curl -sS -o /dev/null -w '%{http_code}' "http://127.0.0.1:3110/v1/vectors/index/$NAME")"
if [ "$HTTP" = "404" ]; then
  echo "  ✓ post-delete GET → 404"
else
  echo "  ✗ post-delete → $HTTP"; FAILED=1
fi

if [ "$FAILED" -eq 0 ]; then
  echo "[g1-smoke] G1 acceptance gate: PASSED"
  exit 0
else
  echo "[g1-smoke] G1 acceptance gate: FAILED"
  exit 1
fi