golangLAKEHOUSE/scripts/relevance_smoke.sh

#!/usr/bin/env bash
# Relevance smoke — code-relevance filter via matrixd /matrix/relevance.
# All assertions go through gateway :3110.
#
# Validates the headline adjacency-pollution scenario:
#   Focus: crates/queryd/src/db.go which defines Connector.
#   Chunk A is about Connector → kept (defined_match).
#   Chunk B is about catalogd::Registry which db.go imports → outranked
#     by Chunk A.
#   Chunk C is unrelated → dropped (no signals fire).
#
# Plus negative paths:
#   - Empty chunks → 400
#   - Threshold honored when set explicitly

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

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

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

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

PIDS=()
TMP="$(mktemp -d)"
CFG="$TMP/relevance.toml"

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

# Custom toml: vectord persistence disabled. /matrix/relevance doesn't
# touch vectord at all, but matrixd config requires the URL anyway.
cat > "$CFG" <<EOF
[gateway]
bind = "127.0.0.1:3110"
storaged_url = "http://127.0.0.1:3211"
catalogd_url = "http://127.0.0.1:3212"
ingestd_url  = "http://127.0.0.1:3213"
queryd_url   = "http://127.0.0.1:3214"
vectord_url  = "http://127.0.0.1:3215"
embedd_url   = "http://127.0.0.1:3216"
pathwayd_url = "http://127.0.0.1:3217"
matrixd_url  = "http://127.0.0.1:3218"

[vectord]
bind = "127.0.0.1:3215"
storaged_url = ""

[matrixd]
bind = "127.0.0.1:3218"
embedd_url  = "http://127.0.0.1:3216"
vectord_url = "http://127.0.0.1:3215"
EOF

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

./bin/matrixd -config "$CFG" > /tmp/matrixd.log 2>&1 &
PIDS+=($!)
poll_health 3218 || { echo "matrixd failed"; tail /tmp/matrixd.log; exit 1; }

./bin/gateway -config "$CFG" > /tmp/gateway.log 2>&1 &
PIDS+=($!)
poll_health 3110 || { echo "gateway failed"; tail /tmp/gateway.log; exit 1; }

FAILED=0

# ── 1. Adjacency-pollution scenario ──────────────────────────────
echo "[relevance-smoke] adjacency-pollution: Connector outranks Registry, junk dropped:"
PAYLOAD='{
  "focus": {
    "Path": "crates/queryd/src/db.go",
    "Content": "pub struct Connector {}\npub fn open_connector() *Connector { return nil }\nuse catalogd::Registry;"
  },
  "chunks": [
    {"source":"lakehouse_symbols_v1","doc_id":"symbol:queryd::struct::Connector","text":"Connector wraps the DuckDB handle. open_connector creates one.","score":0.9},
    {"source":"lakehouse_symbols_v1","doc_id":"symbol:catalogd::struct::Registry","text":"Registry stores manifests. Used by ingestd.","score":0.85},
    {"source":"lakehouse_symbols_v1","doc_id":"symbol:totally_other::Thing","text":"completely unrelated text about something else entirely","score":0.7}
  ],
  "threshold": 0.3
}'
RESP="$(curl -sS -X POST http://127.0.0.1:3110/v1/matrix/relevance -H 'Content-Type: application/json' -d "$PAYLOAD")"

# Connector chunk should be in kept
CONNECTOR_KEPT="$(echo "$RESP" | jq -r '[.kept[] | select(.doc_id | contains("Connector"))] | length')"
# The unrelated junk chunk should be in dropped
JUNK_DROPPED="$(echo "$RESP" | jq -r '[.dropped[] | select(.doc_id | contains("Thing"))] | length')"
# Connector should outrank Registry (whichever bucket they end up in)
CONN_REL="$(echo "$RESP" | jq -r '[.kept[], .dropped[] | select(.doc_id | contains("Connector"))] | .[0].relevance // -999')"
REG_REL="$(echo "$RESP"  | jq -r '[.kept[], .dropped[] | select(.doc_id | contains("Registry"))]  | .[0].relevance // -999')"
TOTAL_IN="$(echo "$RESP" | jq -r '.total_in')"

CONN_OUTRANKS_REG="$(awk -v a="$CONN_REL" -v b="$REG_REL" 'BEGIN{print (a>b)?"true":"false"}')"

if [ "$CONNECTOR_KEPT" = "1" ] && [ "$JUNK_DROPPED" = "1" ] && [ "$CONN_OUTRANKS_REG" = "true" ] && [ "$TOTAL_IN" = "3" ]; then
  echo "  ✓ Connector kept, junk dropped, Connector ($CONN_REL) > Registry ($REG_REL)"
else
  echo "  ✗ kept_connector=$CONNECTOR_KEPT dropped_junk=$JUNK_DROPPED conn=$CONN_REL reg=$REG_REL total=$TOTAL_IN"
  echo "    full: $RESP"
  FAILED=1
fi

# ── 2. Empty chunks → 400 ────────────────────────────────────────
echo "[relevance-smoke] empty chunks → 400:"
HTTP="$(curl -sS -o /dev/null -w '%{http_code}' -X POST http://127.0.0.1:3110/v1/matrix/relevance \
  -H 'Content-Type: application/json' \
  -d '{"focus":{"Path":"x"},"chunks":[]}')"
if [ "$HTTP" = "400" ]; then
  echo "  ✓ 400 on empty chunks"
else
  echo "  ✗ got $HTTP"; FAILED=1
fi

# ── 3. Threshold honored ─────────────────────────────────────────
echo "[relevance-smoke] threshold=10 (impossibly high) drops everything:"
PAYLOAD2='{
  "focus": {"Path": "x.go", "Content": "pub fn known() {}", "DefinedSymbols": ["known"]},
  "chunks": [
    {"source":"s","doc_id":"d1","text":"known appears here","score":0.9}
  ],
  "threshold": 10
}'
RESP2="$(curl -sS -X POST http://127.0.0.1:3110/v1/matrix/relevance -H 'Content-Type: application/json' -d "$PAYLOAD2")"
KEPT_COUNT="$(echo "$RESP2" | jq -r '.kept | length')"
DROP_COUNT="$(echo "$RESP2" | jq -r '.dropped | length')"
if [ "$KEPT_COUNT" = "0" ] && [ "$DROP_COUNT" = "1" ]; then
  echo "  ✓ threshold=10 drops everything (0 kept / 1 dropped)"
else
  echo "  ✗ kept=$KEPT_COUNT dropped=$DROP_COUNT"; FAILED=1
fi

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