#!/usr/bin/env bash
# 07_vector_persistence_restart.sh — GOLAKE-070.
# Verifies vectord persistence: add vectors, search, kill vectord,
# restart, search again — top-1 ID and distance must match within
# float-noise tolerance. The orchestrator's cleanup uses pgrep so the
# restarted vectord gets cleaned up regardless of PID tracking.

set -uo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "${SCRIPT_DIR}/../lib/env.sh"
source "${SCRIPT_DIR}/../lib/http.sh"
source "${SCRIPT_DIR}/../lib/assert.sh"

CASE_ID="GOLAKE-070"
CASE_NAME="Vector persistence — kill+restart preserves state"
CASE_TYPE="integration"
if [ "${1:-}" = "--metadata-only" ]; then return 0 2>/dev/null || exit 0; fi

INDEX_NAME="proof_persist_${PROOF_RUN_ID}"
VECTORD_LOG="${PROOF_REPORT_DIR}/raw/logs/vectord_restart.log"

# Pre-flight: vectord must be reachable.
if ! curl -sf -m 1 "${PROOF_VECTORD_URL}/health" >/dev/null 2>&1; then
    proof_skip "$CASE_ID" "Persistence test — vectord unreachable" \
        "vectord not responding on :3215; harness bootstrap may have failed"
    return 0 2>/dev/null || exit 0
fi

# Build deterministic vectors. Unit basis vectors so search is unambiguous.
proof_post "$CASE_ID" "create_index" "${PROOF_GATEWAY_URL}/v1/vectors/index" \
    "application/json" \
    "{\"name\":\"${INDEX_NAME}\",\"dimension\":4}" >/dev/null
proof_assert_eq "$CASE_ID" "create index → 201" "201" \
    "$(proof_status_of "$CASE_ID" "create_index")"

add_body='{"items":[
    {"id":"p1","vector":[1,0,0,0]},
    {"id":"p2","vector":[0,1,0,0]},
    {"id":"p3","vector":[0,0,1,0]},
    {"id":"p4","vector":[0,0,0,1]}
]}'
proof_post "$CASE_ID" "add_vectors" \
    "${PROOF_GATEWAY_URL}/v1/vectors/index/${INDEX_NAME}/add" \
    "application/json" "$add_body" >/dev/null
proof_assert_eq "$CASE_ID" "add 4 vectors → 200" "200" \
    "$(proof_status_of "$CASE_ID" "add_vectors")"

# Pre-restart search — record top-1 as the canonical reference.
search_body='{"vector":[1,0,0,0],"k":2}'
proof_post "$CASE_ID" "pre_restart_search" \
    "${PROOF_GATEWAY_URL}/v1/vectors/index/${INDEX_NAME}/search" \
    "application/json" "$search_body" >/dev/null
pre_body="${PROOF_REPORT_DIR}/raw/http/${CASE_ID}/pre_restart_search.body"
pre_top1=$(jq -r '.results[0].id'        "$pre_body")
pre_dist=$(jq -r '.results[0].distance'  "$pre_body")
proof_assert_eq "$CASE_ID" "pre-restart top-1 = p1" "p1" "$pre_top1"

# ── kill vectord ────────────────────────────────────────────────
echo "[case-07] killing vectord..." >> "$VECTORD_LOG"
old_pid=$(pgrep -f "^[./]*bin/vectord($| )" | head -1)
if [ -z "$old_pid" ]; then
    proof_skip "$CASE_ID" "vectord PID not found — can't test restart" \
        "pgrep returned no match for ^bin/vectord"
    return 0 2>/dev/null || exit 0
fi
kill "$old_pid" 2>/dev/null || true

# Wait for vectord to actually go down (so the restart path is exercised).
deadline=$(($(date +%s) + 5))
while [ "$(date +%s)" -lt "$deadline" ]; do
    if ! curl -sf -m 1 "${PROOF_VECTORD_URL}/health" >/dev/null 2>&1; then
        break
    fi
    sleep 0.1
done

# Confirm it's down — if still up, kill -9.
if curl -sf -m 1 "${PROOF_VECTORD_URL}/health" >/dev/null 2>&1; then
    kill -9 "$old_pid" 2>/dev/null || true
    sleep 0.5
fi

# ── restart vectord ─────────────────────────────────────────────
cd "$PROOF_REPO_ROOT"
./bin/vectord --config "$PROOF_LAKEHOUSE_CONFIG" >> "$VECTORD_LOG" 2>&1 &
new_pid=$!

# Poll for readiness — give it 8s like the bootstrap does.
deadline=$(($(date +%s) + 8))
ready=0
while [ "$(date +%s)" -lt "$deadline" ]; do
    if curl -sf -m 1 "${PROOF_VECTORD_URL}/health" >/dev/null 2>&1; then
        ready=1; break
    fi
    sleep 0.1
done

if [ "$ready" -eq 0 ]; then
    _proof_record "$CASE_ID" "vectord restart binds within 8s" \
        fail "ready" "timeout" "vectord did not respond to /health after restart; pid=${new_pid}"
    return 0 2>/dev/null || exit 0
fi
_proof_record "$CASE_ID" "vectord restart binds within 8s" \
    pass "ready" "ready" "old_pid=${old_pid} new_pid=${new_pid}"

# ── post-restart search ─────────────────────────────────────────
proof_post "$CASE_ID" "post_restart_search" \
    "${PROOF_GATEWAY_URL}/v1/vectors/index/${INDEX_NAME}/search" \
    "application/json" "$search_body" >/dev/null

post_status=$(proof_status_of "$CASE_ID" "post_restart_search")
proof_assert_eq "$CASE_ID" "post-restart search → 200" "200" "$post_status"

if [ "$post_status" != "200" ]; then
    proof_skip "$CASE_ID" "value assertions skipped — search failed" \
        "post-restart search returned ${post_status}; index may not have rehydrated"
else
    post_body="${PROOF_REPORT_DIR}/raw/http/${CASE_ID}/post_restart_search.body"
    post_top1=$(jq -r '.results[0].id'       "$post_body")
    post_dist=$(jq -r '.results[0].distance' "$post_body")
    proof_assert_eq "$CASE_ID" "post-restart top-1 ID matches pre-restart" \
        "$pre_top1" "$post_top1"
    # Distances should be bit-identical (same float32 graph reloaded).
    proof_assert_eq "$CASE_ID" "post-restart top-1 distance matches pre-restart" \
        "$pre_dist" "$post_dist"
fi

# Cleanup.
proof_delete "$CASE_ID" "post_clean" \
    "${PROOF_GATEWAY_URL}/v1/vectors/index/${INDEX_NAME}" >/dev/null