#!/usr/bin/env bash
# End-to-end test of adding a printer with the REAL continuum-proxy as the
# gateway (e2e-provision.sh uses a stand-in): the provision frame must parse on
# the proxy, the proxy must try the printer, and the answer must come back.
#
# Without REAL_HOST/REAL_SERIAL/REAL_ACCESS_CODE it points the add at a closed
# port on this machine and proves the failure path across the real wire: a
# useful error comes back, no printer row is created, no store entry is made,
# and the proxy's log never contains the access code.
#
# WITH them (a printer you are willing to connect to - this only READS, it
# sends no command) it proves the success path as well: 201, telemetry flows
# under the new id, the proxy's store file is owner-only, and after the proxy
# is restarted with NO printers file the printer comes back from the store.
#   REAL_HOST=192.168.0.20 REAL_SERIAL=... REAL_ACCESS_CODE=... scripts/e2e-provision-proxy.sh
#
# This is the test that the unit tests cannot be. tests/authz.test.ts proves
# tokens are verified and that the role ladder orders correctly; only this
# proves that each route actually asks, that scoping is applied in the query
# rather than after it, and that credentials stay out of responses - the three
# things that were wrong when every route was unauthenticated.
#
# Four users, two organisations, no printers or gateways needed:
#   owner_a, operator_a, viewer_a  in org A, which owns farm A and printer A
#   outsider_b                     in org B, which owns nothing
#
# Usage:
#   scripts/dev-env.sh up && scripts/dev-env.sh schema
#   scripts/e2e-authz.sh
#
#   KEEP_DATA=1   leave the seeded organisations behind for inspection
set -euo pipefail

REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
cd "$REPO_ROOT"

PORT="${PORT:-3034}"
AUTH_PORT="${AUTH_PORT:-3035}"
BASE="http://localhost:$PORT"
DATABASE_URL="${DATABASE_URL:-postgres://continuum:continuum@localhost:5432/continuum}"
VALKEY_URL="${VALKEY_URL:-redis://localhost:6379}"
EDGE_JWT_SECRET="${EDGE_JWT_SECRET:-e2e-edge-secret}"
# Presigning a PUT is local HMAC with no network call, so POST /jobs works
# offline - but the SDK refuses to sign with empty credentials.
R2_ACCESS_KEY_ID="${R2_ACCESS_KEY_ID:-e2e}"
R2_SECRET_ACCESS_KEY="${R2_SECRET_ACCESS_KEY:-e2e}"
R2_ENDPOINT="${R2_ENDPOINT:-http://localhost:9000}"
export DATABASE_URL VALKEY_URL EDGE_JWT_SECRET PORT
export R2_ACCESS_KEY_ID R2_SECRET_ACCESS_KEY R2_ENDPOINT

WORK="$(mktemp -d)"
BACKEND_PID=""
PROXY_PID=""
PROXY_DIR="${PROXY_DIR:-$REPO_ROOT/../continuum-proxy}"
AUTH_PID=""
FAILURES=0

# `uuidgen` is not installed everywhere; the kernel's generator always is.
new_uuid() {
  if [ -r /proc/sys/kernel/random/uuid ]; then
    cat /proc/sys/kernel/random/uuid
  else
    python3 -c 'import uuid; print(uuid.uuid4())'
  fi
}

# Uses DATABASE_URL rather than a hardcoded localhost. The backend under test
# reads that variable, so a psql pointed anywhere else seeds fixtures into a
# different database than the one being exercised - and the failure message
# below names DATABASE_URL, which would then be naming a URL nothing tried.
psql_q() { psql "$DATABASE_URL" -tAq -c "$1"; }

cleanup() {
  local rc=$?
  # Never `kill $PID` with an unset PID: `kill 0` signals the whole process
  # group, which includes this script and whatever launched it.
  local pids=()
  [ -n "$BACKEND_PID" ] && pids+=("$BACKEND_PID")
  [ -n "$AUTH_PID" ] && pids+=("$AUTH_PID")
  [ -n "$PROXY_PID" ] && pids+=("$PROXY_PID")
  if [ ${#pids[@]} -gt 0 ]; then
    kill "${pids[@]}" 2>/dev/null || true
    sleep 0.3
    kill -9 "${pids[@]}" 2>/dev/null || true
  fi
  if [ -z "${KEEP_DATA:-}" ]; then
    for org in "${ORG_A:-}" "${ORG_B:-}"; do
      [ -n "$org" ] && psql_q "DELETE FROM organisations WHERE id = '$org'" >/dev/null 2>&1 || true
    done
  fi
  if [ $rc -ne 0 ]; then
    echo
    echo "--- backend log (tail) ---"; tail -30 "$WORK/backend.log" 2>/dev/null || true
    echo "--- proxy log (tail, credentials are never logged) ---"; tail -30 "$WORK/proxy.log" 2>/dev/null || true
  fi
  rm -rf "$WORK"
  exit $rc
}
trap cleanup EXIT

fail() { echo "FAIL: $*" >&2; exit 1; }
ok()   { echo "  ok: $*"; }
bad()  { echo "  FAILED: $*" >&2; FAILURES=$((FAILURES + 1)); }

# `req <method> <path> <token|-> [json body]` -> prints the status code,
# leaves the response body in $WORK/last.json.
req() {
  local method="$1" path="$2" token="$3" body="${4:-}"
  local args=(-s -o "$WORK/last.json" -w '%{http_code}' -X "$method" "$BASE$path")
  [ "$token" != "-" ] && args+=(-H "authorization: Bearer $token")
  [ -n "$body" ] && args+=(-H 'content-type: application/json' -d "$body")
  curl "${args[@]}"
}

# `expect <code> <method> <path> <token> [body] -- <description>`
expect() {
  local want="$1"; shift
  local method="$1" path="$2" token="$3"; shift 3
  local body=""
  if [ "${1:-}" != "--" ]; then body="$1"; shift; fi
  shift # the --
  local what="$*"
  local got; got="$(req "$method" "$path" "$token" "$body")"
  if [ "$got" = "$want" ]; then
    ok "$what ($got)"
  else
    bad "$what: expected $want, got $got - $(head -c 300 "$WORK/last.json")"
  fi
}

body_has()    { grep -q "$1" "$WORK/last.json" || bad "expected '$1' in: $(head -c 300 "$WORK/last.json")"; }
body_lacks()  { grep -q "$1" "$WORK/last.json" && bad "'$1' leaked into: $(head -c 300 "$WORK/last.json")" || true; }
json()        { python3 -c "import json,sys; d=json.load(sys.stdin); print($1)" < "$WORK/last.json"; }

# --- 0. preconditions ------------------------------------------------------

echo "==> checking the database is up and migrated"
psql_q "SELECT 1" >/dev/null 2>&1 || fail "no database at $DATABASE_URL - run scripts/dev-env.sh up"
psql_q "SELECT org_id FROM farms LIMIT 0" >/dev/null 2>&1 \
  || fail "farms.org_id is missing - run scripts/dev-env.sh schema"
psql_q "SELECT role FROM org_members LIMIT 0" >/dev/null 2>&1 \
  || fail "org_members is missing - run scripts/dev-env.sh schema"
ok "schema has the org layer"

# --- 1. the issuer and the backend ----------------------------------------

echo "==> starting the dev-auth JWKS issuer on :$AUTH_PORT"
bun scripts/dev-auth.ts --port "$AUTH_PORT" > "$WORK/auth.log" 2>&1 &
AUTH_PID=$!
AUTH_URL="http://localhost:$AUTH_PORT"
for _ in $(seq 1 40); do
  curl -sf "$AUTH_URL/auth/v1/.well-known/jwks.json" >/dev/null 2>&1 && break
  sleep 0.25
done
curl -sf "$AUTH_URL/auth/v1/.well-known/jwks.json" >/dev/null 2>&1 \
  || fail "the dev-auth issuer did not come up: $(cat "$WORK/auth.log")"
export SUPABASE_URL="$AUTH_URL"
ok "issuer up, SUPABASE_URL=$SUPABASE_URL"

mint() { curl -sf "$AUTH_URL/token?sub=$1" | python3 -c 'import json,sys; print(json.load(sys.stdin)["access_token"])'; }


echo "==> starting continuum-backend on :$PORT"
DISPATCH_ENABLED=false bun run src/index.ts > "$WORK/backend.log" 2>&1 &
BACKEND_PID=$!
for _ in $(seq 1 60); do
  curl -sf "$BASE/health" >/dev/null 2>&1 && break
  sleep 0.5
done
curl -sf "$BASE/health" >/dev/null 2>&1 || fail "backend did not become healthy: $(cat "$WORK/backend.log")"
ok "backend healthy"

# --- 2. a farm and a real gateway ----------------------------------------

OWNER_ID="$(new_uuid)"; OWNER="$(mint "$OWNER_ID")"
expect 201 POST /orgs "$OWNER" '{"name":"e2e provision-proxy org"}' -- "create an org"
ORG_A="$(json 'd["id"]')"
expect 201 POST /farms "$OWNER" "{\"name\":\"e2e provision-proxy farm\",\"orgId\":\"$ORG_A\"}" -- "create a farm"
FARM_A="$(json 'd["id"]')"
expect 200 POST "/farms/$FARM_A/edge-proxy-token" "$OWNER" -- "mint the gateway token"
PROXY_TOKEN="$(json 'd["edgeProxyToken"]')"
expect 200 POST /auth/edge-token - "{\"farmId\":\"$FARM_A\",\"edgeProxyToken\":\"$PROXY_TOKEN\"}" -- "trade it for an edge JWT"
EDGE_JWT="$(json 'd["token"]')"

echo "==> building and starting the real continuum-proxy with NO printers"
( cd "$PROXY_DIR" && cargo build --quiet 2>&1 | tail -3 ) || fail "proxy did not build"
STORE="$WORK/proxy-store/continuum.db"
: > "$WORK/proxy.log"
start_proxy() {
  # env -C so $! is the daemon itself and cleanup does not orphan it.
  env -C "$PROXY_DIR" \
    CONTINUUM_GATEWAY_ID=e2e-gw \
    CONTINUUM_FARM_ID="$FARM_A" \
    CONTINUUM_GATEWAY_TOKEN="$EDGE_JWT" \
    CONTINUUM_UPLINK_URL="ws://localhost:$PORT/ws/edge/v1" \
    CONTINUUM_GO2RTC_BIN=/nonexistent-go2rtc \
    CONTINUUM_GO2RTC_CONFIG="$WORK/go2rtc.yaml" \
    CONTINUUM_PRINTERS_PATH="$WORK/no-such-printers.toml" \
    CONTINUUM_STORE_PATH="$STORE" \
    RUST_LOG=info \
    "$PROXY_DIR/target/debug/continuum-proxy" >> "$WORK/proxy.log" 2>&1 &
  PROXY_PID=$!
}
stop_proxy() {
  [ -n "$PROXY_PID" ] && kill "$PROXY_PID" 2>/dev/null || true
  sleep 1
  [ -n "$PROXY_PID" ] && kill -9 "$PROXY_PID" 2>/dev/null || true
  PROXY_PID=""
}
wait_for_gateway() {
  for _ in $(seq 1 60); do
    grep -q "gateway e2e-gw connected" "$WORK/backend.log" && return 0
    sleep 0.5
  done
  return 1
}
start_proxy
wait_for_gateway || fail "the proxy did not connect to the backend: $(tail -5 "$WORK/proxy.log")"
ok "the proxy connected with no printers file at all, from its store alone"
[ -f "$STORE" ] && ok "and created its store at $STORE" || bad "no store file was created"

# --- 3. the failure path across the real wire ------------------------------

echo "==> adding a printer that cannot be reached"
DEAD_CODE="DEADCODE-$(new_uuid | cut -c1-8)"
expect 502 POST "/farms/$FARM_A/printers" "$OWNER" \
  "{\"name\":\"Nowhere\",\"vendor\":\"bambu\",\"host\":\"127.0.0.1\",\"accessCode\":\"$DEAD_CODE\",\"serialNumber\":\"01P00A000000099\"}" \
  -- "the proxy reports it could not connect"
body_has GATEWAY_REFUSED
body_has "could not connect"
body_lacks "$DEAD_CODE"
N="$(psql_q "SELECT count(*) FROM printers WHERE farm_id='$FARM_A'")"
[ "$N" = "0" ] && ok "no printer row was created" || bad "a row exists after a failed add: $N"
grep -q "$DEAD_CODE" "$WORK/proxy.log" "$WORK/backend.log" && bad "the access code is in a log" || ok "the code is in neither the proxy's nor the backend's log"
if command -v sqlite3 >/dev/null 2>&1; then
  [ "$(sqlite3 "$STORE" 'select count(*) from printers')" = "0" ] && ok "nothing was stored on the gateway" || bad "the proxy stored a printer it could not reach"
fi

# --- 4. the success path, only with a printer you name ---------------------

if [ -n "${REAL_HOST:-}" ] && [ -n "${REAL_SERIAL:-}" ] && [ -n "${REAL_ACCESS_CODE:-}" ]; then
  echo "==> adding the real printer at $REAL_HOST (read-only: connect and listen)"
  expect 201 POST "/farms/$FARM_A/printers" "$OWNER" \
    "{\"name\":\"Real printer\",\"vendor\":\"bambu\",\"host\":\"$REAL_HOST\",\"accessCode\":\"$REAL_ACCESS_CODE\",\"serialNumber\":\"$REAL_SERIAL\"}" \
    -- "the proxy connected to the printer and the cloud created the row"
  PRINTER_ID="$(json 'd["id"]')"
  body_lacks "$REAL_ACCESS_CODE"
  MODE="$(stat -c %a "$STORE")"
  [ "$MODE" = "600" ] && ok "the store file is owner-only (600)" || bad "the store file mode is $MODE"

  wait_telemetry() {
    for _ in $(seq 1 40); do
      [ -n "$(psql_q "SELECT vendor_state FROM printers WHERE id='$PRINTER_ID' AND vendor_state IS NOT NULL")" ] && return 0
      sleep 0.5
    done
    return 1
  }
  wait_telemetry && ok "telemetry arrives under the new id" || bad "no telemetry for the added printer"

  echo "==> restart the proxy with no printers file: the printer must come back from the store"
  psql_q "UPDATE printers SET vendor_state=NULL, last_seen_at=NULL WHERE id='$PRINTER_ID'" >/dev/null
  stop_proxy
  # The edge JWT is short-lived but outlives this test.
  start_proxy
  wait_telemetry && ok "after a restart the printer reports again, from the store alone" || bad "the printer did not come back after a restart"
  grep -q "$REAL_ACCESS_CODE" "$WORK/proxy.log" "$WORK/backend.log" && bad "the access code is in a log" || ok "the access code is in no log"
else
  echo "  (skipping the success path: set REAL_HOST, REAL_SERIAL and REAL_ACCESS_CODE to run it against a real printer)"
fi

echo
if [ "$FAILURES" -eq 0 ]; then
  echo "PASS - the real proxy took provisioning requests over the real wire."
else
  echo "FAIL - $FAILURES assertion(s) failed." >&2
  exit 1
fi