#!/usr/bin/env bash
# End-to-end test that a camera actually delivers video through the whole
# stack, not just that its signalling round-trips.
#
# e2e-edge.sh covers the relay with go2rtc deliberately absent: it posts a
# stub offer and treats a 503 that came back *from the gateway* as proof the
# message travelled. That is honest about what it proves, which is only the
# round trip. It cannot say a viewer would see anything, and it once read as
# more than it was because a stray go2rtc left over from an earlier run
# answered the stub with an HTTP 500 and the test still printed "ok".
#
# This one runs the real thing end to end, twice - once over direct candidates
# and once pinned to relay-only through Cloudflare TURN, which is how the real
# browser is configured:
#
#   werift peer (stands in for the browser)
#     -> POST /printers/:id/webrtc on the real backend
#     -> /ws/edge/v1 -> the real continuum-proxy -> its real go2rtc
#     -> RTSPS to the printer's camera
#   and the RTP that comes back is counted. The relay phase needs
#   CLOUDFLARE_TURN_KEY_ID / CLOUDFLARE_TURN_API_TOKEN and is skipped, with a
#   message saying the TURN path went unverified, when they are absent.
#
# Not covered: the viewer and the gateway share this host, so what is proven is
# that ICE, DTLS and media work via TURN, not that they survive two distinct
# NATs; and a real browser has still not rendered a frame.
#
# SAFETY: read-only against the printers. It sends no printer command of any
# kind; the proxy's MQTT subscription is passive and the camera is a pull of
# the existing stream. Printer credentials stay in continuum-proxy/printers.toml
# (gitignored) and are never read here beyond the id and name lines.
#
# Needs: a printer with an RTSP camera (an H2C - a P1P exposes none, see
# continuum-pending-hardware-tests finding 14), go2rtc, and these ports free:
# 1984 (go2rtc API, loopback) and 8555 (its WebRTC listener).
#
# Usage:
#   scripts/dev-env.sh up && scripts/dev-env.sh schema
#   scripts/e2e-camera.sh
#
#   CAMERA_ID=h2c           the gateway id (in printers.toml) with a camera
#   GO2RTC_BIN=~/.local/bin/go2rtc
#   PROXY_DIR=../continuum-proxy
#   KEEP_DATA=1             leave the seeded farm behind for inspection
#
#   BROWSER=1               also drive the real web console in a real Chrome
#                           (../continuum-app) and check the picture on
#                           screen. Implies AUTH=supabase, because the app's
#                           client needs a real Supabase session; needs
#                           SUPABASE_URL, SUPABASE_SECRET_KEY and
#                           SUPABASE_PUBLISHABLE_KEY (source ../dev-secrets.sh).
#                           It creates/reuses one Supabase user,
#                           continuum-e2e@example.invalid, and resets its
#                           password each run. Port 3042 must be free.
#   AUTH=supabase           use that real user's token for the API phases too
#                           (default is the local dev-auth issuer)
set -euo pipefail

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

CAMERA_ID="${CAMERA_ID:-h2c}"
GO2RTC_BIN="${GO2RTC_BIN:-$HOME/.local/bin/go2rtc}"
PROXY_DIR="${PROXY_DIR:-$REPO_ROOT/../continuum-proxy}"
PORT="${PORT:-3040}"
AUTH_PORT="${AUTH_PORT:-3041}"
BASE="http://localhost:$PORT"
DATABASE_URL="${DATABASE_URL:-postgres://continuum:continuum@localhost:5432/continuum}"
VALKEY_URL="${VALKEY_URL:-redis://localhost:6379}"
EDGE_JWT_SECRET="${EDGE_JWT_SECRET:-e2e-edge-secret}"
# Nothing here presigns or uploads; the backend just refuses to boot without
# object-storage credentials (src/s3/index.ts).
R2_ACCESS_KEY_ID="${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

BROWSER="${BROWSER:-0}"
AUTH="${AUTH:-dev}"
[ "$BROWSER" = "1" ] && AUTH=supabase
APP_DIR="${APP_DIR:-$REPO_ROOT/../continuum-app}"
APP_PORT="${APP_PORT:-3042}"
CHROME_BIN="${CHROME_BIN:-/usr/bin/google-chrome}"

WORK="$(mktemp -d)"
BACKEND_PID=""
PROXY_PID=""
AUTH_PID=""
APP_PID=""

fail() { echo "FAIL: $*" >&2; exit 1; }
ok()   { echo "  ok: $*"; }
psql_q() { psql "$DATABASE_URL" -tAq -c "$1"; }
new_uuid() { cat /proc/sys/kernel/random/uuid; }
USER_ID="$(new_uuid)"

# The proxy supervises go2rtc, so it is the proxy's PID that has to die, and
# go2rtc with it. Anything that survives holds a printer access code in memory
# and answers the next run's offers - that exact leftover is how this script
# came to exist - so cleanup checks for it rather than assuming.
cleanup() {
  local rc=$?
  for pid in "$PROXY_PID" "$BACKEND_PID" "$AUTH_PID"; do
    [ -n "$pid" ] && kill "$pid" 2>/dev/null || true
  done
  # The dev server forks workers, so it is signalled as a group: it was started
  # with setsid, which makes its PID the group id. `kill 0` would hit us.
  [ -n "$APP_PID" ] && kill -- "-$APP_PID" 2>/dev/null || true
  for _ in $(seq 1 20); do
    [ -n "$PROXY_PID" ] && kill -0 "$PROXY_PID" 2>/dev/null || break
    sleep 0.3
  done
  for pid in "$PROXY_PID" "$BACKEND_PID" "$AUTH_PID"; do
    [ -n "$pid" ] && kill -9 "$pid" 2>/dev/null || true
  done
  [ -n "$APP_PID" ] && kill -9 -- "-$APP_PID" 2>/dev/null || true
  if [ -z "${KEEP_DATA:-}" ] && [ -n "${ORG_ID:-}" ]; then
    psql_q "DELETE FROM organisations WHERE id = '$ORG_ID'" >/dev/null 2>&1 || true
  fi
  if [ $rc -ne 0 ]; then
    echo; echo "--- backend log (tail) ---"; tail -20 "$WORK/backend.log" 2>/dev/null || true
    echo "--- proxy log (tail) ---"; tail -30 "$WORK/proxy.log" 2>/dev/null || true
  fi
  rm -rf "$WORK"
  # A go2rtc that outlived us is a leak, not a detail.
  sleep 0.5
  if ps -eo comm | grep -qx go2rtc; then
    echo "WARNING: a go2rtc process is still running after cleanup:" >&2
    ps -eo pid,etime,cmd | awk '$3 ~ /go2rtc/' >&2
    [ $rc -eq 0 ] && rc=1
  fi
  exit $rc
}
trap cleanup EXIT

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

echo "==> checking preconditions"
psql_q "SELECT org_id FROM farms LIMIT 0" >/dev/null 2>&1 \
  || fail "no migrated database at DATABASE_URL - run scripts/dev-env.sh up && schema"
[ -x "$GO2RTC_BIN" ] || fail "no go2rtc at $GO2RTC_BIN (set GO2RTC_BIN)"
[ -f "$PROXY_DIR/printers.toml" ] || fail "no $PROXY_DIR/printers.toml"
grep -q "^id *= *\"$CAMERA_ID\"" "$PROXY_DIR/printers.toml" \
  || fail "printers.toml has no printer with id '$CAMERA_ID' (set CAMERA_ID)"

# A leftover go2rtc would answer for the one under test and make this pass or
# fail for reasons that have nothing to do with the code. Refuse to start.
if ps -eo comm | grep -qx go2rtc; then
  fail "a go2rtc is already running - it would answer instead of the one under test: $(ps -eo pid,etime,cmd | awk '$3 ~ /go2rtc/' | head -2)"
fi
for p in 1984 8555; do
  ss -ltnu 2>/dev/null | grep -q ":$p " && fail "port $p is already in use"
done
CAM_HOST="$(awk -v id="$CAMERA_ID" -F'"' '/^id *=/ {cur=$2} cur==id && /^(host|address|ip) *=/ {print $2; exit}' "$PROXY_DIR/printers.toml")"
if [ -n "$CAM_HOST" ]; then
  timeout 4 bash -c "</dev/tcp/$CAM_HOST/322" 2>/dev/null \
    || fail "$CAMERA_ID ($CAM_HOST) refuses TCP 322: it has no RTSP camera, or is off"
  ok "$CAMERA_ID accepts RTSP on 322"
else
  ok "could not read $CAMERA_ID's address from printers.toml; skipping the 322 pre-check"
fi

if [ "$AUTH" = "supabase" ]; then
  for name in SUPABASE_URL SUPABASE_SECRET_KEY SUPABASE_PUBLISHABLE_KEY; do
    [ -n "${!name:-}" ] || fail "$name is not set - source ../dev-secrets.sh (AUTH=supabase / BROWSER=1)"
  done
fi
if [ "$BROWSER" = "1" ]; then
  [ -x "$CHROME_BIN" ] || fail "no Chrome at $CHROME_BIN (set CHROME_BIN)"
  [ -d "$APP_DIR/apps/web/node_modules" ] || fail "$APP_DIR has no installed web app - run pnpm install there"
  ss -ltn 2>/dev/null | grep -q ":$APP_PORT " && fail "port $APP_PORT is already in use"
fi

# The real Supabase user, when one is needed. Captured, never echoed: the JSON
# holds a password and a live access token.
if [ "$AUTH" = "supabase" ]; then
  SB_USER="$(bun scripts/e2e-supabase-user.ts)" || fail "could not provision the Supabase test user"
  sb_field() { printf '%s' "$SB_USER" | python3 -c 'import json,sys; print(json.load(sys.stdin)[sys.argv[1]])' "$1"; }
  USER_ID="$(sb_field id)"
  USER_TOKEN="$(sb_field accessToken)"
  SB_EMAIL="$(sb_field email)"
  SB_PASSWORD="$(sb_field password)"
  unset SB_USER
  ok "signed in as the real Supabase test user $USER_ID"
fi

# --- 1. seed ---------------------------------------------------------------

echo "==> seeding an organisation and a farm claiming '$CAMERA_ID'"
EDGE_PROXY_TOKEN="e2e-$(date +%s)"
ORG_ID="$(psql_q "INSERT INTO organisations (name) VALUES ('e2e camera org') RETURNING id")"
# `viewer`: the relay route asks for viewer, so seeding the weakest role that
# should work shows the camera is watchable without any authority to command.
psql_q "INSERT INTO org_members (org_id, user_id, role) VALUES ('$ORG_ID', '$USER_ID', 'viewer')" >/dev/null
FARM_ID="$(psql_q "INSERT INTO farms (name, org_id, edge_proxy_token)
  VALUES ('e2e camera farm', '$ORG_ID', '$EDGE_PROXY_TOKEN') RETURNING id")"
psql_q "INSERT INTO printers (farm_id, name, vendor, gateway_printer_id)
  VALUES ('$FARM_ID', 'camera under test', 'bambu', '$CAMERA_ID')" >/dev/null
CAM_UUID="$(psql_q "SELECT id FROM printers WHERE farm_id='$FARM_ID' AND gateway_printer_id='$CAMERA_ID'")"
ok "org $ORG_ID, farm $FARM_ID, viewer $USER_ID"

# --- 2. backend ------------------------------------------------------------

if [ "$AUTH" = "dev" ]; then
  echo "==> starting the dev-auth issuer on :$AUTH_PORT and the backend on :$PORT"
  bun scripts/dev-auth.ts --port "$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 "$AUTH_URL/auth/v1/.well-known/jwks.json" >/dev/null 2>&1 || fail "dev-auth did not come up"
  export SUPABASE_URL="$AUTH_URL"
  USER_TOKEN="$(curl -sf "$AUTH_URL/token?sub=$USER_ID" | python3 -c 'import json,sys; print(json.load(sys.stdin)["access_token"])')"
else
  echo "==> starting the backend on :$PORT, verifying tokens against the real Supabase JWKS"
fi
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 "$BASE/health" >/dev/null || fail "backend did not become healthy"
TOKEN="$(curl -sf -X POST "$BASE/auth/edge-token" -H 'content-type: application/json' \
  -d "{\"farmId\":\"$FARM_ID\",\"edgeProxyToken\":\"$EDGE_PROXY_TOKEN\"}" \
  | python3 -c 'import json,sys; print(json.load(sys.stdin).get("token",""))')"
[ -n "$TOKEN" ] || fail "no edge token"
ok "backend healthy, edge token minted"

# --- 3. the real gateway, with the real go2rtc ------------------------------

echo "==> starting the real continuum-proxy, which spawns the real go2rtc"
( cd "$PROXY_DIR" && cargo build --quiet 2>&1 | tail -3 ) || fail "proxy did not build"
# STREAM_BASE_URL has to be set for /stream to answer 200; it is never
# dialled, because the media path here is the relay, not a gateway URL.
env -C "$PROXY_DIR" \
  CONTINUUM_GATEWAY_ID=e2e-cam-gw \
  CONTINUUM_FARM_ID="$FARM_ID" \
  CONTINUUM_GATEWAY_TOKEN="$TOKEN" \
  CONTINUUM_UPLINK_URL="ws://localhost:$PORT/ws/edge/v1" \
  CONTINUUM_GO2RTC_BIN="$GO2RTC_BIN" \
  CONTINUUM_GO2RTC_CONFIG="$WORK/go2rtc.yaml" \
  CONTINUUM_STREAM_BASE_URL="http://e2e-gateway.invalid:1984" \
  CONTINUUM_PRINTERS_PATH=printers.toml \
  RUST_LOG=info \
  "$PROXY_DIR/target/debug/continuum-proxy" > "$WORK/proxy.log" 2>&1 &
PROXY_PID=$!

echo "==> waiting for the camera to be advertised"
STREAM=""
for _ in $(seq 1 45); do
  STREAM="$(curl -sf -H "authorization: Bearer $USER_TOKEN" "$BASE/printers/$CAM_UUID/stream" 2>/dev/null || true)"
  [ -n "$STREAM" ] && break
  sleep 1
done
[ -n "$STREAM" ] || fail "GET /printers/$CAM_UUID/stream never answered 200 - the gateway did not report a camera"
# Deliberately not echoed: with TURN configured the body carries a live
# username and credential, and printing it put them in a transcript once.
ok "the gateway advertises camera '$(printf '%s' "$STREAM" | python3 -c 'import json,sys; d=json.load(sys.stdin); print(d["cameraId"], "- iceServers:", len(d["iceServers"]))')'"

# The generated config holds the printer's access code and go2rtc's API
# password. $WORK is mode 0700, which hides a bad mode here, so the file's own
# mode is what is asserted - it was 0644 until this check caught it.
[ -f "$WORK/go2rtc.yaml" ] || fail "the proxy never wrote a go2rtc config"
mode="$(stat -c %a "$WORK/go2rtc.yaml")"
[ "$mode" = "600" ] || fail "go2rtc.yaml is mode $mode, but it holds an access code and must be 600"
ok "the generated go2rtc config is owner-only (mode $mode)"

# --- 4. the viewer ---------------------------------------------------------

# Runs the peer once and reads its `ok<TAB>label` / `FAILED<TAB>label` lines.
# $1 names the phase, $2 is how many results a complete run produces: fewer
# means the peer died before finishing, and a silent peer must not read as a
# pass.
run_viewer() {
  local phase="$1" expected="$2" results seen=0 bad=0 verdict label
  shift 2
  results="$(env BASE="$BASE" PRINTER_UUID="$CAM_UUID" ACCESS_TOKEN="$USER_TOKEN" "$@" \
    bun scripts/e2e-camera-peer.ts 2>&1 || true)"
  while IFS=$'\t' read -r verdict label; do
    case "$verdict" in
      ok)     ok "$label"; seen=$((seen + 1)) ;;
      FAILED) echo "  FAILED: $label" >&2; seen=$((seen + 1)); bad=$((bad + 1)) ;;
    esac
  done < <(printf '%s\n' "$results" | grep -E "^(ok|FAILED)$(printf '\t')")
  if [ "$seen" -lt "$expected" ] && [ "$bad" -eq 0 ]; then
    bad=1; echo "  FAILED: the $phase peer produced only $seen of $expected results" >&2
  fi
  if [ "$bad" -ne 0 ]; then
    printf '%s\n' "$results" | sed 's/^/      | /' >&2
    fail "the camera did not deliver video ($phase)"
  fi
}

echo "==> a real WebRTC peer plays the camera through the relay (direct candidates)"
run_viewer "direct" 5

# The path the product actually uses: the browser is pinned to relay-only, so
# media goes through Cloudflare TURN. Needs real credentials, which come from
# the environment, so it is skipped - loudly - rather than failed without them.
if [ -n "${CLOUDFLARE_TURN_KEY_ID:-}" ] && [ -n "${CLOUDFLARE_TURN_API_TOKEN:-}" ]; then
  echo "==> the same camera, viewer pinned to relay-only through Cloudflare TURN"
  run_viewer "relay-only" 7 ICE_MODE=relay
else
  echo "  SKIPPED: relay-only phase - CLOUDFLARE_TURN_KEY_ID / CLOUDFLARE_TURN_API_TOKEN not set."
  echo "           The TURN-relayed path, which the browser is pinned to, is NOT verified by this run."
fi

# --- 5. the real web console in a real browser -------------------------------

if [ "$BROWSER" = "1" ]; then
  echo "==> starting the web console on :$APP_PORT"
  # setsid so the whole dev server (it forks workers) shares one process group
  # that cleanup can signal; the app is told where the backend is and given the
  # real Supabase project it signs in against.
  setsid env -C "$APP_DIR/apps/web" \
    NUXT_PUBLIC_API_BASE="$BASE" \
    NUXT_PUBLIC_WS_BASE="ws://localhost:$PORT" \
    SUPABASE_URL="$SUPABASE_URL" \
    SUPABASE_KEY="$SUPABASE_PUBLISHABLE_KEY" \
    pnpm exec nuxt dev --host 127.0.0.1 --port "$APP_PORT" > "$WORK/app.log" 2>&1 &
  APP_PID=$!
  for _ in $(seq 1 120); do
    curl -sf -o /dev/null "http://127.0.0.1:$APP_PORT/login" 2>/dev/null && break
    sleep 1
  done
  curl -sf -o /dev/null "http://127.0.0.1:$APP_PORT/login" \
    || { tail -20 "$WORK/app.log" >&2; fail "the web console did not start on :$APP_PORT"; }
  ok "the web console is up"

  echo "==> the real console in real Chrome: sign in, open the fleet, watch the camera"
  BROWSER_OUT="$(env APP_URL="http://127.0.0.1:$APP_PORT" SUPABASE_E2E_EMAIL="$SB_EMAIL" \
    SUPABASE_E2E_PASSWORD="$SB_PASSWORD" CHROME_BIN="$CHROME_BIN" \
    timeout 240 bun scripts/e2e-camera-browser.ts 2>&1 || true)"
  seen=0; bad=0
  while IFS=$'\t' read -r verdict label; do
    case "$verdict" in
      ok)     ok "$label"; seen=$((seen + 1)) ;;
      FAILED) echo "  FAILED: $label" >&2; seen=$((seen + 1)); bad=$((bad + 1)) ;;
    esac
  done < <(printf '%s\n' "$BROWSER_OUT" | grep -E "^(ok|FAILED)$(printf '\t')")
  # A complete run is nine results. Fewer means the driver died part way, and a
  # silent driver must not read as a pass.
  if [ "$seen" -lt 9 ] && [ "$bad" -eq 0 ]; then
    bad=1; echo "  FAILED: the browser run produced only $seen of 9 results" >&2
  fi
  if [ "$bad" -ne 0 ]; then
    printf '%s\n' "$BROWSER_OUT" | sed 's/^/      | /' >&2
    echo "--- web console log (tail) ---" >&2; tail -15 "$WORK/app.log" >&2
    fail "the real browser did not show the camera"
  fi
fi

echo
echo "PASS - a real WebRTC peer received video from the printer's camera"
echo "       through the backend relay, the uplink, the proxy and go2rtc."
if [ -n "${CLOUDFLARE_TURN_KEY_ID:-}" ] && [ -n "${CLOUDFLARE_TURN_API_TOKEN:-}" ]; then
  echo "       Both directly and pinned to relay-only through Cloudflare TURN."
fi
if [ "$BROWSER" = "1" ]; then
  echo "       And the real web console, in real Chrome, showed the picture."
fi