signal-bot/scripts/e2e.sh

#!/bin/bash

# ============================================================================
# End-to-end test: the real bot against the fake Signal server.
#
# Boots the protocol-faithful fake, boots the unmodified bot pointed at it,
# replays every scenario and exits non-zero on the first mismatch. No Signal
# account, no network, no container.
# ============================================================================

set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
readonly SCRIPT_DIR
REPO_ROOT="$(dirname "$SCRIPT_DIR")"
readonly REPO_ROOT
readonly PYTHON="${PYTHON:-$REPO_ROOT/.venv/bin/python}"
readonly FAKE_PORT="${FAKE_PORT:-8099}"
readonly BOT_PORT="${BOT_PORT:-8098}"
readonly FAKE_URL="http://127.0.0.1:${FAKE_PORT}"

# Both spellings of one group, exactly as the real API reports them:
# /v1/groups returns the `group.<base64>` form (what .env holds), while an
# incoming envelope carries the id that base64 decodes to. Modelling only
# one is why the offline suite once passed against a bot that ignored every
# message in its own group.
readonly WATCHED_GROUP="group.WlRKbExYZGhkR05vWldRdFozSnZkWEF0YVdRdE16SXRZbmwwWlhNaElTRT0="
readonly WATCHED_GROUP_INTERNAL="ZTJlLXdhdGNoZWQtZ3JvdXAtaWQtMzItYnl0ZXMhISE="
# A second watched group, so the suite proves replies and rate limits stay
# in the group that asked instead of leaking into the other one.
readonly SECOND_GROUP="group.WlRKbExYTmxZMjl1WkMxbmNtOTFjQzFwWkMwek1pMWllWFJsY3lFaElTRT0="
readonly SECOND_GROUP_INTERNAL="ZTJlLXNlY29uZC1ncm91cC1pZC0zMi1ieXRlcyEhISE="
# Not seeded at boot: these arrive mid-run, which is the point.
readonly THIRD_GROUP="group.WlRKbExYUm9hWEprTFdkeWIzVndMV2xrTFRNeUxXSjVkR1Z6SVNFaElRPT0="
readonly THIRD_GROUP_INTERNAL="ZTJlLXRoaXJkLWdyb3VwLWlkLTMyLWJ5dGVzISEhIQ=="
readonly FOURTH_GROUP="group.WlRKbExXWnZkWEowYUMxbmNtOTFjQzFwWkMwek1pMWllWFJsY3lFaElTRT0="
readonly FOURTH_GROUP_INTERNAL="ZTJlLWZvdXJ0aC1ncm91cC1pZC0zMi1ieXRlcyEhISE="
readonly OTHER_GROUP="group.e2e.other=="

FAKE_PID=""
BOT_PID=""
TEMP_DIR=""

cleanup() {
    # Plain ifs, not `A && B || C`: that is not if-then-else, and C runs when
    # A is true but B fails -- which is exactly the case here (kill on an
    # already-dead pid).
    if [[ -n "$BOT_PID" ]]; then
        kill "$BOT_PID" 2>/dev/null || true
    fi
    if [[ -n "$FAKE_PID" ]]; then
        kill "$FAKE_PID" 2>/dev/null || true
    fi
    wait 2>/dev/null || true
    if [[ -n "$TEMP_DIR" && -d "$TEMP_DIR" ]]; then
        rm -rf "$TEMP_DIR"
    fi
}
trap cleanup EXIT

die() {
    echo "Error: $1" >&2
    exit 1
}

wait_for_url() {
    local url="$1" name="$2" attempt=0
    until curl -sf "$url" >/dev/null 2>&1; do
        attempt=$((attempt + 1))
        if [[ $attempt -ge 100 ]]; then
            echo "Error: $name did not come up at $url" >&2
            exit 1
        fi
        sleep 0.1
    done
}

wait_for_subscription() {
    local attempt=0
    until [[ "$(curl -sf "${FAKE_URL}/_control/ready" | tr -dc '0-9')" != "0" ]]; do
        attempt=$((attempt + 1))
        if [[ $attempt -ge 100 ]]; then
            echo "Error: the bot never subscribed to the receive websocket" >&2
            exit 1
        fi
        sleep 0.1
    done
}

validate_requirements() {
    if [[ ! -x "$PYTHON" ]]; then
        echo "Error: no interpreter at $PYTHON. Run: uv venv .venv && uv pip install -e '.[dev]'" >&2
        exit 1
    fi
    command -v curl >/dev/null || { echo "Error: curl is required" >&2; exit 1; }
}

main() {
    validate_requirements
    TEMP_DIR="$(mktemp -d)"

    echo "== booting the fake Signal server on :${FAKE_PORT}"
    export FAKE_PORT
    "$PYTHON" -m uvicorn fake_signal.server:app \
        --host 127.0.0.1 --port "$FAKE_PORT" --log-level warning &
    FAKE_PID=$!
    wait_for_url "${FAKE_URL}/v1/about" "fake signal server"

    echo "== seeding the fake with a registered, joined account"
    curl -sf -X POST "${FAKE_URL}/_control/accounts" \
        -H 'Content-Type: application/json' \
        -d '["+15550000000"]' >/dev/null
    curl -sf -X POST "${FAKE_URL}/_control/groups" \
        -H 'Content-Type: application/json' \
        -d "[{\"id\":\"${WATCHED_GROUP}\",\"internal_id\":\"${WATCHED_GROUP_INTERNAL}\",\"name\":\"e2e\",\"member\":true,\"joinable\":true},{\"id\":\"${SECOND_GROUP}\",\"internal_id\":\"${SECOND_GROUP_INTERNAL}\",\"name\":\"e2e-second\",\"member\":true,\"joinable\":true}]" >/dev/null

    # GROUP_IDS and TRUSTED_INVITERS deliberately empty: the bot discovers
    # its groups from the account, which is the configuration real
    # deployments use. Set rather than merely unset, because load_dotenv()
    # would otherwise let the developer's own .env decide what this run
    # watches -- and a TRUSTED_INVITERS there would refuse every fixture
    # group. The gate itself is covered in tests/test_trust.py.
    echo "== booting the bot on :${BOT_PORT}, pointed at the fake"
    env -u CAT_API \
        PHONE_NUMBER="+15550000000" \
        GROUP_IDS="" \
        TRUSTED_INVITERS="" \
        API_BASE_URL="$FAKE_URL" \
        DATABASE_PATH="${TEMP_DIR}/e2e.sqlite3" \
        CAT_API_URL="${FAKE_URL}/_fixtures/cat-api" \
        DOG_API_URL="${FAKE_URL}/_fixtures/dog-api" \
        GECKO_API_URL="${FAKE_URL}/_fixtures/gecko-api" \
        BIND_PORT="$BOT_PORT" \
        SILENCE_SECONDS=0 \
        "$PYTHON" -m signal_bot &
    BOT_PID=$!
    wait_for_url "http://127.0.0.1:${BOT_PORT}/healthz" "bot"
    wait_for_subscription

    echo "== replaying scenarios"
    "$PYTHON" -m fake_signal.cli \
        "$REPO_ROOT"/fake_signal/scenarios/*.yaml \
        --base-url "$FAKE_URL" \
        --group "watched=${WATCHED_GROUP_INTERNAL}" \
        --group "reply=${WATCHED_GROUP}" \
        --group "second=${SECOND_GROUP_INTERNAL}" \
        --group "second_reply=${SECOND_GROUP}" \
        --group "third=${THIRD_GROUP_INTERNAL}" \
        --group "third_reply=${THIRD_GROUP}" \
        --group "fourth=${FOURTH_GROUP_INTERNAL}" \
        --group "fourth_reply=${FOURTH_GROUP}" \
        --group "other=${OTHER_GROUP}"

    prove_the_deafness_gate
}

# The gate that did not exist on 2026-08-29, proven against the real process:
# with signal-cli unable to reach Signal, /healthz must go red rather than
# keep answering 200 while nothing arrives.
prove_the_deafness_gate() {
    local health="http://127.0.0.1:${BOT_PORT}/healthz"
    echo "== cutting the fake's connection to Signal"
    curl -sf -X POST "${FAKE_URL}/_control/connection" \
        -H 'Content-Type: application/json' -d '{"alive": false}' >/dev/null

    local code="" waited=0
    while ((waited < 150)); do
        code="$(curl -s -o /dev/null -w '%{http_code}' "$health")"
        [[ "$code" == "503" ]] && break
        sleep 1
        waited=$((waited + 1))
    done
    [[ "$code" == "503" ]] || die "/healthz still answers ${code} with the connection cut"
    curl -s "$health" | grep -q "Closed unexpectedly" ||
        die "/healthz went red without saying why"
    echo "== /healthz turned 503 and named the reason after ${waited}s"

    echo "== restoring the connection"
    curl -sf -X POST "${FAKE_URL}/_control/connection" \
        -H 'Content-Type: application/json' -d '{"alive": true}' >/dev/null
    waited=0
    while ((waited < 150)); do
        code="$(curl -s -o /dev/null -w '%{http_code}' "$health")"
        [[ "$code" == "200" ]] && break
        sleep 1
        waited=$((waited + 1))
    done
    [[ "$code" == "200" ]] || die "/healthz stayed ${code} after the connection came back"
    echo "== /healthz recovered on its own after ${waited}s"
}

main "$@"