voice-cat/tools/vccli/src/main.cpp

/*
 * vccli — headless test client.
 *
 * This is the primary way the protocol is exercised and verified from M1 onward (see
 * AGENTS.md). Each milestone's exit criterion is demonstrated by driving two vccli
 * instances against a real voicecat-server.
 */
#include <atomic>
#include <chrono>
#include <csignal>
#include <cstdio>
#include <cstring>
#include <functional>
#include <iostream>
#include <string>
#include <thread>

#include "voicecat.h"

namespace {

std::atomic<bool> g_stop{false};
void on_sigint(int) { g_stop.store(true); }

struct Stats {
    std::atomic<bool>     auth_done{false};
    std::atomic<bool>     auth_ok{false};
};

void on_event(void* user, const vc_event* ev) {
    auto* st = static_cast<Stats*>(user);
    switch (ev->type) {
        case VC_EVENT_CONNECTION_STATE:
            std::printf("[state] -> %d\n", static_cast<int>(ev->connection_state));
            break;
        case VC_EVENT_AUTH_RESULT:
            st->auth_ok   = (ev->result == VC_OK);
            st->auth_done = true;
            std::printf("[auth] ok=%d user_id=%u %s\n", st->auth_ok.load(), ev->user_id,
                        ev->text ? ev->text : "");
            break;
        case VC_EVENT_USER_JOINED:
            std::printf("[user] joined: %s (id=%u, channel=%u)\n", ev->text ? ev->text : "?",
                        ev->user_id, ev->channel_id);
            break;
        case VC_EVENT_USER_LEFT:
            std::printf("[user] left: id=%u\n", ev->user_id);
            break;
        case VC_EVENT_USER_UPDATED:
            std::printf("[user] updated: id=%u\n", ev->user_id);
            break;
        case VC_EVENT_STREAM_STARTED:
            std::printf("[voice] stream started: user_id=%u stream_id=%u\n", ev->user_id,
                        ev->stream_id);
            break;
        case VC_EVENT_STREAM_STOPPED:
            std::printf("[voice] stream stopped: user_id=%u stream_id=%u\n", ev->user_id,
                        ev->stream_id);
            break;
        case VC_EVENT_TEXT_MESSAGE:
            std::printf("[text] from=%u: %s\n", ev->user_id, ev->text ? ev->text : "");
            break;
        case VC_EVENT_TALK_STATE:
            std::printf("[voice] talk state: user_id=%u stream_id=%u talking=%u\n", ev->user_id,
                        ev->stream_id, ev->u32a);
            break;
        case VC_EVENT_ERROR:
            std::fprintf(stderr, "[error] rc=%d: %s\n", ev->result, ev->text ? ev->text : "");
            break;
        case VC_EVENT_DISCONNECTED:
            std::printf("[disconnected] rc=%d: %s\n", ev->result, ev->text ? ev->text : "");
            g_stop.store(true);
            break;
        default:
            break;
    }
}

bool wait_until(std::atomic<bool>& flag, int timeout_ms) {
    auto deadline = std::chrono::steady_clock::now() + std::chrono::milliseconds(timeout_ms);
    while (!flag.load()) {
        if (std::chrono::steady_clock::now() >= deadline) return false;
        std::this_thread::sleep_for(std::chrono::milliseconds(20));
    }
    return true;
}

void print_usage() {
    std::printf(
        "usage: vccli [--host H] [--port P] [--nick NAME] [--channel ID]\n"
        "             [--voice] [--mute] [--text MSG] [--list-devices]\n"
        "             [--input-device ID] [--input-mode vad|ptt] [--share-screen-audio]\n"
        "  --host H              server host (default 127.0.0.1)\n"
        "  --port P              server TCP port (default 8384)\n"
        "  --nick NAME           guest nickname (default vccli-test)\n"
        "  --channel ID          channel to join after auth (default 1, Lobby)\n"
        "  --voice               start a MIC stream and stay connected until Ctrl+C\n"
        "  --mute                start with the mic muted (only meaningful with --voice)\n"
        "  --text MSG            send MSG to the channel, then exit\n"
        "  --list-devices        print input/output devices (vc_list_devices) and exit\n"
        "  --input-device ID     use device ID (from --list-devices) for the MIC stream\n"
        "  --input-mode vad|ptt  send-side input gate mode (default vad)\n"
        "  --share-screen-audio  also start a SCREEN_AUDIO stream (WASAPI loopback on Windows)\n"
        "\n"
        "While --voice is running, stdin accepts: \"ptt on\", \"ptt off\", \"mode vad\",\n"
        "\"mode ptt\" (PTT key state can't be held interactively in a headless CLI, so it's\n"
        "toggled via these commands instead).\n");
}

void print_device_list(vc_client* c, vc_device_kind kind, const char* label) {
    vc_device_list dl{};
    vc_result      r = vc_list_devices(c, kind, &dl);
    std::printf("%s devices: vc_list_devices -> %d (%s), count=%zu\n", label, r,
                vc_result_string(r), dl.count);
    for (size_t i = 0; i < dl.count; ++i) {
        std::printf("  [%s] %s%s\n", dl.items[i].id, dl.items[i].name,
                    dl.items[i].is_default ? "  (default)" : "");
    }
    vc_free_device_list(&dl);
}

// Background stdin reader for --voice mode: the most portable way to drive PTT/mode toggles
// interactively from a headless CLI (no SIGUSR1 equivalent on Windows).
void run_stdin_commands(vc_client* c, std::atomic<bool>& stop) {
    std::string line;
    while (!stop.load() && std::getline(std::cin, line)) {
        if (line == "ptt on") {
            vc_set_push_to_talk(c, 1);
            std::printf("[ptt] on\n");
        } else if (line == "ptt off") {
            vc_set_push_to_talk(c, 0);
            std::printf("[ptt] off\n");
        } else if (line == "mode vad") {
            vc_set_input_mode(c, VC_INPUT_VOICE_ACTIVATION);
            std::printf("[mode] vad\n");
        } else if (line == "mode ptt") {
            vc_set_input_mode(c, VC_INPUT_PUSH_TO_TALK);
            std::printf("[mode] ptt\n");
        } else if (!line.empty()) {
            std::fprintf(stderr, "unknown command: %s\n", line.c_str());
        }
    }
}

}  // namespace

int main(int argc, char** argv) {
    // MSVCRT/MinGW treat _IOLBF as full buffering for non-console streams, so go unbuffered
    // to keep output visible immediately when piped to a file or another process.
    std::setvbuf(stdout, nullptr, _IONBF, 0);

    std::string host       = "127.0.0.1";
    uint16_t    port       = 8384;
    std::string nick       = "vccli-test";
    uint32_t    channel_id = 1;
    bool        voice_mode = false;
    bool        start_muted = false;
    std::string text_msg;
    bool        have_text = false;
    bool        list_devices = false;
    std::string input_device;
    bool        have_input_device = false;
    vc_input_mode input_mode = VC_INPUT_VOICE_ACTIVATION;
    bool        share_screen_audio = false;

    for (int i = 1; i < argc; ++i) {
        std::string a = argv[i];
        auto next = [&]() -> std::string { return (i + 1 < argc) ? argv[++i] : std::string(); };
        if (a == "--host") host = next();
        else if (a == "--port") port = static_cast<uint16_t>(std::stoi(next()));
        else if (a == "--nick") nick = next();
        else if (a == "--channel") channel_id = static_cast<uint32_t>(std::stoul(next()));
        else if (a == "--voice") voice_mode = true;
        else if (a == "--mute") start_muted = true;
        else if (a == "--text") { text_msg = next(); have_text = true; }
        else if (a == "--list-devices") list_devices = true;
        else if (a == "--input-device") { input_device = next(); have_input_device = true; }
        else if (a == "--input-mode") {
            std::string m = next();
            if (m == "ptt") input_mode = VC_INPUT_PUSH_TO_TALK;
            else if (m != "vad") { std::fprintf(stderr, "--input-mode must be vad|ptt\n"); return 1; }
        }
        else if (a == "--share-screen-audio") share_screen_audio = true;
        else if (a == "--help" || a == "-h") { print_usage(); return 0; }
        else { std::fprintf(stderr, "unknown flag: %s\n", a.c_str()); print_usage(); return 1; }
    }

    std::printf("vccli — VoiceCat test client (core %s, protocol v%d)\n", vc_version_string(),
                VOICECAT_PROTOCOL_VERSION);

    std::signal(SIGINT, on_sigint);

    vc_config cfg{};
    cfg.client_name    = "vccli";
    cfg.client_version = vc_version_string();
    cfg.log_level       = VC_LOG_INFO;

    Stats st;
    vc_callbacks cb{};
    cb.on_event = on_event;
    cb.user     = &st;

    vc_client* c = vc_client_create(&cfg, cb);
    if (c == nullptr) {
        std::fprintf(stderr, "failed to create client\n");
        return 1;
    }

    if (list_devices) {
        // Device enumeration works pre-connect (no server needed) — see docs/voice.md.
        print_device_list(c, VC_DEVICE_INPUT, "input");
        print_device_list(c, VC_DEVICE_OUTPUT, "output");
        vc_client_destroy(c);
        return 0;
    }

    vc_result r = vc_connect(c, host.c_str(), port);
    std::printf("vc_connect(%s:%u) -> %d (%s)\n", host.c_str(), port, r, vc_result_string(r));
    if (r != VC_OK) {
        vc_client_destroy(c);
        return 1;
    }

    r = vc_authenticate_guest(c, nick.c_str());
    std::printf("vc_authenticate_guest(%s) -> %d (%s)\n", nick.c_str(), r, vc_result_string(r));

    if (!wait_until(st.auth_done, 8000) || !st.auth_ok.load()) {
        std::fprintf(stderr, "authentication failed or timed out\n");
        vc_disconnect(c);
        vc_client_destroy(c);
        return 1;
    }

    if (channel_id != 1) {
        r = vc_join_channel(c, channel_id, nullptr);
        std::printf("vc_join_channel(%u) -> %d (%s)\n", channel_id, r, vc_result_string(r));
    }

    if (have_text) {
        r = vc_send_text(c, VC_TEXT_CHANNEL, channel_id, text_msg.c_str());
        std::printf("vc_send_text -> %d (%s)\n", r, vc_result_string(r));
        std::this_thread::sleep_for(std::chrono::milliseconds(300));  // let the relay land
    }

    if (voice_mode) {
        // Give the async UDP binding handshake (TCP UdpBinding -> ack -> plaintext
        // bootstrap packet) a moment to land before announcing a stream.
        std::this_thread::sleep_for(std::chrono::milliseconds(500));

        if (start_muted) vc_set_self_mute(c, 1, 0);

        r = vc_set_input_mode(c, input_mode);
        std::printf("vc_set_input_mode(%s) -> %d (%s)\n",
                    input_mode == VC_INPUT_PUSH_TO_TALK ? "ptt" : "vad", r, vc_result_string(r));

        vc_stream_desc desc{};
        desc.kind      = VC_STREAM_MIC;
        desc.device_id = have_input_device ? input_device.c_str() : nullptr;
        desc.label     = "Microphone";

        uint32_t stream_id = 0;
        r = vc_stream_start(c, &desc, &stream_id);
        std::printf("vc_stream_start -> %d (%s), stream_id=%u\n", r, vc_result_string(r),
                    stream_id);

        if (have_input_device && r == VC_OK) {
            r = vc_set_input_device(c, stream_id, input_device.c_str());
            std::printf("vc_set_input_device -> %d (%s)\n", r, vc_result_string(r));
        }

        uint32_t screen_stream_id = 0;
        if (share_screen_audio) {
            vc_stream_desc sdesc{};
            sdesc.kind  = VC_STREAM_SCREEN_AUDIO;
            sdesc.label = "Desktop audio";
            r = vc_stream_start(c, &sdesc, &screen_stream_id);
            std::printf("vc_stream_start(SCREEN_AUDIO) -> %d (%s), stream_id=%u\n", r,
                        vc_result_string(r), screen_stream_id);
        }

        std::thread stdin_thread(run_stdin_commands, c, std::ref(g_stop));

        std::printf("voice mode: streaming mic, listening for remote streams. Ctrl+C to stop.\n"
                    "(type \"ptt on\"/\"ptt off\"/\"mode vad\"/\"mode ptt\" to drive the input gate)\n");
        while (!g_stop.load()) {
            std::this_thread::sleep_for(std::chrono::milliseconds(200));
        }

        if (share_screen_audio) vc_stream_stop(c, screen_stream_id);
        vc_stream_stop(c, stream_id);

        // Unblock the stdin reader and let it exit before the client is torn down.
        if (stdin_thread.joinable()) {
#if defined(_WIN32)
            // std::getline on a console stdin blocks indefinitely; on Windows there's no
            // portable way to interrupt it from another thread, so detach rather than join —
            // process exit reclaims the thread.
            stdin_thread.detach();
#else
            stdin_thread.join();
#endif
        }
    }

    vc_disconnect(c);
    vc_client_destroy(c);
    std::printf("ok\n");
    return 0;
}