CoopAllTheThings/tests/audio_verify_test.cpp

// Integration test for the two-path audio-format verifier (host/src/audio/audio_format_verifier).
//
// Launches coop_mock_game rendering a tone via WASAPI AUTOCONVERTPCM, injects coop_hook.dll late
// (so the stream is a *guess*), and runs the real verify_stream_format(): it co-captures the hook
// (pre-mix, via the ring's verify tap) and a parallel process-loopback (post-mix, device format)
// and cross-correlates them. Two scenarios:
//   (a) rate: render at the device's channel count but a different rate -> recover the rate.
//   (b) layout: render a DIFFERENT channel count than the device, with distinct per-channel content
//       -> recover channels + bit depth + rate.
// Skips cleanly without an audio endpoint.
#include <cstdint>
#include <cstdio>
#include <string>

#include <windows.h>

#include <mmreg.h>
#include <objbase.h>
#include <tlhelp32.h>

#include "audio/audio_format_verifier.hpp"
#include "audio/process_loopback_capture.hpp" // default_render_format
#include "coop/audio_ring.hpp"
#include "coop/protocol.hpp"
#include "coop/shared_memory.hpp"
#include "coop/tool_paths.hpp"

using namespace coop;

namespace
{
int g_failures = 0;
void check(bool ok, const char* what)
{
	std::printf("%s %s\n", ok ? "  ok:" : "FAIL:", what);
	if (!ok)
	{
		++g_failures;
	}
}

void kill_stray_mock_games()
{
	HANDLE snap = CreateToolhelp32Snapshot(TH32CS_SNAPPROCESS, 0);
	if (snap == INVALID_HANDLE_VALUE)
	{
		return;
	}
	PROCESSENTRY32W pe{};
	pe.dwSize = sizeof(pe);
	for (BOOL ok = Process32FirstW(snap, &pe); ok; ok = Process32NextW(snap, &pe))
	{
		if (_wcsicmp(pe.szExeFile, L"coop_mock_game.exe") == 0)
		{
			if (HANDLE h = OpenProcess(PROCESS_TERMINATE, FALSE, pe.th32ProcessID))
			{
				TerminateProcess(h, 0);
				CloseHandle(h);
			}
		}
	}
	CloseHandle(snap);
}

bool inject(unsigned long pid)
{
	const std::wstring dll = deployed_artifact_path(L"coop_hook.dll");
	if (GetFileAttributesW(dll.c_str()) == INVALID_FILE_ATTRIBUTES)
	{
		return false;
	}
	const DWORD access = PROCESS_CREATE_THREAD | PROCESS_QUERY_INFORMATION | PROCESS_VM_OPERATION |
	                     PROCESS_VM_WRITE | PROCESS_VM_READ;
	HANDLE process = OpenProcess(access, FALSE, pid);
	if (process == nullptr)
	{
		return false;
	}
	const SIZE_T bytes = (dll.size() + 1) * sizeof(wchar_t);
	void* remote = VirtualAllocEx(process, nullptr, bytes, MEM_COMMIT | MEM_RESERVE, PAGE_READWRITE);
	bool ok = false;
	if (remote != nullptr && WriteProcessMemory(process, remote, dll.c_str(), bytes, nullptr))
	{
		auto load = reinterpret_cast<LPTHREAD_START_ROUTINE>(
		    GetProcAddress(GetModuleHandleW(L"kernel32.dll"), "LoadLibraryW"));
		if (HANDLE th = CreateRemoteThread(process, nullptr, 0, load, remote, 0, nullptr))
		{
			WaitForSingleObject(th, INFINITE);
			DWORD code = 0;
			GetExitCodeThread(th, &code);
			CloseHandle(th);
			ok = code != 0;
		}
	}
	if (remote != nullptr)
	{
		VirtualFreeEx(process, remote, 0, MEM_RELEASE);
	}
	CloseHandle(process);
	return ok;
}

bool inject_retry(unsigned long pid)
{
	for (int i = 0; i < 4; ++i)
	{
		if (inject(pid))
		{
			return true;
		}
		Sleep(300);
	}
	return false;
}

struct Scenario
{
	unsigned rate, channels, bits;
	bool distinct;       // distinct per-channel content (so the channel count is recoverable)
	bool recover_layout; // false = rate only (step a); true = full layout (step b)
};

// Launch the mock at the scenario's format, inject the hook late, and run the verifier. `ran` is
// set false when the environment can't support the test (launch/inject failed) so the caller skips.
FormatVerification run(const Scenario& sc, bool& ran)
{
	ran = false;
	FormatVerification fv;
	kill_stray_mock_games();

	if (sc.distinct)
	{
		SetEnvironmentVariableW(L"COOP_TONE_DISTINCT_CH", L"1");
	}
	const std::wstring exe = exe_directory() + L"coop_mock_game.exe";
	std::wstring cmd = L"\"" + exe + L"\" dx11 30 " + std::to_wstring(sc.rate) + L" " +
	                   std::to_wstring(sc.channels) + L" " + std::to_wstring(sc.bits) + L" " +
	                   (sc.bits == 16 ? L"pcm" : L"float");
	STARTUPINFOW si{};
	si.cb = sizeof(si);
	PROCESS_INFORMATION pi{};
	const BOOL launched = CreateProcessW(exe.c_str(), cmd.data(), nullptr, nullptr, FALSE, 0, nullptr, nullptr,
	                                     &si, &pi);
	if (sc.distinct)
	{
		SetEnvironmentVariableW(L"COOP_TONE_DISTINCT_CH", nullptr);
	}
	if (!launched)
	{
		return fv;
	}
	auto cleanup = [&] {
		TerminateProcess(pi.hProcess, 0);
		WaitForSingleObject(pi.hProcess, 2000);
		CloseHandle(pi.hThread);
		CloseHandle(pi.hProcess);
		kill_stray_mock_games();
	};
	Sleep(800);

	SharedMemory shm;
	SharedMemory ring_shm;
	if (!shm.create(shared_memory_name(pi.dwProcessId), sizeof(SharedBlock)) ||
	    !ring_shm.create(audio_ring_name(pi.dwProcessId), audio_ring_total_size(kAudioRingCapacity)))
	{
		cleanup();
		return fv;
	}
	auto* block = shm.as<SharedBlock>();
	block->version = kProtocolVersion;
	block->pad_count = 0;
	block->sequence.store(0, std::memory_order_relaxed);
	for (std::uint32_t s = 0; s < HookSubsys_Count; ++s) // audio subsystem only
	{
		block->control.subsystem_disabled[s].store(s != HookSubsys_Audio ? 1u : 0u, std::memory_order_release);
	}
	block->magic = kProtocolMagic;
	auto* ring = ring_shm.as<AudioRingHeader>();
	audio_ring_init(*ring, kAudioRingCapacity); // capture_enabled stays 0: audible + still measuring

	if (!inject_retry(pi.dwProcessId))
	{
		cleanup();
		return fv;
	}
	Sleep(500); // hook attaches + the pre-existing render client registers as a guess

	fv = verify_stream_format(pi.dwProcessId, ring, /*window_ms=*/1400, sc.recover_layout);
	ran = true;
	cleanup();
	return fv;
}
} // namespace

int main()
{
	const bool com = SUCCEEDED(CoInitializeEx(nullptr, COINIT_MULTITHREADED));

	unsigned dev_rate = 48000, dev_channels = 2;
	if (WAVEFORMATEX* dev = default_render_format())
	{
		dev_rate = dev->nSamplesPerSec;
		dev_channels = dev->nChannels;
		CoTaskMemFree(dev);
	}
	const unsigned mismatched = (dev_rate == 44100) ? 48000u : 44100u; // guarantee a rate mismatch
	std::printf("device: %u Hz / %u ch\n", dev_rate, dev_channels);

	// (a) Rate: render at the device's channel count (no layout mismatch) but a different rate.
	std::printf("== (a) rate recovery: %u Hz / %u ch ==\n", mismatched, dev_channels);
	bool ran = false;
	FormatVerification a = run({mismatched, dev_channels, 32, /*distinct=*/false, /*recover_layout=*/false}, ran);
	if (!ran)
	{
		std::printf("   environment can't run the mock+inject -- skipping audio_verify_test.\n");
		if (com)
		{
			CoUninitialize();
		}
		return 0;
	}
	std::printf("   ok=%d rate=%u score=%.3f\n", a.ok ? 1 : 0, a.rate, a.score);
	if (!a.ok && a.rate == 0 && a.score == 0.0)
	{
		std::printf("   no usable co-capture (no endpoint / silent) -- skipping.\n");
		if (com)
		{
			CoUninitialize();
		}
		return 0;
	}
	check(a.ok, "(a) verifier confidently correlated the two capture paths");
	check(a.rate == mismatched, "(a) recovered the game's true rate (not the device rate)");

	// (b) Layout: render 2ch with distinct per-channel content -- a layout that differs from a
	// multichannel device -- and recover channels + bit depth + rate.
	std::printf("== (b) layout recovery: 44100 Hz / 2 ch / 32-bit float (distinct channels) ==\n");
	FormatVerification b = run({44100, 2, 32, /*distinct=*/true, /*recover_layout=*/true}, ran);
	std::printf("   ok=%d rate=%u ch=%u bits=%u tag=%u score=%.3f\n", b.ok ? 1 : 0, b.rate, b.channels, b.bits,
	            b.format_tag, b.score);
	if (b.ok || b.score > 0.0)
	{
		check(b.layout_ok, "(b) verifier confidently recovered the layout");
		check(b.rate == 44100, "(b) recovered the true rate");
		check(b.channels == 2, "(b) recovered the true channel count (2, not the device's)");
		check(b.bits == 32 && b.format_tag == 3, "(b) recovered 32-bit float");
	}
	else
	{
		std::printf("   no usable co-capture for (b) -- skipping that scenario.\n");
	}

	if (com)
	{
		CoUninitialize();
	}

	if (g_failures == 0)
	{
		std::printf("PASS audio_verify_test\n");
		return 0;
	}
	std::printf("FAILED audio_verify_test (%d)\n", g_failures);
	return 1;
}