jiangchang-platform-kit/tools/screencast/runner.py

"""主编排器：录屏 + 运行 pytest + 生成字幕 + FFmpeg 合成。"""
from __future__ import annotations

import os
import subprocess
import sys
import tempfile
import time
from datetime import datetime
from pathlib import Path
from typing import List, Optional, Tuple


def _ensure_sdk_on_path() -> None:
    """record_screencast.py 直接 python 跑时不走 conftest，SDK 可能不在 sys.path。
    自带兜底：从 tools/screencast/runner.py 上溯到 platform-kit/src。"""
    import importlib.util
    if importlib.util.find_spec("jiangchang_desktop_sdk") is not None:
        return
    # tools/screencast/runner.py → tools/screencast → tools → platform-kit
    here = Path(__file__).resolve()
    src = here.parent.parent.parent / "src"
    if (src / "jiangchang_desktop_sdk").is_dir():
        import sys as _sys
        _sys.path.insert(0, str(src))


_ensure_sdk_on_path()
from jiangchang_desktop_sdk.window_win32 import activate_and_maximize_jiangchang_window  # noqa: E402

from .composer import compose_video
from .recorder import ScreenRecorder
from .subtitle import SubtitleEngine


def run_screencast(
    skill_slug: str,
    subtitle_script: List[Tuple[str, str]],
    pytest_args: List[str],
    output_dir: str,
    media_assets_root: Optional[str] = None,
    music_subdir: str = "music",
    fps: int = 10,
    activate_window: bool = True,
    monitor_index: Optional[int] = None,
) -> str:
    """
    录制一次技能桌面 E2E 演示视频。

    Args:
        skill_slug:       技能唯一标识，如 "query-balance-icbc"
        subtitle_script:  [(关键词, 字幕文案), ...] 按顺序匹配 pytest stdout
        pytest_args:      传递给 pytest 的参数列表
        output_dir:       最终 MP4 输出目录
        media_assets_root: media-assets 仓库本地路径；
                           不传时读 MEDIA_ASSETS_ROOT 环境变量，
                           再不存在则用默认值 D:\\OpenClaw\\client-commons\\media-assets
        music_subdir:     music_assets_root 下音乐子目录，默认 "music"
        fps:               截帧帧率，默认 10
        activate_window:   录屏开始前是否自动激活+最大化匠厂窗口（默认 True；
                          Windows 走 ctypes，非 Windows 走 jiangchang:// 协议）
        monitor_index:     指定录哪个显示器；None=所有显示器合并（旧行为），
                          1=主屏，2+=第 N 屏（推荐多显示器场景显式传 1）

    Returns:
        输出 MP4 的绝对路径
    """
    if media_assets_root is None:
        media_assets_root = os.environ.get(
            "MEDIA_ASSETS_ROOT",
            r"D:\OpenClaw\client-commons\media-assets",
        )

    music_dir = str(Path(media_assets_root) / music_subdir)
    output_dir_path = Path(output_dir)
    output_dir_path.mkdir(parents=True, exist_ok=True)

    date_str = datetime.now().strftime("%Y%m%d_%H%M%S")
    base_name = f"{skill_slug}_{date_str}"
    output_mp4 = output_dir_path / f"{base_name}.mp4"
    subtitle_file = output_dir_path / f"{base_name}.srt"

    engine = SubtitleEngine(subtitle_script)

    with tempfile.TemporaryDirectory(prefix="screencast_frames_") as frames_dir:
        recorder = ScreenRecorder(frames_dir, fps=fps, monitor_index=monitor_index)

        if activate_window:
            ok = activate_and_maximize_jiangchang_window()
            if ok:
                print("[screencast] 已激活+最大化匠厂窗口")
                time.sleep(2)  # 等窗口浮起稳定
            else:
                print("[screencast] 未能激活匠厂窗口，继续录制（可能录到桌面边角）")

        print(f"[screencast] 启动录制 → {output_mp4.name}")
        recorder.start()
        engine.set_start_time(time.time())

        try:
            # Windows 子进程 stdout 默认走系统 ANSI code page（中文 Windows 是 cp936/GBK），
            # 这边用 encoding="utf-8" 解码会乱码。注入 PYTHONIOENCODING + PYTHONUTF8 让
            # 子进程 Python 强制以 UTF-8 输出，两端编码对齐。非 Windows 默认就 UTF-8，无副作用。
            env = os.environ.copy()
            env["PYTHONIOENCODING"] = "utf-8"
            env["PYTHONUTF8"] = "1"

            proc = subprocess.Popen(
                [sys.executable, "-m", "pytest", *pytest_args],
                stdout=subprocess.PIPE,
                stderr=subprocess.STDOUT,
                text=True,
                encoding="utf-8",
                errors="replace",
                env=env,
            )
            assert proc.stdout is not None
            for line in proc.stdout:
                sys.stdout.write(line)
                sys.stdout.flush()
                engine.process_line(line)
            exit_code = proc.wait()
            if exit_code != 0:
                print(f"[screencast] pytest 退出码 {exit_code}，录制仍继续合成")
        finally:
            recorder.stop()
            print(f"[screencast] 录制停止，共 {recorder.frame_count} 帧")

        engine.generate_srt(str(subtitle_file))
        print(f"[screencast] 字幕 → {subtitle_file.name}")

        compose_video(
            frames_dir=frames_dir,
            fps=fps,
            subtitle_path=str(subtitle_file),
            music_dir=music_dir,
            output_path=str(output_mp4),
        )

    return str(output_mp4)