Files
codex-app-server/chv-guest/buildinfo.py
T
host f723eb8a88 feat(chv): 阶段 4 截图三级管线——a11y 角色解析 + diff_shot 逐像素裁剪 + verify_shot 全屏校验
- snapshot 纯字符串解析 a11y 角色计数/interactive/字符数/hash
  (不跑 JS、不取原始 DOM,禁 op 保持拒绝);status 带计数器
  与 verify_share
- diff_shot:PNG 全帧 Pillow 逐像素比对(单通道阈值 10),
  无变化 changed:false size 0;有变化 bbox 外扩 8px、钳制视口、
  宽高下限 32px,再 clip 截 JPEG q70;Pillow 缺失如实报错并
  指引回落 screenshot 全帧;open 不清基线(跨页局部差分靠它)
- verify_shot:全帧 JPEG q70,只用于检查点
- build.sh 与 playwright 同批 pip 装 pillow(只加 pillow);
  buildinfo BASE_CONTENTS 登记 pillow(pip 名覆盖)
- 单测 cloud/tests/test_chv_opt_stage4.py:31 项(bbox 纯函数、
  a11y 解析、计数器、Pillow 缺失回落、禁 op、lockfile 往返)
2026-11-08 09:45:00 +00:00

196 lines
8.1 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
"""生成 CHV 客机镜像的 BUILDINFO.json(build.sh 调用)。
从 build.sh 抽出(B-02),使其可独立单元测试。输入全部是
已落盘的构建产物与读回文件,不编造版本号:versions 来自
客机读回的 dpkg-query / pip freeze(Playwright=1 时另有
ms-playwright 缓存目录名作 chromium 标识);artifacts 的
sha256/size 是对产物文件实测的;image_sha256 即 disk.raw
的 sha256,供 generate_lockfile.py 沿用。
用法:
python3 buildinfo.py OUT_DIR TAG UBUNTU CODEX_VERSION \\
REPO_COMMIT UBUNTU_IMAGE_SHA256 PLAYWRIGHT(0|1)
[CHROMIUM_HEADLESS_SHELL_REV]
CHROMIUM_HEADLESS_SHELL_REV(可选,纯数字):钉死的
ms-playwright 缓存修订号(如 1248)。PLAYWRIGHT=1 且
给了该值时,versions.chromium 里须恰好出现
chromium_headless_shell-<rev>,否则退出 1、构建失败;
未给时只记录、不强制,BUILDINFO.chromium_pinned_rev
记 null,构建输出由 build.sh 明说“未钉死”。
"""
import hashlib
import json
import os
import re
import sys
import time
# 轻量口径(2026-11-06 用户定):Ubuntu Minimal 底座,只装
# codex + Python + SSH + cloud-init + 薄 agent + git + gt +
# 最小中文字体;已裁剪 pandoc/texlive/python-docx 等文档工具
# 与 qemu-guest-agent。chv-sync 是仓库内脚本,版本随 repo_commit。
BASE_CONTENTS = [
"git", "openssh-server", "openssh-client", "cloud-init",
"python3", "python3-pip", "curl", "ca-certificates",
"xz-utils", "fonts-wqy-microhei", "fontconfig", "codex",
"codex-code-mode-host", "codex-resources/bwrap",
"/app/host.py", "gt", "chv-sync",
# 对齐 Muse P2:nspawn 单元启动器 + broker + 浏览器子代理。
"systemd-container", "chv-cell", "chv-broker", "chv-browser",
# feat-chv-opt-landing(阶段 1):数据盘挂载脚本。
"chv-data-mount",
# feat-chv-opt-landing(阶段 2):客机运行时三分服务。
"chv-daemon", "chv-execd", "chv-syncd",
# feat-chv-opt-landing(阶段 2):cell veth 的 networkd
# 不管配置(须排在 80-container-ve.network 之前)。
"79-chv-cell.network",
# feat-chv-opt-landing(阶段 4):Pillow(pip 包,diff_shot
# 逐像素比对与全帧 JPEG 编码用;只加 pillow,不动其它包版本。
# check/generate lockfile 按 pip 名覆盖,不走 DECLARED_SOURCES)。
"pillow",
]
# 执行器默认内核 cmdline(config.py),构建产物须与它一起记录(B-12),
# 否则换宿主/换执行器配置时无法复现。
KERNEL_CMDLINE = "console=hvc0 root=/dev/vda1 rw"
# 浏览器装在系统路径(B-22),不是某用户的 ~/.cache:构建时
# PLAYWRIGHT_BROWSERS_PATH 指这里,agent 运行时也须设同一变量。
PLAYWRIGHT_BROWSERS_PATH = "/usr/local/share/ms-playwright"
def _read_lines(path):
try:
with open(path) as fh:
return [line.strip() for line in fh if line.strip()]
except OSError:
return []
def _sha256_size(path):
digest = hashlib.sha256()
size = 0
with open(path, "rb") as fh:
for chunk in iter(lambda: fh.read(1 << 20), b""):
digest.update(chunk)
size += len(chunk)
return digest.hexdigest(), size
def build(outdir, tag, ubuntu, codex_version, repo_commit,
ubuntu_image_sha256, playwright, chromium_pinned_rev=None,
extra_contents=None):
disk_path = os.path.join(outdir, "disk.raw")
vmlinux_path = os.path.join(outdir, "vmlinux")
disk_sha, disk_size = _sha256_size(disk_path)
vmlinux_sha, vmlinux_size = _sha256_size(vmlinux_path)
contents = list(BASE_CONTENTS)
# extra_contents:构建时才确定的附加内容(如 P1 的 vsock_notify,
# 文件存在才拷入)。调用方传什么记什么,不编默认值。
for item in extra_contents or []:
if item and item not in contents:
contents.append(item)
versions = {
"dpkg": _read_lines(
os.path.join(outdir, "guest-versions-dpkg.txt")),
"pip": _read_lines(
os.path.join(outdir, "guest-versions-pip.txt")),
"gt": _read_lines(
os.path.join(outdir, "guest-versions-gt.txt")),
}
gt_version = ""
for line in versions["gt"]:
m = re.search(r"(\d+\.\d+\.\d+)", line)
if m:
gt_version = m.group(1)
break
if playwright:
contents += ["playwright", "chromium-headless-shell"]
versions["chromium"] = _read_lines(
os.path.join(outdir, "guest-versions-chromium.txt"))
info = {
"tag": tag,
"ubuntu": ubuntu,
"codex_version": codex_version,
"repo_commit": repo_commit,
"gt_version": gt_version,
"built_at": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
"contents": contents,
"versions": versions,
"ubuntu_image_sha256": ubuntu_image_sha256,
"ubuntu_image_sha256_set": True,
"kernel_cmdline": KERNEL_CMDLINE,
"playwright": bool(playwright),
"playwright_browsers_path": PLAYWRIGHT_BROWSERS_PATH
if playwright else "",
# feat-chv-closeup(M4):钉死的 Chromium 修订号(未设
# 记 null,绝不编一个默认值出来假装已钉死)。
"chromium_pinned_rev": chromium_pinned_rev or None,
"image_sha256": disk_sha,
"artifacts": {
"disk.raw": {"sha256": disk_sha, "size": disk_size},
"vmlinux": {"sha256": vmlinux_sha, "size": vmlinux_size},
},
}
path = os.path.join(outdir, "BUILDINFO.json")
with open(path, "w") as fh:
json.dump(info, fh, indent=2)
fh.write("\n")
return info
def main(argv):
if len(argv) not in (8, 9, 10):
print("用法:buildinfo.py OUT TAG UBUNTU CODEX_VERSION "
"REPO_COMMIT UBUNTU_IMAGE_SHA256 PLAYWRIGHT "
"[CHROMIUM_HEADLESS_SHELL_REV] [EXTRA_CONTENTS]", file=sys.stderr)
return 2
_, outdir, tag, ubuntu, codex_version, repo_commit, \
ubuntu_image_sha256, playwright = argv[:8]
chromium_pinned_rev = argv[8] if len(argv) >= 9 else None
# 第 10 参数:逗号分隔的附加内容(如 vsock_notify),可空。
extra_contents = None
if len(argv) == 10 and argv[9]:
extra_contents = [s for s in argv[9].split(",") if s]
if chromium_pinned_rev and not re.fullmatch(r"[0-9]+",
chromium_pinned_rev):
print("CHROMIUM_HEADLESS_SHELL_REV 须为纯数字:%s"
% chromium_pinned_rev, file=sys.stderr)
return 2
info = build(outdir, tag, ubuntu, codex_version, repo_commit,
ubuntu_image_sha256, playwright == "1",
chromium_pinned_rev, extra_contents)
if not info["versions"]["dpkg"]:
print("BUILDINFO versions.dpkg 为空", file=sys.stderr)
return 1
if not info["versions"]["pip"]:
print("BUILDINFO versions.pip 为空", file=sys.stderr)
return 1
if not info["gt_version"]:
print("BUILDINFO gt_version 为空(gt 未装好)", file=sys.stderr)
return 1
if playwright == "1" and not info["versions"].get("chromium"):
print("BUILDINFO versions.chromium 为空(浏览器未装好或"
"读回路径不对)", file=sys.stderr)
return 1
if playwright == "1" and chromium_pinned_rev:
# feat-chv-closeup(M4):钉死校验——读回的缓存目录名
# 须恰好是该修订号,playwright 升级导致目录名变了就
# 在这里失败,不静默换浏览器版本。
expected = "chromium_headless_shell-%s" % chromium_pinned_rev
if expected not in (info["versions"].get("chromium") or []):
print("Chromium 修订号与钉死值不符:读回 %s,钉死 %s"
% (info["versions"].get("chromium"), expected),
file=sys.stderr)
return 1
if info["tag"] != tag:
print("BUILDINFO tag 不一致", file=sys.stderr)
return 1
return 0
if __name__ == "__main__":
raise SystemExit(main(sys.argv))