Files
codex-app-server/chv-guest/chv-browser.py
T
host 1c8fc3f7c8 对齐 Muse P4:浏览器完全对齐(CDP broker 单元外 + a11y-tree-only + 确定性分类器)
- chv-guest/chv-cdp-broker.py(新):单元外 CDP broker,用户 chv-browser,
  独家 chromium.launch(headless=True, args=LAUNCH_ARGS);启动参数白名单
  无 --remote-debugging-port、无 devtools;导航前 URL 校验 + 拦截名单;
  快照恒带 untrusted_input 与 injection_flags;高风险表单在页时 open
  即 ask 入队;观测到导航 POST 自动暂停;命中拦截规则的下载取消 + 暂停
  + ask;全部回包与错误经 sanitize_error + response_leaks 检查。
- chv-guest/chv-browser.py(P2 版重构):改为 broker 客户端,不再直连
  Playwright(本文件无 playwright import),保留 URL 校验 + 快照截断
  作为第二层防线;暂停状态与 broker 同步。
- chv-guest/chv_browser_guard.py(新):纯 stdlib 共享规则——validate_url、
  拦截名单加载/匹配、快照截断、错误消毒(去 HTML、截断 200 字符、凭据形
  key=value 与 sk- 形 token 打码)、注入启发式(中英文各 6 条)、表单风险
  扫描、下载扫描(可执行扩展名)、文件型 ask 队列(pending/allowed/denied,
  与 P3 ApprovalQueue 同语义)、启动参数与回包泄露检查、脚本注入面
  禁止清单(FORBIDDEN_PAGE_ATTRS/FORBIDDEN_OPS)。
- chv-guest/browser-blocklist.txt(新):静态拦截名单;首版只有 RFC 2606
  .test 自测条目,生产条目由运维构建时填入,无在线更新。
- chv-guest/build.sh/buildinfo.py:P2 三脚本 + P4 三文件纳入镜像与
  buildinfo;新增 chv-cdp-broker.service 与 /run/chv/ask-queue tmpfiles。
- docs/chv-muse-p4-gap.md(新):现状 vs Muse 官方要求差距表、改动、
  诚实边界、P2 合入约定、真机待验证清单(round 12)。
- docs/chv-production-readiness.md:补 §15(P4 一节;编号合入时若与
  P2 的 §15 撞,顺延)。
- cloud/tests/test_chv_muse_p4.py(新,36 项):guard 单元、AST 钉住
  禁止属性、假 Playwright broker 测试、假 broker agent 测试、真 Unix
  socket 联调、buildinfo/build 干跑断言;含否定测试(evaluate 被拒、
  DOM 外泄被拒、DevTools 不可达、私有地址被拒、高风险表单被拦、
  注入文本被标注)。

测试:P4 新测试 36/36;全量 cloud 套件 1903 项,两次连续全过
(skipped=8)。附记:第一次全量跑出 1 个失败但输出未保留、后两次
均未复现,疑为时序抖动,未追认。
真机验证未做:排队等 round-11/第三棒释放 100.65.51.33,清单见 gap
表 §5。本地提交,未推未合未部署。
2026-11-06 22:36:56 +00:00

306 lines
11 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
"""chv-browser:浏览器子代理(客机侧、单元外独立进程)。
对齐 Muse P4(见 docs/chv-muse-p4-gap.md):本文件源自 P2 的
chv-browser.py(c61484a),P4 在此基础上重构——子代理不再直连
Playwright/Chromium,Chromium 的所有权在单元外 CDP broker
(chv-cdp-broker.py)手里;本进程只是 broker 的客户端。
子代理只向单元返回页面无障碍树快照(Playwright
accessibility.snapshot,经 broker 取回),不见原始 DOM,不能
在页面上下文跑 JS,不暴露交互操作,不开 DevTools。
操作(Unix socket /run/chv/browser.sock,JSON 行):
open {url} -> 经 broker 导航并返回 {title, url, a11y,
truncated, untrusted_input, injection_flags,
form_risk}
snapshot {} -> 当前页同上
screenshot {} -> 截图落盘,返回 {path}
close {} -> 关当前页
pause {} -> 暂停(用户接管/填表/自动暂停的统一状态)
resume {} -> 解除暂停
status {} -> {paused, url, form_risk}
list_asks {} -> 待审批 ask 列表
resolve_ask {ask_id, decision} -> 写回 allow/denied
ping {} -> {"ok": true}
暂停时除 ping/resume/status/list_asks/resolve_ask 外一切操作
拒绝——用户接管或凭证注入填表时,代理完全不能行动。
URL 校验、快照截断、错误消毒、禁用操作表都在
chv_browser_guard.py(纯函数模块,两脚本共用)。本层再做一次
validate_url 与 truncate_a11y(纵深防御),回包先过泄露检查。
只用标准库。运行身份:系统用户 chv-browser,socket 0600
(broker 以 root 连,不受模式限制)。
"""
import importlib.util
import json
import os
import socket
import sys
BROWSER_SOCK = "/run/chv/browser.sock"
CDP_SOCK = "/run/chv/cdp-broker.sock"
MAX_REQUEST_BYTES = 65536
_GUARD = None
def _load_guard():
"""加载同目录的 chv_browser_guard(纯函数模块)。"""
global _GUARD
if _GUARD is not None:
return _GUARD
here = os.path.dirname(os.path.abspath(__file__))
path = os.path.join(here, "chv_browser_guard.py")
spec = importlib.util.spec_from_file_location(
"chv_browser_guard", path)
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
_GUARD = module
return module
class BrowserAgent:
"""浏览器子代理:CDP broker 的客户端。broker_call 供单测注入
假 broker(收到 req dict 返回 resp dict);正常运行时走
Unix socket 直连 broker。"""
def __init__(self, cdp_sock_path=CDP_SOCK, broker_call=None):
self._guard = _load_guard()
self._cdp_sock_path = cdp_sock_path
self._broker_call = broker_call
self._paused = False
def _call(self, req):
if self._broker_call is not None:
return self._broker_call(req)
try:
conn = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
conn.settimeout(120)
conn.connect(self._cdp_sock_path)
except OSError as e:
return {"ok": False,
"error": "CDP broker 未就绪:%s" % e}
try:
conn.sendall((json.dumps(req, ensure_ascii=False)
+ "\n").encode())
data = b""
while len(data) < MAX_REQUEST_BYTES:
chunk = conn.recv(4096)
if not chunk:
break
data += chunk
if data.endswith(b"\n"):
break
except OSError as e:
return {"ok": False,
"error": "CDP broker 通信失败:%s" % e}
finally:
conn.close()
try:
resp = json.loads(data.decode())
except (ValueError, UnicodeDecodeError):
return {"ok": False, "error": "CDP broker 回包不是 JSON"}
if not isinstance(resp, dict) or "ok" not in resp:
return {"ok": False, "error": "CDP broker 回包格式不对"}
return resp
def _sync_paused(self, resp):
"""从回包同步暂停镜像状态(broker 暂停时本层同样拒绝)。"""
if isinstance(resp, dict) and "已暂停" in str(
resp.get("error", "")):
self._paused = True
return resp
def _blocked_while_paused(self):
return {"ok": False,
"error": "浏览器已暂停(用户接管/填表/自动暂停)"}
def open(self, url):
if self._paused:
return self._blocked_while_paused()
ok, err = self._guard.validate_url(url)
if not ok:
return {"ok": False, "error": err}
resp = self._call({"op": "open", "url": url})
if resp.get("ok") and isinstance(resp.get("a11y"), dict):
tree, truncated = self._guard.truncate_a11y(resp["a11y"])
resp = dict(resp)
resp["a11y"] = tree
resp["truncated"] = bool(resp.get("truncated")
or truncated)
return self._sync_paused(resp)
def snapshot(self):
if self._paused:
return self._blocked_while_paused()
resp = self._call({"op": "snapshot"})
if resp.get("ok") and isinstance(resp.get("a11y"), dict):
tree, truncated = self._guard.truncate_a11y(resp["a11y"])
resp = dict(resp)
resp["a11y"] = tree
resp["truncated"] = bool(resp.get("truncated")
or truncated)
return self._sync_paused(resp)
def screenshot(self):
if self._paused:
return self._blocked_while_paused()
return self._sync_paused(self._call({"op": "screenshot"}))
def close(self):
if self._paused:
return self._blocked_while_paused()
resp = self._call({"op": "close"})
return self._sync_paused(resp)
def pause(self):
resp = self._call({"op": "pause"})
if resp.get("ok"):
self._paused = True
return resp
def resume(self):
resp = self._call({"op": "resume"})
if resp.get("ok"):
self._paused = False
return resp
def status(self):
resp = self._call({"op": "status"})
if isinstance(resp, dict) and "paused" in resp:
self._paused = bool(resp["paused"])
return resp
def list_asks(self):
return self._call({"op": "list_asks"})
def resolve_ask(self, ask_id, decision):
resp = self._call({"op": "resolve_ask", "ask_id": ask_id,
"decision": decision})
if resp.get("ok") and resp.get("decision") == "allowed":
self._paused = False
return resp
def handle_request(agent, req):
"""处理一个请求 dict,返回响应 dict(纯逻辑,可单测)。"""
guard = _load_guard()
if not isinstance(req, dict):
return {"ok": False, "error": "请求须是 JSON 对象"}
op = req.get("op")
if op in guard.FORBIDDEN_OPS:
return {"ok": False,
"error": "操作 %r 不暴露(无 JS/无原始 DOM/无交互)"
% op}
if op == "ping":
return {"ok": True, "browser": True}
if op == "open":
return agent.open(req.get("url"))
if op == "snapshot":
return agent.snapshot()
if op == "screenshot":
return agent.screenshot()
if op == "close":
return agent.close()
if op == "pause":
return agent.pause()
if op == "resume":
return agent.resume()
if op == "status":
return agent.status()
if op == "list_asks":
return agent.list_asks()
if op == "resolve_ask":
return agent.resolve_ask(req.get("ask_id"),
req.get("decision"))
return {"ok": False,
"error": "未知操作:%r(白名单:open/snapshot/screenshot/"
"close/pause/resume/status/list_asks/resolve_ask/"
"ping)" % (op,)}
def _handle_conn(agent, conn):
"""一个连接一请求一响应;回包先过泄露检查,不过即换通用错;
错误信息过消毒,绝不把页面原文原样放进回包。"""
guard = _load_guard()
conn.settimeout(120)
data = b""
while len(data) < MAX_REQUEST_BYTES:
chunk = conn.recv(4096)
if not chunk:
break
data += chunk
if data.endswith(b"\n"):
break
try:
req = json.loads(data.decode())
except (ValueError, UnicodeDecodeError):
resp = {"ok": False, "error": "请求不是合法 JSON"}
else:
try:
resp = handle_request(agent, req)
except Exception as e:
resp = {"ok": False,
"error": guard.sanitize_error(e)}
if guard.response_leaks(resp):
resp = {"ok": False, "error": "响应泄露检查未通过(已拦截)"}
conn.sendall((json.dumps(resp, ensure_ascii=False) + "\n").encode())
def serve(sock_path=BROWSER_SOCK, cdp_sock_path=CDP_SOCK):
"""监听 Unix socket,逐连接处理。socket 0600。建不起来即抛错,
不要静默带病跑。"""
if os.path.exists(sock_path):
os.remove(sock_path)
os.makedirs(os.path.dirname(sock_path), exist_ok=True)
srv = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
srv.bind(sock_path)
srv.listen(16)
os.chmod(sock_path, 0o600)
print("chv-browser: 监听 %s" % sock_path, file=sys.stderr, flush=True)
agent = BrowserAgent(cdp_sock_path=cdp_sock_path)
try:
while True:
try:
conn, _ = srv.accept()
except OSError:
continue
try:
_handle_conn(agent, conn)
except OSError as e:
print("chv-browser: 连接处理异常:%s"
% _load_guard().sanitize_error(e),
file=sys.stderr, flush=True)
finally:
try:
conn.close()
except OSError:
pass
finally:
pass
def main(argv):
sock_path = BROWSER_SOCK
cdp_sock_path = CDP_SOCK
i = 0
while i < len(argv):
if argv[i] == "--socket" and i + 1 < len(argv):
sock_path = argv[i + 1]
i += 2
elif argv[i] == "--cdp-socket" and i + 1 < len(argv):
cdp_sock_path = argv[i + 1]
i += 2
else:
print("chv-browser: 未知参数:%s" % argv[i], file=sys.stderr)
return 2
serve(sock_path, cdp_sock_path)
return 0
if __name__ == "__main__":
raise SystemExit(main(sys.argv[1:]))