host
3a56f83114
- 默认 auto 只走免费链 searxng -> duckduckgo；即使环境里有 付费 key 也不调用 Perplexity/Exa/Tavily/Brave，SearXNG 失败也不回落付费，默认使用零付费花费。 - 付费后端代码/测试/文档全部保留；显式 pin（tavily/exa/ perplexity/brave）仍照常调用，是有意覆盖不是默认。 - 解冻开关 WEBSEARCH_ENABLE_PAID，仅精确值 "1" 才恢复旧链 （perplexity/exa/tavily/brave/searxng/duckduckgo），默认关； 开关经 worker search_env 透传进 MCP config env。 - HttpClient 超时/DNS 失败改报显式错误（timeout after Ns / URL error），绝不把超时写成“无结果”。 - SearXNG 默认参数核实：代码无 SEARXNG_URL 硬编码默认值； SEARXNG_ENGINES 默认 bing,360search 已在基线；WEBSEARCH_TIMEOUT 默认 20 秒。主机 env 实测仅 SEARXNG_URL=http://searx.diante.me 一行，故默认 pin 生效；文档 https 漂移改回 http（主机 nginx 仅听 80、无 443 vhost，https 在 TLS 层即失败）。 - 旧测试更新原因：test_websearch_mcp 原断言默认 auto 为 perplexity 优先，与新冻结语义直接冲突，故改为断言冻结后 的 searxng -> duckduckgo 回退 + 不泄漏 key；旧 perplexity -> exa 回退断言移至解冻开关测试（WEBSEARCH_ENABLE_PAID=1 下）。 未删断言、未加 skip、未放宽门禁。 - 文档另删 WEBSEARCH_PROVIDERS 说法：代码从未实现该变量。 - 未推、未建 PR、未合并、未部署、未改主机 env/nginx/filter/ 证书、未做付费后端 live 验证、未创建生产任务。
457 lines
20 KiB
Python
457 lines
20 KiB
Python
"""Worker wiring for web search MCP: tenant seeding + egress filter.
|
|
|
|
No Docker, no network: _tenant_dirs runs against temp dirs, and the
|
|
egress check only reads the repo filter file.
|
|
"""
|
|
|
|
import os
|
|
import re
|
|
import sys
|
|
import tempfile
|
|
import unittest
|
|
from pathlib import Path
|
|
|
|
try:
|
|
from cloud.server import init_db
|
|
from cloud.worker import Worker
|
|
except ImportError:
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
|
|
from cloud.server import init_db
|
|
from cloud.worker import Worker
|
|
|
|
REPO_ROOT = Path(__file__).resolve().parents[2]
|
|
|
|
|
|
class WorkerWebsearchTestCase(unittest.TestCase):
|
|
def setUp(self):
|
|
self.tmp = tempfile.TemporaryDirectory()
|
|
self.db_path = os.path.join(self.tmp.name, "control.db")
|
|
init_db(self.db_path)
|
|
self.template_home = os.path.join(self.tmp.name, "tpl-home")
|
|
os.makedirs(self.template_home)
|
|
open(os.path.join(self.template_home, "config.toml"),
|
|
"w").write('[model_provider.xcmapi]\n'
|
|
'base_url="https://xcmapi.org/v1"\n')
|
|
self.template_repo = os.path.join(self.tmp.name, "tpl-repo")
|
|
os.makedirs(os.path.join(self.template_repo, ".git"))
|
|
open(os.path.join(self.template_repo, "sample.py"),
|
|
"w").write("def add(a, b):\n return a + b\n")
|
|
|
|
def tearDown(self):
|
|
self.tmp.cleanup()
|
|
|
|
def _worker(self, **kwargs):
|
|
kwargs.setdefault("env", {"XCM_API_KEY": "test-placeholder"})
|
|
kwargs.setdefault("tenants_root",
|
|
os.path.join(self.tmp.name, "tenants"))
|
|
kwargs.setdefault("tenant_template_home", self.template_home)
|
|
kwargs.setdefault("tenant_template_repo", self.template_repo)
|
|
kwargs.setdefault("tenant_isolation", True)
|
|
return Worker(self.db_path, "/fake/host.py", **kwargs)
|
|
|
|
def test_flag_off_is_old_behaviour(self):
|
|
worker = self._worker()
|
|
self.assertFalse(worker.websearch_mcp)
|
|
dirs = worker._tenant_dirs("projA")
|
|
config = open(os.path.join(dirs["codex_home"],
|
|
"config.toml")).read()
|
|
self.assertNotIn("[mcp_servers.websearch]", config)
|
|
self.assertFalse(os.path.exists(
|
|
os.path.join(dirs["codex_home"], "websearch_mcp.py")))
|
|
|
|
def test_flag_on_seeds_container_path_and_scripts(self):
|
|
worker = self._worker(websearch_mcp=True)
|
|
dirs = worker._tenant_dirs("projA")
|
|
home = dirs["codex_home"]
|
|
config = open(os.path.join(home, "config.toml")).read()
|
|
self.assertIn("[mcp_servers.websearch]", config)
|
|
# Container path, not the host temp path: this config is
|
|
# read inside the task container, where the tenant home is
|
|
# mounted at /var/lib/codex-app-server/codex-home.
|
|
self.assertIn("/var/lib/codex-app-server/codex-home/"
|
|
"websearch_mcp.py", config)
|
|
self.assertNotIn(self.tmp.name, config)
|
|
self.assertTrue(os.path.exists(
|
|
os.path.join(home, "websearch.py")))
|
|
self.assertTrue(os.path.exists(
|
|
os.path.join(home, "websearch_mcp.py")))
|
|
# The copied MCP script is the real one (not a stub).
|
|
script = open(os.path.join(home, "websearch_mcp.py")).read()
|
|
self.assertIn("web_search", script)
|
|
self.assertIn("web_fetch", script)
|
|
|
|
def test_old_tenant_merges_on_next_task(self):
|
|
worker = self._worker()
|
|
dirs = worker._tenant_dirs("projA")
|
|
config_path = os.path.join(dirs["codex_home"], "config.toml")
|
|
self.assertNotIn("[mcp_servers.websearch]",
|
|
open(config_path).read())
|
|
# Flag flips on later (deploy enables it): next task's
|
|
# _tenant_dirs must merge, not require a new project.
|
|
worker2 = self._worker(websearch_mcp=True)
|
|
worker2._tenant_dirs("projA")
|
|
config = open(config_path).read()
|
|
self.assertIn("[mcp_servers.websearch]", config)
|
|
self.assertIn("xcmapi.org", config)
|
|
self.assertEqual(config.count("[mcp_servers.websearch]"), 1)
|
|
# Third call stays idempotent.
|
|
worker2._tenant_dirs("projA")
|
|
config = open(config_path).read()
|
|
self.assertEqual(config.count("[mcp_servers.websearch]"), 1)
|
|
|
|
|
|
class DockerEnvTestCase(unittest.TestCase):
|
|
def setUp(self):
|
|
self.tmp = tempfile.TemporaryDirectory()
|
|
self.db_path = os.path.join(self.tmp.name, "control.db")
|
|
init_db(self.db_path)
|
|
|
|
def tearDown(self):
|
|
self.tmp.cleanup()
|
|
|
|
def _docker_context(self):
|
|
worker = Worker(self.db_path, "/fake/host.py",
|
|
env={"XCM_API_KEY": "test-placeholder"},
|
|
tenant_isolation=False, egress_proxy_port=None)
|
|
return worker._docker_task_context({"project_id": "projA"})
|
|
|
|
def test_searxng_url_passes_into_container_env(self):
|
|
from unittest import mock
|
|
with mock.patch.dict(os.environ,
|
|
{"SEARXNG_URL": "http://searx.diante.me"}):
|
|
ok, _, _, env, err = self._docker_context()
|
|
self.assertTrue(ok)
|
|
self.assertIsNone(err)
|
|
self.assertEqual(env.get("SEARXNG_URL"), "http://searx.diante.me")
|
|
|
|
def test_paid_unfreeze_switch_passes_into_container_env(self):
|
|
# The freeze switch must reach the MCP process (which reads
|
|
# only config.toml env, never worker env); without this
|
|
# passthrough, WEBSEARCH_ENABLE_PAID=1 on the host would
|
|
# silently leave default auto frozen inside containers.
|
|
from unittest import mock
|
|
with mock.patch.dict(os.environ,
|
|
{"WEBSEARCH_ENABLE_PAID": "1"}):
|
|
ok, _, _, env, err = self._docker_context()
|
|
self.assertTrue(ok)
|
|
self.assertIsNone(err)
|
|
self.assertEqual(env.get("WEBSEARCH_ENABLE_PAID"), "1")
|
|
|
|
def test_no_search_env_means_no_extra_env(self):
|
|
from unittest import mock
|
|
with mock.patch.dict(os.environ, {}, clear=False):
|
|
for k in ("SEARXNG_URL", "WEBSEARCH_ENABLE_PAID",
|
|
"PERPLEXITY_API_KEY", "EXA_API_KEY",
|
|
"TAVILY_API_KEY", "BRAVE_API_KEY"):
|
|
os.environ.pop(k, None)
|
|
ok, _, _, env, err = self._docker_context()
|
|
self.assertTrue(ok)
|
|
self.assertIsNone(err)
|
|
self.assertIsNone(env)
|
|
|
|
|
|
class EgressFilterTestCase(unittest.TestCase):
|
|
def test_search_domains_present_in_basic_form(self):
|
|
lines = open(REPO_ROOT / "deploy" / "egress" /
|
|
"tinyproxy-filter").read().splitlines()
|
|
entries = [ln for ln in lines
|
|
if ln and not ln.startswith("#")]
|
|
# No extended-regex syntax in any entry: + ? | and bare
|
|
# parens are literal in BASIC and would break the allowlist.
|
|
for entry in entries:
|
|
self.assertNotIn("+", entry)
|
|
self.assertNotIn("?", entry)
|
|
self.assertNotIn("|", entry)
|
|
self.assertNotIn("(", entry.replace("\\(", ""))
|
|
self.assertNotIn(")", entry.replace("\\)", ""))
|
|
expected = [
|
|
r"^\(.*\.\)*perplexity\.ai$",
|
|
r"^\(.*\.\)*exa\.ai$",
|
|
r"^\(.*\.\)*tavily\.com$",
|
|
r"^\(.*\.\)*search\.brave\.com$",
|
|
r"^\(.*\.\)*duckduckgo\.com$",
|
|
r"^searx\.diante\.me$",
|
|
]
|
|
for want in expected:
|
|
self.assertIn(want, entries, "missing filter entry: %s" % want)
|
|
|
|
def test_platform_browser_programming_domains(self):
|
|
lines = open(REPO_ROOT / "deploy" / "egress" /
|
|
"tinyproxy-filter").read().splitlines()
|
|
entries = [ln for ln in lines
|
|
if ln and not ln.startswith("#")]
|
|
expected = [
|
|
r"^\(.*\.\)*python\.org$",
|
|
r"^\(.*\.\)*nodejs\.org$",
|
|
r"^\(.*\.\)*go\.dev$",
|
|
r"^\(.*\.\)*pkg\.go\.dev$",
|
|
r"^\(.*\.\)*rust-lang\.org$",
|
|
r"^\(.*\.\)*developer\.mozilla\.org$",
|
|
r"^\(.*\.\)*crates\.io$",
|
|
r"^\(.*\.\)*stackoverflow\.com$",
|
|
r"^\(.*\.\)*cve\.mitre\.org$",
|
|
r"^\(.*\.\)*nvd\.nist\.gov$",
|
|
]
|
|
for want in expected:
|
|
self.assertIn(want, entries, "missing filter entry: %s" % want)
|
|
# Already-present programming domains are NOT duplicated.
|
|
for already in (r"^\(.*\.\)*github\.com$",
|
|
r"^\(.*\.\)*pypi\.org$",
|
|
r"^\(.*\.\)*npmjs\.org$"):
|
|
self.assertEqual(entries.count(already), 1,
|
|
"duplicated filter entry: %s" % already)
|
|
# Control-plane guard: searx stays exact-only, and no
|
|
# diante.me wildcard may appear (it would open api.diante.me).
|
|
self.assertIn(r"^searx\.diante\.me$", entries)
|
|
self.assertNotIn(r"^\(.*\.\)*diante\.me$", entries)
|
|
|
|
def test_platform_browser_filter_matching_semantics(self):
|
|
# Translate POSIX BASIC group syntax to Python regex and
|
|
# check the subdomain anchoring the comments promise.
|
|
lines = open(REPO_ROOT / "deploy" / "egress" /
|
|
"tinyproxy-filter").read().splitlines()
|
|
entries = [ln for ln in lines
|
|
if ln and not ln.startswith("#")]
|
|
|
|
def matches(domain):
|
|
for entry in entries:
|
|
py = entry.replace("\\(", "(").replace("\\)", ")")
|
|
if re.match(py, domain):
|
|
return True
|
|
return False
|
|
|
|
# Subdomain coverage via the apex rules.
|
|
self.assertTrue(matches("docs.python.org"))
|
|
self.assertTrue(matches("docs.rust-lang.org"))
|
|
self.assertTrue(matches("developer.mozilla.org"))
|
|
self.assertTrue(matches("pkg.go.dev"))
|
|
# Anchoring: lookalikes and suffix tricks must not match.
|
|
self.assertFalse(matches("evilpython.org"))
|
|
self.assertFalse(matches("python.org.evil.com"))
|
|
self.assertFalse(matches("notstackoverflow.com"))
|
|
# Fail-closed: control plane and out-of-scope categories
|
|
# (shopping, social, mail, video) open no rule.
|
|
self.assertFalse(matches("api.diante.me"))
|
|
self.assertFalse(matches("www.amazon.com"))
|
|
self.assertFalse(matches("www.youtube.com"))
|
|
self.assertFalse(matches("mail.google.com"))
|
|
|
|
|
|
class PlaywrightAllowlistWiringTestCase(unittest.TestCase):
|
|
"""BROWSER_ALLOWED_HOSTS: worker env -> MCP env wiring.
|
|
|
|
No Docker, no network, no real Chromium: _docker_task_context
|
|
runs against temp tenant dirs with a fake executor whose
|
|
ensure_network always succeeds, and the MCP-side enforcement
|
|
is checked through _allowed_hosts/_check_allowed_url (the same
|
|
entry points Browser.navigate uses), not a launched browser.
|
|
Values here are test placeholders, never real credentials.
|
|
"""
|
|
|
|
def setUp(self):
|
|
self.tmp = tempfile.TemporaryDirectory()
|
|
self.db_path = os.path.join(self.tmp.name, "control.db")
|
|
init_db(self.db_path)
|
|
self.template_home = os.path.join(self.tmp.name, "tpl-home")
|
|
os.makedirs(self.template_home)
|
|
open(os.path.join(self.template_home, "config.toml"),
|
|
"w").write('[model_provider.xcmapi]\n'
|
|
'base_url="https://xcmapi.org/v1"\n')
|
|
self.template_repo = os.path.join(self.tmp.name, "tpl-repo")
|
|
os.makedirs(os.path.join(self.template_repo, ".git"))
|
|
open(os.path.join(self.template_repo, "sample.py"),
|
|
"w").write("def add(a, b):\n return a + b\n")
|
|
|
|
def tearDown(self):
|
|
self.tmp.cleanup()
|
|
|
|
def _worker(self):
|
|
from types import SimpleNamespace
|
|
fake_executor = SimpleNamespace(
|
|
ensure_network=lambda network: True)
|
|
return Worker(self.db_path, "/fake/host.py",
|
|
env={"XCM_API_KEY": "test-placeholder"},
|
|
tenants_root=os.path.join(self.tmp.name,
|
|
"tenants"),
|
|
tenant_template_home=self.template_home,
|
|
tenant_template_repo=self.template_repo,
|
|
tenant_isolation=True, playwright_mcp=True,
|
|
executor=fake_executor)
|
|
|
|
def _context(self, worker):
|
|
return worker._docker_task_context({"project_id": "projA"})
|
|
|
|
def _config(self, worker):
|
|
home = worker._tenant_dirs("projA")["codex_home"]
|
|
return open(os.path.join(home, "config.toml")).read()
|
|
|
|
def _env_block(self, config):
|
|
import json
|
|
block = {}
|
|
in_block = False
|
|
for line in config.splitlines():
|
|
stripped = line.strip()
|
|
if stripped == "[mcp_servers.playwright.env]":
|
|
in_block = True
|
|
continue
|
|
if in_block:
|
|
if stripped.startswith("["):
|
|
break
|
|
if "=" in stripped:
|
|
key, raw = stripped.split("=", 1)
|
|
block[key.strip()] = json.loads(raw.strip())
|
|
return block
|
|
|
|
def _drop_ambient(self):
|
|
# mock.patch.dict only overlays: drop any search/allowlist
|
|
# keys the ambient environment may carry so each case sees
|
|
# exactly the env it declares (pops are restored on exit).
|
|
for key in ("SEARXNG_URL", "SEARXNG_ENGINES",
|
|
"PERPLEXITY_API_KEY", "EXA_API_KEY",
|
|
"TAVILY_API_KEY", "BRAVE_API_KEY"):
|
|
os.environ.pop(key, None)
|
|
|
|
def test_switch_off_passes_no_variable(self):
|
|
from unittest import mock
|
|
worker = self._worker()
|
|
with mock.patch.dict(os.environ, {}, clear=False):
|
|
os.environ.pop("BROWSER_ALLOWED_HOSTS", None)
|
|
self._drop_ambient()
|
|
ok, _, _, env, err = self._context(worker)
|
|
self.assertTrue(ok)
|
|
self.assertIsNone(err)
|
|
block = self._env_block(self._config(worker))
|
|
self.assertEqual(block.get("PLAYWRIGHT_BROWSERS_PATH"),
|
|
"/opt/ms-playwright")
|
|
self.assertNotIn("BROWSER_ALLOWED_HOSTS", block)
|
|
# The allowlist never reaches the container env either:
|
|
# the config.toml MCP env block is the only channel.
|
|
self.assertIsNone(env)
|
|
|
|
def test_switch_on_reaches_mcp_env(self):
|
|
from unittest import mock
|
|
worker = self._worker()
|
|
with mock.patch.dict(
|
|
os.environ,
|
|
{"BROWSER_ALLOWED_HOSTS": "example.com, .python.org"}):
|
|
self._drop_ambient()
|
|
ok, _, _, env, err = self._context(worker)
|
|
self.assertTrue(ok)
|
|
self.assertIsNone(err)
|
|
block = self._env_block(self._config(worker))
|
|
# Verbatim, not normalised here: normalisation happens
|
|
# at read time in _allowed_hosts.
|
|
self.assertEqual(block.get("BROWSER_ALLOWED_HOSTS"),
|
|
"example.com, .python.org")
|
|
self.assertEqual(block.get("PLAYWRIGHT_BROWSERS_PATH"),
|
|
"/opt/ms-playwright")
|
|
self.assertIsNone(env)
|
|
|
|
def test_empty_value_is_never_written(self):
|
|
from unittest import mock
|
|
worker = self._worker()
|
|
with mock.patch.dict(os.environ, {"BROWSER_ALLOWED_HOSTS": ""}):
|
|
ok, _, _, _, err = self._context(worker)
|
|
self.assertTrue(ok)
|
|
self.assertIsNone(err)
|
|
block = self._env_block(self._config(worker))
|
|
self.assertNotIn("BROWSER_ALLOWED_HOSTS", block)
|
|
|
|
def test_old_tenant_merge_is_idempotent(self):
|
|
from unittest import mock
|
|
worker = self._worker()
|
|
# Old tenant: seeded before the wiring existed, with a
|
|
# stale env block and a section after it.
|
|
home = worker._tenant_dirs("projA")["codex_home"]
|
|
config_path = os.path.join(home, "config.toml")
|
|
with open(config_path, "a", encoding="utf-8") as fh:
|
|
fh.write("\n[mcp_servers.playwright.env]\n"
|
|
'BROWSER_ALLOWED_HOSTS = "stale.example"\n'
|
|
"\n[other]\nkey = 1\n")
|
|
with mock.patch.dict(
|
|
os.environ,
|
|
{"BROWSER_ALLOWED_HOSTS": "example.com"}):
|
|
ok, _, _, _, err = self._context(worker)
|
|
self.assertTrue(ok)
|
|
self.assertIsNone(err)
|
|
config = open(config_path).read()
|
|
self.assertEqual(config.count("[mcp_servers.playwright.env]"), 1)
|
|
self.assertIn("[other]\nkey = 1\n", config)
|
|
self.assertEqual(
|
|
self._env_block(config).get("BROWSER_ALLOWED_HOSTS"),
|
|
"example.com")
|
|
# Second prep with the same env rewrites nothing.
|
|
before = open(config_path, "rb").read()
|
|
mtime_before = os.stat(config_path).st_mtime_ns
|
|
with mock.patch.dict(
|
|
os.environ,
|
|
{"BROWSER_ALLOWED_HOSTS": "example.com"}):
|
|
ok, _, _, _, err = self._context(worker)
|
|
self.assertTrue(ok)
|
|
self.assertIsNone(err)
|
|
self.assertEqual(open(config_path, "rb").read(), before)
|
|
self.assertEqual(os.stat(config_path).st_mtime_ns, mtime_before)
|
|
|
|
def test_ensure_playwright_mcp_env_noop_when_identical(self):
|
|
from cloud.playwright_browser import ensure_playwright_mcp_env
|
|
home = os.path.join(self.tmp.name, "home")
|
|
os.makedirs(home)
|
|
config_path = os.path.join(home, "config.toml")
|
|
open(config_path, "w").write(
|
|
'[model_provider.xcmapi]\n'
|
|
'base_url="https://xcmapi.org/v1"\n')
|
|
env = {"PLAYWRIGHT_BROWSERS_PATH": "/opt/ms-playwright",
|
|
"BROWSER_ALLOWED_HOSTS": "example.com"}
|
|
self.assertTrue(ensure_playwright_mcp_env(home, env))
|
|
before = open(config_path, "rb").read()
|
|
mtime_before = os.stat(config_path).st_mtime_ns
|
|
self.assertFalse(ensure_playwright_mcp_env(home, env))
|
|
self.assertEqual(open(config_path, "rb").read(), before)
|
|
self.assertEqual(os.stat(config_path).st_mtime_ns, mtime_before)
|
|
# A changed value still rewrites, in place, once.
|
|
env2 = dict(env, BROWSER_ALLOWED_HOSTS="other.example")
|
|
self.assertTrue(ensure_playwright_mcp_env(home, env2))
|
|
config = open(config_path).read()
|
|
self.assertEqual(config.count("[mcp_servers.playwright.env]"), 1)
|
|
self.assertEqual(
|
|
self._env_block(config).get("BROWSER_ALLOWED_HOSTS"),
|
|
"other.example")
|
|
|
|
def test_wiring_semantics_allowlist_only_after_wiring(self):
|
|
from unittest import mock
|
|
from cloud.playwright_browser import (
|
|
BrowserError, _allowed_hosts, _check_allowed_url)
|
|
worker = self._worker()
|
|
# Switch off: the MCP env has no variable, so no limit.
|
|
with mock.patch.dict(os.environ, {}, clear=False):
|
|
os.environ.pop("BROWSER_ALLOWED_HOSTS", None)
|
|
self._drop_ambient()
|
|
ok, _, _, _, err = self._context(worker)
|
|
self.assertTrue(ok)
|
|
self.assertIsNone(err)
|
|
block = self._env_block(self._config(worker))
|
|
self.assertNotIn("BROWSER_ALLOWED_HOSTS", block)
|
|
with mock.patch.dict(os.environ, {}, clear=False):
|
|
os.environ.pop("BROWSER_ALLOWED_HOSTS", None)
|
|
self.assertIsNone(_allowed_hosts())
|
|
_check_allowed_url("https://anything.example")
|
|
# Switch on: the written block, applied as MCP process
|
|
# env, makes the allowlist enforce.
|
|
with mock.patch.dict(
|
|
os.environ,
|
|
{"BROWSER_ALLOWED_HOSTS": "example.com, .python.org"}):
|
|
ok, _, _, _, err = self._context(worker)
|
|
self.assertTrue(ok)
|
|
block = self._env_block(self._config(worker))
|
|
self.assertIn("BROWSER_ALLOWED_HOSTS", block)
|
|
with mock.patch.dict(os.environ, block):
|
|
self.assertEqual(_allowed_hosts(),
|
|
["example.com", ".python.org"])
|
|
_check_allowed_url("https://docs.python.org")
|
|
with self.assertRaises(BrowserError):
|
|
_check_allowed_url("https://evil.com")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|