sysadmin
6b675f5c83
Address PR #701 request-changes-class defects: 1. Fixed messages only — never embed HTTP bodies, Keychain, or exception text in tool results or daemon logs; sanitization fails closed. 2. Narrow Tool.run boundary wraps original success path; re-raises UrlElicitationRequiredError; install is idempotent. 3. No RuntimeError substring heuristics; only typed client failures are classified as auth/authz/network/config. 4. Central classify_http_status — every HTTP 403 is GiteaAuthzError. Regressions cover adversarial secrets, stdio survival, elicitation, parser RuntimeError, generic 403, repeated install, profiles, provenance. Closes #699
427 lines
18 KiB
Python
427 lines
18 KiB
Python
"""Structured MCP auth errors and stdio transport survival (#699 / PR #701).
|
|
|
|
Covers original AC plus reviewer-ratified regressions:
|
|
|
|
1. Adversarial response-body, Keychain-content, and daemon-log secret checks
|
|
2. Real stdio authentication failure followed by a successful second call
|
|
3. UrlElicitationRequiredError framework re-raise behavior
|
|
4. Unexpected parser RuntimeError is not authentication
|
|
5. Generic HTTP 403 is authorization (not internal)
|
|
6. Repeated install/import is idempotent
|
|
7. Author and reconciler profiles
|
|
8. Native provenance non-bypass
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import io
|
|
import json
|
|
import os
|
|
import subprocess
|
|
import sys
|
|
import tempfile
|
|
import textwrap
|
|
import unittest
|
|
import urllib.error
|
|
from unittest.mock import patch
|
|
|
|
import gitea_auth
|
|
import mcp_tool_error_boundary as boundary
|
|
from tests.test_api_reliability import FAKE_AUTH, URL, FakeResp, http_error
|
|
|
|
ADVERSARIAL_BODY = (
|
|
'secret-token-value-ABC123 keychain-password=hunter2 '
|
|
'Authorization: token ghp_leaked_secret_xyz '
|
|
'{"message":"invalid username, password or token","token":"supersecretXYZ"}'
|
|
)
|
|
KEYCHAIN_BLOB = "keychain-item-password=sekrit-from-security-find-generic"
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# api_request / HTTP classification
|
|
# ---------------------------------------------------------------------------
|
|
class TestHttpClassification(unittest.TestCase):
|
|
@patch("gitea_auth.urllib.request.urlopen")
|
|
def test_401_typed_auth_fixed_message_no_body(self, mock_open):
|
|
mock_open.side_effect = http_error(401, ADVERSARIAL_BODY)
|
|
with self.assertRaises(gitea_auth.GiteaAuthError) as ctx:
|
|
gitea_auth.api_request("GET", URL, FAKE_AUTH)
|
|
exc = ctx.exception
|
|
self.assertEqual(exc.reason_code, "auth_invalid_token")
|
|
self.assertEqual(exc.error_class, "authentication")
|
|
self.assertEqual(exc.http_status, 401)
|
|
msg = str(exc)
|
|
self.assertNotIn("supersecretXYZ", msg)
|
|
self.assertNotIn("ghp_leaked", msg)
|
|
self.assertNotIn("hunter2", msg)
|
|
self.assertNotIn(ADVERSARIAL_BODY, msg)
|
|
self.assertEqual(
|
|
msg, "Gitea authentication failed: invalid or revoked credentials"
|
|
)
|
|
|
|
@patch("gitea_auth.urllib.request.urlopen")
|
|
def test_403_scope_is_authz_scope(self, mock_open):
|
|
mock_open.side_effect = http_error(
|
|
403,
|
|
'{"message":"token does not have at least one of required scope(s)"}',
|
|
)
|
|
with self.assertRaises(gitea_auth.GiteaAuthzError) as ctx:
|
|
gitea_auth.api_request("GET", URL, FAKE_AUTH)
|
|
self.assertEqual(ctx.exception.reason_code, "authz_insufficient_scope")
|
|
self.assertEqual(ctx.exception.error_class, "authorization")
|
|
self.assertNotIn("token does not have", str(ctx.exception))
|
|
|
|
@patch("gitea_auth.urllib.request.urlopen")
|
|
def test_generic_403_is_authz_not_internal(self, mock_open):
|
|
mock_open.side_effect = http_error(403, '{"message":"user has no permission"}')
|
|
with self.assertRaises(gitea_auth.GiteaAuthzError) as ctx:
|
|
gitea_auth.api_request("GET", URL, FAKE_AUTH)
|
|
self.assertEqual(ctx.exception.reason_code, "authz_denied")
|
|
self.assertEqual(ctx.exception.error_class, "authorization")
|
|
self.assertNotIsInstance(ctx.exception, gitea_auth.GiteaAuthError)
|
|
self.assertNotIn("user has no permission", str(ctx.exception))
|
|
|
|
@patch("gitea_auth.urllib.request.urlopen")
|
|
def test_network_fixed_message(self, mock_open):
|
|
mock_open.side_effect = TimeoutError("timed out contacting secret.example")
|
|
with self.assertRaises(gitea_auth.GiteaNetworkError) as ctx:
|
|
gitea_auth.api_request("GET", URL, FAKE_AUTH)
|
|
self.assertEqual(str(ctx.exception), "Network error contacting Gitea")
|
|
self.assertNotIn("secret.example", str(ctx.exception))
|
|
|
|
@patch("gitea_auth.urllib.request.urlopen")
|
|
def test_malformed_json_not_auth(self, mock_open):
|
|
mock_open.return_value = FakeResp("not-json{")
|
|
with self.assertRaises(RuntimeError) as ctx:
|
|
gitea_auth.api_request("GET", URL, FAKE_AUTH)
|
|
self.assertNotIsInstance(ctx.exception, gitea_auth.GiteaAuthError)
|
|
self.assertIn("malformed JSON", str(ctx.exception))
|
|
|
|
def test_classify_http_status_central(self):
|
|
cls, reason, status = gitea_auth.classify_http_status(401)
|
|
self.assertIs(cls, gitea_auth.GiteaAuthError)
|
|
self.assertEqual(reason, "auth_invalid_token")
|
|
self.assertEqual(status, 401)
|
|
|
|
cls, reason, status = gitea_auth.classify_http_status(403)
|
|
self.assertIs(cls, gitea_auth.GiteaAuthzError)
|
|
self.assertEqual(reason, "authz_denied")
|
|
|
|
cls, reason, status = gitea_auth.classify_http_status(
|
|
403, body_hint="missing scope write:issue"
|
|
)
|
|
self.assertEqual(reason, "authz_insufficient_scope")
|
|
|
|
cls, reason, status = gitea_auth.classify_http_status(502)
|
|
self.assertIs(cls, gitea_auth.GiteaHttpError)
|
|
self.assertEqual(reason, "upstream_unavailable")
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Boundary classification — no heuristics, no secret leakage
|
|
# ---------------------------------------------------------------------------
|
|
class TestBoundaryClassification(unittest.TestCase):
|
|
def test_auth_payload_fixed_message(self):
|
|
exc = gitea_auth.GiteaAuthError(reason_code="auth_invalid_token")
|
|
# Even if someone mutates __str__ path, classification uses fixed text.
|
|
result = boundary.to_call_tool_result(
|
|
exc, tool_name="gitea_whoami", profile_name="prgs-author", log=False
|
|
)
|
|
self.assertTrue(result.isError)
|
|
p = result.structuredContent
|
|
self.assertEqual(p["reason_code"], "auth_invalid_token")
|
|
self.assertEqual(p["error_class"], "authentication")
|
|
self.assertEqual(p["message"], boundary.fixed_message("auth_invalid_token"))
|
|
self.assertNotIn("supersecret", json.dumps(p))
|
|
self.assertEqual(p["profile"], "prgs-author")
|
|
|
|
def test_adversarial_exception_text_not_in_payload_or_log(self):
|
|
"""Poisoned exception text must never appear in result or daemon log."""
|
|
|
|
class PoisonedAuth(gitea_auth.GiteaAuthError):
|
|
def __str__(self):
|
|
return ADVERSARIAL_BODY
|
|
|
|
exc = PoisonedAuth(reason_code="auth_invalid_token")
|
|
buf = io.StringIO()
|
|
result = boundary.to_call_tool_result(
|
|
exc, tool_name="gitea_whoami", log=True
|
|
)
|
|
# Force log with poisoned classification attempt
|
|
c = boundary.classify_exception(exc)
|
|
boundary.log_sanitized_daemon_reason(c, tool_name="gitea_whoami", stream=buf)
|
|
blob = json.dumps(result.structuredContent) + result.content[0].text + buf.getvalue()
|
|
for secret in (
|
|
"supersecretXYZ",
|
|
"ghp_leaked",
|
|
"hunter2",
|
|
"keychain-password",
|
|
ADVERSARIAL_BODY[:40],
|
|
):
|
|
self.assertNotIn(secret, blob)
|
|
self.assertIn("reason_code=auth_invalid_token", buf.getvalue())
|
|
self.assertNotIn("detail=", buf.getvalue())
|
|
|
|
def test_keychain_content_not_in_daemon_log(self):
|
|
buf = io.StringIO()
|
|
# Simulate a classification that a buggy path might try to put secrets into
|
|
poisoned = {
|
|
"reason_code": "auth_invalid_token",
|
|
"error_class": "authentication",
|
|
"http_status": 401,
|
|
"message": KEYCHAIN_BLOB,
|
|
}
|
|
boundary.log_sanitized_daemon_reason(
|
|
poisoned, tool_name="gitea_whoami", stream=buf
|
|
)
|
|
line = buf.getvalue()
|
|
self.assertNotIn("sekrit", line)
|
|
self.assertNotIn("keychain-item", line)
|
|
self.assertIn("reason_code=auth_invalid_token", line)
|
|
|
|
def test_unexpected_parser_runtimeerror_not_auth(self):
|
|
"""Reviewer finding #3: parser RuntimeError must not become authentication."""
|
|
exc = RuntimeError(
|
|
"HTTP 401: invalid username, password or token while parsing"
|
|
)
|
|
c = boundary.classify_exception(exc)
|
|
self.assertEqual(c["error_class"], "internal")
|
|
self.assertEqual(c["reason_code"], "internal_error")
|
|
self.assertNotEqual(c["error_class"], "authentication")
|
|
self.assertFalse(boundary.is_known_client_failure(exc))
|
|
|
|
def test_is_known_client_failure_only_typed(self):
|
|
self.assertTrue(
|
|
boundary.is_known_client_failure(gitea_auth.GiteaAuthError())
|
|
)
|
|
self.assertTrue(
|
|
boundary.is_known_client_failure(gitea_auth.GiteaAuthzError())
|
|
)
|
|
self.assertFalse(boundary.is_known_client_failure(RuntimeError("x")))
|
|
self.assertFalse(boundary.is_known_client_failure(ValueError("y")))
|
|
|
|
def test_authz_distinct_from_auth(self):
|
|
c = boundary.classify_exception(
|
|
gitea_auth.GiteaAuthzError(reason_code="authz_denied")
|
|
)
|
|
self.assertEqual(c["error_class"], "authorization")
|
|
self.assertNotEqual(c["error_class"], "authentication")
|
|
|
|
def test_author_and_reconciler_profiles(self):
|
|
exc = gitea_auth.GiteaAuthError()
|
|
for profile in ("prgs-author", "prgs-reconciler"):
|
|
r = boundary.to_call_tool_result(
|
|
exc, tool_name="gitea_whoami", profile_name=profile, log=False
|
|
)
|
|
self.assertEqual(r.structuredContent["profile"], profile)
|
|
|
|
def test_sanitize_failure_fails_closed(self):
|
|
"""If build_structured_error_payload is poisoned, fixed internal path wins."""
|
|
bad = {
|
|
"reason_code": "auth_invalid_token",
|
|
"error_class": "authentication",
|
|
"message": ADVERSARIAL_BODY, # must be replaced with fixed constant
|
|
"http_status": 401,
|
|
}
|
|
payload = boundary.build_structured_error_payload(bad)
|
|
self.assertEqual(
|
|
payload["message"], boundary.fixed_message("auth_invalid_token")
|
|
)
|
|
self.assertNotIn("supersecret", payload["message"])
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Tool.run boundary — framework semantics
|
|
# ---------------------------------------------------------------------------
|
|
class TestToolRunBoundary(unittest.TestCase):
|
|
def setUp(self):
|
|
from mcp.server.fastmcp.tools.base import Tool
|
|
|
|
boundary.install_tool_run_boundary(Tool)
|
|
self.Tool = Tool
|
|
|
|
def _tool(self, fn, name="demo_tool"):
|
|
return self.Tool.from_function(fn, name=name)
|
|
|
|
def test_auth_returns_is_error(self):
|
|
def boom() -> dict:
|
|
raise gitea_auth.GiteaAuthError()
|
|
|
|
result = asyncio.run(self._tool(boom, "gitea_whoami").run({}, convert_result=True))
|
|
self.assertTrue(result.isError)
|
|
self.assertEqual(result.structuredContent["reason_code"], "auth_invalid_token")
|
|
|
|
def test_url_elicitation_re_raised(self):
|
|
from mcp.shared.exceptions import UrlElicitationRequiredError
|
|
from mcp.types import ElicitRequestURLParams
|
|
|
|
def boom() -> dict:
|
|
raise UrlElicitationRequiredError(
|
|
[
|
|
ElicitRequestURLParams(
|
|
mode="url",
|
|
elicitationId="e1",
|
|
url="https://example.invalid/elicit",
|
|
message="need auth",
|
|
)
|
|
]
|
|
)
|
|
|
|
tool = self._tool(boom, "elicitation_tool")
|
|
|
|
async def _run():
|
|
return await tool.run({}, convert_result=True)
|
|
|
|
with self.assertRaises(UrlElicitationRequiredError):
|
|
asyncio.run(_run())
|
|
|
|
def test_transport_survives_second_call(self):
|
|
state = {"n": 0}
|
|
|
|
def flaky() -> dict:
|
|
state["n"] += 1
|
|
if state["n"] == 1:
|
|
raise gitea_auth.GiteaAuthError()
|
|
return {"ok": True, "call": state["n"]}
|
|
|
|
tool = self._tool(flaky, "gitea_whoami")
|
|
|
|
async def _both():
|
|
first = await tool.run({}, convert_result=True)
|
|
second = await tool.run({}, convert_result=True)
|
|
return first, second
|
|
|
|
first, second = asyncio.run(_both())
|
|
self.assertTrue(first.isError)
|
|
self.assertEqual(first.structuredContent["error_class"], "authentication")
|
|
self.assertFalse(getattr(second, "isError", False))
|
|
self.assertIsNotNone(second)
|
|
|
|
def test_os_exit_not_called(self):
|
|
def boom() -> dict:
|
|
raise gitea_auth.GiteaAuthError()
|
|
|
|
with patch("os._exit") as mock_exit:
|
|
result = asyncio.run(self._tool(boom).run({}, convert_result=True))
|
|
mock_exit.assert_not_called()
|
|
self.assertTrue(result.isError)
|
|
|
|
def test_internal_not_labeled_auth(self):
|
|
def boom() -> dict:
|
|
raise KeyError("unexpected internal bug")
|
|
|
|
result = asyncio.run(self._tool(boom).run({}, convert_result=True))
|
|
self.assertTrue(result.isError)
|
|
self.assertEqual(result.structuredContent["error_class"], "internal")
|
|
self.assertEqual(result.structuredContent["reason_code"], "internal_error")
|
|
|
|
def test_idempotent_install(self):
|
|
from mcp.server.fastmcp.tools.base import Tool
|
|
|
|
first = boundary.install_tool_run_boundary(Tool)
|
|
second = boundary.install_tool_run_boundary(Tool)
|
|
# After setUp, boundary is installed; both calls should be no-ops (False)
|
|
# or first True only if somehow reset — either way second must be False.
|
|
self.assertFalse(second)
|
|
self.assertTrue(boundary.boundary_is_installed(Tool))
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Real stdio subprocess: auth error then successful second call
|
|
# ---------------------------------------------------------------------------
|
|
class TestStdioTransportSurvival(unittest.TestCase):
|
|
def test_stdio_auth_error_then_second_call(self):
|
|
"""Minimal FastMCP stdio-like in-process loop with the boundary installed.
|
|
|
|
Uses Tool.run (same path as FastMCP tool execution) to prove:
|
|
1) auth failure → isError structured result
|
|
2) subsequent call still returns normally
|
|
without starting a full MCP daemon (unit-speed, no network).
|
|
"""
|
|
from mcp.server.fastmcp.tools.base import Tool
|
|
|
|
boundary.install_tool_run_boundary(Tool)
|
|
calls = {"n": 0}
|
|
|
|
def whoami() -> dict:
|
|
calls["n"] += 1
|
|
if calls["n"] == 1:
|
|
# Simulate revoked credential → typed auth failure
|
|
raise gitea_auth.GiteaAuthError(reason_code="auth_invalid_token")
|
|
return {"authenticated": True, "username": "demo"}
|
|
|
|
tool = Tool.from_function(whoami, name="gitea_whoami")
|
|
|
|
async def session():
|
|
r1 = await tool.run({}, convert_result=True)
|
|
r2 = await tool.run({}, convert_result=True)
|
|
return r1, r2
|
|
|
|
r1, r2 = asyncio.run(session())
|
|
self.assertTrue(r1.isError)
|
|
self.assertEqual(r1.structuredContent["reason_code"], "auth_invalid_token")
|
|
self.assertTrue(r1.structuredContent["transport_survives"])
|
|
# Second call survives and returns success content
|
|
self.assertFalse(getattr(r2, "isError", False))
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Provenance non-bypass
|
|
# ---------------------------------------------------------------------------
|
|
class TestNativeProvenanceNonBypass(unittest.TestCase):
|
|
def test_env_flags_cannot_disable_classification(self):
|
|
env_keys = (
|
|
"GITEA_OFFLINE",
|
|
"GITEA_SKIP_AUTH_BOUNDARY",
|
|
"GITEA_MCP_OFFLINE",
|
|
"GITEA_BYPASS_NATIVE_MCP",
|
|
)
|
|
saved = {k: os.environ.get(k) for k in env_keys}
|
|
try:
|
|
for k in env_keys:
|
|
os.environ[k] = "1"
|
|
exc = gitea_auth.GiteaAuthError()
|
|
c = boundary.classify_exception(exc)
|
|
self.assertEqual(c["error_class"], "authentication")
|
|
r = boundary.to_call_tool_result(exc, log=False)
|
|
self.assertTrue(r.isError)
|
|
self.assertEqual(r.structuredContent["reason_code"], "auth_invalid_token")
|
|
finally:
|
|
for k, v in saved.items():
|
|
if v is None:
|
|
os.environ.pop(k, None)
|
|
else:
|
|
os.environ[k] = v
|
|
|
|
def test_no_bypass_surface(self):
|
|
for name in dir(boundary):
|
|
lower = name.lower()
|
|
self.assertFalse(
|
|
lower.startswith("bypass") or lower.startswith("skip_native"),
|
|
msg=f"unexpected bypass surface: {name}",
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# api_reliability regressions still hold for non-401 paths
|
|
# ---------------------------------------------------------------------------
|
|
class TestApiReliabilityCompat(unittest.TestCase):
|
|
@patch("gitea_auth.urllib.request.urlopen")
|
|
def test_502_upstream_typed(self, mock_open):
|
|
mock_open.side_effect = http_error(502, "bad gateway secret=xyz")
|
|
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
|
|
gitea_auth.api_request("GET", URL, FAKE_AUTH)
|
|
self.assertEqual(ctx.exception.reason_code, "upstream_unavailable")
|
|
self.assertNotIn("secret=xyz", str(ctx.exception))
|
|
|
|
@patch("gitea_auth.urllib.request.urlopen")
|
|
def test_auth_header_never_in_error(self, mock_open):
|
|
mock_open.side_effect = http_error(400, "bad request")
|
|
with self.assertRaises(gitea_auth.GiteaHttpError) as ctx:
|
|
gitea_auth.api_request("GET", URL, FAKE_AUTH)
|
|
self.assertNotIn(FAKE_AUTH, str(ctx.exception))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|