refactor(gateway): remove the single-tenant data-plane paths (audit #400 finding 3)

All three backends (docker, firecracker, macos-container) now launch through
the consolidated orchestrator, and every production gateway sets
BOT_BOTTLE_ORCHESTRATOR_URL — so the legacy single-tenant (`resolver is None`)
branches in the shared gateway's data plane were unreachable dead code, a second
security-relevant path to keep correct in parallel with the live one. Make the
orchestrator resolver mandatory and delete the single-tenant paths from the
three data-plane modules.

egress_addon.py: drop the static routes file entirely — EGRESS_ROUTES, _reload,
the SIGHUP handler, self.config, and the SUPERVISE_BOTTLE_SLUG env slug. The
per-request /resolve is the only policy source; __init__ fail-closes if
BOT_BOTTLE_ORCHESTRATOR_URL is unset. Introspection (`_egress.local/allowlist`)
now reports the calling bottle's *resolved* routes. The block/redact log gates
and _req_ctx redaction now read the per-flow config/env from the request-time
stash, so they use each bottle's log level and token set (they silently used the
empty static config before). Nothing sends `docker kill --signal HUP` to the
gateway in the consolidated model (the egress applicators fail closed), so
removing the SIGHUP reload is safe.

git_http_backend.py: resolver mandatory; no flat-root fallback. main() refuses
to start without an orchestrator URL; a request whose source resolves to no
bottle 404s.

supervise_server.py: resolver mandatory; every proposal is attributed to the
source-IP-resolved bottle. Remove handle_list_egress_routes (the proxy-fetch
introspection that only worked when the proxy carried one bottle's identity) —
list-egress-routes is answered from the resolved policy. main() refuses to start
without an orchestrator URL.

Tests: a host-side fake resolver serves each test's Config through the real
parse path (a small YAML-subset emitter round-trips route_to_yaml_dict); the
response/websocket hooks stash it as request() would. Deletes the tests for the
removed static-config, SIGHUP-reload, and single-tenant-passthrough paths; adds
fail-closed-without-orchestrator coverage.

Follow-up: gateway_init still forwards SIGHUP to the egress child (now dormant —
no one sends it); the README still describes the docker backend's per-bottle
topology. Both are outside the data-plane teardown.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UoEZHDjv84ChoZbozQERhJ
This commit is contained in:
2026-07-17 18:02:59 -04:00
parent 2aec30e501
commit b601b663e2
8 changed files with 361 additions and 418 deletions
+15 -56
View File
@@ -41,7 +41,6 @@ from bot_bottle.supervise_server import (
_response_timeout_from_env,
format_response_text,
handle_initialize,
handle_list_egress_routes,
handle_tools_call,
handle_tools_list,
jsonrpc_error,
@@ -448,49 +447,6 @@ class TestHandleToolsCall(unittest.TestCase):
self.assertEqual(1, len(_sv.list_pending_proposals("dev")))
class TestHandleListEgressRoutes(unittest.TestCase):
def test_success_returns_body_text(self):
class _Resp:
def __enter__(self):
return self
def __exit__(self, exc_type: type[BaseException] | None, exc: BaseException | None, tb: object) -> bool:
return False
def read(self):
return b"[{\"host\": \"example.com\"}]"
class _Opener:
def open(self, *args, **kwargs): # noqa: ANN001, ANN002, ANN003 # type: ignore
return _Resp()
with patch.object(supervise_server.urllib.request, "build_opener", return_value=_Opener()):
result = handle_list_egress_routes(
{},
ServerConfig(bottle_slug="dev"),
)
self.assertFalse(result["isError"]) # type: ignore[index]
text = result["content"][0]["text"] # type: ignore[index]
self.assertIn("example.com", text)
def test_url_error_returns_tool_error(self):
class _Opener:
def open(self, *args, **kwargs): # noqa: ANN001, ANN002, ANN003 # type: ignore
raise OSError("egress unavailable")
with patch.object(supervise_server.urllib.request, "build_opener", return_value=_Opener()):
result = handle_list_egress_routes(
{},
ServerConfig(bottle_slug="dev"),
)
self.assertTrue(result["isError"]) # type: ignore[index]
text = result["content"][0]["text"] # type: ignore[index]
self.assertIn("could not reach", text)
self.assertIn("egress unavailable", text)
class TestResponseTimeoutEnv(unittest.TestCase):
def test_unset_uses_default(self):
self.assertEqual(
@@ -671,12 +627,13 @@ def _handler(resolver: object) -> MCPHandler:
class TestAttributedConfig(unittest.TestCase):
"""Consolidated supervise: each proposal is attributed to the calling
bottle by source IP; single-tenant keeps the env slug (PRD 0070)."""
"""Each proposal is attributed to the calling bottle by source IP (PRD
0070); a server without a resolver fails closed rather than queuing under an
unattributed slug."""
def test_single_tenant_keeps_env_slug(self) -> None:
cfg = _handler(None)._attributed_config(ServerConfig(bottle_slug="dev"))
self.assertEqual("dev", cfg.bottle_slug)
def test_missing_resolver_fails_closed(self) -> None:
with self.assertRaises(_RpcInternalError):
_handler(None)._attributed_config(ServerConfig(bottle_slug="dev"))
def test_consolidated_binds_source_ip_bottle(self) -> None:
r = _FakeResolver(bottle_id="bottle-x")
@@ -698,10 +655,10 @@ class TestAttributedConfig(unittest.TestCase):
class TestResolvedRoutesPayload(unittest.TestCase):
"""`list-egress-routes` answers from the calling bottle's resolved policy in
consolidated mode — not the gateway's empty static table. Regression: an
empty list led agents to propose replace-all route files that dropped base
hosts like api.anthropic.com on approval."""
"""`list-egress-routes` answers from the calling bottle's resolved policy
not the gateway's empty static table. Regression: an empty list led agents
to propose replace-all route files that dropped base hosts like
api.anthropic.com on approval."""
def test_returns_resolved_bottle_routes(self) -> None:
policy = (
@@ -728,9 +685,11 @@ class TestResolvedRoutesPayload(unittest.TestCase):
data = json.loads(payload["content"][0]["text"]) # type: ignore[index]
self.assertEqual([], data["routes"])
def test_single_tenant_returns_none(self) -> None:
# No resolver → caller falls back to the static introspection endpoint.
self.assertIsNone(_handler(None)._resolved_routes_payload())
def test_missing_resolver_fails_closed(self) -> None:
# A server without a resolver is a misconfig, not a mode: raise rather
# than list anything.
with self.assertRaises(_RpcInternalError):
_handler(None)._resolved_routes_payload()
if __name__ == "__main__":