fix(orchestrator): address review on host control server transport (#468)
prd-number-check / require-numbered-prds (pull_request) Failing after 11s
test / integration-docker (pull_request) Successful in 20s
lint / lint (push) Successful in 59s
test / unit (pull_request) Failing after 52s
test / coverage (pull_request) Has been skipped
tracker-policy-pr / check-pr (pull_request) Failing after 11m18s

Codex review on #496:

- **High — ambiguous delivery no longer orphans a launched bottle.** A
  timeout / dropped response from the host controller is now the ambiguous
  BrokerUnavailableError (distinct from the definite BrokerAuthError /
  BrokerClientError). OrchestratorCore.launch_bottle keeps the registry
  row on the ambiguous case instead of deregistering — deregistering would
  orphan a running container with no record (reconcile reaps rows, never
  containers). The row is left for reconcile to reap iff the bottle is not
  actually live. Definite failures still roll back, so a real failure
  leaves no orphan row.
- **Medium — the privileged endpoint bounds request bodies.** The host
  server rejects an oversized Content-Length with 413 before reading it,
  and sets a per-request socket timeout, so a caller that can merely reach
  the socket (no signed token) can't exhaust memory or a handler thread.

Tests: ambiguous-keep vs definite-rollback in the launch path; the
BrokerUnavailableError/BrokerClientError split in BrokerClient; the 413
body cap + handler error paths (driven in-thread, since daemon request
threads lose coverage) plus a deterministic real-socket check that
declares an oversized Content-Length but sends a sliver (rejection on the
header, no unread-body reset race); and the __main__ entrypoint broker
selection. Diff-coverage 98%; pyright clean; pylint 9.8.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-07-26 08:43:00 +00:00
parent 79dd4926bb
commit 1553a98275
8 changed files with 340 additions and 30 deletions
+16 -1
View File
@@ -38,7 +38,21 @@ _ALLOWED_OPS = ("launch", "teardown")
class BrokerAuthError(Exception):
"""A broker request failed provenance or schema verification —
bad/absent signature, malformed token, or a payload that doesn't match
the fixed launch-request shape. Fail-closed: the broker must not act."""
the fixed launch-request shape. Fail-closed: the broker must not act.
A **definite** negative: nothing was launched, so a caller may safely roll
back as if the op never happened."""
class BrokerUnavailableError(Exception):
"""A brokered request could not be carried to a verdict: the broker (or the
wire to it) was unreachable, timed out, or dropped the response.
Crucially **ambiguous** — unlike `BrokerAuthError`, the op MAY already have
taken effect on the backend before the response was lost, so a caller must
NOT assume it did nothing (e.g. must not roll a registry row back as if no
launch happened, which would orphan a running container). Only the in-process
brokers never raise this; the out-of-process `BrokerClient` does."""
@dataclass(frozen=True)
@@ -179,6 +193,7 @@ class StubBroker(LaunchBroker):
__all__ = [
"BrokerAuthError",
"BrokerUnavailableError",
"LaunchRequest",
"SubmitBroker",
"LaunchBroker",
+16 -9
View File
@@ -20,15 +20,17 @@ import json
import urllib.error
import urllib.request
from .broker import BrokerAuthError, LaunchRequest
from .broker import BrokerAuthError, BrokerUnavailableError, LaunchRequest
DEFAULT_TIMEOUT_SECONDS = 5.0
class BrokerClientError(RuntimeError):
"""A brokered launch/teardown could not be delivered to the host control
server: unreachable, or an unexpected status other than the fail-closed 401
(which surfaces as `BrokerAuthError`, matching the in-process broker)."""
"""The host control server *responded*, but with an unexpected status other
than the fail-closed 401 (which surfaces as `BrokerAuthError`) — e.g. a 502
backend failure or a malformed body. A definite negative: the host processed
the request and it did not launch. (A *no-response* failure — unreachable /
timeout / dropped — is the ambiguous `BrokerUnavailableError` instead.)"""
class BrokerClient:
@@ -45,9 +47,11 @@ class BrokerClient:
verified and acted on.
Raises `BrokerAuthError` on a fail-closed 401 (bad provenance/schema —
the same exception the in-process broker raises), or `BrokerClientError`
if the controller is unreachable, times out, or returns any other
non-success status."""
the same exception the in-process broker raises); `BrokerClientError` if
the host *responds* with any other non-success status or a malformed
body (a definite negative); or `BrokerUnavailableError` if no response is
obtained (unreachable / timeout / dropped) — the **ambiguous** case, where
the host may already have acted, so the caller must not roll back."""
data = json.dumps({"token": token}).encode()
req = urllib.request.Request(
f"{self._base}/broker", data=data, method="POST",
@@ -65,8 +69,11 @@ class BrokerClient:
raise BrokerClientError(
f"POST /broker: HTTP {e.code} {detail}".rstrip()
) from e
except (urllib.error.URLError, TimeoutError, OSError, ValueError) as e:
raise BrokerClientError(f"POST /broker: {e}") from e
except (urllib.error.URLError, TimeoutError, OSError) as e:
# No usable response — unreachable, timed out, or the connection
# dropped mid-exchange. Ambiguous: the request may already have
# launched the bottle, so this is NOT a definite failure.
raise BrokerUnavailableError(f"POST /broker: {e}") from e
def _json_object(raw: bytes) -> dict[str, object]:
+31 -4
View File
@@ -57,6 +57,16 @@ BROKER_SECRET_ENV = "BOT_BOTTLE_BROKER_SECRET"
# (8099) — a separate privileged component listening on its own socket.
DEFAULT_PORT = 8091
# Cap on the request body. A signed broker request is tiny, so rejecting anything
# larger *before reading it* keeps a caller that can merely reach the socket (no
# signed token needed) from exhausting memory or a handler thread with a huge
# Content-Length — the signed token, not mere reachability, is the authority.
MAX_BODY_BYTES = 64 * 1024
# Per-request socket timeout, bounding how long a stalled / slow-loris caller can
# hold a handler thread on this privileged listener.
REQUEST_TIMEOUT_SECONDS = 15
def _parse_json_object(body: bytes) -> Json:
"""Parse a JSON object body. Raises ValueError for non-objects / bad JSON."""
@@ -130,6 +140,10 @@ def dispatch( # pylint: disable=too-many-return-statements
class Handler(http.server.BaseHTTPRequestHandler):
"""Thin stdlib adapter: read the body, call `dispatch`, write JSON."""
# Socket timeout per request (applied by StreamRequestHandler.setup) so a
# stalled caller can't pin a handler thread on this privileged listener.
timeout = REQUEST_TIMEOUT_SECONDS
# Quiet by default; opt back into stdlib access logging with
# BOT_BOTTLE_HOST_CONTROLLER_DEBUG (the controller has its own logging).
def log_message(self, format: str, *args: typing.Any) -> None: # noqa: A002
@@ -137,12 +151,21 @@ class Handler(http.server.BaseHTTPRequestHandler):
super().log_message(format, *args)
def _serve(self, method: str) -> None:
"""Read the request body, dispatch it, and write the JSON reply. A
dispatch that raises (it shouldn't — dispatch is total) still returns a
500 rather than dropping the connection."""
"""Read the request body (bounded), dispatch it, and write the JSON
reply. A dispatch that raises (it shouldn't — dispatch is total) still
returns a 500 rather than dropping the connection."""
server = self.server
assert isinstance(server, HostControlServer)
length = int(self.headers.get("Content-Length") or 0)
try:
length = int(self.headers.get("Content-Length") or 0)
except ValueError:
self._reply(400, {"error": "invalid Content-Length"})
return
if length < 0 or length > MAX_BODY_BYTES:
# Reject before reading: nothing legitimate is this big, so an
# oversized declared length is a bug or a resource-exhaustion attempt.
self._reply(413, {"error": "request body too large"})
return
body = self.rfile.read(length) if length > 0 else b""
try:
status, payload = dispatch(server.broker, method, self.path, body)
@@ -150,6 +173,10 @@ class Handler(http.server.BaseHTTPRequestHandler):
sys.stderr.write(f"host controller: {method} {self.path} failed: {e!r}\n")
sys.stderr.flush()
status, payload = 500, {"error": f"internal error: {e}"}
self._reply(status, payload)
def _reply(self, status: int, payload: typing.Mapping[str, object]) -> None:
"""Write one JSON response with an explicit Content-Length."""
data = json.dumps(payload).encode()
self.send_response(status)
self.send_header("Content-Type", "application/json")
+16 -7
View File
@@ -25,7 +25,7 @@ import json
from collections.abc import Iterable
from datetime import datetime, timezone
from .broker import LaunchRequest, SubmitBroker, sign_request
from .broker import BrokerUnavailableError, LaunchRequest, SubmitBroker, sign_request
from .store.registry_store import DEFAULT_REAP_GRACE_SECONDS, BottleRecord, RegistryStore
from .supervisor import (
AuditEntry,
@@ -111,14 +111,23 @@ class OrchestratorCore:
image_ref=image_ref,
slot=slot,
)
launched = False
try:
self._broker.submit(sign_request(req, self._secret))
launched = True
finally:
if not launched:
self.registry.deregister(rec.bottle_id)
self._tokens.pop(rec.bottle_id, None)
except BrokerUnavailableError:
# Ambiguous delivery failure (timeout / dropped response): the broker
# may already have launched the bottle before the response was lost.
# Do NOT deregister — that would orphan a running container with no
# registry row (reconcile reaps rows, never containers). Keep the row
# so reconcile reaps it iff the bottle is not actually live; surface
# the error so the caller knows the launch is unconfirmed.
raise
except Exception:
# A definite failure — a fail-closed rejection, a backend launch
# error, or the host reporting it did not launch: nothing is running,
# so roll the registry entry back to leave no orphan.
self.registry.deregister(rec.bottle_id)
self._tokens.pop(rec.bottle_id, None)
raise
return rec
def teardown_bottle(self, bottle_id: str) -> bool:
+37 -4
View File
@@ -8,7 +8,11 @@ import unittest
import urllib.error
from unittest.mock import MagicMock, patch
from bot_bottle.orchestrator.broker import BrokerAuthError, LaunchRequest
from bot_bottle.orchestrator.broker import (
BrokerAuthError,
BrokerUnavailableError,
LaunchRequest,
)
from bot_bottle.orchestrator.broker_client import BrokerClient, BrokerClientError
_URLOPEN = "bot_bottle.orchestrator.broker_client.urllib.request.urlopen"
@@ -58,14 +62,25 @@ class TestSubmit(unittest.TestCase):
with self.assertRaises(BrokerAuthError):
self.c.submit("forged")
def test_502_raises_broker_client_error(self) -> None:
def test_502_is_a_definite_client_error(self) -> None:
# The host responded — it processed the request and did not launch, so a
# definite BrokerClientError (the caller may safely roll back).
with patch(_URLOPEN, side_effect=_http_error(502, {"error": "docker down"})):
with self.assertRaises(BrokerClientError):
self.c.submit("tok")
def test_unreachable_raises_broker_client_error(self) -> None:
def test_unreachable_is_ambiguous_unavailable(self) -> None:
# No response at all — the request may already have launched, so the
# AMBIGUOUS BrokerUnavailableError (the caller must NOT roll back).
with patch(_URLOPEN, side_effect=urllib.error.URLError("refused")):
with self.assertRaises(BrokerClientError):
with self.assertRaises(BrokerUnavailableError):
self.c.submit("tok")
def test_timeout_is_ambiguous_unavailable(self) -> None:
# A dropped/late response after the request was sent is the exact orphan
# risk: the host may have launched. Must be ambiguous, not a definite fail.
with patch(_URLOPEN, side_effect=TimeoutError("read timed out")):
with self.assertRaises(BrokerUnavailableError):
self.c.submit("tok")
def test_malformed_success_body_raises(self) -> None:
@@ -79,6 +94,24 @@ class TestSubmit(unittest.TestCase):
with self.assertRaises(BrokerAuthError):
self.c.submit("forged")
def test_non_json_success_body_raises(self) -> None:
# A 200 whose body isn't JSON is tolerated into {} then fails the
# missing-field check — a definite client error, not a crash.
m = MagicMock()
m.__enter__.return_value.read.return_value = b"not json at all"
with patch(_URLOPEN, return_value=m):
with self.assertRaises(BrokerClientError):
self.c.submit("tok")
def test_unreadable_error_body_is_tolerated(self) -> None:
# An HTTPError whose body can't be read (fp=None) still classifies by
# status — the error detail is best-effort.
err = urllib.error.HTTPError(
"http://host/broker", 502, "err", {}, None) # type: ignore[arg-type]
with patch(_URLOPEN, side_effect=err):
with self.assertRaises(BrokerClientError):
self.c.submit("tok")
if __name__ == "__main__":
unittest.main()
+129
View File
@@ -7,10 +7,14 @@ the full sign -> POST -> verify -> act seam over HTTP.
from __future__ import annotations
import http.client
import io
import json
import secrets
import threading
import typing
import unittest
from unittest.mock import MagicMock, patch
from bot_bottle.orchestrator.broker import (
BrokerAuthError,
@@ -21,8 +25,12 @@ from bot_bottle.orchestrator.broker import (
)
from bot_bottle.orchestrator.broker_client import BrokerClient
from bot_bottle.orchestrator.host_server import (
MAX_BODY_BYTES,
Handler,
HostControlServer,
broker_secret_from_env,
dispatch,
main,
make_host_server,
)
@@ -97,6 +105,16 @@ class TestDispatch(unittest.TestCase):
status, _ = dispatch(self.broker, "POST", "/broker", b"{not json")
self.assertEqual(400, status)
def test_empty_body_is_missing_token_400(self) -> None:
# Empty body parses to {} (no token) → 400, never reaching the broker.
status, _ = dispatch(self.broker, "POST", "/broker", b"")
self.assertEqual(400, status)
self.assertEqual([], self.broker.launched)
def test_non_object_body_is_400(self) -> None:
status, _ = dispatch(self.broker, "POST", "/broker", b"[1, 2]")
self.assertEqual(400, status)
def test_unknown_route_404(self) -> None:
status, _ = dispatch(self.broker, "GET", "/nope", b"")
self.assertEqual(404, status)
@@ -152,5 +170,116 @@ class TestSeamRoundTrip(unittest.TestCase):
self.assertEqual([], broker.launched) # fail-closed across the wire
class TestRequestLimits(unittest.TestCase):
"""The privileged listener must not let a caller that can merely reach the
socket (no signed token) exhaust it via an oversized declared body — and it
rejects on the Content-Length *header*, before reading the body."""
def _addr(self) -> tuple[str, int]:
self.broker = StubBroker(secrets.token_bytes(16))
server = make_host_server(self.broker, "127.0.0.1", 0)
self.addCleanup(server.server_close)
threading.Thread(target=server.serve_forever, daemon=True).start()
self.addCleanup(server.shutdown)
host, port = server.server_address[:2]
return typing.cast(str, host), port
def test_oversized_content_length_is_rejected_before_reading(self) -> None:
host, port = self._addr()
conn = http.client.HTTPConnection(host, port, timeout=5)
self.addCleanup(conn.close)
# Declare an oversized body but send only a sliver: the server must reject
# on the header before reading, so the caller gets a clean, deterministic
# 413 (no large unread body to race a connection reset).
conn.putrequest("POST", "/broker", skip_accept_encoding=True)
conn.putheader("Content-Type", "application/json")
conn.putheader("Content-Length", str(MAX_BODY_BYTES + 1))
conn.endheaders()
conn.send(b"{}") # far short of the declared length; never read
resp = conn.getresponse()
self.assertEqual(413, resp.status)
self.assertEqual([], self.broker.launched) # never reached the broker
class TestServeUnit(unittest.TestCase):
"""Drive `Handler._serve` directly (no socket). The real per-request handler
runs in a daemon thread whose coverage/trace data is lost, so the
bounded-body and error paths are exercised here in the main thread instead."""
def _handler(self, broker: LaunchBroker, headers: dict[str, str],
body: bytes = b"") -> tuple[Handler, MagicMock]:
server = HostControlServer.__new__(HostControlServer)
server.broker = broker
h = Handler.__new__(Handler)
h.server = server
h.headers = headers # type: ignore[assignment] — dict is a valid .get() stand-in
h.path = "/broker"
h.rfile = io.BytesIO(body)
h.wfile = io.BytesIO()
send_response = MagicMock()
h.send_response = send_response # type: ignore[method-assign]
h.send_header = MagicMock() # type: ignore[method-assign]
h.end_headers = MagicMock() # type: ignore[method-assign]
return h, send_response
def test_oversized_content_length_is_413(self) -> None:
broker = StubBroker(secrets.token_bytes(16))
h, send_response = self._handler(broker, {"Content-Length": str(MAX_BODY_BYTES + 1)})
h.do_POST() # exercises do_POST -> _serve
send_response.assert_called_once_with(413)
self.assertEqual([], broker.launched) # rejected before the broker
def test_invalid_content_length_is_400(self) -> None:
h, send_response = self._handler(StubBroker(secrets.token_bytes(16)),
{"Content-Length": "not-a-number"})
h._serve("POST")
send_response.assert_called_once_with(400)
def test_valid_request_dispatches_200(self) -> None:
secret = secrets.token_bytes(16)
broker = StubBroker(secret)
body = _body({"token": sign_request(
LaunchRequest(op="teardown", bottle_id="b1"), secret)})
h, send_response = self._handler(broker, {"Content-Length": str(len(body))}, body)
h._serve("POST")
send_response.assert_called_once_with(200)
self.assertEqual(["b1"], [r.bottle_id for r in broker.torn_down])
def test_dispatch_exception_becomes_500(self) -> None:
# dispatch is total, but the handler still guards it: a raised dispatch
# returns 500 rather than dropping the connection.
h, send_response = self._handler(
StubBroker(secrets.token_bytes(16)), {"Content-Length": "0"})
with patch("bot_bottle.orchestrator.host_server.dispatch",
side_effect=RuntimeError("boom")):
h._serve("POST")
send_response.assert_called_once_with(500)
def test_health_over_do_get(self) -> None:
h, send_response = self._handler(StubBroker(secrets.token_bytes(16)), {})
h.path = "/health"
h.do_GET()
send_response.assert_called_once_with(200)
class TestMain(unittest.TestCase):
def test_fail_closed_without_secret(self) -> None:
with patch("bot_bottle.orchestrator.host_server.broker_secret_from_env",
return_value=None):
self.assertEqual(2, main(["--port", "0"]))
def test_serves_then_shuts_down_cleanly(self) -> None:
fake = MagicMock()
fake.server_address = ("127.0.0.1", 0)
fake.serve_forever.side_effect = KeyboardInterrupt
with patch("bot_bottle.orchestrator.host_server.broker_secret_from_env",
return_value=b"k"), \
patch("bot_bottle.orchestrator.host_server.make_host_server",
return_value=fake):
self.assertEqual(0, main(["--port", "0"]))
fake.serve_forever.assert_called_once()
fake.server_close.assert_called_once()
if __name__ == "__main__":
unittest.main()
+64
View File
@@ -0,0 +1,64 @@
"""Unit: the orchestrator dev-harness entrypoint (`python -m bot_bottle.orchestrator`).
Exercises broker selection (stub / docker / http) and the fail-closed http path,
patching `make_server` so the serve loop returns instead of blocking.
"""
from __future__ import annotations
import os
import secrets
import tempfile
import unittest
from pathlib import Path
from unittest.mock import MagicMock, patch
from bot_bottle.orchestrator.__main__ import main
def _fake_server() -> MagicMock:
fake = MagicMock()
fake.server_address = ("127.0.0.1", 0)
# Break out of serve_forever immediately, exercising the try/finally.
fake.serve_forever.side_effect = KeyboardInterrupt
return fake
class TestMain(unittest.TestCase):
def _run(self, broker: str, env: dict[str, str] | None = None) -> tuple[int, MagicMock]:
fake = _fake_server()
with tempfile.TemporaryDirectory() as d:
argv = ["--db", str(Path(d) / "r.db"), "--port", "0", "--broker", broker]
with patch("bot_bottle.orchestrator.__main__.make_server", return_value=fake), \
patch.dict("os.environ", env or {}, clear=False):
if env is None:
os.environ.pop("BOT_BOTTLE_BROKER_SECRET", None)
rc = main(argv)
return rc, fake
def test_stub_broker_serves_and_closes(self) -> None:
rc, fake = self._run("stub")
self.assertEqual(0, rc)
fake.serve_forever.assert_called_once()
fake.server_close.assert_called_once()
def test_docker_broker_serves(self) -> None:
rc, _ = self._run("docker")
self.assertEqual(0, rc)
def test_http_broker_with_secret_serves(self) -> None:
rc, _ = self._run(
"http", env={"BOT_BOTTLE_BROKER_SECRET": secrets.token_bytes(16).hex()})
self.assertEqual(0, rc)
def test_http_broker_without_secret_exits(self) -> None:
# Fail-closed: --broker http with no shared secret is a usage error.
with tempfile.TemporaryDirectory() as d:
with patch.dict("os.environ", {}, clear=False):
os.environ.pop("BOT_BOTTLE_BROKER_SECRET", None)
with self.assertRaises(SystemExit):
main(["--db", str(Path(d) / "r.db"), "--broker", "http"])
if __name__ == "__main__":
unittest.main()
+31 -5
View File
@@ -11,7 +11,12 @@ from contextlib import closing
from pathlib import Path
from unittest.mock import patch
from bot_bottle.orchestrator.broker import LaunchBroker, LaunchRequest, StubBroker
from bot_bottle.orchestrator.broker import (
BrokerUnavailableError,
LaunchBroker,
LaunchRequest,
StubBroker,
)
from bot_bottle.orchestrator.store.registry_store import RegistryStore
from bot_bottle.orchestrator.service import OrchestratorCore
from bot_bottle.orchestrator.store.secret_store import new_env_var_secret
@@ -25,8 +30,8 @@ from bot_bottle.orchestrator.supervisor import (
class _FailingBroker(LaunchBroker):
"""Verifies the token like any broker, then fails the launch — to
exercise the orchestrator's registry rollback."""
"""Verifies the token like any broker, then fails the launch *definitely*
to exercise the orchestrator's registry rollback."""
def _launch(self, req: LaunchRequest) -> None:
raise RuntimeError("launch failed")
@@ -35,6 +40,18 @@ class _FailingBroker(LaunchBroker):
pass
class _UnavailableBroker(LaunchBroker):
"""Verifies the token, then raises the *ambiguous* BrokerUnavailableError —
the host may already have launched so the orchestrator must KEEP the
registry row rather than orphan a running container."""
def _launch(self, req: LaunchRequest) -> None:
raise BrokerUnavailableError("delivery dropped after send")
def _teardown(self, req: LaunchRequest) -> None:
pass
class TestOrchestrator(unittest.TestCase):
def setUp(self) -> None:
self._tmp = tempfile.TemporaryDirectory()
@@ -136,11 +153,20 @@ class TestOrchestrator(unittest.TestCase):
self.assertIsNotNone(self.orch.resolve("10.243.0.3", rec.identity_token))
self.assertIsNone(self.orch.resolve("10.243.0.3", "wrong-token"))
def test_launch_rolls_back_registry_on_broker_failure(self) -> None:
def test_launch_rolls_back_registry_on_definite_broker_failure(self) -> None:
orch = OrchestratorCore(self.store, _FailingBroker(self.secret), self.secret)
with self.assertRaises(RuntimeError):
orch.launch_bottle("10.243.0.9")
self.assertEqual([], self.store.all()) # no orphan
self.assertEqual([], self.store.all()) # no orphan row
def test_launch_keeps_registry_on_ambiguous_broker_failure(self) -> None:
# The host may already have launched the bottle before the response was
# lost, so deregistering would orphan a running container with no row.
# The row is kept for reconcile to reap iff the bottle is not live.
orch = OrchestratorCore(self.store, _UnavailableBroker(self.secret), self.secret)
with self.assertRaises(BrokerUnavailableError):
orch.launch_bottle("10.243.0.9")
self.assertEqual(1, len(self.store.all())) # row survives — no orphan container
def test_gateway_status_reports_unconfigured(self) -> None:
# The orchestrator no longer owns a standalone gateway lifecycle; the