feat(orchestrator): durable launch-broker secret via TrustDomain (#468)
prd-number-check / require-numbered-prds (pull_request) Failing after 11s
tracker-policy-pr / check-pr (pull_request) Successful in 16s
test / integration-docker (pull_request) Failing after 45s
test / unit (pull_request) Successful in 56s
test / coverage (pull_request) Has been skipped
lint / lint (push) Failing after 14m57s

Chunk 2 of the host-control-server stack: close the PRD's **durable
secret** gap and replace chunk 1's BOT_BOTTLE_BROKER_SECRET stopgap.

- trust_domain.py: two new domains. LAUNCH_BROKER holds the durable
  HS256 key both the orchestrator (signer) and the host control server
  (verifier) share for the broker's launch JWT — a host-canonical key
  file minted 0600 on first use, so a restarted orchestrator re-verifies
  against the same key. HOST_CONTROLLER is the separate domain for the
  controller's own lifecycle endpoints, keyed by a key the orchestrator
  never holds (its role is `host`, deliberately outside control-plane
  ROLES). LaunchBrokerProvisioning is the fail-closed seam.
- orchestrator_auth.py: ROLE_HOST, outside ROLES.
- paths.py: key-file + env-var constants for both domains.

Key resolution is split by owner (addresses codex review on #497):
broker_secret(allow_host_file=...) — the host controller / dev-harness
(True) may mint/read the durable host key file it owns; the GUEST
orchestrator (--broker http, default False) must be *injected* the key
and fails closed if it isn't. A guest that fell back to the host file
would mint a process-local key unrelated to the host controller's, so
startup would succeed but every launch would 401 — this prevents that
silent divergence.

Tested: domain boundary + separation, provisioning fail-closed, and
broker_secret env-only (guest) vs host-file (host) resolution. pyright
clean; pylint 9.86.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-07-26 07:34:36 +00:00
parent 1553a98275
commit 5f1d3fbd15
8 changed files with 288 additions and 59 deletions
+32 -11
View File
@@ -10,7 +10,9 @@ from __future__ import annotations
import http.client
import io
import json
import os
import secrets
import tempfile
import threading
import typing
import unittest
@@ -28,11 +30,12 @@ from bot_bottle.orchestrator.host_server import (
MAX_BODY_BYTES,
Handler,
HostControlServer,
broker_secret_from_env,
broker_secret,
dispatch,
main,
make_host_server,
)
from bot_bottle.paths import LAUNCH_BROKER_KEY_ENV
def _body(obj: object) -> bytes:
@@ -124,16 +127,34 @@ class TestDispatch(unittest.TestCase):
self.assertEqual(200, status)
class TestBrokerSecretFromEnv(unittest.TestCase):
def test_reads_hex_secret(self) -> None:
s = secrets.token_bytes(16)
self.assertEqual(s, broker_secret_from_env({"BOT_BOTTLE_BROKER_SECRET": s.hex()}))
class TestBrokerSecret(unittest.TestCase):
"""The durable launch-broker key (#468/#476): prefer the env-injected key,
else the durable host key file, so signer and verifier resolve the same one."""
def test_unset_is_none(self) -> None:
self.assertIsNone(broker_secret_from_env({}))
def test_reads_injected_key_from_env(self) -> None:
# The injected key is honoured regardless of allow_host_file — both the
# host controller and the guest orchestrator take an injected key.
self.assertEqual(
b"injected-key", broker_secret({LAUNCH_BROKER_KEY_ENV: "injected-key"}))
self.assertEqual(
b"injected-key",
broker_secret({LAUNCH_BROKER_KEY_ENV: "injected-key"}, allow_host_file=True))
def test_invalid_hex_is_none(self) -> None:
self.assertIsNone(broker_secret_from_env({"BOT_BOTTLE_BROKER_SECRET": "not-hex"}))
def test_guest_without_injection_fails_closed(self) -> None:
# The default (guest orchestrator): no env key and NO host-file fallback,
# so it returns None rather than mint a divergent process-local key.
self.assertIsNone(broker_secret({}))
def test_host_side_falls_back_to_the_durable_key_file(self) -> None:
# allow_host_file=True (host controller / dev-harness): mint/read the
# durable host key file, the same key on every call (restart re-adoption).
with tempfile.TemporaryDirectory() as root:
with patch.dict("os.environ", {"BOT_BOTTLE_ROOT": root}, clear=False):
os.environ.pop(LAUNCH_BROKER_KEY_ENV, None)
first = broker_secret(allow_host_file=True)
second = broker_secret(allow_host_file=True)
self.assertTrue(first)
self.assertEqual(first, second)
class TestSeamRoundTrip(unittest.TestCase):
@@ -264,7 +285,7 @@ class TestServeUnit(unittest.TestCase):
class TestMain(unittest.TestCase):
def test_fail_closed_without_secret(self) -> None:
with patch("bot_bottle.orchestrator.host_server.broker_secret_from_env",
with patch("bot_bottle.orchestrator.host_server.broker_secret",
return_value=None):
self.assertEqual(2, main(["--port", "0"]))
@@ -272,7 +293,7 @@ class TestMain(unittest.TestCase):
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",
with patch("bot_bottle.orchestrator.host_server.broker_secret",
return_value=b"k"), \
patch("bot_bottle.orchestrator.host_server.make_host_server",
return_value=fake):